{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 928, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008620689655172414, "grad_norm": 0.752173662185669, "learning_rate": 4.2553191489361704e-07, "loss": 3.6935362815856934, "step": 2 }, { "epoch": 0.017241379310344827, "grad_norm": 3.0686516761779785, "learning_rate": 1.276595744680851e-06, "loss": 2.4514498710632324, "step": 4 }, { "epoch": 0.02586206896551724, "grad_norm": 3.670806407928467, "learning_rate": 2.1276595744680853e-06, "loss": 2.2222416400909424, "step": 6 }, { "epoch": 0.034482758620689655, "grad_norm": 0.4838178753852844, "learning_rate": 2.978723404255319e-06, "loss": 1.9781272411346436, "step": 8 }, { "epoch": 0.04310344827586207, "grad_norm": 3.7360541820526123, "learning_rate": 3.8297872340425535e-06, "loss": 1.768671989440918, "step": 10 }, { "epoch": 0.05172413793103448, "grad_norm": 0.6814174056053162, "learning_rate": 4.680851063829788e-06, "loss": 1.7612519264221191, "step": 12 }, { "epoch": 0.0603448275862069, "grad_norm": 0.6352251768112183, "learning_rate": 5.531914893617022e-06, "loss": 1.8349356651306152, "step": 14 }, { "epoch": 0.06896551724137931, "grad_norm": 0.4332002103328705, "learning_rate": 6.382978723404256e-06, "loss": 0.766176164150238, "step": 16 }, { "epoch": 0.07758620689655173, "grad_norm": 0.5920107364654541, "learning_rate": 7.234042553191491e-06, "loss": 0.9314699769020081, "step": 18 }, { "epoch": 0.08620689655172414, "grad_norm": 0.40042662620544434, "learning_rate": 8.085106382978723e-06, "loss": 1.5076656341552734, "step": 20 }, { "epoch": 0.09482758620689655, "grad_norm": 0.33145302534103394, "learning_rate": 8.936170212765958e-06, "loss": 1.6648786067962646, "step": 22 }, { "epoch": 0.10344827586206896, "grad_norm": 0.7193792462348938, "learning_rate": 9.787234042553192e-06, "loss": 1.508145809173584, "step": 24 }, { "epoch": 0.11206896551724138, "grad_norm": 2.580322027206421, "learning_rate": 1.0638297872340426e-05, "loss": 1.3233157396316528, "step": 26 }, { "epoch": 0.1206896551724138, "grad_norm": 1.6866916418075562, "learning_rate": 1.1489361702127662e-05, "loss": 0.5060393214225769, "step": 28 }, { "epoch": 0.12931034482758622, "grad_norm": 0.40954306721687317, "learning_rate": 1.2340425531914895e-05, "loss": 1.489959716796875, "step": 30 }, { "epoch": 0.13793103448275862, "grad_norm": 0.9065203666687012, "learning_rate": 1.3191489361702127e-05, "loss": 1.14947509765625, "step": 32 }, { "epoch": 0.14655172413793102, "grad_norm": 0.3966251611709595, "learning_rate": 1.4042553191489363e-05, "loss": 1.3647483587265015, "step": 34 }, { "epoch": 0.15517241379310345, "grad_norm": 0.3009808659553528, "learning_rate": 1.4893617021276596e-05, "loss": 1.4109106063842773, "step": 36 }, { "epoch": 0.16379310344827586, "grad_norm": 0.33264291286468506, "learning_rate": 1.5744680851063832e-05, "loss": 1.3988299369812012, "step": 38 }, { "epoch": 0.1724137931034483, "grad_norm": 0.3600396513938904, "learning_rate": 1.6595744680851064e-05, "loss": 1.4429720640182495, "step": 40 }, { "epoch": 0.1810344827586207, "grad_norm": 0.65086430311203, "learning_rate": 1.74468085106383e-05, "loss": 1.5474897623062134, "step": 42 }, { "epoch": 0.1896551724137931, "grad_norm": 0.8449164628982544, "learning_rate": 1.8297872340425533e-05, "loss": 0.9270882606506348, "step": 44 }, { "epoch": 0.19827586206896552, "grad_norm": 0.561241626739502, "learning_rate": 1.914893617021277e-05, "loss": 1.1169898509979248, "step": 46 }, { "epoch": 0.20689655172413793, "grad_norm": 0.2715710401535034, "learning_rate": 2e-05, "loss": 1.3745737075805664, "step": 48 }, { "epoch": 0.21551724137931033, "grad_norm": 0.3442396819591522, "learning_rate": 1.999977111433554e-05, "loss": 1.4785292148590088, "step": 50 }, { "epoch": 0.22413793103448276, "grad_norm": 0.6824942827224731, "learning_rate": 1.9999084468984077e-05, "loss": 0.7019240260124207, "step": 52 }, { "epoch": 0.23275862068965517, "grad_norm": 0.31582292914390564, "learning_rate": 1.9997940098870788e-05, "loss": 1.4191925525665283, "step": 54 }, { "epoch": 0.2413793103448276, "grad_norm": 0.27809372544288635, "learning_rate": 1.9996338062202316e-05, "loss": 1.3712444305419922, "step": 56 }, { "epoch": 0.25, "grad_norm": 0.5872206091880798, "learning_rate": 1.9994278440463823e-05, "loss": 1.4150975942611694, "step": 58 }, { "epoch": 0.25862068965517243, "grad_norm": 0.2935428321361542, "learning_rate": 1.9991761338414844e-05, "loss": 1.3828074932098389, "step": 60 }, { "epoch": 0.2672413793103448, "grad_norm": 1.7192302942276, "learning_rate": 1.998878688408395e-05, "loss": 1.0158110857009888, "step": 62 }, { "epoch": 0.27586206896551724, "grad_norm": 0.22481945157051086, "learning_rate": 1.9985355228762237e-05, "loss": 1.3290989398956299, "step": 64 }, { "epoch": 0.28448275862068967, "grad_norm": 0.2971683144569397, "learning_rate": 1.9981466546995648e-05, "loss": 1.303815484046936, "step": 66 }, { "epoch": 0.29310344827586204, "grad_norm": 0.23132647573947906, "learning_rate": 1.997712103657607e-05, "loss": 1.2936116456985474, "step": 68 }, { "epoch": 0.3017241379310345, "grad_norm": 0.2712137699127197, "learning_rate": 1.9972318918531294e-05, "loss": 1.0591557025909424, "step": 70 }, { "epoch": 0.3103448275862069, "grad_norm": 1.0306100845336914, "learning_rate": 1.9967060437113752e-05, "loss": 0.9161477088928223, "step": 72 }, { "epoch": 0.31896551724137934, "grad_norm": 0.7370746731758118, "learning_rate": 1.996134585978812e-05, "loss": 1.130851149559021, "step": 74 }, { "epoch": 0.3275862068965517, "grad_norm": 0.36369481682777405, "learning_rate": 1.995517547721769e-05, "loss": 1.167314052581787, "step": 76 }, { "epoch": 0.33620689655172414, "grad_norm": 0.31680384278297424, "learning_rate": 1.9948549603249602e-05, "loss": 1.1086735725402832, "step": 78 }, { "epoch": 0.3448275862068966, "grad_norm": 1.57016921043396, "learning_rate": 1.9941468574898867e-05, "loss": 1.0062172412872314, "step": 80 }, { "epoch": 0.35344827586206895, "grad_norm": 0.39987874031066895, "learning_rate": 1.993393275233123e-05, "loss": 1.3131077289581299, "step": 82 }, { "epoch": 0.3620689655172414, "grad_norm": 0.738694965839386, "learning_rate": 1.9925942518844875e-05, "loss": 1.1570929288864136, "step": 84 }, { "epoch": 0.3706896551724138, "grad_norm": 0.4991850256919861, "learning_rate": 1.991749828085088e-05, "loss": 1.3317445516586304, "step": 86 }, { "epoch": 0.3793103448275862, "grad_norm": 0.496286541223526, "learning_rate": 1.9908600467852585e-05, "loss": 1.2484678030014038, "step": 88 }, { "epoch": 0.3879310344827586, "grad_norm": 0.6867333054542542, "learning_rate": 1.9899249532423733e-05, "loss": 1.0302324295043945, "step": 90 }, { "epoch": 0.39655172413793105, "grad_norm": 0.2537033259868622, "learning_rate": 1.9889445950185452e-05, "loss": 0.8809990882873535, "step": 92 }, { "epoch": 0.4051724137931034, "grad_norm": 0.7086202502250671, "learning_rate": 1.9879190219782058e-05, "loss": 1.0718659162521362, "step": 94 }, { "epoch": 0.41379310344827586, "grad_norm": 0.6780977845191956, "learning_rate": 1.98684828628557e-05, "loss": 1.2635523080825806, "step": 96 }, { "epoch": 0.4224137931034483, "grad_norm": 0.9746212363243103, "learning_rate": 1.9857324424019827e-05, "loss": 1.186186671257019, "step": 98 }, { "epoch": 0.43103448275862066, "grad_norm": 1.5146777629852295, "learning_rate": 1.9845715470831476e-05, "loss": 1.1258275508880615, "step": 100 }, { "epoch": 0.4396551724137931, "grad_norm": 0.6449897289276123, "learning_rate": 1.983365659376242e-05, "loss": 1.2144218683242798, "step": 102 }, { "epoch": 0.4482758620689655, "grad_norm": 0.3542836606502533, "learning_rate": 1.9821148406169124e-05, "loss": 1.2573832273483276, "step": 104 }, { "epoch": 0.45689655172413796, "grad_norm": 0.7458034753799438, "learning_rate": 1.9808191544261545e-05, "loss": 0.9863552451133728, "step": 106 }, { "epoch": 0.46551724137931033, "grad_norm": 1.6855500936508179, "learning_rate": 1.9794786667070786e-05, "loss": 1.1030296087265015, "step": 108 }, { "epoch": 0.47413793103448276, "grad_norm": 1.344683289527893, "learning_rate": 1.9780934456415567e-05, "loss": 1.1802244186401367, "step": 110 }, { "epoch": 0.4827586206896552, "grad_norm": 0.39590156078338623, "learning_rate": 1.976663561686753e-05, "loss": 1.410926103591919, "step": 112 }, { "epoch": 0.49137931034482757, "grad_norm": 0.6388300657272339, "learning_rate": 1.975189087571544e-05, "loss": 0.8382052183151245, "step": 114 }, { "epoch": 0.5, "grad_norm": 1.3271642923355103, "learning_rate": 1.9736700982928156e-05, "loss": 0.8902297616004944, "step": 116 }, { "epoch": 0.5086206896551724, "grad_norm": 0.28911092877388, "learning_rate": 1.9721066711116496e-05, "loss": 1.2678132057189941, "step": 118 }, { "epoch": 0.5172413793103449, "grad_norm": 0.41628220677375793, "learning_rate": 1.9704988855493948e-05, "loss": 1.1739540100097656, "step": 120 }, { "epoch": 0.5258620689655172, "grad_norm": 0.2931750416755676, "learning_rate": 1.9688468233836224e-05, "loss": 1.2742866277694702, "step": 122 }, { "epoch": 0.5344827586206896, "grad_norm": 0.3954867422580719, "learning_rate": 1.9671505686439637e-05, "loss": 1.3943136930465698, "step": 124 }, { "epoch": 0.5431034482758621, "grad_norm": 0.45475512742996216, "learning_rate": 1.9654102076078406e-05, "loss": 1.564052939414978, "step": 126 }, { "epoch": 0.5517241379310345, "grad_norm": 0.2707035541534424, "learning_rate": 1.963625828796073e-05, "loss": 1.28196382522583, "step": 128 }, { "epoch": 0.5603448275862069, "grad_norm": 0.32626017928123474, "learning_rate": 1.9617975229683784e-05, "loss": 1.2830570936203003, "step": 130 }, { "epoch": 0.5689655172413793, "grad_norm": 0.9617651104927063, "learning_rate": 1.959925383118756e-05, "loss": 1.1657885313034058, "step": 132 }, { "epoch": 0.5775862068965517, "grad_norm": 0.7409307956695557, "learning_rate": 1.9580095044707553e-05, "loss": 0.7719605565071106, "step": 134 }, { "epoch": 0.5862068965517241, "grad_norm": 0.3257262110710144, "learning_rate": 1.956049984472634e-05, "loss": 0.9887097477912903, "step": 136 }, { "epoch": 0.5948275862068966, "grad_norm": 0.13194787502288818, "learning_rate": 1.954046922792399e-05, "loss": 0.9446215033531189, "step": 138 }, { "epoch": 0.603448275862069, "grad_norm": 0.3538772761821747, "learning_rate": 1.9520004213127412e-05, "loss": 0.9638822078704834, "step": 140 }, { "epoch": 0.6120689655172413, "grad_norm": 0.307935893535614, "learning_rate": 1.9499105841258488e-05, "loss": 1.028863549232483, "step": 142 }, { "epoch": 0.6206896551724138, "grad_norm": 0.2776618003845215, "learning_rate": 1.9477775175281166e-05, "loss": 1.0197412967681885, "step": 144 }, { "epoch": 0.6293103448275862, "grad_norm": 0.2247132509946823, "learning_rate": 1.945601330014737e-05, "loss": 1.2361186742782593, "step": 146 }, { "epoch": 0.6379310344827587, "grad_norm": 0.47068798542022705, "learning_rate": 1.9433821322741814e-05, "loss": 1.2686266899108887, "step": 148 }, { "epoch": 0.646551724137931, "grad_norm": 0.35479265451431274, "learning_rate": 1.9411200371825724e-05, "loss": 1.1161521673202515, "step": 150 }, { "epoch": 0.6551724137931034, "grad_norm": 0.9881391525268555, "learning_rate": 1.9388151597979407e-05, "loss": 0.8658434152603149, "step": 152 }, { "epoch": 0.6637931034482759, "grad_norm": 1.1565440893173218, "learning_rate": 1.9364676173543734e-05, "loss": 1.0216702222824097, "step": 154 }, { "epoch": 0.6724137931034483, "grad_norm": 1.531794548034668, "learning_rate": 1.934077529256051e-05, "loss": 1.0728117227554321, "step": 156 }, { "epoch": 0.6810344827586207, "grad_norm": 0.47022947669029236, "learning_rate": 1.9316450170711732e-05, "loss": 1.2310281991958618, "step": 158 }, { "epoch": 0.6896551724137931, "grad_norm": 0.5281792283058167, "learning_rate": 1.929170204525779e-05, "loss": 1.2321813106536865, "step": 160 }, { "epoch": 0.6982758620689655, "grad_norm": 0.5046831369400024, "learning_rate": 1.9266532174974476e-05, "loss": 1.5227911472320557, "step": 162 }, { "epoch": 0.7068965517241379, "grad_norm": 0.4423198103904724, "learning_rate": 1.9240941840089015e-05, "loss": 0.9460239410400391, "step": 164 }, { "epoch": 0.7155172413793104, "grad_norm": 0.4108419120311737, "learning_rate": 1.9214932342214923e-05, "loss": 1.24778151512146, "step": 166 }, { "epoch": 0.7241379310344828, "grad_norm": 0.40896740555763245, "learning_rate": 1.9188505004285795e-05, "loss": 1.3147329092025757, "step": 168 }, { "epoch": 0.7327586206896551, "grad_norm": 0.5323073863983154, "learning_rate": 1.916166117048803e-05, "loss": 1.223319411277771, "step": 170 }, { "epoch": 0.7413793103448276, "grad_norm": 0.5909634232521057, "learning_rate": 1.9134402206192468e-05, "loss": 1.2373883724212646, "step": 172 }, { "epoch": 0.75, "grad_norm": 6.457983016967773, "learning_rate": 1.910672949788491e-05, "loss": 0.937210202217102, "step": 174 }, { "epoch": 0.7586206896551724, "grad_norm": 0.8323431015014648, "learning_rate": 1.9078644453095634e-05, "loss": 0.6929088234901428, "step": 176 }, { "epoch": 0.7672413793103449, "grad_norm": 1.8793997764587402, "learning_rate": 1.9050148500327783e-05, "loss": 1.1937777996063232, "step": 178 }, { "epoch": 0.7758620689655172, "grad_norm": 0.40397757291793823, "learning_rate": 1.9021243088984705e-05, "loss": 0.9337822198867798, "step": 180 }, { "epoch": 0.7844827586206896, "grad_norm": 0.3196965754032135, "learning_rate": 1.8991929689296245e-05, "loss": 0.9228455424308777, "step": 182 }, { "epoch": 0.7931034482758621, "grad_norm": 0.24245284497737885, "learning_rate": 1.896220979224395e-05, "loss": 0.77471923828125, "step": 184 }, { "epoch": 0.8017241379310345, "grad_norm": 0.35483860969543457, "learning_rate": 1.8932084909485233e-05, "loss": 1.335769772529602, "step": 186 }, { "epoch": 0.8103448275862069, "grad_norm": 1.2779498100280762, "learning_rate": 1.89015565732765e-05, "loss": 1.4579006433486938, "step": 188 }, { "epoch": 0.8189655172413793, "grad_norm": 0.5677570104598999, "learning_rate": 1.8870626336395204e-05, "loss": 1.2512203454971313, "step": 190 }, { "epoch": 0.8275862068965517, "grad_norm": 0.3824968934059143, "learning_rate": 1.8839295772060856e-05, "loss": 1.217123031616211, "step": 192 }, { "epoch": 0.8362068965517241, "grad_norm": 0.3712068200111389, "learning_rate": 1.8807566473855018e-05, "loss": 1.2150022983551025, "step": 194 }, { "epoch": 0.8448275862068966, "grad_norm": 0.4604543447494507, "learning_rate": 1.8775440055640245e-05, "loss": 1.2615362405776978, "step": 196 }, { "epoch": 0.853448275862069, "grad_norm": 0.6100837588310242, "learning_rate": 1.8742918151478008e-05, "loss": 0.9542128443717957, "step": 198 }, { "epoch": 0.8620689655172413, "grad_norm": 0.43527752161026, "learning_rate": 1.8710002415545552e-05, "loss": 1.2213218212127686, "step": 200 }, { "epoch": 0.8706896551724138, "grad_norm": 0.37527814507484436, "learning_rate": 1.867669452205179e-05, "loss": 1.2830454111099243, "step": 202 }, { "epoch": 0.8793103448275862, "grad_norm": 1.642726182937622, "learning_rate": 1.8642996165152126e-05, "loss": 0.8405295610427856, "step": 204 }, { "epoch": 0.8879310344827587, "grad_norm": 0.20496216416358948, "learning_rate": 1.86089090588623e-05, "loss": 1.2193654775619507, "step": 206 }, { "epoch": 0.896551724137931, "grad_norm": 0.3890923261642456, "learning_rate": 1.857443493697119e-05, "loss": 1.2507728338241577, "step": 208 }, { "epoch": 0.9051724137931034, "grad_norm": 0.6140430569648743, "learning_rate": 1.853957555295265e-05, "loss": 0.5853071212768555, "step": 210 }, { "epoch": 0.9137931034482759, "grad_norm": 1.1236848831176758, "learning_rate": 1.850433267987628e-05, "loss": 0.9337871074676514, "step": 212 }, { "epoch": 0.9224137931034483, "grad_norm": 1.0812921524047852, "learning_rate": 1.84687081103173e-05, "loss": 1.1255706548690796, "step": 214 }, { "epoch": 0.9310344827586207, "grad_norm": 0.34510231018066406, "learning_rate": 1.8432703656265317e-05, "loss": 1.2182952165603638, "step": 216 }, { "epoch": 0.9396551724137931, "grad_norm": 1.5022380352020264, "learning_rate": 1.83963211490322e-05, "loss": 0.755200207233429, "step": 218 }, { "epoch": 0.9482758620689655, "grad_norm": 1.6012593507766724, "learning_rate": 1.8359562439158915e-05, "loss": 0.9116122722625732, "step": 220 }, { "epoch": 0.9568965517241379, "grad_norm": 0.5603123903274536, "learning_rate": 1.8322429396321395e-05, "loss": 1.314684271812439, "step": 222 }, { "epoch": 0.9655172413793104, "grad_norm": 1.2745404243469238, "learning_rate": 1.828492390923547e-05, "loss": 0.8659108877182007, "step": 224 }, { "epoch": 0.9741379310344828, "grad_norm": 0.2233542650938034, "learning_rate": 1.824704788556076e-05, "loss": 0.8610473275184631, "step": 226 }, { "epoch": 0.9827586206896551, "grad_norm": 0.27494016289711, "learning_rate": 1.820880325180368e-05, "loss": 1.2119630575180054, "step": 228 }, { "epoch": 0.9913793103448276, "grad_norm": 0.8948925733566284, "learning_rate": 1.817019195321943e-05, "loss": 0.886069118976593, "step": 230 }, { "epoch": 1.0, "grad_norm": 0.4077295958995819, "learning_rate": 1.8131215953713065e-05, "loss": 0.7485522031784058, "step": 232 }, { "epoch": 1.0086206896551724, "grad_norm": 0.6140213012695312, "learning_rate": 1.809187723573959e-05, "loss": 0.8965163826942444, "step": 234 }, { "epoch": 1.0172413793103448, "grad_norm": 0.9723572731018066, "learning_rate": 1.8052177800203142e-05, "loss": 0.745244026184082, "step": 236 }, { "epoch": 1.0258620689655173, "grad_norm": 1.8601301908493042, "learning_rate": 1.8012119666355207e-05, "loss": 0.8928873538970947, "step": 238 }, { "epoch": 1.0344827586206897, "grad_norm": 0.7225033044815063, "learning_rate": 1.7971704871691913e-05, "loss": 0.5402289628982544, "step": 240 }, { "epoch": 1.043103448275862, "grad_norm": 0.3545401394367218, "learning_rate": 1.7930935471850397e-05, "loss": 1.0471925735473633, "step": 242 }, { "epoch": 1.0517241379310345, "grad_norm": 0.36405056715011597, "learning_rate": 1.7889813540504255e-05, "loss": 0.3569323420524597, "step": 244 }, { "epoch": 1.0603448275862069, "grad_norm": 0.44639429450035095, "learning_rate": 1.7848341169258066e-05, "loss": 1.0155720710754395, "step": 246 }, { "epoch": 1.0689655172413792, "grad_norm": 0.3922642469406128, "learning_rate": 1.780652046754099e-05, "loss": 0.9613431096076965, "step": 248 }, { "epoch": 1.0775862068965518, "grad_norm": 0.46293577551841736, "learning_rate": 1.776435356249949e-05, "loss": 0.9193274974822998, "step": 250 }, { "epoch": 1.0862068965517242, "grad_norm": 0.6368116736412048, "learning_rate": 1.772184259888915e-05, "loss": 0.42583054304122925, "step": 252 }, { "epoch": 1.0948275862068966, "grad_norm": 1.0385651588439941, "learning_rate": 1.7678989738965554e-05, "loss": 0.9037254452705383, "step": 254 }, { "epoch": 1.103448275862069, "grad_norm": 0.548372209072113, "learning_rate": 1.7635797162374325e-05, "loss": 0.6561298370361328, "step": 256 }, { "epoch": 1.1120689655172413, "grad_norm": 0.8821052312850952, "learning_rate": 1.7592267066040266e-05, "loss": 0.5268462896347046, "step": 258 }, { "epoch": 1.1206896551724137, "grad_norm": 16.59650993347168, "learning_rate": 1.7548401664055605e-05, "loss": 0.6683530211448669, "step": 260 }, { "epoch": 1.1293103448275863, "grad_norm": 0.24353168904781342, "learning_rate": 1.7504203187567378e-05, "loss": 1.1267895698547363, "step": 262 }, { "epoch": 1.1379310344827587, "grad_norm": 0.23041954636573792, "learning_rate": 1.7459673884663956e-05, "loss": 0.864532470703125, "step": 264 }, { "epoch": 1.146551724137931, "grad_norm": 0.24124076962471008, "learning_rate": 1.7414816020260694e-05, "loss": 1.043933629989624, "step": 266 }, { "epoch": 1.1551724137931034, "grad_norm": 0.36801600456237793, "learning_rate": 1.7369631875984715e-05, "loss": 1.0288755893707275, "step": 268 }, { "epoch": 1.1637931034482758, "grad_norm": 0.2811622619628906, "learning_rate": 1.7324123750058895e-05, "loss": 1.0703890323638916, "step": 270 }, { "epoch": 1.1724137931034484, "grad_norm": 0.8666506409645081, "learning_rate": 1.7278293957184924e-05, "loss": 1.0030405521392822, "step": 272 }, { "epoch": 1.1810344827586208, "grad_norm": 0.8689898252487183, "learning_rate": 1.7232144828425606e-05, "loss": 0.8162426352500916, "step": 274 }, { "epoch": 1.1896551724137931, "grad_norm": 0.28137898445129395, "learning_rate": 1.718567871108627e-05, "loss": 0.5113853216171265, "step": 276 }, { "epoch": 1.1982758620689655, "grad_norm": 0.3475714921951294, "learning_rate": 1.7138897968595394e-05, "loss": 1.0502547025680542, "step": 278 }, { "epoch": 1.206896551724138, "grad_norm": 0.31786224246025085, "learning_rate": 1.7091804980384382e-05, "loss": 0.9660123586654663, "step": 280 }, { "epoch": 1.2155172413793103, "grad_norm": 0.297315388917923, "learning_rate": 1.7044402141766547e-05, "loss": 0.5680896043777466, "step": 282 }, { "epoch": 1.2241379310344827, "grad_norm": 3.397669553756714, "learning_rate": 1.6996691863815274e-05, "loss": 0.6948413848876953, "step": 284 }, { "epoch": 1.2327586206896552, "grad_norm": 0.8230817914009094, "learning_rate": 1.694867657324137e-05, "loss": 0.8091163635253906, "step": 286 }, { "epoch": 1.2413793103448276, "grad_norm": 0.5911218523979187, "learning_rate": 1.6900358712269656e-05, "loss": 0.4585968852043152, "step": 288 }, { "epoch": 1.25, "grad_norm": 0.30154550075531006, "learning_rate": 1.6851740738514745e-05, "loss": 0.9265656471252441, "step": 290 }, { "epoch": 1.2586206896551724, "grad_norm": 0.33858662843704224, "learning_rate": 1.680282512485601e-05, "loss": 0.8860665559768677, "step": 292 }, { "epoch": 1.2672413793103448, "grad_norm": 0.6046611070632935, "learning_rate": 1.675361435931184e-05, "loss": 1.003743052482605, "step": 294 }, { "epoch": 1.2758620689655173, "grad_norm": 0.265019029378891, "learning_rate": 1.670411094491308e-05, "loss": 0.7721095085144043, "step": 296 }, { "epoch": 1.2844827586206897, "grad_norm": 0.1970166265964508, "learning_rate": 1.665431739957569e-05, "loss": 1.0421152114868164, "step": 298 }, { "epoch": 1.293103448275862, "grad_norm": 0.391703337430954, "learning_rate": 1.660423625597273e-05, "loss": 0.9568123817443848, "step": 300 }, { "epoch": 1.3017241379310345, "grad_norm": 0.28192439675331116, "learning_rate": 1.6553870061405496e-05, "loss": 0.610411524772644, "step": 302 }, { "epoch": 1.3103448275862069, "grad_norm": 0.2877638339996338, "learning_rate": 1.6503221377673965e-05, "loss": 0.5043181777000427, "step": 304 }, { "epoch": 1.3189655172413794, "grad_norm": 0.3669877350330353, "learning_rate": 1.6452292780946495e-05, "loss": 1.1974719762802124, "step": 306 }, { "epoch": 1.3275862068965516, "grad_norm": 0.2513487637042999, "learning_rate": 1.6401086861628802e-05, "loss": 0.6518297791481018, "step": 308 }, { "epoch": 1.3362068965517242, "grad_norm": 0.6886904835700989, "learning_rate": 1.6349606224232193e-05, "loss": 0.9824197292327881, "step": 310 }, { "epoch": 1.3448275862068966, "grad_norm": 0.27164769172668457, "learning_rate": 1.6297853487241087e-05, "loss": 0.9464894533157349, "step": 312 }, { "epoch": 1.353448275862069, "grad_norm": 0.6101466417312622, "learning_rate": 1.6245831282979834e-05, "loss": 1.1367565393447876, "step": 314 }, { "epoch": 1.3620689655172413, "grad_norm": 0.4131507873535156, "learning_rate": 1.6193542257478837e-05, "loss": 1.3186949491500854, "step": 316 }, { "epoch": 1.3706896551724137, "grad_norm": 0.39837753772735596, "learning_rate": 1.6140989070339947e-05, "loss": 0.9798977375030518, "step": 318 }, { "epoch": 1.3793103448275863, "grad_norm": 1.0206124782562256, "learning_rate": 1.60881743946012e-05, "loss": 0.7535231709480286, "step": 320 }, { "epoch": 1.3879310344827587, "grad_norm": 0.7909939289093018, "learning_rate": 1.6035100916600856e-05, "loss": 1.412162184715271, "step": 322 }, { "epoch": 1.396551724137931, "grad_norm": 0.604773759841919, "learning_rate": 1.5981771335840744e-05, "loss": 0.5099858641624451, "step": 324 }, { "epoch": 1.4051724137931034, "grad_norm": 0.4729211926460266, "learning_rate": 1.5928188364848995e-05, "loss": 0.5017666220664978, "step": 326 }, { "epoch": 1.4137931034482758, "grad_norm": 0.7915529012680054, "learning_rate": 1.5874354729042023e-05, "loss": 0.8372330069541931, "step": 328 }, { "epoch": 1.4224137931034484, "grad_norm": 0.37416186928749084, "learning_rate": 1.5820273166585947e-05, "loss": 0.7255274057388306, "step": 330 }, { "epoch": 1.4310344827586206, "grad_norm": 0.6319824457168579, "learning_rate": 1.576594642825729e-05, "loss": 0.6583790183067322, "step": 332 }, { "epoch": 1.4396551724137931, "grad_norm": 0.2038448005914688, "learning_rate": 1.571137727730307e-05, "loss": 0.5846832990646362, "step": 334 }, { "epoch": 1.4482758620689655, "grad_norm": 0.442600816488266, "learning_rate": 1.5656568489300265e-05, "loss": 0.6714300513267517, "step": 336 }, { "epoch": 1.456896551724138, "grad_norm": 1.4567723274230957, "learning_rate": 1.560152285201462e-05, "loss": 1.0285781621932983, "step": 338 }, { "epoch": 1.4655172413793103, "grad_norm": 0.9464113712310791, "learning_rate": 1.5546243165258857e-05, "loss": 1.34324049949646, "step": 340 }, { "epoch": 1.4741379310344827, "grad_norm": 0.3753282129764557, "learning_rate": 1.5490732240750275e-05, "loss": 1.1209205389022827, "step": 342 }, { "epoch": 1.4827586206896552, "grad_norm": 0.3289780020713806, "learning_rate": 1.5434992901967735e-05, "loss": 0.944566547870636, "step": 344 }, { "epoch": 1.4913793103448276, "grad_norm": 0.5948997735977173, "learning_rate": 1.5379027984008024e-05, "loss": 0.4405466318130493, "step": 346 }, { "epoch": 1.5, "grad_norm": 1.1603318452835083, "learning_rate": 1.5322840333441687e-05, "loss": 0.8692161440849304, "step": 348 }, { "epoch": 1.5086206896551724, "grad_norm": 0.3296312093734741, "learning_rate": 1.526643280816822e-05, "loss": 1.0229344367980957, "step": 350 }, { "epoch": 1.5172413793103448, "grad_norm": 1.4501453638076782, "learning_rate": 1.5209808277270714e-05, "loss": 0.9797338843345642, "step": 352 }, { "epoch": 1.5258620689655173, "grad_norm": 0.7663815021514893, "learning_rate": 1.515296962086992e-05, "loss": 1.0694770812988281, "step": 354 }, { "epoch": 1.5344827586206895, "grad_norm": 0.7203207612037659, "learning_rate": 1.5095919729977757e-05, "loss": 0.8981337547302246, "step": 356 }, { "epoch": 1.543103448275862, "grad_norm": 0.17651817202568054, "learning_rate": 1.5038661506350267e-05, "loss": 0.7348160743713379, "step": 358 }, { "epoch": 1.5517241379310345, "grad_norm": 0.3057866096496582, "learning_rate": 1.4981197862340015e-05, "loss": 1.3365731239318848, "step": 360 }, { "epoch": 1.5603448275862069, "grad_norm": 0.2411855012178421, "learning_rate": 1.4923531720747975e-05, "loss": 1.0422999858856201, "step": 362 }, { "epoch": 1.5689655172413794, "grad_norm": 0.30987802147865295, "learning_rate": 1.4865666014674833e-05, "loss": 1.064208984375, "step": 364 }, { "epoch": 1.5775862068965516, "grad_norm": 0.4095076024532318, "learning_rate": 1.4807603687371835e-05, "loss": 0.7693328857421875, "step": 366 }, { "epoch": 1.5862068965517242, "grad_norm": 0.2905380129814148, "learning_rate": 1.4749347692091061e-05, "loss": 1.014492154121399, "step": 368 }, { "epoch": 1.5948275862068966, "grad_norm": 0.2323673665523529, "learning_rate": 1.4690900991935218e-05, "loss": 0.9833155274391174, "step": 370 }, { "epoch": 1.603448275862069, "grad_norm": 1.5103213787078857, "learning_rate": 1.4632266559706933e-05, "loss": 1.0599433183670044, "step": 372 }, { "epoch": 1.6120689655172413, "grad_norm": 0.3394826352596283, "learning_rate": 1.457344737775753e-05, "loss": 0.7715789675712585, "step": 374 }, { "epoch": 1.6206896551724137, "grad_norm": 0.24792537093162537, "learning_rate": 1.451444643783536e-05, "loss": 1.008685827255249, "step": 376 }, { "epoch": 1.6293103448275863, "grad_norm": 0.2639085054397583, "learning_rate": 1.4455266740933598e-05, "loss": 1.1693607568740845, "step": 378 }, { "epoch": 1.6379310344827587, "grad_norm": 0.27107664942741394, "learning_rate": 1.439591129713764e-05, "loss": 0.7295485734939575, "step": 380 }, { "epoch": 1.646551724137931, "grad_norm": 2.177382707595825, "learning_rate": 1.4336383125471974e-05, "loss": 1.3163925409317017, "step": 382 }, { "epoch": 1.6551724137931034, "grad_norm": 0.5485315322875977, "learning_rate": 1.4276685253746623e-05, "loss": 1.00065279006958, "step": 384 }, { "epoch": 1.6637931034482758, "grad_norm": 0.25248005986213684, "learning_rate": 1.4216820718403153e-05, "loss": 0.9677169322967529, "step": 386 }, { "epoch": 1.6724137931034484, "grad_norm": 0.3703874945640564, "learning_rate": 1.4156792564360222e-05, "loss": 1.3287030458450317, "step": 388 }, { "epoch": 1.6810344827586206, "grad_norm": 1.0064659118652344, "learning_rate": 1.4096603844858696e-05, "loss": 0.8481764197349548, "step": 390 }, { "epoch": 1.6896551724137931, "grad_norm": 0.3846883773803711, "learning_rate": 1.4036257621306375e-05, "loss": 0.41724586486816406, "step": 392 }, { "epoch": 1.6982758620689655, "grad_norm": 1.3841114044189453, "learning_rate": 1.3975756963122242e-05, "loss": 1.0509485006332397, "step": 394 }, { "epoch": 1.706896551724138, "grad_norm": 0.7592343688011169, "learning_rate": 1.3915104947580382e-05, "loss": 1.0144211053848267, "step": 396 }, { "epoch": 1.7155172413793105, "grad_norm": 1.6238418817520142, "learning_rate": 1.3854304659653435e-05, "loss": 1.0040127038955688, "step": 398 }, { "epoch": 1.7241379310344827, "grad_norm": 0.42679479718208313, "learning_rate": 1.3793359191855684e-05, "loss": 1.0181949138641357, "step": 400 }, { "epoch": 1.7327586206896552, "grad_norm": 0.29004621505737305, "learning_rate": 1.3732271644085779e-05, "loss": 0.7873343229293823, "step": 402 }, { "epoch": 1.7413793103448276, "grad_norm": 0.2753044366836548, "learning_rate": 1.3671045123469038e-05, "loss": 0.594070553779602, "step": 404 }, { "epoch": 1.75, "grad_norm": 0.860210657119751, "learning_rate": 1.3609682744199434e-05, "loss": 0.6642279028892517, "step": 406 }, { "epoch": 1.7586206896551724, "grad_norm": 0.3674435615539551, "learning_rate": 1.354818762738118e-05, "loss": 0.7117359042167664, "step": 408 }, { "epoch": 1.7672413793103448, "grad_norm": 0.23552259802818298, "learning_rate": 1.3486562900869975e-05, "loss": 0.7889873385429382, "step": 410 }, { "epoch": 1.7758620689655173, "grad_norm": 0.3450159728527069, "learning_rate": 1.3424811699113924e-05, "loss": 0.7825038433074951, "step": 412 }, { "epoch": 1.7844827586206895, "grad_norm": 0.6731851100921631, "learning_rate": 1.3362937162994115e-05, "loss": 0.6144068837165833, "step": 414 }, { "epoch": 1.793103448275862, "grad_norm": 0.29475781321525574, "learning_rate": 1.3300942439664826e-05, "loss": 0.7337537407875061, "step": 416 }, { "epoch": 1.8017241379310345, "grad_norm": 2.000307083129883, "learning_rate": 1.3238830682393498e-05, "loss": 0.9792155027389526, "step": 418 }, { "epoch": 1.8103448275862069, "grad_norm": 0.6585050821304321, "learning_rate": 1.317660505040031e-05, "loss": 1.0592936277389526, "step": 420 }, { "epoch": 1.8189655172413794, "grad_norm": 0.6050742268562317, "learning_rate": 1.3114268708697517e-05, "loss": 1.1423420906066895, "step": 422 }, { "epoch": 1.8275862068965516, "grad_norm": 0.22784169018268585, "learning_rate": 1.305182482792845e-05, "loss": 1.0336556434631348, "step": 424 }, { "epoch": 1.8362068965517242, "grad_norm": 0.28103554248809814, "learning_rate": 1.298927658420625e-05, "loss": 0.633764386177063, "step": 426 }, { "epoch": 1.8448275862068966, "grad_norm": 0.3265269696712494, "learning_rate": 1.292662715895232e-05, "loss": 1.000012993812561, "step": 428 }, { "epoch": 1.853448275862069, "grad_norm": 0.25722262263298035, "learning_rate": 1.2863879738734515e-05, "loss": 0.972018301486969, "step": 430 }, { "epoch": 1.8620689655172413, "grad_norm": 0.3606722056865692, "learning_rate": 1.2801037515105048e-05, "loss": 1.0186474323272705, "step": 432 }, { "epoch": 1.8706896551724137, "grad_norm": 0.5681195855140686, "learning_rate": 1.2738103684438167e-05, "loss": 1.1112819910049438, "step": 434 }, { "epoch": 1.8793103448275863, "grad_norm": 0.2608093321323395, "learning_rate": 1.267508144776757e-05, "loss": 0.6823700070381165, "step": 436 }, { "epoch": 1.8879310344827587, "grad_norm": 0.5412386059761047, "learning_rate": 1.2611974010623598e-05, "loss": 0.9664647579193115, "step": 438 }, { "epoch": 1.896551724137931, "grad_norm": 0.2498435080051422, "learning_rate": 1.2548784582870175e-05, "loss": 0.9077426791191101, "step": 440 }, { "epoch": 1.9051724137931034, "grad_norm": 0.25406646728515625, "learning_rate": 1.2485516378541562e-05, "loss": 1.095183253288269, "step": 442 }, { "epoch": 1.9137931034482758, "grad_norm": 0.3728492558002472, "learning_rate": 1.2422172615678867e-05, "loss": 0.2406305968761444, "step": 444 }, { "epoch": 1.9224137931034484, "grad_norm": 1.3624857664108276, "learning_rate": 1.2358756516166368e-05, "loss": 0.7011273503303528, "step": 446 }, { "epoch": 1.9310344827586206, "grad_norm": 0.31631484627723694, "learning_rate": 1.2295271305567637e-05, "loss": 1.040317177772522, "step": 448 }, { "epoch": 1.9396551724137931, "grad_norm": 1.0889196395874023, "learning_rate": 1.2231720212961476e-05, "loss": 1.0238956212997437, "step": 450 }, { "epoch": 1.9482758620689655, "grad_norm": 0.17187516391277313, "learning_rate": 1.2168106470777676e-05, "loss": 0.8691494464874268, "step": 452 }, { "epoch": 1.956896551724138, "grad_norm": 0.3179636299610138, "learning_rate": 1.2104433314632605e-05, "loss": 1.03307044506073, "step": 454 }, { "epoch": 1.9655172413793105, "grad_norm": 0.2639262080192566, "learning_rate": 1.2040703983164628e-05, "loss": 1.0065069198608398, "step": 456 }, { "epoch": 1.9741379310344827, "grad_norm": 8.715909004211426, "learning_rate": 1.1976921717869387e-05, "loss": 0.3249227702617645, "step": 458 }, { "epoch": 1.9827586206896552, "grad_norm": 0.4118382930755615, "learning_rate": 1.1913089762934918e-05, "loss": 0.9767223596572876, "step": 460 }, { "epoch": 1.9913793103448276, "grad_norm": 0.8583071827888489, "learning_rate": 1.184921136507665e-05, "loss": 0.6757299304008484, "step": 462 }, { "epoch": 2.0, "grad_norm": 1.8066082000732422, "learning_rate": 1.1785289773372252e-05, "loss": 0.8873772621154785, "step": 464 }, { "epoch": 2.0086206896551726, "grad_norm": 0.31068357825279236, "learning_rate": 1.1721328239096397e-05, "loss": 0.4577694237232208, "step": 466 }, { "epoch": 2.0172413793103448, "grad_norm": 1.1041500568389893, "learning_rate": 1.1657330015555365e-05, "loss": 0.729465663433075, "step": 468 }, { "epoch": 2.0258620689655173, "grad_norm": 0.2672136723995209, "learning_rate": 1.159329835792158e-05, "loss": 0.58217453956604, "step": 470 }, { "epoch": 2.0344827586206895, "grad_norm": 2.1604278087615967, "learning_rate": 1.1529236523068046e-05, "loss": 0.5115339159965515, "step": 472 }, { "epoch": 2.043103448275862, "grad_norm": 0.3200737237930298, "learning_rate": 1.146514776940268e-05, "loss": 0.5147908329963684, "step": 474 }, { "epoch": 2.0517241379310347, "grad_norm": 0.6346356272697449, "learning_rate": 1.1401035356702585e-05, "loss": 0.5318877100944519, "step": 476 }, { "epoch": 2.060344827586207, "grad_norm": 0.5195797681808472, "learning_rate": 1.133690254594825e-05, "loss": 0.3974412977695465, "step": 478 }, { "epoch": 2.0689655172413794, "grad_norm": 0.3041704297065735, "learning_rate": 1.1272752599157673e-05, "loss": 0.7926555871963501, "step": 480 }, { "epoch": 2.0775862068965516, "grad_norm": 0.3499699831008911, "learning_rate": 1.1208588779220454e-05, "loss": 0.4678128659725189, "step": 482 }, { "epoch": 2.086206896551724, "grad_norm": 0.33471551537513733, "learning_rate": 1.1144414349731826e-05, "loss": 0.6200590133666992, "step": 484 }, { "epoch": 2.0948275862068964, "grad_norm": 0.2929646372795105, "learning_rate": 1.1080232574826669e-05, "loss": 0.5513038039207458, "step": 486 }, { "epoch": 2.103448275862069, "grad_norm": 1.0158162117004395, "learning_rate": 1.101604671901346e-05, "loss": 0.6488674283027649, "step": 488 }, { "epoch": 2.1120689655172415, "grad_norm": 0.3108230531215668, "learning_rate": 1.0951860047008268e-05, "loss": 0.6901264786720276, "step": 490 }, { "epoch": 2.1206896551724137, "grad_norm": 1.0879099369049072, "learning_rate": 1.0887675823568662e-05, "loss": 0.6872219443321228, "step": 492 }, { "epoch": 2.1293103448275863, "grad_norm": 0.6477283835411072, "learning_rate": 1.0823497313327666e-05, "loss": 0.7422826886177063, "step": 494 }, { "epoch": 2.1379310344827585, "grad_norm": 0.44943997263908386, "learning_rate": 1.075932778062772e-05, "loss": 0.6594029664993286, "step": 496 }, { "epoch": 2.146551724137931, "grad_norm": 0.9052010774612427, "learning_rate": 1.0695170489354627e-05, "loss": 0.3747510313987732, "step": 498 }, { "epoch": 2.1551724137931036, "grad_norm": 0.7915022969245911, "learning_rate": 1.0631028702771558e-05, "loss": 0.3904026746749878, "step": 500 }, { "epoch": 2.163793103448276, "grad_norm": 0.3351036012172699, "learning_rate": 1.0566905683353048e-05, "loss": 0.42320704460144043, "step": 502 }, { "epoch": 2.1724137931034484, "grad_norm": 0.39706820249557495, "learning_rate": 1.0502804692619085e-05, "loss": 0.5195796489715576, "step": 504 }, { "epoch": 2.1810344827586206, "grad_norm": 0.7268723249435425, "learning_rate": 1.0438728990969182e-05, "loss": 0.7010811567306519, "step": 506 }, { "epoch": 2.189655172413793, "grad_norm": 2.3827953338623047, "learning_rate": 1.0374681837516585e-05, "loss": 0.47865381836891174, "step": 508 }, { "epoch": 2.1982758620689653, "grad_norm": 0.3070574998855591, "learning_rate": 1.0310666489922452e-05, "loss": 0.7136699557304382, "step": 510 }, { "epoch": 2.206896551724138, "grad_norm": 0.36808905005455017, "learning_rate": 1.0246686204230213e-05, "loss": 0.5507462024688721, "step": 512 }, { "epoch": 2.2155172413793105, "grad_norm": 0.49329182505607605, "learning_rate": 1.0182744234699897e-05, "loss": 0.5582562685012817, "step": 514 }, { "epoch": 2.2241379310344827, "grad_norm": 1.3508820533752441, "learning_rate": 1.0118843833642672e-05, "loss": 0.403819739818573, "step": 516 }, { "epoch": 2.2327586206896552, "grad_norm": 0.1710726022720337, "learning_rate": 1.005498825125536e-05, "loss": 0.0842498317360878, "step": 518 }, { "epoch": 2.2413793103448274, "grad_norm": 0.8797479867935181, "learning_rate": 9.991180735455171e-06, "loss": 0.14793738722801208, "step": 520 }, { "epoch": 2.25, "grad_norm": 0.6412666440010071, "learning_rate": 9.927424531714463e-06, "loss": 0.7687300443649292, "step": 522 }, { "epoch": 2.2586206896551726, "grad_norm": 0.3679327070713043, "learning_rate": 9.863722882895703e-06, "loss": 0.5136147141456604, "step": 524 }, { "epoch": 2.2672413793103448, "grad_norm": 0.66014564037323, "learning_rate": 9.800079029086487e-06, "loss": 0.48577654361724854, "step": 526 }, { "epoch": 2.2758620689655173, "grad_norm": 0.36126595735549927, "learning_rate": 9.736496207434767e-06, "loss": 0.5481493473052979, "step": 528 }, { "epoch": 2.2844827586206895, "grad_norm": 0.18358245491981506, "learning_rate": 9.672977651984183e-06, "loss": 0.4460916519165039, "step": 530 }, { "epoch": 2.293103448275862, "grad_norm": 0.5238314867019653, "learning_rate": 9.609526593509572e-06, "loss": 0.44660893082618713, "step": 532 }, { "epoch": 2.3017241379310347, "grad_norm": 0.45486119389533997, "learning_rate": 9.54614625935264e-06, "loss": 0.4977568984031677, "step": 534 }, { "epoch": 2.310344827586207, "grad_norm": 0.3980855643749237, "learning_rate": 9.482839873257814e-06, "loss": 0.44564345479011536, "step": 536 }, { "epoch": 2.3189655172413794, "grad_norm": 0.1288735568523407, "learning_rate": 9.41961065520825e-06, "loss": 0.34829026460647583, "step": 538 }, { "epoch": 2.3275862068965516, "grad_norm": 0.3644492030143738, "learning_rate": 9.356461821262088e-06, "loss": 0.42181143164634705, "step": 540 }, { "epoch": 2.336206896551724, "grad_norm": 0.45030930638313293, "learning_rate": 9.293396583388835e-06, "loss": 0.6050075888633728, "step": 542 }, { "epoch": 2.344827586206897, "grad_norm": 0.49424102902412415, "learning_rate": 9.230418149306028e-06, "loss": 0.7277567982673645, "step": 544 }, { "epoch": 2.353448275862069, "grad_norm": 0.2475537806749344, "learning_rate": 9.167529722316039e-06, "loss": 0.25289204716682434, "step": 546 }, { "epoch": 2.3620689655172415, "grad_norm": 0.5678421258926392, "learning_rate": 9.104734501143195e-06, "loss": 0.732049822807312, "step": 548 }, { "epoch": 2.3706896551724137, "grad_norm": 5.805917739868164, "learning_rate": 9.04203567977102e-06, "loss": 0.561985969543457, "step": 550 }, { "epoch": 2.3793103448275863, "grad_norm": 1.29057776927948, "learning_rate": 8.979436447279833e-06, "loss": 0.7146962285041809, "step": 552 }, { "epoch": 2.3879310344827585, "grad_norm": 0.24367839097976685, "learning_rate": 8.916939987684497e-06, "loss": 0.5743066072463989, "step": 554 }, { "epoch": 2.396551724137931, "grad_norm": 0.29842236638069153, "learning_rate": 8.854549479772508e-06, "loss": 0.6506761312484741, "step": 556 }, { "epoch": 2.405172413793103, "grad_norm": 0.4994705319404602, "learning_rate": 8.792268096942265e-06, "loss": 0.4716731607913971, "step": 558 }, { "epoch": 2.413793103448276, "grad_norm": 0.3811204135417938, "learning_rate": 8.730099007041712e-06, "loss": 0.6651344299316406, "step": 560 }, { "epoch": 2.4224137931034484, "grad_norm": 0.7616989016532898, "learning_rate": 8.668045372207165e-06, "loss": 0.5968424081802368, "step": 562 }, { "epoch": 2.4310344827586206, "grad_norm": 0.31395435333251953, "learning_rate": 8.606110348702502e-06, "loss": 0.656068742275238, "step": 564 }, { "epoch": 2.439655172413793, "grad_norm": 3.1607255935668945, "learning_rate": 8.544297086758612e-06, "loss": 0.6287741661071777, "step": 566 }, { "epoch": 2.4482758620689653, "grad_norm": 0.47689536213874817, "learning_rate": 8.482608730413173e-06, "loss": 0.3020762503147125, "step": 568 }, { "epoch": 2.456896551724138, "grad_norm": 0.2523362636566162, "learning_rate": 8.421048417350722e-06, "loss": 1.0642119646072388, "step": 570 }, { "epoch": 2.4655172413793105, "grad_norm": 0.746324896812439, "learning_rate": 8.359619278743072e-06, "loss": 0.46571430563926697, "step": 572 }, { "epoch": 2.4741379310344827, "grad_norm": 0.2691429555416107, "learning_rate": 8.298324439090044e-06, "loss": 0.5474472641944885, "step": 574 }, { "epoch": 2.4827586206896552, "grad_norm": 0.3174271881580353, "learning_rate": 8.23716701606056e-06, "loss": 0.7401635050773621, "step": 576 }, { "epoch": 2.4913793103448274, "grad_norm": 1.0416983366012573, "learning_rate": 8.176150120334035e-06, "loss": 0.4356614053249359, "step": 578 }, { "epoch": 2.5, "grad_norm": 0.4628841280937195, "learning_rate": 8.115276855442186e-06, "loss": 0.7132285237312317, "step": 580 }, { "epoch": 2.5086206896551726, "grad_norm": 0.2986053228378296, "learning_rate": 8.054550317611166e-06, "loss": 0.6939521431922913, "step": 582 }, { "epoch": 2.5172413793103448, "grad_norm": 0.4543410837650299, "learning_rate": 7.99397359560408e-06, "loss": 0.5915881395339966, "step": 584 }, { "epoch": 2.5258620689655173, "grad_norm": 0.42003390192985535, "learning_rate": 7.933549770563868e-06, "loss": 0.5379845499992371, "step": 586 }, { "epoch": 2.5344827586206895, "grad_norm": 0.28614842891693115, "learning_rate": 7.873281915856618e-06, "loss": 0.6815016269683838, "step": 588 }, { "epoch": 2.543103448275862, "grad_norm": 0.32113906741142273, "learning_rate": 7.8131730969152e-06, "loss": 0.7555568218231201, "step": 590 }, { "epoch": 2.5517241379310347, "grad_norm": 0.3256307542324066, "learning_rate": 7.753226371083398e-06, "loss": 0.6491318941116333, "step": 592 }, { "epoch": 2.560344827586207, "grad_norm": 0.3508186638355255, "learning_rate": 7.693444787460346e-06, "loss": 0.38945457339286804, "step": 594 }, { "epoch": 2.5689655172413794, "grad_norm": 0.19432027637958527, "learning_rate": 7.6338313867455e-06, "loss": 0.5126080513000488, "step": 596 }, { "epoch": 2.5775862068965516, "grad_norm": 0.3698360323905945, "learning_rate": 7.574389201083925e-06, "loss": 0.6170058250427246, "step": 598 }, { "epoch": 2.586206896551724, "grad_norm": 0.7802625894546509, "learning_rate": 7.515121253912107e-06, "loss": 0.6505869030952454, "step": 600 }, { "epoch": 2.594827586206897, "grad_norm": 0.12341656535863876, "learning_rate": 7.456030559804146e-06, "loss": 0.47480010986328125, "step": 602 }, { "epoch": 2.603448275862069, "grad_norm": 0.6200041174888611, "learning_rate": 7.3971201243184425e-06, "loss": 0.5783487558364868, "step": 604 }, { "epoch": 2.612068965517241, "grad_norm": 0.9620341062545776, "learning_rate": 7.338392943844807e-06, "loss": 0.5066084265708923, "step": 606 }, { "epoch": 2.6206896551724137, "grad_norm": 0.3163914382457733, "learning_rate": 7.279852005452072e-06, "loss": 0.7519516348838806, "step": 608 }, { "epoch": 2.6293103448275863, "grad_norm": 0.7371922731399536, "learning_rate": 7.221500286736145e-06, "loss": 0.6951370239257812, "step": 610 }, { "epoch": 2.637931034482759, "grad_norm": 0.87571781873703, "learning_rate": 7.16334075566856e-06, "loss": 0.7426925301551819, "step": 612 }, { "epoch": 2.646551724137931, "grad_norm": 0.34502312541007996, "learning_rate": 7.105376370445516e-06, "loss": 0.6338915824890137, "step": 614 }, { "epoch": 2.655172413793103, "grad_norm": 0.551734209060669, "learning_rate": 7.047610079337426e-06, "loss": 0.43320754170417786, "step": 616 }, { "epoch": 2.663793103448276, "grad_norm": 0.3614158034324646, "learning_rate": 6.990044820538932e-06, "loss": 0.7193683981895447, "step": 618 }, { "epoch": 2.6724137931034484, "grad_norm": 0.15170885622501373, "learning_rate": 6.932683522019486e-06, "loss": 0.4045131802558899, "step": 620 }, { "epoch": 2.6810344827586206, "grad_norm": 0.3657248318195343, "learning_rate": 6.875529101374407e-06, "loss": 0.7818766832351685, "step": 622 }, { "epoch": 2.689655172413793, "grad_norm": 0.34267038106918335, "learning_rate": 6.818584465676476e-06, "loss": 0.4748293161392212, "step": 624 }, { "epoch": 2.6982758620689653, "grad_norm": 0.2588467001914978, "learning_rate": 6.761852511328097e-06, "loss": 0.6603924036026001, "step": 626 }, { "epoch": 2.706896551724138, "grad_norm": 0.5171433687210083, "learning_rate": 6.705336123913943e-06, "loss": 0.4325425326824188, "step": 628 }, { "epoch": 2.7155172413793105, "grad_norm": 0.5215042233467102, "learning_rate": 6.649038178054216e-06, "loss": 0.8396017551422119, "step": 630 }, { "epoch": 2.7241379310344827, "grad_norm": 1.0772958993911743, "learning_rate": 6.592961537258415e-06, "loss": 0.34978973865509033, "step": 632 }, { "epoch": 2.7327586206896552, "grad_norm": 0.2992818057537079, "learning_rate": 6.53710905377969e-06, "loss": 0.7622851133346558, "step": 634 }, { "epoch": 2.7413793103448274, "grad_norm": 0.5735934972763062, "learning_rate": 6.48148356846978e-06, "loss": 0.5066753625869751, "step": 636 }, { "epoch": 2.75, "grad_norm": 0.30223897099494934, "learning_rate": 6.426087910634488e-06, "loss": 0.7104685306549072, "step": 638 }, { "epoch": 2.7586206896551726, "grad_norm": 0.575935959815979, "learning_rate": 6.370924897889815e-06, "loss": 0.45420828461647034, "step": 640 }, { "epoch": 2.7672413793103448, "grad_norm": 0.6481202244758606, "learning_rate": 6.315997336018602e-06, "loss": 0.6258912086486816, "step": 642 }, { "epoch": 2.7758620689655173, "grad_norm": 0.3766607940196991, "learning_rate": 6.261308018827857e-06, "loss": 0.8025404214859009, "step": 644 }, { "epoch": 2.7844827586206895, "grad_norm": 0.47904494404792786, "learning_rate": 6.206859728006616e-06, "loss": 0.6612002849578857, "step": 646 }, { "epoch": 2.793103448275862, "grad_norm": 0.2501460015773773, "learning_rate": 6.152655232984493e-06, "loss": 0.3472132980823517, "step": 648 }, { "epoch": 2.8017241379310347, "grad_norm": 1.059028148651123, "learning_rate": 6.0986972907907805e-06, "loss": 0.5596845746040344, "step": 650 }, { "epoch": 2.810344827586207, "grad_norm": 1.5540813207626343, "learning_rate": 6.044988645914256e-06, "loss": 0.7260704636573792, "step": 652 }, { "epoch": 2.8189655172413794, "grad_norm": 0.5435662865638733, "learning_rate": 5.991532030163549e-06, "loss": 0.7274701595306396, "step": 654 }, { "epoch": 2.8275862068965516, "grad_norm": 0.24130015075206757, "learning_rate": 5.938330162528225e-06, "loss": 0.5958088636398315, "step": 656 }, { "epoch": 2.836206896551724, "grad_norm": 0.32772472500801086, "learning_rate": 5.8853857490404605e-06, "loss": 0.7417409420013428, "step": 658 }, { "epoch": 2.844827586206897, "grad_norm": 0.34546273946762085, "learning_rate": 5.832701482637433e-06, "loss": 0.19964106380939484, "step": 660 }, { "epoch": 2.853448275862069, "grad_norm": 0.9264662861824036, "learning_rate": 5.780280043024316e-06, "loss": 0.3988272547721863, "step": 662 }, { "epoch": 2.862068965517241, "grad_norm": 0.47499191761016846, "learning_rate": 5.728124096538014e-06, "loss": 0.4928115904331207, "step": 664 }, { "epoch": 2.8706896551724137, "grad_norm": 0.24683460593223572, "learning_rate": 5.676236296011513e-06, "loss": 0.42225298285484314, "step": 666 }, { "epoch": 2.8793103448275863, "grad_norm": 0.4660603106021881, "learning_rate": 5.624619280638979e-06, "loss": 0.36263778805732727, "step": 668 }, { "epoch": 2.887931034482759, "grad_norm": 0.8654661774635315, "learning_rate": 5.573275675841481e-06, "loss": 0.720154345035553, "step": 670 }, { "epoch": 2.896551724137931, "grad_norm": 0.5549874901771545, "learning_rate": 5.522208093133492e-06, "loss": 0.44341281056404114, "step": 672 }, { "epoch": 2.905172413793103, "grad_norm": 0.3595507740974426, "learning_rate": 5.4714191299900325e-06, "loss": 0.712740957736969, "step": 674 }, { "epoch": 2.913793103448276, "grad_norm": 0.898064374923706, "learning_rate": 5.4209113697145656e-06, "loss": 0.7482072710990906, "step": 676 }, { "epoch": 2.9224137931034484, "grad_norm": 0.32744261622428894, "learning_rate": 5.370687381307591e-06, "loss": 0.6825791001319885, "step": 678 }, { "epoch": 2.9310344827586206, "grad_norm": 0.3922792971134186, "learning_rate": 5.320749719335997e-06, "loss": 0.5156247615814209, "step": 680 }, { "epoch": 2.939655172413793, "grad_norm": 0.21706661581993103, "learning_rate": 5.271100923803095e-06, "loss": 0.29097798466682434, "step": 682 }, { "epoch": 2.9482758620689653, "grad_norm": 0.2500763237476349, "learning_rate": 5.2217435200194595e-06, "loss": 0.42494314908981323, "step": 684 }, { "epoch": 2.956896551724138, "grad_norm": 0.28385624289512634, "learning_rate": 5.172680018474456e-06, "loss": 0.6773520708084106, "step": 686 }, { "epoch": 2.9655172413793105, "grad_norm": 0.32070091366767883, "learning_rate": 5.123912914708566e-06, "loss": 0.6991716027259827, "step": 688 }, { "epoch": 2.9741379310344827, "grad_norm": 0.28078293800354004, "learning_rate": 5.075444689186439e-06, "loss": 0.9952356815338135, "step": 690 }, { "epoch": 2.9827586206896552, "grad_norm": 0.30109333992004395, "learning_rate": 5.02727780717075e-06, "loss": 0.9628766179084778, "step": 692 }, { "epoch": 2.9913793103448274, "grad_norm": 0.4280763864517212, "learning_rate": 4.979414718596779e-06, "loss": 0.46527406573295593, "step": 694 }, { "epoch": 3.0, "grad_norm": 0.32468336820602417, "learning_rate": 4.931857857947829e-06, "loss": 0.8153132200241089, "step": 696 }, { "epoch": 3.0086206896551726, "grad_norm": 0.38036271929740906, "learning_rate": 4.884609644131373e-06, "loss": 0.2907155454158783, "step": 698 }, { "epoch": 3.0172413793103448, "grad_norm": 0.28837043046951294, "learning_rate": 4.837672480356037e-06, "loss": 0.4242869019508362, "step": 700 }, { "epoch": 3.0258620689655173, "grad_norm": 0.582526683807373, "learning_rate": 4.791048754009362e-06, "loss": 0.3136082589626312, "step": 702 }, { "epoch": 3.0344827586206895, "grad_norm": 0.7384637594223022, "learning_rate": 4.7447408365363616e-06, "loss": 0.6226381063461304, "step": 704 }, { "epoch": 3.043103448275862, "grad_norm": 0.09337347000837326, "learning_rate": 4.698751083318918e-06, "loss": 0.0870320051908493, "step": 706 }, { "epoch": 3.0517241379310347, "grad_norm": 1.523980736732483, "learning_rate": 4.653081833555975e-06, "loss": 0.379879891872406, "step": 708 }, { "epoch": 3.060344827586207, "grad_norm": 0.2947269380092621, "learning_rate": 4.60773541014454e-06, "loss": 0.10685593634843826, "step": 710 }, { "epoch": 3.0689655172413794, "grad_norm": 0.9110690951347351, "learning_rate": 4.562714119561566e-06, "loss": 0.40309441089630127, "step": 712 }, { "epoch": 3.0775862068965516, "grad_norm": 0.4863778054714203, "learning_rate": 4.518020251746607e-06, "loss": 0.6567556262016296, "step": 714 }, { "epoch": 3.086206896551724, "grad_norm": 0.4967314898967743, "learning_rate": 4.473656079985362e-06, "loss": 0.14177639782428741, "step": 716 }, { "epoch": 3.0948275862068964, "grad_norm": 0.4328520596027374, "learning_rate": 4.429623860794032e-06, "loss": 0.3785516917705536, "step": 718 }, { "epoch": 3.103448275862069, "grad_norm": 0.7979432344436646, "learning_rate": 4.38592583380457e-06, "loss": 0.18618693947792053, "step": 720 }, { "epoch": 3.1120689655172415, "grad_norm": 0.3564269542694092, "learning_rate": 4.3425642216507325e-06, "loss": 0.20070935785770416, "step": 722 }, { "epoch": 3.1206896551724137, "grad_norm": 0.34848275780677795, "learning_rate": 4.2995412298550624e-06, "loss": 0.3287600874900818, "step": 724 }, { "epoch": 3.1293103448275863, "grad_norm": 0.4305904507637024, "learning_rate": 4.256859046716677e-06, "loss": 0.36046263575553894, "step": 726 }, { "epoch": 3.1379310344827585, "grad_norm": 0.708617627620697, "learning_rate": 4.214519843199995e-06, "loss": 0.4107988774776459, "step": 728 }, { "epoch": 3.146551724137931, "grad_norm": 0.0694451779127121, "learning_rate": 4.172525772824283e-06, "loss": 0.2075681984424591, "step": 730 }, { "epoch": 3.1551724137931036, "grad_norm": 0.164693221449852, "learning_rate": 4.130878971554148e-06, "loss": 0.17175163328647614, "step": 732 }, { "epoch": 3.163793103448276, "grad_norm": 0.36916273832321167, "learning_rate": 4.0895815576908686e-06, "loss": 0.3509948253631592, "step": 734 }, { "epoch": 3.1724137931034484, "grad_norm": 0.2566669285297394, "learning_rate": 4.048635631764673e-06, "loss": 0.22303853929042816, "step": 736 }, { "epoch": 3.1810344827586206, "grad_norm": 1.5648850202560425, "learning_rate": 4.008043276427886e-06, "loss": 0.523650050163269, "step": 738 }, { "epoch": 3.189655172413793, "grad_norm": 0.22325409948825836, "learning_rate": 3.967806556349001e-06, "loss": 0.08064466714859009, "step": 740 }, { "epoch": 3.1982758620689653, "grad_norm": 0.08049521595239639, "learning_rate": 3.927927518107664e-06, "loss": 0.17742744088172913, "step": 742 }, { "epoch": 3.206896551724138, "grad_norm": 0.3570193350315094, "learning_rate": 3.888408190090583e-06, "loss": 0.2840654253959656, "step": 744 }, { "epoch": 3.2155172413793105, "grad_norm": 0.5950610041618347, "learning_rate": 3.8492505823883394e-06, "loss": 0.27302879095077515, "step": 746 }, { "epoch": 3.2241379310344827, "grad_norm": 0.6008321046829224, "learning_rate": 3.810456686693178e-06, "loss": 0.38051924109458923, "step": 748 }, { "epoch": 3.2327586206896552, "grad_norm": 0.2667677104473114, "learning_rate": 3.7720284761976657e-06, "loss": 0.33380451798439026, "step": 750 }, { "epoch": 3.2413793103448274, "grad_norm": 1.0264617204666138, "learning_rate": 3.7339679054943645e-06, "loss": 0.2860594093799591, "step": 752 }, { "epoch": 3.25, "grad_norm": 0.5752837657928467, "learning_rate": 3.696276910476382e-06, "loss": 0.36991697549819946, "step": 754 }, { "epoch": 3.2586206896551726, "grad_norm": 0.29292166233062744, "learning_rate": 3.6589574082389324e-06, "loss": 0.3221489191055298, "step": 756 }, { "epoch": 3.2672413793103448, "grad_norm": 0.35932210087776184, "learning_rate": 3.6220112969818045e-06, "loss": 0.37856197357177734, "step": 758 }, { "epoch": 3.2758620689655173, "grad_norm": 0.11113092303276062, "learning_rate": 3.5854404559128287e-06, "loss": 0.24704982340335846, "step": 760 }, { "epoch": 3.2844827586206895, "grad_norm": 1.6768494844436646, "learning_rate": 3.549246745152283e-06, "loss": 0.36558791995048523, "step": 762 }, { "epoch": 3.293103448275862, "grad_norm": 0.4623495638370514, "learning_rate": 3.5134320056382877e-06, "loss": 0.3346759080886841, "step": 764 }, { "epoch": 3.3017241379310347, "grad_norm": 0.18975688517093658, "learning_rate": 3.477998059033163e-06, "loss": 0.2471802681684494, "step": 766 }, { "epoch": 3.310344827586207, "grad_norm": 0.2749144434928894, "learning_rate": 3.4429467076307823e-06, "loss": 0.34330496191978455, "step": 768 }, { "epoch": 3.3189655172413794, "grad_norm": 0.7870236039161682, "learning_rate": 3.4082797342648867e-06, "loss": 0.10211128741502762, "step": 770 }, { "epoch": 3.3275862068965516, "grad_norm": 0.4417794346809387, "learning_rate": 3.373998902218423e-06, "loss": 0.22283262014389038, "step": 772 }, { "epoch": 3.336206896551724, "grad_norm": 2.35225510597229, "learning_rate": 3.3401059551338326e-06, "loss": 0.3982272148132324, "step": 774 }, { "epoch": 3.344827586206897, "grad_norm": 0.32708537578582764, "learning_rate": 3.3066026169243916e-06, "loss": 0.35799640417099, "step": 776 }, { "epoch": 3.353448275862069, "grad_norm": 0.39861956238746643, "learning_rate": 3.2734905916865045e-06, "loss": 0.33809182047843933, "step": 778 }, { "epoch": 3.3620689655172415, "grad_norm": 2.7856783866882324, "learning_rate": 3.2407715636130365e-06, "loss": 0.24870137870311737, "step": 780 }, { "epoch": 3.3706896551724137, "grad_norm": 0.3867567777633667, "learning_rate": 3.20844719690765e-06, "loss": 0.25115785002708435, "step": 782 }, { "epoch": 3.3793103448275863, "grad_norm": 0.2818472385406494, "learning_rate": 3.1765191357001596e-06, "loss": 0.34631893038749695, "step": 784 }, { "epoch": 3.3879310344827585, "grad_norm": 0.6454493999481201, "learning_rate": 3.1449890039628956e-06, "loss": 0.21534167230129242, "step": 786 }, { "epoch": 3.396551724137931, "grad_norm": 0.2576633095741272, "learning_rate": 3.1138584054281177e-06, "loss": 0.38198593258857727, "step": 788 }, { "epoch": 3.405172413793103, "grad_norm": 0.3199053704738617, "learning_rate": 3.0831289235064297e-06, "loss": 0.3233962655067444, "step": 790 }, { "epoch": 3.413793103448276, "grad_norm": 0.24734322726726532, "learning_rate": 3.0528021212062536e-06, "loss": 0.39972445368766785, "step": 792 }, { "epoch": 3.4224137931034484, "grad_norm": 0.7525281310081482, "learning_rate": 3.0228795410543182e-06, "loss": 0.2797224819660187, "step": 794 }, { "epoch": 3.4310344827586206, "grad_norm": 0.38152387738227844, "learning_rate": 2.9933627050172152e-06, "loss": 0.4961601793766022, "step": 796 }, { "epoch": 3.439655172413793, "grad_norm": 0.6566803455352783, "learning_rate": 2.96425311442397e-06, "loss": 0.2608637511730194, "step": 798 }, { "epoch": 3.4482758620689653, "grad_norm": 0.2898580729961395, "learning_rate": 2.9355522498896914e-06, "loss": 0.389303594827652, "step": 800 }, { "epoch": 3.456896551724138, "grad_norm": 0.2688350975513458, "learning_rate": 2.907261571240257e-06, "loss": 0.416867733001709, "step": 802 }, { "epoch": 3.4655172413793105, "grad_norm": 0.3749980032444, "learning_rate": 2.879382517438062e-06, "loss": 0.28168269991874695, "step": 804 }, { "epoch": 3.4741379310344827, "grad_norm": 0.5589833855628967, "learning_rate": 2.8519165065088293e-06, "loss": 0.39084625244140625, "step": 806 }, { "epoch": 3.4827586206896552, "grad_norm": 0.2921109199523926, "learning_rate": 2.824864935469487e-06, "loss": 0.3399796187877655, "step": 808 }, { "epoch": 3.4913793103448274, "grad_norm": 0.22237980365753174, "learning_rate": 2.7982291802570983e-06, "loss": 0.10816089808940887, "step": 810 }, { "epoch": 3.5, "grad_norm": 0.608170747756958, "learning_rate": 2.7720105956588983e-06, "loss": 0.3328501880168915, "step": 812 }, { "epoch": 3.5086206896551726, "grad_norm": 1.1251869201660156, "learning_rate": 2.7462105152433617e-06, "loss": 0.4947846531867981, "step": 814 }, { "epoch": 3.5172413793103448, "grad_norm": 0.5909225344657898, "learning_rate": 2.720830251292391e-06, "loss": 0.3645175099372864, "step": 816 }, { "epoch": 3.5258620689655173, "grad_norm": 0.3970613181591034, "learning_rate": 2.695871094734559e-06, "loss": 0.4159550368785858, "step": 818 }, { "epoch": 3.5344827586206895, "grad_norm": 0.3088339567184448, "learning_rate": 2.6713343150794506e-06, "loss": 0.31124040484428406, "step": 820 }, { "epoch": 3.543103448275862, "grad_norm": 0.8232600688934326, "learning_rate": 2.6472211603530894e-06, "loss": 0.2729651927947998, "step": 822 }, { "epoch": 3.5517241379310347, "grad_norm": 0.47030189633369446, "learning_rate": 2.6235328570344666e-06, "loss": 0.27673032879829407, "step": 824 }, { "epoch": 3.560344827586207, "grad_norm": 0.07642904669046402, "learning_rate": 2.600270609993143e-06, "loss": 0.0557853989303112, "step": 826 }, { "epoch": 3.5689655172413794, "grad_norm": 1.2752304077148438, "learning_rate": 2.5774356024279827e-06, "loss": 0.18158602714538574, "step": 828 }, { "epoch": 3.5775862068965516, "grad_norm": 0.2896014153957367, "learning_rate": 2.555028995806956e-06, "loss": 0.18923550844192505, "step": 830 }, { "epoch": 3.586206896551724, "grad_norm": 0.3300286829471588, "learning_rate": 2.5330519298080757e-06, "loss": 0.22178103029727936, "step": 832 }, { "epoch": 3.594827586206897, "grad_norm": 0.47191181778907776, "learning_rate": 2.511505522261417e-06, "loss": 0.43088600039482117, "step": 834 }, { "epoch": 3.603448275862069, "grad_norm": 0.5750867128372192, "learning_rate": 2.4903908690922746e-06, "loss": 0.3035900592803955, "step": 836 }, { "epoch": 3.612068965517241, "grad_norm": 0.31900304555892944, "learning_rate": 2.4697090442654055e-06, "loss": 0.3073073923587799, "step": 838 }, { "epoch": 3.6206896551724137, "grad_norm": 0.9884761571884155, "learning_rate": 2.4494610997304156e-06, "loss": 0.1451842337846756, "step": 840 }, { "epoch": 3.6293103448275863, "grad_norm": 0.5963663458824158, "learning_rate": 2.4296480653682444e-06, "loss": 0.19056405127048492, "step": 842 }, { "epoch": 3.637931034482759, "grad_norm": 0.4518829882144928, "learning_rate": 2.4102709489387925e-06, "loss": 0.3310995101928711, "step": 844 }, { "epoch": 3.646551724137931, "grad_norm": 13.950098991394043, "learning_rate": 2.391330736029649e-06, "loss": 0.27216413617134094, "step": 846 }, { "epoch": 3.655172413793103, "grad_norm": 1.5341519117355347, "learning_rate": 2.3728283900059756e-06, "loss": 0.13349619507789612, "step": 848 }, { "epoch": 3.663793103448276, "grad_norm": 0.07572399079799652, "learning_rate": 2.3547648519614967e-06, "loss": 0.20533311367034912, "step": 850 }, { "epoch": 3.6724137931034484, "grad_norm": 0.36925849318504333, "learning_rate": 2.3371410406706356e-06, "loss": 0.38371843099594116, "step": 852 }, { "epoch": 3.6810344827586206, "grad_norm": 0.9557275176048279, "learning_rate": 2.319957852541786e-06, "loss": 0.2169187366962433, "step": 854 }, { "epoch": 3.689655172413793, "grad_norm": 0.5187146663665771, "learning_rate": 2.303216161571706e-06, "loss": 0.37597841024398804, "step": 856 }, { "epoch": 3.6982758620689653, "grad_norm": 0.2956836223602295, "learning_rate": 2.2869168193010793e-06, "loss": 0.4011721611022949, "step": 858 }, { "epoch": 3.706896551724138, "grad_norm": 0.09843911975622177, "learning_rate": 2.2710606547711917e-06, "loss": 0.18101970851421356, "step": 860 }, { "epoch": 3.7155172413793105, "grad_norm": 0.6112839579582214, "learning_rate": 2.2556484744817635e-06, "loss": 0.23301751911640167, "step": 862 }, { "epoch": 3.7241379310344827, "grad_norm": 0.03941560536623001, "learning_rate": 2.2406810623499382e-06, "loss": 0.1944858729839325, "step": 864 }, { "epoch": 3.7327586206896552, "grad_norm": 0.2406272292137146, "learning_rate": 2.226159179670395e-06, "loss": 0.11213114112615585, "step": 866 }, { "epoch": 3.7413793103448274, "grad_norm": 0.9250267148017883, "learning_rate": 2.2120835650766386e-06, "loss": 0.25432637333869934, "step": 868 }, { "epoch": 3.75, "grad_norm": 0.3792153596878052, "learning_rate": 2.1984549345034234e-06, "loss": 0.2917807102203369, "step": 870 }, { "epoch": 3.7586206896551726, "grad_norm": 0.050461042672395706, "learning_rate": 2.1852739811503433e-06, "loss": 0.1030154600739479, "step": 872 }, { "epoch": 3.7672413793103448, "grad_norm": 0.03659242019057274, "learning_rate": 2.172541375446566e-06, "loss": 0.24243952333927155, "step": 874 }, { "epoch": 3.7758620689655173, "grad_norm": 0.3581734895706177, "learning_rate": 2.1602577650167436e-06, "loss": 0.4455357789993286, "step": 876 }, { "epoch": 3.7844827586206895, "grad_norm": 0.6977261304855347, "learning_rate": 2.1484237746480574e-06, "loss": 0.5109292268753052, "step": 878 }, { "epoch": 3.793103448275862, "grad_norm": 0.25545695424079895, "learning_rate": 2.1370400062584544e-06, "loss": 0.1860283464193344, "step": 880 }, { "epoch": 3.8017241379310347, "grad_norm": 0.5381384491920471, "learning_rate": 2.1261070388660202e-06, "loss": 0.20024971663951874, "step": 882 }, { "epoch": 3.810344827586207, "grad_norm": 0.3756001591682434, "learning_rate": 2.115625428559535e-06, "loss": 0.43951112031936646, "step": 884 }, { "epoch": 3.8189655172413794, "grad_norm": 0.5115352869033813, "learning_rate": 2.105595708470185e-06, "loss": 0.16899777948856354, "step": 886 }, { "epoch": 3.8275862068965516, "grad_norm": 0.2846692204475403, "learning_rate": 2.096018388744448e-06, "loss": 0.26339343190193176, "step": 888 }, { "epoch": 3.836206896551724, "grad_norm": 0.7379516959190369, "learning_rate": 2.086893956518142e-06, "loss": 0.11539773643016815, "step": 890 }, { "epoch": 3.844827586206897, "grad_norm": 0.5147801041603088, "learning_rate": 2.078222875891654e-06, "loss": 0.3523973822593689, "step": 892 }, { "epoch": 3.853448275862069, "grad_norm": 0.15211860835552216, "learning_rate": 2.070005587906328e-06, "loss": 0.33388248085975647, "step": 894 }, { "epoch": 3.862068965517241, "grad_norm": 0.3375397324562073, "learning_rate": 2.0622425105220346e-06, "loss": 0.2652340531349182, "step": 896 }, { "epoch": 3.8706896551724137, "grad_norm": 0.3318890333175659, "learning_rate": 2.0549340385959123e-06, "loss": 0.1966915875673294, "step": 898 }, { "epoch": 3.8793103448275863, "grad_norm": 0.3057389259338379, "learning_rate": 2.0480805438622865e-06, "loss": 0.391522079706192, "step": 900 }, { "epoch": 3.887931034482759, "grad_norm": 0.5989668369293213, "learning_rate": 2.0416823749137542e-06, "loss": 0.3690534234046936, "step": 902 }, { "epoch": 3.896551724137931, "grad_norm": 0.3611077666282654, "learning_rate": 2.03573985718346e-06, "loss": 0.35606420040130615, "step": 904 }, { "epoch": 3.905172413793103, "grad_norm": 0.518487274646759, "learning_rate": 2.0302532929285423e-06, "loss": 0.37323978543281555, "step": 906 }, { "epoch": 3.913793103448276, "grad_norm": 0.3315095603466034, "learning_rate": 2.0252229612147587e-06, "loss": 0.22919489443302155, "step": 908 }, { "epoch": 3.9224137931034484, "grad_norm": 0.22296565771102905, "learning_rate": 2.0206491179022887e-06, "loss": 0.17647181451320648, "step": 910 }, { "epoch": 3.9310344827586206, "grad_norm": 0.2577214539051056, "learning_rate": 2.0165319956327258e-06, "loss": 0.23643004894256592, "step": 912 }, { "epoch": 3.939655172413793, "grad_norm": 0.37906980514526367, "learning_rate": 2.01287180381724e-06, "loss": 0.3691279888153076, "step": 914 }, { "epoch": 3.9482758620689653, "grad_norm": 0.30090105533599854, "learning_rate": 2.0096687286259286e-06, "loss": 0.3844853937625885, "step": 916 }, { "epoch": 3.956896551724138, "grad_norm": 0.3276263475418091, "learning_rate": 2.006922932978346e-06, "loss": 0.28372105956077576, "step": 918 }, { "epoch": 3.9655172413793105, "grad_norm": 2.499201536178589, "learning_rate": 2.004634556535215e-06, "loss": 0.36251726746559143, "step": 920 }, { "epoch": 3.9741379310344827, "grad_norm": 0.3088098466396332, "learning_rate": 2.0028037156913294e-06, "loss": 0.2959789037704468, "step": 922 }, { "epoch": 3.9827586206896552, "grad_norm": 0.5072318911552429, "learning_rate": 2.0014305035696265e-06, "loss": 0.3481578230857849, "step": 924 }, { "epoch": 3.9913793103448274, "grad_norm": 0.469334214925766, "learning_rate": 2.0005149900164546e-06, "loss": 0.36124011874198914, "step": 926 }, { "epoch": 4.0, "grad_norm": 0.7579672932624817, "learning_rate": 2.000057221598022e-06, "loss": 0.39811837673187256, "step": 928 }, { "epoch": 4.0, "step": 928, "total_flos": 3.6942184710227886e+18, "train_loss": 0.7407096255137103, "train_runtime": 10071.2083, "train_samples_per_second": 5.529, "train_steps_per_second": 0.092 } ], "logging_steps": 2, "max_steps": 928, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.6942184710227886e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }