{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 696, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008620689655172414, "grad_norm": 0.5692610740661621, "learning_rate": 5.714285714285715e-07, "loss": 1.9584773778915405, "step": 2 }, { "epoch": 0.017241379310344827, "grad_norm": 0.726763904094696, "learning_rate": 1.7142857142857145e-06, "loss": 6.022436618804932, "step": 4 }, { "epoch": 0.02586206896551724, "grad_norm": 1.3075555562973022, "learning_rate": 2.8571428571428573e-06, "loss": 1.9596091508865356, "step": 6 }, { "epoch": 0.034482758620689655, "grad_norm": 0.4725358784198761, "learning_rate": 4.000000000000001e-06, "loss": 1.622937560081482, "step": 8 }, { "epoch": 0.04310344827586207, "grad_norm": 3.1994080543518066, "learning_rate": 5.142857142857142e-06, "loss": 2.567897319793701, "step": 10 }, { "epoch": 0.05172413793103448, "grad_norm": 0.3738505244255066, "learning_rate": 6.285714285714286e-06, "loss": 1.8926677703857422, "step": 12 }, { "epoch": 0.0603448275862069, "grad_norm": 0.6169027090072632, "learning_rate": 7.428571428571429e-06, "loss": 1.7960844039916992, "step": 14 }, { "epoch": 0.06896551724137931, "grad_norm": 0.7442793250083923, "learning_rate": 8.571428571428571e-06, "loss": 1.7497979402542114, "step": 16 }, { "epoch": 0.07758620689655173, "grad_norm": 3.6816675662994385, "learning_rate": 9.714285714285715e-06, "loss": 2.5326366424560547, "step": 18 }, { "epoch": 0.08620689655172414, "grad_norm": 0.4809480607509613, "learning_rate": 1.0857142857142858e-05, "loss": 1.7976326942443848, "step": 20 }, { "epoch": 0.09482758620689655, "grad_norm": 1.6670607328414917, "learning_rate": 1.2e-05, "loss": 3.13413667678833, "step": 22 }, { "epoch": 0.10344827586206896, "grad_norm": 2.1275734901428223, "learning_rate": 1.3142857142857145e-05, "loss": 1.9254695177078247, "step": 24 }, { "epoch": 0.11206896551724138, "grad_norm": 5.445179462432861, "learning_rate": 1.4285714285714287e-05, "loss": 2.0263671875, "step": 26 }, { "epoch": 0.1206896551724138, "grad_norm": 3.1292130947113037, "learning_rate": 1.542857142857143e-05, "loss": 2.157352924346924, "step": 28 }, { "epoch": 0.12931034482758622, "grad_norm": 0.3002319037914276, "learning_rate": 1.6571428571428574e-05, "loss": 1.6684068441390991, "step": 30 }, { "epoch": 0.13793103448275862, "grad_norm": 0.3610835671424866, "learning_rate": 1.7714285714285717e-05, "loss": 1.6966811418533325, "step": 32 }, { "epoch": 0.14655172413793102, "grad_norm": 2.521209955215454, "learning_rate": 1.885714285714286e-05, "loss": 1.5750758647918701, "step": 34 }, { "epoch": 0.15517241379310345, "grad_norm": 2.5947937965393066, "learning_rate": 2e-05, "loss": 1.5068325996398926, "step": 36 }, { "epoch": 0.16379310344827586, "grad_norm": 0.5535445809364319, "learning_rate": 1.9995836718255602e-05, "loss": 1.582505702972412, "step": 38 }, { "epoch": 0.1724137931034483, "grad_norm": 6.105097770690918, "learning_rate": 1.9983350724781264e-05, "loss": 1.5262649059295654, "step": 40 }, { "epoch": 0.1810344827586207, "grad_norm": 0.7298107743263245, "learning_rate": 1.996255357129003e-05, "loss": 1.858609914779663, "step": 42 }, { "epoch": 0.1896551724137931, "grad_norm": 0.6571905612945557, "learning_rate": 1.9933464498761785e-05, "loss": 1.520866870880127, "step": 44 }, { "epoch": 0.19827586206896552, "grad_norm": 0.5775193572044373, "learning_rate": 1.989611041964199e-05, "loss": 1.286926507949829, "step": 46 }, { "epoch": 0.20689655172413793, "grad_norm": 0.757246196269989, "learning_rate": 1.985052589294303e-05, "loss": 0.9975602030754089, "step": 48 }, { "epoch": 0.21551724137931033, "grad_norm": 0.2879011929035187, "learning_rate": 1.9796753092271085e-05, "loss": 1.4037001132965088, "step": 50 }, { "epoch": 0.22413793103448276, "grad_norm": 0.39832451939582825, "learning_rate": 1.973484176680824e-05, "loss": 1.5926319360733032, "step": 52 }, { "epoch": 0.23275862068965517, "grad_norm": 0.3482792377471924, "learning_rate": 1.9664849195285844e-05, "loss": 1.0562762022018433, "step": 54 }, { "epoch": 0.2413793103448276, "grad_norm": 0.24125751852989197, "learning_rate": 1.958684013299173e-05, "loss": 0.927044689655304, "step": 56 }, { "epoch": 0.25, "grad_norm": 0.5061832070350647, "learning_rate": 1.950088675186034e-05, "loss": 0.9711346626281738, "step": 58 }, { "epoch": 0.25862068965517243, "grad_norm": 0.7697155475616455, "learning_rate": 1.9407068573701116e-05, "loss": 1.0954338312149048, "step": 60 }, { "epoch": 0.2672413793103448, "grad_norm": 0.31880345940589905, "learning_rate": 1.9305472396627044e-05, "loss": 1.4207227230072021, "step": 62 }, { "epoch": 0.27586206896551724, "grad_norm": 0.3055737316608429, "learning_rate": 1.919619221475131e-05, "loss": 0.9308554530143738, "step": 64 }, { "epoch": 0.28448275862068967, "grad_norm": 0.2709406316280365, "learning_rate": 1.90793291312264e-05, "loss": 1.4012649059295654, "step": 66 }, { "epoch": 0.29310344827586204, "grad_norm": 0.3806637227535248, "learning_rate": 1.895499126470615e-05, "loss": 0.8479315638542175, "step": 68 }, { "epoch": 0.3017241379310345, "grad_norm": 0.3242409825325012, "learning_rate": 1.8823293649317186e-05, "loss": 1.381568193435669, "step": 70 }, { "epoch": 0.3103448275862069, "grad_norm": 0.13824906945228577, "learning_rate": 1.868435812823238e-05, "loss": 0.6094793677330017, "step": 72 }, { "epoch": 0.31896551724137934, "grad_norm": 0.27344992756843567, "learning_rate": 1.853831324094475e-05, "loss": 0.8938958644866943, "step": 74 }, { "epoch": 0.3275862068965517, "grad_norm": 0.660277783870697, "learning_rate": 1.8385294104346103e-05, "loss": 1.2029653787612915, "step": 76 }, { "epoch": 0.33620689655172414, "grad_norm": 0.30026018619537354, "learning_rate": 1.8225442287720417e-05, "loss": 1.3596869707107544, "step": 78 }, { "epoch": 0.3448275862068966, "grad_norm": 0.3138439953327179, "learning_rate": 1.805890568176769e-05, "loss": 1.4085049629211426, "step": 80 }, { "epoch": 0.35344827586206895, "grad_norm": 0.5029515624046326, "learning_rate": 1.7885838361779333e-05, "loss": 1.2587382793426514, "step": 82 }, { "epoch": 0.3620689655172414, "grad_norm": 0.3618926405906677, "learning_rate": 1.7706400445091755e-05, "loss": 1.3189198970794678, "step": 84 }, { "epoch": 0.3706896551724138, "grad_norm": 0.7304700016975403, "learning_rate": 1.7520757942950026e-05, "loss": 1.327932596206665, "step": 86 }, { "epoch": 0.3793103448275862, "grad_norm": 0.5044423937797546, "learning_rate": 1.7329082606918616e-05, "loss": 1.0215771198272705, "step": 88 }, { "epoch": 0.3879310344827586, "grad_norm": 0.38377389311790466, "learning_rate": 1.7131551769981392e-05, "loss": 1.5617601871490479, "step": 90 }, { "epoch": 0.39655172413793105, "grad_norm": 0.2912510931491852, "learning_rate": 1.6928348182477765e-05, "loss": 1.3252155780792236, "step": 92 }, { "epoch": 0.4051724137931034, "grad_norm": 0.3194431960582733, "learning_rate": 1.67196598430269e-05, "loss": 1.335471272468567, "step": 94 }, { "epoch": 0.41379310344827586, "grad_norm": 0.3167501986026764, "learning_rate": 1.6505679824596338e-05, "loss": 1.4329684972763062, "step": 96 }, { "epoch": 0.4224137931034483, "grad_norm": 0.27103397250175476, "learning_rate": 1.6286606095875938e-05, "loss": 1.302343487739563, "step": 98 }, { "epoch": 0.43103448275862066, "grad_norm": 0.3172292113304138, "learning_rate": 1.6062641338122474e-05, "loss": 1.3569573163986206, "step": 100 }, { "epoch": 0.4396551724137931, "grad_norm": 0.2844351530075073, "learning_rate": 1.583399275764424e-05, "loss": 1.309763789176941, "step": 102 }, { "epoch": 0.4482758620689655, "grad_norm": 0.4061580002307892, "learning_rate": 1.5600871894099243e-05, "loss": 0.9164461493492126, "step": 104 }, { "epoch": 0.45689655172413796, "grad_norm": 1.267133355140686, "learning_rate": 1.5363494424784238e-05, "loss": 0.8275090456008911, "step": 106 }, { "epoch": 0.46551724137931033, "grad_norm": 0.3342474102973938, "learning_rate": 1.5122079965095786e-05, "loss": 0.7831904292106628, "step": 108 }, { "epoch": 0.47413793103448276, "grad_norm": 0.33141425251960754, "learning_rate": 1.4876851865347857e-05, "loss": 1.0925136804580688, "step": 110 }, { "epoch": 0.4827586206896552, "grad_norm": 0.296645849943161, "learning_rate": 1.4628037004133986e-05, "loss": 0.9729475378990173, "step": 112 }, { "epoch": 0.49137931034482757, "grad_norm": 0.7777587175369263, "learning_rate": 1.4375865578425157e-05, "loss": 0.6473991274833679, "step": 114 }, { "epoch": 0.5, "grad_norm": 0.38521984219551086, "learning_rate": 1.4120570890597611e-05, "loss": 1.1790492534637451, "step": 116 }, { "epoch": 0.5086206896551724, "grad_norm": 0.4623865485191345, "learning_rate": 1.3862389132587639e-05, "loss": 1.2727322578430176, "step": 118 }, { "epoch": 0.5172413793103449, "grad_norm": 0.5431216955184937, "learning_rate": 1.3601559167372983e-05, "loss": 0.7860153913497925, "step": 120 }, { "epoch": 0.5258620689655172, "grad_norm": 0.5915956497192383, "learning_rate": 1.3338322307983105e-05, "loss": 1.043981671333313, "step": 122 }, { "epoch": 0.5344827586206896, "grad_norm": 0.24551472067832947, "learning_rate": 1.3072922094242703e-05, "loss": 1.278051733970642, "step": 124 }, { "epoch": 0.5431034482758621, "grad_norm": 0.2816060781478882, "learning_rate": 1.2805604067455076e-05, "loss": 1.255641222000122, "step": 126 }, { "epoch": 0.5517241379310345, "grad_norm": 0.4124661684036255, "learning_rate": 1.2536615543233748e-05, "loss": 1.255129337310791, "step": 128 }, { "epoch": 0.5603448275862069, "grad_norm": 0.5298042893409729, "learning_rate": 1.2266205382692574e-05, "loss": 1.5166298151016235, "step": 130 }, { "epoch": 0.5689655172413793, "grad_norm": 0.2111591249704361, "learning_rate": 1.199462376220597e-05, "loss": 0.8270851373672485, "step": 132 }, { "epoch": 0.5775862068965517, "grad_norm": 0.889839768409729, "learning_rate": 1.1722121941952313e-05, "loss": 0.6701672077178955, "step": 134 }, { "epoch": 0.5862068965517241, "grad_norm": 0.2590690553188324, "learning_rate": 1.144895203345462e-05, "loss": 1.077882170677185, "step": 136 }, { "epoch": 0.5948275862068966, "grad_norm": 0.298973947763443, "learning_rate": 1.11753667663336e-05, "loss": 0.8770455718040466, "step": 138 }, { "epoch": 0.603448275862069, "grad_norm": 0.6260126233100891, "learning_rate": 1.0901619254488831e-05, "loss": 0.9084359407424927, "step": 140 }, { "epoch": 0.6120689655172413, "grad_norm": 0.2761947512626648, "learning_rate": 1.0627962761924462e-05, "loss": 1.370908260345459, "step": 142 }, { "epoch": 0.6206896551724138, "grad_norm": 0.3692832291126251, "learning_rate": 1.0354650468435985e-05, "loss": 0.7351585030555725, "step": 144 }, { "epoch": 0.6293103448275862, "grad_norm": 0.4929635524749756, "learning_rate": 1.0081935235374955e-05, "loss": 1.2708691358566284, "step": 146 }, { "epoch": 0.6379310344827587, "grad_norm": 0.3487298786640167, "learning_rate": 9.810069371708313e-06, "loss": 1.2674932479858398, "step": 148 }, { "epoch": 0.646551724137931, "grad_norm": 0.36564555764198303, "learning_rate": 9.539304400588752e-06, "loss": 1.0046426057815552, "step": 150 }, { "epoch": 0.6551724137931034, "grad_norm": 0.2302585393190384, "learning_rate": 9.269890826652113e-06, "loss": 0.664213240146637, "step": 152 }, { "epoch": 0.6637931034482759, "grad_norm": 0.3203712999820709, "learning_rate": 9.00207790425708e-06, "loss": 1.5197818279266357, "step": 154 }, { "epoch": 0.6724137931034483, "grad_norm": 0.6393405199050903, "learning_rate": 8.73611340688159e-06, "loss": 1.062941312789917, "step": 156 }, { "epoch": 0.6810344827586207, "grad_norm": 0.33355581760406494, "learning_rate": 8.472243397889327e-06, "loss": 0.7909774780273438, "step": 158 }, { "epoch": 0.6896551724137931, "grad_norm": 0.34659793972969055, "learning_rate": 8.210712002878366e-06, "loss": 0.3939180374145508, "step": 160 }, { "epoch": 0.6982758620689655, "grad_norm": 0.995121955871582, "learning_rate": 7.951761183822578e-06, "loss": 1.134759545326233, "step": 162 }, { "epoch": 0.7068965517241379, "grad_norm": 1.618648886680603, "learning_rate": 7.695630515214783e-06, "loss": 0.9670589566230774, "step": 164 }, { "epoch": 0.7155172413793104, "grad_norm": 0.22626011073589325, "learning_rate": 7.442556962418712e-06, "loss": 1.3202883005142212, "step": 166 }, { "epoch": 0.7241379310344828, "grad_norm": 0.32568663358688354, "learning_rate": 7.192774662434887e-06, "loss": 0.7861534357070923, "step": 168 }, { "epoch": 0.7327586206896551, "grad_norm": 1.0204657316207886, "learning_rate": 6.94651470728322e-06, "loss": 0.8559544682502747, "step": 170 }, { "epoch": 0.7413793103448276, "grad_norm": 0.46275442838668823, "learning_rate": 6.7040049302027445e-06, "loss": 1.349075198173523, "step": 172 }, { "epoch": 0.75, "grad_norm": 0.3042738139629364, "learning_rate": 6.465469694866295e-06, "loss": 1.2694404125213623, "step": 174 }, { "epoch": 0.7586206896551724, "grad_norm": 0.24299518764019012, "learning_rate": 6.2311296878051355e-06, "loss": 1.2068278789520264, "step": 176 }, { "epoch": 0.7672413793103449, "grad_norm": 0.3234924376010895, "learning_rate": 6.001201714235567e-06, "loss": 1.311326503753662, "step": 178 }, { "epoch": 0.7758620689655172, "grad_norm": 0.7479709982872009, "learning_rate": 5.7758984974764586e-06, "loss": 0.768395185470581, "step": 180 }, { "epoch": 0.7844827586206896, "grad_norm": 0.35784727334976196, "learning_rate": 5.555428482143206e-06, "loss": 1.1966248750686646, "step": 182 }, { "epoch": 0.7931034482758621, "grad_norm": 0.4064531922340393, "learning_rate": 5.339995641300257e-06, "loss": 1.1476389169692993, "step": 184 }, { "epoch": 0.8017241379310345, "grad_norm": 0.31240594387054443, "learning_rate": 5.129799287750601e-06, "loss": 0.9965859651565552, "step": 186 }, { "epoch": 0.8103448275862069, "grad_norm": 0.3878633975982666, "learning_rate": 4.9250338896367814e-06, "loss": 0.8189845085144043, "step": 188 }, { "epoch": 0.8189655172413793, "grad_norm": 0.29073813557624817, "learning_rate": 4.725888890524101e-06, "loss": 1.2450443506240845, "step": 190 }, { "epoch": 0.8275862068965517, "grad_norm": 1.2100752592086792, "learning_rate": 4.5325485341324026e-06, "loss": 0.9530048966407776, "step": 192 }, { "epoch": 0.8362068965517241, "grad_norm": 0.4809584319591522, "learning_rate": 4.345191693878623e-06, "loss": 1.2201794385910034, "step": 194 }, { "epoch": 0.8448275862068966, "grad_norm": 0.9147862792015076, "learning_rate": 4.163991707387815e-06, "loss": 0.8178768754005432, "step": 196 }, { "epoch": 0.853448275862069, "grad_norm": 0.27828192710876465, "learning_rate": 3.989116216125717e-06, "loss": 1.228522539138794, "step": 198 }, { "epoch": 0.8620689655172413, "grad_norm": 0.7031840085983276, "learning_rate": 3.8207270103012905e-06, "loss": 1.3021351099014282, "step": 200 }, { "epoch": 0.8706896551724138, "grad_norm": 0.6149956583976746, "learning_rate": 3.6589798791826593e-06, "loss": 0.6399316787719727, "step": 202 }, { "epoch": 0.8793103448275862, "grad_norm": 0.2772592604160309, "learning_rate": 3.5040244669649804e-06, "loss": 1.600140929222107, "step": 204 }, { "epoch": 0.8879310344827587, "grad_norm": 0.1492106020450592, "learning_rate": 3.3560041343235544e-06, "loss": 1.0438815355300903, "step": 206 }, { "epoch": 0.896551724137931, "grad_norm": 0.3777860701084137, "learning_rate": 3.2150558257803178e-06, "loss": 1.339942216873169, "step": 208 }, { "epoch": 0.9051724137931034, "grad_norm": 0.6718384027481079, "learning_rate": 3.081309943006349e-06, "loss": 0.9232547879219055, "step": 210 }, { "epoch": 0.9137931034482759, "grad_norm": 0.9841593503952026, "learning_rate": 2.9548902241776783e-06, "loss": 1.1493092775344849, "step": 212 }, { "epoch": 0.9224137931034483, "grad_norm": 0.8034397959709167, "learning_rate": 2.8359136294959814e-06, "loss": 1.5147000551223755, "step": 214 }, { "epoch": 0.9310344827586207, "grad_norm": 1.0949209928512573, "learning_rate": 2.7244902329800697e-06, "loss": 1.3095285892486572, "step": 216 }, { "epoch": 0.9396551724137931, "grad_norm": 0.22381076216697693, "learning_rate": 2.620723120628298e-06, "loss": 1.230783462524414, "step": 218 }, { "epoch": 0.9482758620689655, "grad_norm": 0.3169087767601013, "learning_rate": 2.5247082950461204e-06, "loss": 1.3510628938674927, "step": 220 }, { "epoch": 0.9568965517241379, "grad_norm": 0.23972630500793457, "learning_rate": 2.4365345866269884e-06, "loss": 1.1361650228500366, "step": 222 }, { "epoch": 0.9655172413793104, "grad_norm": 0.32792967557907104, "learning_rate": 2.35628357136881e-06, "loss": 1.2898920774459839, "step": 224 }, { "epoch": 0.9741379310344828, "grad_norm": 0.4268532693386078, "learning_rate": 2.284029495401986e-06, "loss": 1.3678969144821167, "step": 226 }, { "epoch": 0.9827586206896551, "grad_norm": 0.7636785507202148, "learning_rate": 2.219839206298835e-06, "loss": 0.8566112518310547, "step": 228 }, { "epoch": 0.9913793103448276, "grad_norm": 0.9001679420471191, "learning_rate": 2.163772091227977e-06, "loss": 0.8546447157859802, "step": 230 }, { "epoch": 1.0, "grad_norm": 0.9462145566940308, "learning_rate": 2.115880022010884e-06, "loss": 1.1330009698867798, "step": 232 }, { "epoch": 1.0086206896551724, "grad_norm": 0.3172188103199005, "learning_rate": 2.076207307131444e-06, "loss": 1.1593165397644043, "step": 234 }, { "epoch": 1.0172413793103448, "grad_norm": 0.3420685827732086, "learning_rate": 2.0447906507428975e-06, "loss": 0.6197730898857117, "step": 236 }, { "epoch": 1.0258620689655173, "grad_norm": 0.32782989740371704, "learning_rate": 2.021659118710141e-06, "loss": 1.2394027709960938, "step": 238 }, { "epoch": 1.0344827586206897, "grad_norm": 0.2151000201702118, "learning_rate": 2.0068341117187347e-06, "loss": 1.2157349586486816, "step": 240 }, { "epoch": 1.043103448275862, "grad_norm": 0.23503771424293518, "learning_rate": 2.00032934547556e-06, "loss": 1.2545582056045532, "step": 242 }, { "epoch": 1.0517241379310345, "grad_norm": 0.33568423986434937, "learning_rate": 2.002150838019407e-06, "loss": 1.173262596130371, "step": 244 }, { "epoch": 1.0603448275862069, "grad_norm": 0.23418180644512177, "learning_rate": 2.012296904153243e-06, "loss": 1.1772663593292236, "step": 246 }, { "epoch": 1.0689655172413792, "grad_norm": 0.2445734143257141, "learning_rate": 2.030758157003306e-06, "loss": 1.1834620237350464, "step": 248 }, { "epoch": 1.0775862068965518, "grad_norm": 1.2816580533981323, "learning_rate": 2.057517516703605e-06, "loss": 0.8118759393692017, "step": 250 }, { "epoch": 1.0862068965517242, "grad_norm": 0.30513474345207214, "learning_rate": 2.0925502261977544e-06, "loss": 0.7529575824737549, "step": 252 }, { "epoch": 1.0948275862068966, "grad_norm": 0.35363683104515076, "learning_rate": 2.1358238741435576e-06, "loss": 0.7137669324874878, "step": 254 }, { "epoch": 1.103448275862069, "grad_norm": 0.20758303999900818, "learning_rate": 2.1872984248991204e-06, "loss": 1.1082866191864014, "step": 256 }, { "epoch": 1.1120689655172413, "grad_norm": 0.44538792967796326, "learning_rate": 2.246926255562788e-06, "loss": 1.020033359527588, "step": 258 }, { "epoch": 1.1206896551724137, "grad_norm": 0.32762372493743896, "learning_rate": 2.3146522000325895e-06, "loss": 0.4955134391784668, "step": 260 }, { "epoch": 1.1293103448275863, "grad_norm": 0.4477788507938385, "learning_rate": 2.3904136000444754e-06, "loss": 1.212654709815979, "step": 262 }, { "epoch": 1.1379310344827587, "grad_norm": 0.2977157235145569, "learning_rate": 2.4741403631420874e-06, "loss": 1.2140189409255981, "step": 264 }, { "epoch": 1.146551724137931, "grad_norm": 0.49766677618026733, "learning_rate": 2.5657550275244664e-06, "loss": 1.3088136911392212, "step": 266 }, { "epoch": 1.1551724137931034, "grad_norm": 1.1656190156936646, "learning_rate": 2.66517283371167e-06, "loss": 0.9128588438034058, "step": 268 }, { "epoch": 1.1637931034482758, "grad_norm": 0.25955432653427124, "learning_rate": 2.7723018029620165e-06, "loss": 1.2309114933013916, "step": 270 }, { "epoch": 1.1724137931034484, "grad_norm": 1.4371591806411743, "learning_rate": 2.8870428223683972e-06, "loss": 0.8446346521377563, "step": 272 }, { "epoch": 1.1810344827586208, "grad_norm": 0.7202423810958862, "learning_rate": 3.009289736554944e-06, "loss": 1.3168221712112427, "step": 274 }, { "epoch": 1.1896551724137931, "grad_norm": 0.2864224314689636, "learning_rate": 3.1389294458891755e-06, "loss": 0.7556365132331848, "step": 276 }, { "epoch": 1.1982758620689655, "grad_norm": 0.3141017556190491, "learning_rate": 3.2758420111188274e-06, "loss": 1.229781985282898, "step": 278 }, { "epoch": 1.206896551724138, "grad_norm": 0.650051474571228, "learning_rate": 3.419900764336468e-06, "loss": 0.888131320476532, "step": 280 }, { "epoch": 1.2155172413793103, "grad_norm": 0.5339681506156921, "learning_rate": 3.5709724261693514e-06, "loss": 1.2144626379013062, "step": 282 }, { "epoch": 1.2241379310344827, "grad_norm": 0.27003324031829834, "learning_rate": 3.7289172290859634e-06, "loss": 0.8701605200767517, "step": 284 }, { "epoch": 1.2327586206896552, "grad_norm": 0.10487275570631027, "learning_rate": 3.893589046705279e-06, "loss": 0.5924324989318848, "step": 286 }, { "epoch": 1.2413793103448276, "grad_norm": 0.5368720293045044, "learning_rate": 4.064835528989056e-06, "loss": 1.1794689893722534, "step": 288 }, { "epoch": 1.25, "grad_norm": 0.47765061259269714, "learning_rate": 4.242498243192066e-06, "loss": 0.7260119915008545, "step": 290 }, { "epoch": 1.2586206896551724, "grad_norm": 0.3096713423728943, "learning_rate": 4.426412820439941e-06, "loss": 1.0264055728912354, "step": 292 }, { "epoch": 1.2672413793103448, "grad_norm": 0.4803042411804199, "learning_rate": 4.616409107798898e-06, "loss": 1.4605242013931274, "step": 294 }, { "epoch": 1.2758620689655173, "grad_norm": 0.356592059135437, "learning_rate": 4.812311325696798e-06, "loss": 0.7666136622428894, "step": 296 }, { "epoch": 1.2844827586206897, "grad_norm": 0.5286064743995667, "learning_rate": 5.013938230549751e-06, "loss": 1.0257295370101929, "step": 298 }, { "epoch": 1.293103448275862, "grad_norm": 0.8442373275756836, "learning_rate": 5.221103282443953e-06, "loss": 1.0583548545837402, "step": 300 }, { "epoch": 1.3017241379310345, "grad_norm": 0.32554081082344055, "learning_rate": 5.433614817717478e-06, "loss": 0.9327218532562256, "step": 302 }, { "epoch": 1.3103448275862069, "grad_norm": 0.37990084290504456, "learning_rate": 5.6512762262824986e-06, "loss": 1.2481307983398438, "step": 304 }, { "epoch": 1.3189655172413794, "grad_norm": 0.3042522072792053, "learning_rate": 5.873886133523725e-06, "loss": 1.1840277910232544, "step": 306 }, { "epoch": 1.3275862068965516, "grad_norm": 0.6558886170387268, "learning_rate": 6.101238586604963e-06, "loss": 0.6794692277908325, "step": 308 }, { "epoch": 1.3362068965517242, "grad_norm": 0.18041777610778809, "learning_rate": 6.333123245011208e-06, "loss": 0.9396043419837952, "step": 310 }, { "epoch": 1.3448275862068966, "grad_norm": 0.5412018895149231, "learning_rate": 6.569325575150216e-06, "loss": 1.292694091796875, "step": 312 }, { "epoch": 1.353448275862069, "grad_norm": 0.48298704624176025, "learning_rate": 6.809627048833306e-06, "loss": 1.1025623083114624, "step": 314 }, { "epoch": 1.3620689655172413, "grad_norm": 0.40131139755249023, "learning_rate": 7.053805345451903e-06, "loss": 0.7764808535575867, "step": 316 }, { "epoch": 1.3706896551724137, "grad_norm": 0.5116880536079407, "learning_rate": 7.3016345576627605e-06, "loss": 1.2299896478652954, "step": 318 }, { "epoch": 1.3793103448275863, "grad_norm": 0.11877727508544922, "learning_rate": 7.552885400391432e-06, "loss": 0.8323980569839478, "step": 320 }, { "epoch": 1.3879310344827587, "grad_norm": 1.5366413593292236, "learning_rate": 7.80732542296087e-06, "loss": 1.1044297218322754, "step": 322 }, { "epoch": 1.396551724137931, "grad_norm": 0.4911424517631531, "learning_rate": 8.064719224148607e-06, "loss": 1.518593430519104, "step": 324 }, { "epoch": 1.4051724137931034, "grad_norm": 1.790497899055481, "learning_rate": 8.324828669973863e-06, "loss": 1.134735345840454, "step": 326 }, { "epoch": 1.4137931034482758, "grad_norm": 0.5793009996414185, "learning_rate": 8.587413114012767e-06, "loss": 0.9491145610809326, "step": 328 }, { "epoch": 1.4224137931034484, "grad_norm": 0.4418241083621979, "learning_rate": 8.852229620038169e-06, "loss": 0.7093353271484375, "step": 330 }, { "epoch": 1.4310344827586206, "grad_norm": 0.29193559288978577, "learning_rate": 9.119033186777797e-06, "loss": 1.178290605545044, "step": 332 }, { "epoch": 1.4396551724137931, "grad_norm": 0.7738173007965088, "learning_rate": 9.387576974583059e-06, "loss": 1.2559309005737305, "step": 334 }, { "epoch": 1.4482758620689655, "grad_norm": 0.4955233931541443, "learning_rate": 9.657612533798527e-06, "loss": 1.1395691633224487, "step": 336 }, { "epoch": 1.456896551724138, "grad_norm": 0.33920466899871826, "learning_rate": 9.928890034621103e-06, "loss": 0.824805498123169, "step": 338 }, { "epoch": 1.4655172413793103, "grad_norm": 0.43428322672843933, "learning_rate": 1.020115849823592e-05, "loss": 1.2302451133728027, "step": 340 }, { "epoch": 1.4741379310344827, "grad_norm": 0.2865593731403351, "learning_rate": 1.04741660290154e-05, "loss": 1.2292989492416382, "step": 342 }, { "epoch": 1.4827586206896552, "grad_norm": 0.32383060455322266, "learning_rate": 1.0747660047566425e-05, "loss": 0.9929612278938293, "step": 344 }, { "epoch": 1.4913793103448276, "grad_norm": 0.33553263545036316, "learning_rate": 1.1021387524410204e-05, "loss": 0.8662385940551758, "step": 346 }, { "epoch": 1.5, "grad_norm": 0.5123760104179382, "learning_rate": 1.129509521407843e-05, "loss": 0.1633024513721466, "step": 348 }, { "epoch": 1.5086206896551724, "grad_norm": 0.23127630352973938, "learning_rate": 1.1568529889409417e-05, "loss": 0.7720933556556702, "step": 350 }, { "epoch": 1.5172413793103448, "grad_norm": 0.4621216654777527, "learning_rate": 1.1841438575827132e-05, "loss": 0.43289288878440857, "step": 352 }, { "epoch": 1.5258620689655173, "grad_norm": 0.24998484551906586, "learning_rate": 1.2113568785386663e-05, "loss": 0.7231047749519348, "step": 354 }, { "epoch": 1.5344827586206895, "grad_norm": 1.216570496559143, "learning_rate": 1.2384668750369462e-05, "loss": 0.5929489731788635, "step": 356 }, { "epoch": 1.543103448275862, "grad_norm": 0.45301932096481323, "learning_rate": 1.2654487656212154e-05, "loss": 1.3106164932250977, "step": 358 }, { "epoch": 1.5517241379310345, "grad_norm": 0.26960089802742004, "learning_rate": 1.2922775873553643e-05, "loss": 0.6820691823959351, "step": 360 }, { "epoch": 1.5603448275862069, "grad_norm": 0.5970767736434937, "learning_rate": 1.3189285189185581e-05, "loss": 1.2352055311203003, "step": 362 }, { "epoch": 1.5689655172413794, "grad_norm": 0.5552269816398621, "learning_rate": 1.3453769035692767e-05, "loss": 1.2412972450256348, "step": 364 }, { "epoch": 1.5775862068965516, "grad_norm": 0.373104453086853, "learning_rate": 1.3715982719570773e-05, "loss": 1.192505955696106, "step": 366 }, { "epoch": 1.5862068965517242, "grad_norm": 0.36400294303894043, "learning_rate": 1.397568364761001e-05, "loss": 1.2814549207687378, "step": 368 }, { "epoch": 1.5948275862068966, "grad_norm": 0.39620983600616455, "learning_rate": 1.4232631551336535e-05, "loss": 1.2581911087036133, "step": 370 }, { "epoch": 1.603448275862069, "grad_norm": 1.385265588760376, "learning_rate": 1.4486588709302146e-05, "loss": 1.0574073791503906, "step": 372 }, { "epoch": 1.6120689655172413, "grad_norm": 0.7239859104156494, "learning_rate": 1.4737320167018063e-05, "loss": 0.6223809123039246, "step": 374 }, { "epoch": 1.6206896551724137, "grad_norm": 2.1304306983947754, "learning_rate": 1.4984593954328579e-05, "loss": 0.8683441281318665, "step": 376 }, { "epoch": 1.6293103448275863, "grad_norm": 0.36936265230178833, "learning_rate": 1.5228181300023775e-05, "loss": 1.1772154569625854, "step": 378 }, { "epoch": 1.6379310344827587, "grad_norm": 0.45922592282295227, "learning_rate": 1.5467856843492662e-05, "loss": 1.0002669095993042, "step": 380 }, { "epoch": 1.646551724137931, "grad_norm": 1.180850625038147, "learning_rate": 1.5703398843220852e-05, "loss": 0.7394900321960449, "step": 382 }, { "epoch": 1.6551724137931034, "grad_norm": 0.7287831902503967, "learning_rate": 1.5934589381940026e-05, "loss": 0.7356396913528442, "step": 384 }, { "epoch": 1.6637931034482758, "grad_norm": 0.45975226163864136, "learning_rate": 1.6161214568239207e-05, "loss": 1.3296085596084595, "step": 386 }, { "epoch": 1.6724137931034484, "grad_norm": 0.8266739845275879, "learning_rate": 1.638306473445153e-05, "loss": 1.1994720697402954, "step": 388 }, { "epoch": 1.6810344827586206, "grad_norm": 0.2567940950393677, "learning_rate": 1.6599934630633217e-05, "loss": 1.0203474760055542, "step": 390 }, { "epoch": 1.6896551724137931, "grad_norm": 0.32722774147987366, "learning_rate": 1.681162361445544e-05, "loss": 0.8025456666946411, "step": 392 }, { "epoch": 1.6982758620689655, "grad_norm": 0.3686321973800659, "learning_rate": 1.7017935836833353e-05, "loss": 1.2664248943328857, "step": 394 }, { "epoch": 1.706896551724138, "grad_norm": 0.2905973792076111, "learning_rate": 1.7218680423120506e-05, "loss": 0.8020282983779907, "step": 396 }, { "epoch": 1.7155172413793105, "grad_norm": 0.2557852268218994, "learning_rate": 1.7413671649701026e-05, "loss": 0.8401910066604614, "step": 398 }, { "epoch": 1.7241379310344827, "grad_norm": 0.1601221263408661, "learning_rate": 1.7602729115816268e-05, "loss": 0.9220103621482849, "step": 400 }, { "epoch": 1.7327586206896552, "grad_norm": 0.7182515859603882, "learning_rate": 1.77856779104668e-05, "loss": 0.999250054359436, "step": 402 }, { "epoch": 1.7413793103448276, "grad_norm": 0.8001770973205566, "learning_rate": 1.7962348774235565e-05, "loss": 1.7149617671966553, "step": 404 }, { "epoch": 1.75, "grad_norm": 1.6669609546661377, "learning_rate": 1.8132578255882124e-05, "loss": 0.9877924919128418, "step": 406 }, { "epoch": 1.7586206896551724, "grad_norm": 0.735676109790802, "learning_rate": 1.8296208863563515e-05, "loss": 1.2993067502975464, "step": 408 }, { "epoch": 1.7672413793103448, "grad_norm": 6.548970699310303, "learning_rate": 1.8453089210541577e-05, "loss": 0.8246227502822876, "step": 410 }, { "epoch": 1.7758620689655173, "grad_norm": 0.4565357565879822, "learning_rate": 1.8603074155241946e-05, "loss": 1.2052366733551025, "step": 412 }, { "epoch": 1.7844827586206895, "grad_norm": 0.3367665112018585, "learning_rate": 1.8746024935535238e-05, "loss": 1.217560887336731, "step": 414 }, { "epoch": 1.793103448275862, "grad_norm": 0.7779958844184875, "learning_rate": 1.8881809297116126e-05, "loss": 0.3758542239665985, "step": 416 }, { "epoch": 1.8017241379310345, "grad_norm": 0.5207919478416443, "learning_rate": 1.901030161586157e-05, "loss": 1.4365136623382568, "step": 418 }, { "epoch": 1.8103448275862069, "grad_norm": 6.575118541717529, "learning_rate": 1.9131383014054904e-05, "loss": 0.7461058497428894, "step": 420 }, { "epoch": 1.8189655172413794, "grad_norm": 0.35711878538131714, "learning_rate": 1.924494147036844e-05, "loss": 1.2452733516693115, "step": 422 }, { "epoch": 1.8275862068965516, "grad_norm": 0.410709410905838, "learning_rate": 1.9350871923502582e-05, "loss": 1.1930017471313477, "step": 424 }, { "epoch": 1.8362068965517242, "grad_norm": 0.6211258769035339, "learning_rate": 1.944907636938585e-05, "loss": 1.0968483686447144, "step": 426 }, { "epoch": 1.8448275862068966, "grad_norm": 7.162904739379883, "learning_rate": 1.953946395184563e-05, "loss": 0.3261430561542511, "step": 428 }, { "epoch": 1.853448275862069, "grad_norm": 7.713586807250977, "learning_rate": 1.962195104666592e-05, "loss": 0.6268512010574341, "step": 430 }, { "epoch": 1.8620689655172413, "grad_norm": 0.4543277323246002, "learning_rate": 1.9696461338954278e-05, "loss": 0.832156240940094, "step": 432 }, { "epoch": 1.8706896551724137, "grad_norm": 2.5041592121124268, "learning_rate": 1.976292589374634e-05, "loss": 0.5735204815864563, "step": 434 }, { "epoch": 1.8793103448275863, "grad_norm": 0.7300209403038025, "learning_rate": 1.9821283219782627e-05, "loss": 0.5290496945381165, "step": 436 }, { "epoch": 1.8879310344827587, "grad_norm": 0.34921202063560486, "learning_rate": 1.9871479326398668e-05, "loss": 1.232295036315918, "step": 438 }, { "epoch": 1.896551724137931, "grad_norm": 0.3079286217689514, "learning_rate": 1.9913467773475727e-05, "loss": 1.189243197441101, "step": 440 }, { "epoch": 1.9051724137931034, "grad_norm": 0.23536956310272217, "learning_rate": 1.9947209714405984e-05, "loss": 0.7931770086288452, "step": 442 }, { "epoch": 1.9137931034482758, "grad_norm": 1.4744566679000854, "learning_rate": 1.9972673932032394e-05, "loss": 0.7982081174850464, "step": 444 }, { "epoch": 1.9224137931034484, "grad_norm": 0.3188006281852722, "learning_rate": 1.9989836867529987e-05, "loss": 0.661638081073761, "step": 446 }, { "epoch": 1.9310344827586206, "grad_norm": 0.5140587687492371, "learning_rate": 1.999868264220186e-05, "loss": 1.3983592987060547, "step": 448 }, { "epoch": 1.9396551724137931, "grad_norm": 0.6525475382804871, "learning_rate": 1.999920307216975e-05, "loss": 1.5112402439117432, "step": 450 }, { "epoch": 1.9482758620689655, "grad_norm": 0.236190065741539, "learning_rate": 1.9991397675945524e-05, "loss": 1.2273776531219482, "step": 452 }, { "epoch": 1.956896551724138, "grad_norm": 0.2825621962547302, "learning_rate": 1.9975273674876653e-05, "loss": 0.7660670876502991, "step": 454 }, { "epoch": 1.9655172413793105, "grad_norm": 0.21918132901191711, "learning_rate": 1.99508459864652e-05, "loss": 0.9497285485267639, "step": 456 }, { "epoch": 1.9741379310344827, "grad_norm": 0.38524022698402405, "learning_rate": 1.991813721056655e-05, "loss": 1.0104745626449585, "step": 458 }, { "epoch": 1.9827586206896552, "grad_norm": 3.191633701324463, "learning_rate": 1.987717760848061e-05, "loss": 0.919417679309845, "step": 460 }, { "epoch": 1.9913793103448276, "grad_norm": 0.2649468183517456, "learning_rate": 1.982800507495485e-05, "loss": 1.400168538093567, "step": 462 }, { "epoch": 2.0, "grad_norm": 0.6692625880241394, "learning_rate": 1.977066510312508e-05, "loss": 1.335584282875061, "step": 464 }, { "epoch": 2.0086206896551726, "grad_norm": 0.93243408203125, "learning_rate": 1.9705210742426404e-05, "loss": 1.1145689487457275, "step": 466 }, { "epoch": 2.0172413793103448, "grad_norm": 0.8251880407333374, "learning_rate": 1.9631702549513264e-05, "loss": 1.1242371797561646, "step": 468 }, { "epoch": 2.0258620689655173, "grad_norm": 1.484380841255188, "learning_rate": 1.9550208532234013e-05, "loss": 1.022644281387329, "step": 470 }, { "epoch": 2.0344827586206895, "grad_norm": 0.8342429995536804, "learning_rate": 1.9460804086711857e-05, "loss": 0.6067448258399963, "step": 472 }, { "epoch": 2.043103448275862, "grad_norm": 6.31473445892334, "learning_rate": 1.936357192759033e-05, "loss": 1.1570570468902588, "step": 474 }, { "epoch": 2.0517241379310347, "grad_norm": 0.2635251581668854, "learning_rate": 1.9258602011507896e-05, "loss": 1.0996088981628418, "step": 476 }, { "epoch": 2.060344827586207, "grad_norm": 0.5212433338165283, "learning_rate": 1.9145991453872398e-05, "loss": 0.6901102066040039, "step": 478 }, { "epoch": 2.0689655172413794, "grad_norm": 0.4480215311050415, "learning_rate": 1.902584443901246e-05, "loss": 1.4176607131958008, "step": 480 }, { "epoch": 2.0775862068965516, "grad_norm": 2.65861439704895, "learning_rate": 1.8898272123788897e-05, "loss": 1.0099068880081177, "step": 482 }, { "epoch": 2.086206896551724, "grad_norm": 0.35105887055397034, "learning_rate": 1.8763392534755276e-05, "loss": 0.9407973289489746, "step": 484 }, { "epoch": 2.0948275862068964, "grad_norm": 0.3949888348579407, "learning_rate": 1.862133045896286e-05, "loss": 1.2682446241378784, "step": 486 }, { "epoch": 2.103448275862069, "grad_norm": 0.16779205203056335, "learning_rate": 1.847221732851092e-05, "loss": 0.2819199562072754, "step": 488 }, { "epoch": 2.1120689655172415, "grad_norm": 1.363291621208191, "learning_rate": 1.831619109894921e-05, "loss": 0.4681054651737213, "step": 490 }, { "epoch": 2.1206896551724137, "grad_norm": 0.33102285861968994, "learning_rate": 1.81533961216451e-05, "loss": 0.9479153156280518, "step": 492 }, { "epoch": 2.1293103448275863, "grad_norm": 0.6415525674819946, "learning_rate": 1.79839830102335e-05, "loss": 1.2515679597854614, "step": 494 }, { "epoch": 2.1379310344827585, "grad_norm": 0.2858109474182129, "learning_rate": 1.780810850127307e-05, "loss": 1.110595464706421, "step": 496 }, { "epoch": 2.146551724137931, "grad_norm": 0.7833629846572876, "learning_rate": 1.7625935309237705e-05, "loss": 0.6906008720397949, "step": 498 }, { "epoch": 2.1551724137931036, "grad_norm": 0.3774907886981964, "learning_rate": 1.7437631975977327e-05, "loss": 0.8901933431625366, "step": 500 }, { "epoch": 2.163793103448276, "grad_norm": 1.0206127166748047, "learning_rate": 1.7243372714787447e-05, "loss": 1.1632163524627686, "step": 502 }, { "epoch": 2.1724137931034484, "grad_norm": 0.2904803454875946, "learning_rate": 1.704333724923158e-05, "loss": 1.0225820541381836, "step": 504 }, { "epoch": 2.1810344827586206, "grad_norm": 1.0189746618270874, "learning_rate": 1.683771064686572e-05, "loss": 0.596871018409729, "step": 506 }, { "epoch": 2.189655172413793, "grad_norm": 0.2902408540248871, "learning_rate": 1.6626683148018704e-05, "loss": 1.1479698419570923, "step": 508 }, { "epoch": 2.1982758620689653, "grad_norm": 0.32355165481567383, "learning_rate": 1.6410449989786864e-05, "loss": 1.113614559173584, "step": 510 }, { "epoch": 2.206896551724138, "grad_norm": 0.34692347049713135, "learning_rate": 1.6189211225405815e-05, "loss": 0.7449208498001099, "step": 512 }, { "epoch": 2.2155172413793105, "grad_norm": 0.30047309398651123, "learning_rate": 1.596317153916643e-05, "loss": 1.1159427165985107, "step": 514 }, { "epoch": 2.2241379310344827, "grad_norm": 0.6437045335769653, "learning_rate": 1.5732540057046285e-05, "loss": 0.7390024662017822, "step": 516 }, { "epoch": 2.2327586206896552, "grad_norm": 0.46292436122894287, "learning_rate": 1.5497530153231886e-05, "loss": 0.7803560495376587, "step": 518 }, { "epoch": 2.2413793103448274, "grad_norm": 0.5340967774391174, "learning_rate": 1.5258359252710415e-05, "loss": 1.3723326921463013, "step": 520 }, { "epoch": 2.25, "grad_norm": 0.31911370158195496, "learning_rate": 1.5015248630113865e-05, "loss": 0.7922369241714478, "step": 522 }, { "epoch": 2.2586206896551726, "grad_norm": 0.4369973838329315, "learning_rate": 1.476842320500153e-05, "loss": 0.7873719334602356, "step": 524 }, { "epoch": 2.2672413793103448, "grad_norm": 5.220350742340088, "learning_rate": 1.4518111333770401e-05, "loss": 0.7667290568351746, "step": 526 }, { "epoch": 2.2758620689655173, "grad_norm": 0.7911840081214905, "learning_rate": 1.4264544598385801e-05, "loss": 1.106222152709961, "step": 528 }, { "epoch": 2.2844827586206895, "grad_norm": 0.27636000514030457, "learning_rate": 1.4007957592127807e-05, "loss": 1.0902438163757324, "step": 530 }, { "epoch": 2.293103448275862, "grad_norm": 0.4640883505344391, "learning_rate": 1.374858770255177e-05, "loss": 0.8156579732894897, "step": 532 }, { "epoch": 2.3017241379310347, "grad_norm": 0.8998560905456543, "learning_rate": 1.3486674891863518e-05, "loss": 1.139012098312378, "step": 534 }, { "epoch": 2.310344827586207, "grad_norm": 0.4182785451412201, "learning_rate": 1.322246147491271e-05, "loss": 1.191633701324463, "step": 536 }, { "epoch": 2.3189655172413794, "grad_norm": 0.39193910360336304, "learning_rate": 1.2956191895009415e-05, "loss": 0.7655143141746521, "step": 538 }, { "epoch": 2.3275862068965516, "grad_norm": 0.4902004301548004, "learning_rate": 1.268811249777167e-05, "loss": 0.9563652276992798, "step": 540 }, { "epoch": 2.336206896551724, "grad_norm": 0.6500739455223083, "learning_rate": 1.2418471303212933e-05, "loss": 0.7211173176765442, "step": 542 }, { "epoch": 2.344827586206897, "grad_norm": 0.32692751288414, "learning_rate": 1.2147517776280517e-05, "loss": 1.0490473508834839, "step": 544 }, { "epoch": 2.353448275862069, "grad_norm": 0.8291403651237488, "learning_rate": 1.1875502596057116e-05, "loss": 0.8839560151100159, "step": 546 }, { "epoch": 2.3620689655172415, "grad_norm": 0.28376197814941406, "learning_rate": 1.1602677423839195e-05, "loss": 1.127523422241211, "step": 548 }, { "epoch": 2.3706896551724137, "grad_norm": 0.604331910610199, "learning_rate": 1.1329294670306513e-05, "loss": 0.6361532807350159, "step": 550 }, { "epoch": 2.3793103448275863, "grad_norm": 0.6158839464187622, "learning_rate": 1.1055607261998416e-05, "loss": 0.31083130836486816, "step": 552 }, { "epoch": 2.3879310344827585, "grad_norm": 0.3060431480407715, "learning_rate": 1.078186840731281e-05, "loss": 1.2638636827468872, "step": 554 }, { "epoch": 2.396551724137931, "grad_norm": 0.25409573316574097, "learning_rate": 1.0508331362244472e-05, "loss": 1.079472303390503, "step": 556 }, { "epoch": 2.405172413793103, "grad_norm": 0.15330657362937927, "learning_rate": 1.0235249196079217e-05, "loss": 0.4111257493495941, "step": 558 }, { "epoch": 2.413793103448276, "grad_norm": 0.5213512778282166, "learning_rate": 9.96287455726086e-06, "loss": 0.9900328516960144, "step": 560 }, { "epoch": 2.4224137931034484, "grad_norm": 0.28381043672561646, "learning_rate": 9.691459439647469e-06, "loss": 0.8341249823570251, "step": 562 }, { "epoch": 2.4310344827586206, "grad_norm": 0.676983654499054, "learning_rate": 9.421254949373347e-06, "loss": 0.8743176460266113, "step": 564 }, { "epoch": 2.439655172413793, "grad_norm": 0.3603588938713074, "learning_rate": 9.152511072532206e-06, "loss": 1.056296467781067, "step": 566 }, { "epoch": 2.4482758620689653, "grad_norm": 1.0118433237075806, "learning_rate": 8.88547644389654e-06, "loss": 1.413284182548523, "step": 568 }, { "epoch": 2.456896551724138, "grad_norm": 1.1313719749450684, "learning_rate": 8.62039811688737e-06, "loss": 0.1686408817768097, "step": 570 }, { "epoch": 2.4655172413793105, "grad_norm": 0.2529284656047821, "learning_rate": 8.357521335006843e-06, "loss": 0.9291278123855591, "step": 572 }, { "epoch": 2.4741379310344827, "grad_norm": 0.26292645931243896, "learning_rate": 8.097089304945431e-06, "loss": 1.1657003164291382, "step": 574 }, { "epoch": 2.4827586206896552, "grad_norm": 0.46254923939704895, "learning_rate": 7.839342971573412e-06, "loss": 1.1208579540252686, "step": 576 }, { "epoch": 2.4913793103448274, "grad_norm": 0.5573145151138306, "learning_rate": 7.584520795025116e-06, "loss": 0.6583477258682251, "step": 578 }, { "epoch": 2.5, "grad_norm": 0.3368423283100128, "learning_rate": 7.332858530081812e-06, "loss": 1.1409282684326172, "step": 580 }, { "epoch": 2.5086206896551726, "grad_norm": 0.22401149570941925, "learning_rate": 7.084589008057583e-06, "loss": 0.9950229525566101, "step": 582 }, { "epoch": 2.5172413793103448, "grad_norm": 0.4168458580970764, "learning_rate": 6.839941921389941e-06, "loss": 0.677608847618103, "step": 584 }, { "epoch": 2.5258620689655173, "grad_norm": 0.3188498616218567, "learning_rate": 6.599143611134356e-06, "loss": 0.21669866144657135, "step": 586 }, { "epoch": 2.5344827586206895, "grad_norm": 0.41348910331726074, "learning_rate": 6.362416857559549e-06, "loss": 0.7037891745567322, "step": 588 }, { "epoch": 2.543103448275862, "grad_norm": 3.121192216873169, "learning_rate": 6.129980674036977e-06, "loss": 0.9864909648895264, "step": 590 }, { "epoch": 2.5517241379310347, "grad_norm": 0.6518086194992065, "learning_rate": 5.90205010441544e-06, "loss": 0.8599920272827148, "step": 592 }, { "epoch": 2.560344827586207, "grad_norm": 0.6577050685882568, "learning_rate": 5.678836024068174e-06, "loss": 0.7931281328201294, "step": 594 }, { "epoch": 2.5689655172413794, "grad_norm": 0.1971147507429123, "learning_rate": 5.4605449447964406e-06, "loss": 0.7438328862190247, "step": 596 }, { "epoch": 2.5775862068965516, "grad_norm": 0.687308132648468, "learning_rate": 5.24737882377032e-06, "loss": 0.7791666984558105, "step": 598 }, { "epoch": 2.586206896551724, "grad_norm": 0.24792003631591797, "learning_rate": 5.039534876683188e-06, "loss": 1.1297264099121094, "step": 600 }, { "epoch": 2.594827586206897, "grad_norm": 0.431932657957077, "learning_rate": 4.837205395292953e-06, "loss": 0.6758660674095154, "step": 602 }, { "epoch": 2.603448275862069, "grad_norm": 1.7007827758789062, "learning_rate": 4.640577569518789e-06, "loss": 1.114516019821167, "step": 604 }, { "epoch": 2.612068965517241, "grad_norm": 0.2791440188884735, "learning_rate": 4.449833314257892e-06, "loss": 0.6865538954734802, "step": 606 }, { "epoch": 2.6206896551724137, "grad_norm": 0.14818964898586273, "learning_rate": 4.265149101082668e-06, "loss": 0.667411744594574, "step": 608 }, { "epoch": 2.6293103448275863, "grad_norm": 0.47603490948677063, "learning_rate": 4.086695794973827e-06, "loss": 0.999786376953125, "step": 610 }, { "epoch": 2.637931034482759, "grad_norm": 0.26607102155685425, "learning_rate": 3.914638496240613e-06, "loss": 0.8935456275939941, "step": 612 }, { "epoch": 2.646551724137931, "grad_norm": 0.5287325382232666, "learning_rate": 3.7491363877742946e-06, "loss": 0.293642520904541, "step": 614 }, { "epoch": 2.655172413793103, "grad_norm": 0.7885716557502747, "learning_rate": 3.5903425877764024e-06, "loss": 0.860302209854126, "step": 616 }, { "epoch": 2.663793103448276, "grad_norm": 0.23788996040821075, "learning_rate": 3.4384040080977486e-06, "loss": 0.679624617099762, "step": 618 }, { "epoch": 2.6724137931034484, "grad_norm": 0.5915703773498535, "learning_rate": 3.2934612183194636e-06, "loss": 0.6118066310882568, "step": 620 }, { "epoch": 2.6810344827586206, "grad_norm": 0.347929984331131, "learning_rate": 3.1556483157016765e-06, "loss": 1.0104352235794067, "step": 622 }, { "epoch": 2.689655172413793, "grad_norm": 0.3776116967201233, "learning_rate": 3.0250928011203114e-06, "loss": 0.7297549843788147, "step": 624 }, { "epoch": 2.6982758620689653, "grad_norm": 0.33936139941215515, "learning_rate": 2.9019154611065938e-06, "loss": 1.0180128812789917, "step": 626 }, { "epoch": 2.706896551724138, "grad_norm": 1.2539973258972168, "learning_rate": 2.7862302560985105e-06, "loss": 0.729310154914856, "step": 628 }, { "epoch": 2.7155172413793105, "grad_norm": 0.11071612685918808, "learning_rate": 2.6781442150076485e-06, "loss": 0.5759393572807312, "step": 630 }, { "epoch": 2.7241379310344827, "grad_norm": 0.3599656820297241, "learning_rate": 2.577757336198829e-06, "loss": 0.8420278429985046, "step": 632 }, { "epoch": 2.7327586206896552, "grad_norm": 0.45908743143081665, "learning_rate": 2.4851624949742624e-06, "loss": 1.203715443611145, "step": 634 }, { "epoch": 2.7413793103448274, "grad_norm": 0.4836440682411194, "learning_rate": 2.4004453576477363e-06, "loss": 1.251405119895935, "step": 636 }, { "epoch": 2.75, "grad_norm": 0.406963974237442, "learning_rate": 2.323684302288429e-06, "loss": 0.5981881022453308, "step": 638 }, { "epoch": 2.7586206896551726, "grad_norm": 0.4914894700050354, "learning_rate": 2.2549503462075524e-06, "loss": 0.4858713448047638, "step": 640 }, { "epoch": 2.7672413793103448, "grad_norm": 0.49679532647132874, "learning_rate": 2.1943070802550147e-06, "loss": 1.0236581563949585, "step": 642 }, { "epoch": 2.7758620689655173, "grad_norm": 0.5968631505966187, "learning_rate": 2.141810609986821e-06, "loss": 0.7582760453224182, "step": 644 }, { "epoch": 2.7844827586206895, "grad_norm": 0.47396087646484375, "learning_rate": 2.0975095037577143e-06, "loss": 0.7772106528282166, "step": 646 }, { "epoch": 2.793103448275862, "grad_norm": 0.29245540499687195, "learning_rate": 2.0614447477869856e-06, "loss": 0.9372343420982361, "step": 648 }, { "epoch": 2.8017241379310347, "grad_norm": 0.3278985023498535, "learning_rate": 2.0336497082391155e-06, "loss": 1.1293443441390991, "step": 650 }, { "epoch": 2.810344827586207, "grad_norm": 0.2128603756427765, "learning_rate": 2.0141501003542617e-06, "loss": 0.21890364587306976, "step": 652 }, { "epoch": 2.8189655172413794, "grad_norm": 0.2553781569004059, "learning_rate": 2.002963964657213e-06, "loss": 0.9752658605575562, "step": 654 }, { "epoch": 2.8275862068965516, "grad_norm": 0.6789045333862305, "learning_rate": 2.0001016502667552e-06, "loss": 1.158425211906433, "step": 656 }, { "epoch": 2.836206896551724, "grad_norm": 0.2958366572856903, "learning_rate": 2.0055658053209428e-06, "loss": 0.09864208102226257, "step": 658 }, { "epoch": 2.844827586206897, "grad_norm": 0.5826700925827026, "learning_rate": 2.0193513745271104e-06, "loss": 1.1222366094589233, "step": 660 }, { "epoch": 2.853448275862069, "grad_norm": 0.2867080867290497, "learning_rate": 2.041445603838903e-06, "loss": 0.7978563904762268, "step": 662 }, { "epoch": 2.862068965517241, "grad_norm": 0.9346190690994263, "learning_rate": 2.071828052255974e-06, "loss": 1.0888785123825073, "step": 664 }, { "epoch": 2.8706896551724137, "grad_norm": 0.4730575382709503, "learning_rate": 2.110470610735471e-06, "loss": 0.8604229688644409, "step": 666 }, { "epoch": 2.8793103448275863, "grad_norm": 0.3757993280887604, "learning_rate": 2.157337528197775e-06, "loss": 0.6924110054969788, "step": 668 }, { "epoch": 2.887931034482759, "grad_norm": 0.7365322709083557, "learning_rate": 2.2123854446024656e-06, "loss": 1.1259899139404297, "step": 670 }, { "epoch": 2.896551724137931, "grad_norm": 0.20995132625102997, "learning_rate": 2.275563431063895e-06, "loss": 0.5768133997917175, "step": 672 }, { "epoch": 2.905172413793103, "grad_norm": 0.12330807000398636, "learning_rate": 2.346813036969242e-06, "loss": 0.655694842338562, "step": 674 }, { "epoch": 2.913793103448276, "grad_norm": 0.295114129781723, "learning_rate": 2.4260683440554954e-06, "loss": 0.6339759230613708, "step": 676 }, { "epoch": 2.9224137931034484, "grad_norm": 0.3862989544868469, "learning_rate": 2.5132560273952874e-06, "loss": 0.9285910129547119, "step": 678 }, { "epoch": 2.9310344827586206, "grad_norm": 0.33736833930015564, "learning_rate": 2.6082954232351966e-06, "loss": 0.8067626953125, "step": 680 }, { "epoch": 2.939655172413793, "grad_norm": 0.23088297247886658, "learning_rate": 2.711098603623742e-06, "loss": 1.2526490688323975, "step": 682 }, { "epoch": 2.9482758620689653, "grad_norm": 0.29236695170402527, "learning_rate": 2.821570457759993e-06, "loss": 1.1392483711242676, "step": 684 }, { "epoch": 2.956896551724138, "grad_norm": 2.1297762393951416, "learning_rate": 2.9396087799875866e-06, "loss": 0.7813910841941833, "step": 686 }, { "epoch": 2.9655172413793105, "grad_norm": 0.7009169459342957, "learning_rate": 3.065104364352743e-06, "loss": 0.9301526546478271, "step": 688 }, { "epoch": 2.9741379310344827, "grad_norm": 0.6672054529190063, "learning_rate": 3.197941105638702e-06, "loss": 1.025092601776123, "step": 690 }, { "epoch": 2.9827586206896552, "grad_norm": 0.5058484673500061, "learning_rate": 3.337996106783247e-06, "loss": 0.6867604851722717, "step": 692 }, { "epoch": 2.9913793103448274, "grad_norm": 0.34245193004608154, "learning_rate": 3.4851397925798167e-06, "loss": 1.19440495967865, "step": 694 }, { "epoch": 3.0, "grad_norm": 0.4390437602996826, "learning_rate": 3.6392360295571228e-06, "loss": 1.113608717918396, "step": 696 }, { "epoch": 3.0, "step": 696, "total_flos": 2.7548743231466373e+18, "train_loss": 1.0648414060130886, "train_runtime": 11016.7324, "train_samples_per_second": 3.791, "train_steps_per_second": 0.063 } ], "logging_steps": 2, "max_steps": 696, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2.7548743231466373e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }