{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1892, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004228329809725159, "grad_norm": 6.600518226623535, "learning_rate": 1.0526315789473685e-07, "loss": 1.8237226009368896, "step": 2 }, { "epoch": 0.008456659619450317, "grad_norm": 0.9379130601882935, "learning_rate": 3.1578947368421055e-07, "loss": 2.177493095397949, "step": 4 }, { "epoch": 0.012684989429175475, "grad_norm": 3.6401278972625732, "learning_rate": 5.263157894736843e-07, "loss": 2.1492836475372314, "step": 6 }, { "epoch": 0.016913319238900635, "grad_norm": 0.9547787308692932, "learning_rate": 7.368421052631579e-07, "loss": 1.9534509181976318, "step": 8 }, { "epoch": 0.021141649048625793, "grad_norm": 2.7486395835876465, "learning_rate": 9.473684210526317e-07, "loss": 2.0047357082366943, "step": 10 }, { "epoch": 0.02536997885835095, "grad_norm": 1.9829468727111816, "learning_rate": 1.1578947368421053e-06, "loss": 1.6684722900390625, "step": 12 }, { "epoch": 0.02959830866807611, "grad_norm": 0.7353739142417908, "learning_rate": 1.3684210526315791e-06, "loss": 1.619055986404419, "step": 14 }, { "epoch": 0.03382663847780127, "grad_norm": 0.9400134682655334, "learning_rate": 1.5789473684210526e-06, "loss": 1.7449512481689453, "step": 16 }, { "epoch": 0.03805496828752643, "grad_norm": 1.2510457038879395, "learning_rate": 1.7894736842105265e-06, "loss": 1.7587066888809204, "step": 18 }, { "epoch": 0.042283298097251586, "grad_norm": 4.52321720123291, "learning_rate": 2.0000000000000003e-06, "loss": 1.6912537813186646, "step": 20 }, { "epoch": 0.046511627906976744, "grad_norm": 7.146050453186035, "learning_rate": 2.2105263157894738e-06, "loss": 1.5326210260391235, "step": 22 }, { "epoch": 0.0507399577167019, "grad_norm": 1.5333527326583862, "learning_rate": 2.4210526315789477e-06, "loss": 1.7473461627960205, "step": 24 }, { "epoch": 0.05496828752642706, "grad_norm": 1.9742282629013062, "learning_rate": 2.631578947368421e-06, "loss": 1.3772677183151245, "step": 26 }, { "epoch": 0.05919661733615222, "grad_norm": 0.5260951519012451, "learning_rate": 2.842105263157895e-06, "loss": 1.6295863389968872, "step": 28 }, { "epoch": 0.06342494714587738, "grad_norm": 0.7318488359451294, "learning_rate": 3.052631578947369e-06, "loss": 1.27083158493042, "step": 30 }, { "epoch": 0.06765327695560254, "grad_norm": 2.3866994380950928, "learning_rate": 3.2631578947368423e-06, "loss": 1.053689956665039, "step": 32 }, { "epoch": 0.07188160676532769, "grad_norm": 1.2083148956298828, "learning_rate": 3.473684210526316e-06, "loss": 1.1827961206436157, "step": 34 }, { "epoch": 0.07610993657505286, "grad_norm": 1.15328049659729, "learning_rate": 3.6842105263157896e-06, "loss": 1.3492432832717896, "step": 36 }, { "epoch": 0.080338266384778, "grad_norm": 1.3496743440628052, "learning_rate": 3.894736842105263e-06, "loss": 1.2592878341674805, "step": 38 }, { "epoch": 0.08456659619450317, "grad_norm": 1.8648970127105713, "learning_rate": 4.105263157894737e-06, "loss": 1.2325811386108398, "step": 40 }, { "epoch": 0.08879492600422834, "grad_norm": 2.665983200073242, "learning_rate": 4.315789473684211e-06, "loss": 1.6488211154937744, "step": 42 }, { "epoch": 0.09302325581395349, "grad_norm": 2.625236749649048, "learning_rate": 4.526315789473685e-06, "loss": 1.6180524826049805, "step": 44 }, { "epoch": 0.09725158562367865, "grad_norm": 0.5827649831771851, "learning_rate": 4.736842105263158e-06, "loss": 1.2748819589614868, "step": 46 }, { "epoch": 0.1014799154334038, "grad_norm": 0.7074928283691406, "learning_rate": 4.947368421052632e-06, "loss": 1.4886584281921387, "step": 48 }, { "epoch": 0.10570824524312897, "grad_norm": 1.119913935661316, "learning_rate": 5.157894736842106e-06, "loss": 1.4856940507888794, "step": 50 }, { "epoch": 0.10993657505285412, "grad_norm": 1.3313361406326294, "learning_rate": 5.36842105263158e-06, "loss": 0.7060391902923584, "step": 52 }, { "epoch": 0.11416490486257928, "grad_norm": 0.5544728636741638, "learning_rate": 5.578947368421052e-06, "loss": 1.0533510446548462, "step": 54 }, { "epoch": 0.11839323467230443, "grad_norm": 0.6537541151046753, "learning_rate": 5.789473684210527e-06, "loss": 1.3604283332824707, "step": 56 }, { "epoch": 0.1226215644820296, "grad_norm": 0.7256506681442261, "learning_rate": 6e-06, "loss": 1.3856151103973389, "step": 58 }, { "epoch": 0.12684989429175475, "grad_norm": 0.8060622215270996, "learning_rate": 6.2105263157894745e-06, "loss": 1.3991085290908813, "step": 60 }, { "epoch": 0.13107822410147993, "grad_norm": 1.4142024517059326, "learning_rate": 6.421052631578948e-06, "loss": 0.7651398777961731, "step": 62 }, { "epoch": 0.13530655391120508, "grad_norm": 0.7716662883758545, "learning_rate": 6.631578947368421e-06, "loss": 1.006196141242981, "step": 64 }, { "epoch": 0.13953488372093023, "grad_norm": 0.44893163442611694, "learning_rate": 6.842105263157896e-06, "loss": 1.3261468410491943, "step": 66 }, { "epoch": 0.14376321353065538, "grad_norm": 0.9389207363128662, "learning_rate": 7.052631578947369e-06, "loss": 1.3669592142105103, "step": 68 }, { "epoch": 0.14799154334038056, "grad_norm": 1.580122709274292, "learning_rate": 7.263157894736843e-06, "loss": 1.3526923656463623, "step": 70 }, { "epoch": 0.1522198731501057, "grad_norm": 0.715559720993042, "learning_rate": 7.473684210526316e-06, "loss": 1.3386205434799194, "step": 72 }, { "epoch": 0.15644820295983086, "grad_norm": 0.597973644733429, "learning_rate": 7.68421052631579e-06, "loss": 0.9182925820350647, "step": 74 }, { "epoch": 0.160676532769556, "grad_norm": 0.8445482850074768, "learning_rate": 7.894736842105265e-06, "loss": 0.8244398236274719, "step": 76 }, { "epoch": 0.1649048625792812, "grad_norm": 1.098714828491211, "learning_rate": 8.105263157894736e-06, "loss": 1.291409969329834, "step": 78 }, { "epoch": 0.16913319238900634, "grad_norm": 3.9219131469726562, "learning_rate": 8.315789473684212e-06, "loss": 1.0494245290756226, "step": 80 }, { "epoch": 0.1733615221987315, "grad_norm": 1.0094599723815918, "learning_rate": 8.526315789473685e-06, "loss": 1.1030141115188599, "step": 82 }, { "epoch": 0.17758985200845667, "grad_norm": 0.4699074625968933, "learning_rate": 8.736842105263158e-06, "loss": 0.8207240700721741, "step": 84 }, { "epoch": 0.18181818181818182, "grad_norm": 1.192646861076355, "learning_rate": 8.947368421052632e-06, "loss": 1.7233288288116455, "step": 86 }, { "epoch": 0.18604651162790697, "grad_norm": 1.4525370597839355, "learning_rate": 9.157894736842105e-06, "loss": 1.2845737934112549, "step": 88 }, { "epoch": 0.19027484143763213, "grad_norm": 2.855733633041382, "learning_rate": 9.36842105263158e-06, "loss": 1.0188437700271606, "step": 90 }, { "epoch": 0.1945031712473573, "grad_norm": 0.9708726406097412, "learning_rate": 9.578947368421054e-06, "loss": 1.313187837600708, "step": 92 }, { "epoch": 0.19873150105708245, "grad_norm": 0.8037315607070923, "learning_rate": 9.789473684210527e-06, "loss": 0.9850687980651855, "step": 94 }, { "epoch": 0.2029598308668076, "grad_norm": 1.2460066080093384, "learning_rate": 1e-05, "loss": 1.291996717453003, "step": 96 }, { "epoch": 0.20718816067653276, "grad_norm": 2.393672466278076, "learning_rate": 9.999972492846047e-06, "loss": 1.390143871307373, "step": 98 }, { "epoch": 0.21141649048625794, "grad_norm": 0.7215428352355957, "learning_rate": 9.999889971720468e-06, "loss": 1.365293264389038, "step": 100 }, { "epoch": 0.2156448202959831, "grad_norm": 0.6862542629241943, "learning_rate": 9.999752437632121e-06, "loss": 1.2429871559143066, "step": 102 }, { "epoch": 0.21987315010570824, "grad_norm": 1.001516580581665, "learning_rate": 9.999559892262412e-06, "loss": 1.3055249452590942, "step": 104 }, { "epoch": 0.22410147991543342, "grad_norm": 0.9053167104721069, "learning_rate": 9.999312337965291e-06, "loss": 1.2950866222381592, "step": 106 }, { "epoch": 0.22832980972515857, "grad_norm": 2.085611343383789, "learning_rate": 9.999009777767202e-06, "loss": 1.0194011926651, "step": 108 }, { "epoch": 0.23255813953488372, "grad_norm": 1.8900271654129028, "learning_rate": 9.99865221536707e-06, "loss": 1.2824671268463135, "step": 110 }, { "epoch": 0.23678646934460887, "grad_norm": 1.576374888420105, "learning_rate": 9.998239655136237e-06, "loss": 1.3616923093795776, "step": 112 }, { "epoch": 0.24101479915433405, "grad_norm": 0.7874072790145874, "learning_rate": 9.997772102118417e-06, "loss": 1.5419936180114746, "step": 114 }, { "epoch": 0.2452431289640592, "grad_norm": 1.69489324092865, "learning_rate": 9.997249562029637e-06, "loss": 1.3231698274612427, "step": 116 }, { "epoch": 0.24947145877378435, "grad_norm": 5.2726569175720215, "learning_rate": 9.996672041258154e-06, "loss": 1.3425744771957397, "step": 118 }, { "epoch": 0.2536997885835095, "grad_norm": 5.125090599060059, "learning_rate": 9.996039546864395e-06, "loss": 0.8081343173980713, "step": 120 }, { "epoch": 0.25792811839323465, "grad_norm": 1.0195448398590088, "learning_rate": 9.995352086580858e-06, "loss": 1.3033736944198608, "step": 122 }, { "epoch": 0.26215644820295986, "grad_norm": 0.6856747269630432, "learning_rate": 9.994609668812022e-06, "loss": 1.1338609457015991, "step": 124 }, { "epoch": 0.266384778012685, "grad_norm": 0.8176230788230896, "learning_rate": 9.993812302634237e-06, "loss": 1.339530348777771, "step": 126 }, { "epoch": 0.27061310782241016, "grad_norm": 1.3336821794509888, "learning_rate": 9.99295999779563e-06, "loss": 0.9904228448867798, "step": 128 }, { "epoch": 0.2748414376321353, "grad_norm": 0.6856302618980408, "learning_rate": 9.99205276471597e-06, "loss": 0.9754419326782227, "step": 130 }, { "epoch": 0.27906976744186046, "grad_norm": 1.4551591873168945, "learning_rate": 9.991090614486546e-06, "loss": 1.2865650653839111, "step": 132 }, { "epoch": 0.2832980972515856, "grad_norm": 1.366995096206665, "learning_rate": 9.990073558870028e-06, "loss": 0.8697801232337952, "step": 134 }, { "epoch": 0.28752642706131076, "grad_norm": 1.617035150527954, "learning_rate": 9.989001610300333e-06, "loss": 1.1105601787567139, "step": 136 }, { "epoch": 0.2917547568710359, "grad_norm": 0.985630214214325, "learning_rate": 9.987874781882461e-06, "loss": 1.4482934474945068, "step": 138 }, { "epoch": 0.2959830866807611, "grad_norm": 0.798952579498291, "learning_rate": 9.986693087392341e-06, "loss": 0.931736409664154, "step": 140 }, { "epoch": 0.30021141649048627, "grad_norm": 0.8778660297393799, "learning_rate": 9.985456541276667e-06, "loss": 1.5555022954940796, "step": 142 }, { "epoch": 0.3044397463002114, "grad_norm": 1.51679265499115, "learning_rate": 9.984165158652708e-06, "loss": 1.1012063026428223, "step": 144 }, { "epoch": 0.3086680761099366, "grad_norm": 2.1246626377105713, "learning_rate": 9.982818955308135e-06, "loss": 0.6569087505340576, "step": 146 }, { "epoch": 0.3128964059196617, "grad_norm": 0.983216404914856, "learning_rate": 9.98141794770083e-06, "loss": 1.2501945495605469, "step": 148 }, { "epoch": 0.3171247357293869, "grad_norm": 0.5688833594322205, "learning_rate": 9.979962152958669e-06, "loss": 1.2672028541564941, "step": 150 }, { "epoch": 0.321353065539112, "grad_norm": 1.2884414196014404, "learning_rate": 9.97845158887933e-06, "loss": 1.1956697702407837, "step": 152 }, { "epoch": 0.32558139534883723, "grad_norm": 4.915762424468994, "learning_rate": 9.976886273930063e-06, "loss": 0.7369368076324463, "step": 154 }, { "epoch": 0.3298097251585624, "grad_norm": 0.7244618535041809, "learning_rate": 9.975266227247474e-06, "loss": 1.2410112619400024, "step": 156 }, { "epoch": 0.33403805496828753, "grad_norm": 1.7355754375457764, "learning_rate": 9.973591468637286e-06, "loss": 1.2742222547531128, "step": 158 }, { "epoch": 0.3382663847780127, "grad_norm": 1.005354881286621, "learning_rate": 9.971862018574094e-06, "loss": 1.2645097970962524, "step": 160 }, { "epoch": 0.34249471458773784, "grad_norm": 1.4742780923843384, "learning_rate": 9.97007789820112e-06, "loss": 1.0934655666351318, "step": 162 }, { "epoch": 0.346723044397463, "grad_norm": 0.6067954301834106, "learning_rate": 9.968239129329953e-06, "loss": 0.9992556571960449, "step": 164 }, { "epoch": 0.35095137420718814, "grad_norm": 0.7189213633537292, "learning_rate": 9.96634573444028e-06, "loss": 0.86094069480896, "step": 166 }, { "epoch": 0.35517970401691334, "grad_norm": 0.8776316046714783, "learning_rate": 9.964397736679615e-06, "loss": 1.166183590888977, "step": 168 }, { "epoch": 0.3594080338266385, "grad_norm": 1.8415720462799072, "learning_rate": 9.962395159863014e-06, "loss": 1.19687020778656, "step": 170 }, { "epoch": 0.36363636363636365, "grad_norm": 0.8034511804580688, "learning_rate": 9.960338028472781e-06, "loss": 1.0361794233322144, "step": 172 }, { "epoch": 0.3678646934460888, "grad_norm": 1.972852110862732, "learning_rate": 9.958226367658176e-06, "loss": 1.3538862466812134, "step": 174 }, { "epoch": 0.37209302325581395, "grad_norm": 0.5073724389076233, "learning_rate": 9.9560602032351e-06, "loss": 1.0553520917892456, "step": 176 }, { "epoch": 0.3763213530655391, "grad_norm": 6.142226219177246, "learning_rate": 9.953839561685783e-06, "loss": 0.8884780406951904, "step": 178 }, { "epoch": 0.38054968287526425, "grad_norm": 0.4901098906993866, "learning_rate": 9.95156447015846e-06, "loss": 1.2782907485961914, "step": 180 }, { "epoch": 0.38477801268498946, "grad_norm": 2.2544772624969482, "learning_rate": 9.94923495646704e-06, "loss": 1.5415595769882202, "step": 182 }, { "epoch": 0.3890063424947146, "grad_norm": 0.8252478241920471, "learning_rate": 9.946851049090764e-06, "loss": 1.3345184326171875, "step": 184 }, { "epoch": 0.39323467230443976, "grad_norm": 1.5435305833816528, "learning_rate": 9.944412777173854e-06, "loss": 1.100764513015747, "step": 186 }, { "epoch": 0.3974630021141649, "grad_norm": 1.0362918376922607, "learning_rate": 9.941920170525168e-06, "loss": 0.9947601556777954, "step": 188 }, { "epoch": 0.40169133192389006, "grad_norm": 0.9996115565299988, "learning_rate": 9.939373259617822e-06, "loss": 0.9994030594825745, "step": 190 }, { "epoch": 0.4059196617336152, "grad_norm": 1.1988707780838013, "learning_rate": 9.936772075588825e-06, "loss": 1.3002077341079712, "step": 192 }, { "epoch": 0.41014799154334036, "grad_norm": 1.1431132555007935, "learning_rate": 9.934116650238697e-06, "loss": 1.0243961811065674, "step": 194 }, { "epoch": 0.4143763213530655, "grad_norm": 1.9708222150802612, "learning_rate": 9.931407016031078e-06, "loss": 1.2891334295272827, "step": 196 }, { "epoch": 0.4186046511627907, "grad_norm": 1.4265059232711792, "learning_rate": 9.928643206092338e-06, "loss": 1.0587490797042847, "step": 198 }, { "epoch": 0.42283298097251587, "grad_norm": 0.45469123125076294, "learning_rate": 9.925825254211161e-06, "loss": 1.1754745244979858, "step": 200 }, { "epoch": 0.427061310782241, "grad_norm": 1.1116875410079956, "learning_rate": 9.922953194838143e-06, "loss": 0.5503789782524109, "step": 202 }, { "epoch": 0.4312896405919662, "grad_norm": 0.9840441942214966, "learning_rate": 9.920027063085363e-06, "loss": 1.231194019317627, "step": 204 }, { "epoch": 0.4355179704016913, "grad_norm": 1.634084701538086, "learning_rate": 9.917046894725957e-06, "loss": 1.3036829233169556, "step": 206 }, { "epoch": 0.4397463002114165, "grad_norm": 2.6745824813842773, "learning_rate": 9.91401272619368e-06, "loss": 0.7920123338699341, "step": 208 }, { "epoch": 0.4439746300211416, "grad_norm": 1.1491070985794067, "learning_rate": 9.910924594582463e-06, "loss": 1.292312502861023, "step": 210 }, { "epoch": 0.44820295983086683, "grad_norm": 0.7069352865219116, "learning_rate": 9.907782537645955e-06, "loss": 1.2731815576553345, "step": 212 }, { "epoch": 0.452431289640592, "grad_norm": 1.1025632619857788, "learning_rate": 9.904586593797062e-06, "loss": 1.421501636505127, "step": 214 }, { "epoch": 0.45665961945031713, "grad_norm": 6.244607448577881, "learning_rate": 9.901336802107485e-06, "loss": 0.6334855556488037, "step": 216 }, { "epoch": 0.4608879492600423, "grad_norm": 5.14506196975708, "learning_rate": 9.89803320230723e-06, "loss": 1.007392168045044, "step": 218 }, { "epoch": 0.46511627906976744, "grad_norm": 0.707037627696991, "learning_rate": 9.894675834784136e-06, "loss": 1.2749420404434204, "step": 220 }, { "epoch": 0.4693446088794926, "grad_norm": 0.8601136207580566, "learning_rate": 9.891264740583367e-06, "loss": 1.2337135076522827, "step": 222 }, { "epoch": 0.47357293868921774, "grad_norm": 0.6010662317276001, "learning_rate": 9.88779996140692e-06, "loss": 1.3391776084899902, "step": 224 }, { "epoch": 0.47780126849894294, "grad_norm": 0.5571805238723755, "learning_rate": 9.884281539613109e-06, "loss": 1.2502403259277344, "step": 226 }, { "epoch": 0.4820295983086681, "grad_norm": 0.6004804372787476, "learning_rate": 9.880709518216061e-06, "loss": 1.2420992851257324, "step": 228 }, { "epoch": 0.48625792811839325, "grad_norm": 0.609634518623352, "learning_rate": 9.87708394088517e-06, "loss": 0.9015083909034729, "step": 230 }, { "epoch": 0.4904862579281184, "grad_norm": 1.2300268411636353, "learning_rate": 9.873404851944573e-06, "loss": 1.2525571584701538, "step": 232 }, { "epoch": 0.49471458773784355, "grad_norm": 1.20383620262146, "learning_rate": 9.869672296372611e-06, "loss": 0.9424136877059937, "step": 234 }, { "epoch": 0.4989429175475687, "grad_norm": 2.365712881088257, "learning_rate": 9.86588631980128e-06, "loss": 0.8979898691177368, "step": 236 }, { "epoch": 0.5031712473572939, "grad_norm": 1.6679710149765015, "learning_rate": 9.86204696851566e-06, "loss": 0.8301448822021484, "step": 238 }, { "epoch": 0.507399577167019, "grad_norm": 0.8096380233764648, "learning_rate": 9.858154289453363e-06, "loss": 0.9053617715835571, "step": 240 }, { "epoch": 0.5116279069767442, "grad_norm": 0.8598445057868958, "learning_rate": 9.854208330203958e-06, "loss": 1.310163974761963, "step": 242 }, { "epoch": 0.5158562367864693, "grad_norm": 1.7396758794784546, "learning_rate": 9.850209139008377e-06, "loss": 1.3538213968276978, "step": 244 }, { "epoch": 0.5200845665961945, "grad_norm": 4.000462055206299, "learning_rate": 9.846156764758344e-06, "loss": 1.2874318361282349, "step": 246 }, { "epoch": 0.5243128964059197, "grad_norm": 1.5453267097473145, "learning_rate": 9.842051256995759e-06, "loss": 1.2406648397445679, "step": 248 }, { "epoch": 0.5285412262156448, "grad_norm": 2.2413809299468994, "learning_rate": 9.837892665912105e-06, "loss": 1.1729331016540527, "step": 250 }, { "epoch": 0.53276955602537, "grad_norm": 2.8266003131866455, "learning_rate": 9.833681042347827e-06, "loss": 1.1244916915893555, "step": 252 }, { "epoch": 0.5369978858350951, "grad_norm": 1.1614079475402832, "learning_rate": 9.829416437791721e-06, "loss": 1.7403753995895386, "step": 254 }, { "epoch": 0.5412262156448203, "grad_norm": 0.7869177460670471, "learning_rate": 9.825098904380284e-06, "loss": 1.212131142616272, "step": 256 }, { "epoch": 0.5454545454545454, "grad_norm": 0.7466682195663452, "learning_rate": 9.820728494897101e-06, "loss": 1.385369062423706, "step": 258 }, { "epoch": 0.5496828752642706, "grad_norm": 0.6654893159866333, "learning_rate": 9.816305262772182e-06, "loss": 1.0036770105361938, "step": 260 }, { "epoch": 0.5539112050739958, "grad_norm": 0.6252197623252869, "learning_rate": 9.811829262081315e-06, "loss": 1.193932056427002, "step": 262 }, { "epoch": 0.5581395348837209, "grad_norm": 0.8854541778564453, "learning_rate": 9.807300547545411e-06, "loss": 1.0674093961715698, "step": 264 }, { "epoch": 0.5623678646934461, "grad_norm": 0.6116937398910522, "learning_rate": 9.802719174529821e-06, "loss": 1.4963663816452026, "step": 266 }, { "epoch": 0.5665961945031712, "grad_norm": 4.466889381408691, "learning_rate": 9.798085199043672e-06, "loss": 0.5087726712226868, "step": 268 }, { "epoch": 0.5708245243128964, "grad_norm": 1.9887669086456299, "learning_rate": 9.793398677739177e-06, "loss": 1.038787603378296, "step": 270 }, { "epoch": 0.5750528541226215, "grad_norm": 0.8510664701461792, "learning_rate": 9.788659667910942e-06, "loss": 1.2038744688034058, "step": 272 }, { "epoch": 0.5792811839323467, "grad_norm": 0.8940061926841736, "learning_rate": 9.783868227495262e-06, "loss": 0.9457172751426697, "step": 274 }, { "epoch": 0.5835095137420718, "grad_norm": 1.0325781106948853, "learning_rate": 9.779024415069427e-06, "loss": 0.9331569671630859, "step": 276 }, { "epoch": 0.587737843551797, "grad_norm": 0.2700626254081726, "learning_rate": 9.774128289850987e-06, "loss": 0.8638818264007568, "step": 278 }, { "epoch": 0.5919661733615222, "grad_norm": 0.9726315140724182, "learning_rate": 9.769179911697037e-06, "loss": 1.2323265075683594, "step": 280 }, { "epoch": 0.5961945031712473, "grad_norm": 1.1700775623321533, "learning_rate": 9.764179341103493e-06, "loss": 1.4492056369781494, "step": 282 }, { "epoch": 0.6004228329809725, "grad_norm": 0.36804908514022827, "learning_rate": 9.759126639204337e-06, "loss": 0.9317707419395447, "step": 284 }, { "epoch": 0.6046511627906976, "grad_norm": 0.6657048463821411, "learning_rate": 9.75402186777088e-06, "loss": 1.276046633720398, "step": 286 }, { "epoch": 0.6088794926004228, "grad_norm": 0.7841780781745911, "learning_rate": 9.748865089211004e-06, "loss": 0.41809362173080444, "step": 288 }, { "epoch": 0.6131078224101479, "grad_norm": 1.347035527229309, "learning_rate": 9.743656366568398e-06, "loss": 0.9361241459846497, "step": 290 }, { "epoch": 0.6173361522198731, "grad_norm": 1.025502324104309, "learning_rate": 9.738395763521792e-06, "loss": 0.8632029891014099, "step": 292 }, { "epoch": 0.6215644820295984, "grad_norm": 1.7217018604278564, "learning_rate": 9.733083344384164e-06, "loss": 0.7083306312561035, "step": 294 }, { "epoch": 0.6257928118393234, "grad_norm": 4.861369609832764, "learning_rate": 9.727719174101981e-06, "loss": 0.7388262748718262, "step": 296 }, { "epoch": 0.6300211416490487, "grad_norm": 0.7243149280548096, "learning_rate": 9.722303318254376e-06, "loss": 1.2930943965911865, "step": 298 }, { "epoch": 0.6342494714587738, "grad_norm": 0.8271642327308655, "learning_rate": 9.71683584305236e-06, "loss": 1.2394402027130127, "step": 300 }, { "epoch": 0.638477801268499, "grad_norm": 1.2420814037322998, "learning_rate": 9.71131681533802e-06, "loss": 0.7275918126106262, "step": 302 }, { "epoch": 0.642706131078224, "grad_norm": 1.0073308944702148, "learning_rate": 9.705746302583682e-06, "loss": 0.8101838827133179, "step": 304 }, { "epoch": 0.6469344608879493, "grad_norm": 0.7706353068351746, "learning_rate": 9.700124372891104e-06, "loss": 0.9103120565414429, "step": 306 }, { "epoch": 0.6511627906976745, "grad_norm": 0.7608069777488708, "learning_rate": 9.694451094990636e-06, "loss": 1.2332878112792969, "step": 308 }, { "epoch": 0.6553911205073996, "grad_norm": 1.1971544027328491, "learning_rate": 9.68872653824038e-06, "loss": 1.2112975120544434, "step": 310 }, { "epoch": 0.6596194503171248, "grad_norm": 0.7539268136024475, "learning_rate": 9.68295077262534e-06, "loss": 1.2073795795440674, "step": 312 }, { "epoch": 0.6638477801268499, "grad_norm": 0.6137844324111938, "learning_rate": 9.677123868756573e-06, "loss": 1.2273811101913452, "step": 314 }, { "epoch": 0.6680761099365751, "grad_norm": 1.5550919771194458, "learning_rate": 9.671245897870318e-06, "loss": 1.0734241008758545, "step": 316 }, { "epoch": 0.6723044397463002, "grad_norm": 1.2906231880187988, "learning_rate": 9.665316931827131e-06, "loss": 0.7602683901786804, "step": 318 }, { "epoch": 0.6765327695560254, "grad_norm": 0.983270525932312, "learning_rate": 9.659337043111006e-06, "loss": 1.2467325925827026, "step": 320 }, { "epoch": 0.6807610993657506, "grad_norm": 0.8718048930168152, "learning_rate": 9.653306304828483e-06, "loss": 1.3052424192428589, "step": 322 }, { "epoch": 0.6849894291754757, "grad_norm": 3.4318206310272217, "learning_rate": 9.647224790707762e-06, "loss": 1.0759638547897339, "step": 324 }, { "epoch": 0.6892177589852009, "grad_norm": 0.7728905081748962, "learning_rate": 9.641092575097795e-06, "loss": 1.261592149734497, "step": 326 }, { "epoch": 0.693446088794926, "grad_norm": 1.081065058708191, "learning_rate": 9.63490973296738e-06, "loss": 1.189112663269043, "step": 328 }, { "epoch": 0.6976744186046512, "grad_norm": 2.5428218841552734, "learning_rate": 9.62867633990425e-06, "loss": 0.8537653088569641, "step": 330 }, { "epoch": 0.7019027484143763, "grad_norm": 0.7610387802124023, "learning_rate": 9.622392472114136e-06, "loss": 1.2257684469223022, "step": 332 }, { "epoch": 0.7061310782241015, "grad_norm": 2.0971336364746094, "learning_rate": 9.61605820641985e-06, "loss": 1.1948940753936768, "step": 334 }, { "epoch": 0.7103594080338267, "grad_norm": 1.0323524475097656, "learning_rate": 9.60967362026033e-06, "loss": 1.2227460145950317, "step": 336 }, { "epoch": 0.7145877378435518, "grad_norm": 0.6978811621665955, "learning_rate": 9.60323879168971e-06, "loss": 1.3514995574951172, "step": 338 }, { "epoch": 0.718816067653277, "grad_norm": 4.863390922546387, "learning_rate": 9.596753799376355e-06, "loss": 1.2532682418823242, "step": 340 }, { "epoch": 0.7230443974630021, "grad_norm": 1.4355098009109497, "learning_rate": 9.5902187226019e-06, "loss": 1.1126630306243896, "step": 342 }, { "epoch": 0.7272727272727273, "grad_norm": 0.6303990483283997, "learning_rate": 9.583633641260285e-06, "loss": 0.8820483088493347, "step": 344 }, { "epoch": 0.7315010570824524, "grad_norm": 1.261123776435852, "learning_rate": 9.576998635856774e-06, "loss": 0.8531261682510376, "step": 346 }, { "epoch": 0.7357293868921776, "grad_norm": 1.1800024509429932, "learning_rate": 9.570313787506974e-06, "loss": 0.9762965440750122, "step": 348 }, { "epoch": 0.7399577167019028, "grad_norm": 1.604637861251831, "learning_rate": 9.563579177935844e-06, "loss": 1.3076279163360596, "step": 350 }, { "epoch": 0.7441860465116279, "grad_norm": 1.4105664491653442, "learning_rate": 9.556794889476687e-06, "loss": 1.1614964008331299, "step": 352 }, { "epoch": 0.7484143763213531, "grad_norm": 1.3700246810913086, "learning_rate": 9.549961005070161e-06, "loss": 0.6993850469589233, "step": 354 }, { "epoch": 0.7526427061310782, "grad_norm": 0.7506694793701172, "learning_rate": 9.543077608263245e-06, "loss": 1.0176137685775757, "step": 356 }, { "epoch": 0.7568710359408034, "grad_norm": 0.7903097867965698, "learning_rate": 9.536144783208229e-06, "loss": 1.2136379480361938, "step": 358 }, { "epoch": 0.7610993657505285, "grad_norm": 1.0530319213867188, "learning_rate": 9.529162614661687e-06, "loss": 0.7734493017196655, "step": 360 }, { "epoch": 0.7653276955602537, "grad_norm": 1.0323588848114014, "learning_rate": 9.522131187983433e-06, "loss": 1.0844217538833618, "step": 362 }, { "epoch": 0.7695560253699789, "grad_norm": 1.4858239889144897, "learning_rate": 9.515050589135485e-06, "loss": 1.0758330821990967, "step": 364 }, { "epoch": 0.773784355179704, "grad_norm": 0.7186597585678101, "learning_rate": 9.507920904681006e-06, "loss": 1.26792311668396, "step": 366 }, { "epoch": 0.7780126849894292, "grad_norm": 0.7266662120819092, "learning_rate": 9.500742221783257e-06, "loss": 1.2078866958618164, "step": 368 }, { "epoch": 0.7822410147991543, "grad_norm": 1.0280641317367554, "learning_rate": 9.493514628204516e-06, "loss": 0.8731786012649536, "step": 370 }, { "epoch": 0.7864693446088795, "grad_norm": 1.2709866762161255, "learning_rate": 9.48623821230502e-06, "loss": 1.1921396255493164, "step": 372 }, { "epoch": 0.7906976744186046, "grad_norm": 0.73567795753479, "learning_rate": 9.478913063041878e-06, "loss": 1.2111607789993286, "step": 374 }, { "epoch": 0.7949260042283298, "grad_norm": 0.7828412652015686, "learning_rate": 9.471539269967982e-06, "loss": 1.2977322340011597, "step": 376 }, { "epoch": 0.7991543340380549, "grad_norm": 1.0530914068222046, "learning_rate": 9.464116923230913e-06, "loss": 0.9466285705566406, "step": 378 }, { "epoch": 0.8033826638477801, "grad_norm": 26.593673706054688, "learning_rate": 9.456646113571844e-06, "loss": 1.3063145875930786, "step": 380 }, { "epoch": 0.8076109936575053, "grad_norm": 0.7288174033164978, "learning_rate": 9.449126932324424e-06, "loss": 1.1733064651489258, "step": 382 }, { "epoch": 0.8118393234672304, "grad_norm": 0.6493620872497559, "learning_rate": 9.441559471413665e-06, "loss": 0.9614385366439819, "step": 384 }, { "epoch": 0.8160676532769556, "grad_norm": 2.4709386825561523, "learning_rate": 9.433943823354816e-06, "loss": 0.9508975744247437, "step": 386 }, { "epoch": 0.8202959830866807, "grad_norm": 0.7295433878898621, "learning_rate": 9.426280081252232e-06, "loss": 1.4723398685455322, "step": 388 }, { "epoch": 0.8245243128964059, "grad_norm": 1.891506552696228, "learning_rate": 9.418568338798245e-06, "loss": 1.1596574783325195, "step": 390 }, { "epoch": 0.828752642706131, "grad_norm": 5.755686283111572, "learning_rate": 9.410808690271999e-06, "loss": 0.9429236054420471, "step": 392 }, { "epoch": 0.8329809725158562, "grad_norm": 0.7156573534011841, "learning_rate": 9.40300123053832e-06, "loss": 1.2517704963684082, "step": 394 }, { "epoch": 0.8372093023255814, "grad_norm": 0.14748039841651917, "learning_rate": 9.395146055046535e-06, "loss": 0.7719935774803162, "step": 396 }, { "epoch": 0.8414376321353065, "grad_norm": 1.2652807235717773, "learning_rate": 9.387243259829323e-06, "loss": 0.6809054613113403, "step": 398 }, { "epoch": 0.8456659619450317, "grad_norm": 1.0099992752075195, "learning_rate": 9.37929294150153e-06, "loss": 1.1260234117507935, "step": 400 }, { "epoch": 0.8498942917547568, "grad_norm": 1.456437110900879, "learning_rate": 9.371295197258992e-06, "loss": 0.9322273135185242, "step": 402 }, { "epoch": 0.854122621564482, "grad_norm": 0.7160536050796509, "learning_rate": 9.363250124877345e-06, "loss": 0.8035686612129211, "step": 404 }, { "epoch": 0.8583509513742071, "grad_norm": 2.845180034637451, "learning_rate": 9.35515782271083e-06, "loss": 0.9903221130371094, "step": 406 }, { "epoch": 0.8625792811839323, "grad_norm": 0.6360803246498108, "learning_rate": 9.347018389691093e-06, "loss": 1.0462050437927246, "step": 408 }, { "epoch": 0.8668076109936576, "grad_norm": 1.2062623500823975, "learning_rate": 9.338831925325974e-06, "loss": 0.9053915143013, "step": 410 }, { "epoch": 0.8710359408033826, "grad_norm": 2.0964910984039307, "learning_rate": 9.330598529698287e-06, "loss": 1.1499651670455933, "step": 412 }, { "epoch": 0.8752642706131079, "grad_norm": 1.0524271726608276, "learning_rate": 9.322318303464603e-06, "loss": 1.0052086114883423, "step": 414 }, { "epoch": 0.879492600422833, "grad_norm": 3.517848253250122, "learning_rate": 9.313991347854015e-06, "loss": 1.1003140211105347, "step": 416 }, { "epoch": 0.8837209302325582, "grad_norm": 0.7005598545074463, "learning_rate": 9.305617764666897e-06, "loss": 1.2165828943252563, "step": 418 }, { "epoch": 0.8879492600422833, "grad_norm": 1.066104769706726, "learning_rate": 9.297197656273672e-06, "loss": 1.1641000509262085, "step": 420 }, { "epoch": 0.8921775898520085, "grad_norm": 1.7423568964004517, "learning_rate": 9.288731125613544e-06, "loss": 0.9372566938400269, "step": 422 }, { "epoch": 0.8964059196617337, "grad_norm": 0.6225127577781677, "learning_rate": 9.280218276193255e-06, "loss": 1.2311619520187378, "step": 424 }, { "epoch": 0.9006342494714588, "grad_norm": 1.2216049432754517, "learning_rate": 9.271659212085807e-06, "loss": 1.0583581924438477, "step": 426 }, { "epoch": 0.904862579281184, "grad_norm": 1.0575178861618042, "learning_rate": 9.263054037929199e-06, "loss": 0.8793905377388, "step": 428 }, { "epoch": 0.9090909090909091, "grad_norm": 0.6346449255943298, "learning_rate": 9.254402858925142e-06, "loss": 1.0896297693252563, "step": 430 }, { "epoch": 0.9133192389006343, "grad_norm": 0.7554831504821777, "learning_rate": 9.245705780837774e-06, "loss": 1.2526198625564575, "step": 432 }, { "epoch": 0.9175475687103594, "grad_norm": 1.06531822681427, "learning_rate": 9.236962909992368e-06, "loss": 0.528249979019165, "step": 434 }, { "epoch": 0.9217758985200846, "grad_norm": 2.202963352203369, "learning_rate": 9.228174353274037e-06, "loss": 0.39939671754837036, "step": 436 }, { "epoch": 0.9260042283298098, "grad_norm": 0.34896644949913025, "learning_rate": 9.219340218126413e-06, "loss": 0.9322280883789062, "step": 438 }, { "epoch": 0.9302325581395349, "grad_norm": 0.6050517559051514, "learning_rate": 9.210460612550348e-06, "loss": 1.1424052715301514, "step": 440 }, { "epoch": 0.9344608879492601, "grad_norm": 1.4462559223175049, "learning_rate": 9.20153564510259e-06, "loss": 0.7159886360168457, "step": 442 }, { "epoch": 0.9386892177589852, "grad_norm": 0.7197861075401306, "learning_rate": 9.19256542489445e-06, "loss": 1.2515994310379028, "step": 444 }, { "epoch": 0.9429175475687104, "grad_norm": 0.6754164695739746, "learning_rate": 9.183550061590476e-06, "loss": 1.0920875072479248, "step": 446 }, { "epoch": 0.9471458773784355, "grad_norm": 7.038702487945557, "learning_rate": 9.174489665407103e-06, "loss": 1.1936589479446411, "step": 448 }, { "epoch": 0.9513742071881607, "grad_norm": 15.700501441955566, "learning_rate": 9.165384347111317e-06, "loss": 0.79295814037323, "step": 450 }, { "epoch": 0.9556025369978859, "grad_norm": 0.6612499356269836, "learning_rate": 9.156234218019291e-06, "loss": 0.9135705232620239, "step": 452 }, { "epoch": 0.959830866807611, "grad_norm": 1.0069290399551392, "learning_rate": 9.147039389995029e-06, "loss": 1.319082260131836, "step": 454 }, { "epoch": 0.9640591966173362, "grad_norm": 1.4353666305541992, "learning_rate": 9.137799975448998e-06, "loss": 0.6567050814628601, "step": 456 }, { "epoch": 0.9682875264270613, "grad_norm": 1.2823227643966675, "learning_rate": 9.128516087336755e-06, "loss": 0.8801347017288208, "step": 458 }, { "epoch": 0.9725158562367865, "grad_norm": 0.9648775458335876, "learning_rate": 9.119187839157559e-06, "loss": 1.2280669212341309, "step": 460 }, { "epoch": 0.9767441860465116, "grad_norm": 0.690932035446167, "learning_rate": 9.109815344952995e-06, "loss": 1.2126575708389282, "step": 462 }, { "epoch": 0.9809725158562368, "grad_norm": 2.884694814682007, "learning_rate": 9.100398719305566e-06, "loss": 0.7473848462104797, "step": 464 }, { "epoch": 0.985200845665962, "grad_norm": 0.8109061121940613, "learning_rate": 9.090938077337305e-06, "loss": 1.2065980434417725, "step": 466 }, { "epoch": 0.9894291754756871, "grad_norm": 1.9574133157730103, "learning_rate": 9.081433534708363e-06, "loss": 0.9871285557746887, "step": 468 }, { "epoch": 0.9936575052854123, "grad_norm": 0.6658157110214233, "learning_rate": 9.071885207615591e-06, "loss": 1.2436178922653198, "step": 470 }, { "epoch": 0.9978858350951374, "grad_norm": 0.584966242313385, "learning_rate": 9.062293212791123e-06, "loss": 1.2470791339874268, "step": 472 }, { "epoch": 1.0021141649048626, "grad_norm": 0.8050594925880432, "learning_rate": 9.052657667500951e-06, "loss": 0.8934606909751892, "step": 474 }, { "epoch": 1.0063424947145878, "grad_norm": 1.9476158618927002, "learning_rate": 9.042978689543487e-06, "loss": 1.134462594985962, "step": 476 }, { "epoch": 1.0105708245243128, "grad_norm": 0.9855302572250366, "learning_rate": 9.033256397248124e-06, "loss": 0.4775067865848541, "step": 478 }, { "epoch": 1.014799154334038, "grad_norm": 3.4939801692962646, "learning_rate": 9.02349090947379e-06, "loss": 0.7034808397293091, "step": 480 }, { "epoch": 1.0190274841437632, "grad_norm": 2.7364814281463623, "learning_rate": 9.013682345607502e-06, "loss": 0.766993522644043, "step": 482 }, { "epoch": 1.0232558139534884, "grad_norm": 0.6091821789741516, "learning_rate": 9.003830825562887e-06, "loss": 1.0236061811447144, "step": 484 }, { "epoch": 1.0274841437632136, "grad_norm": 1.468000054359436, "learning_rate": 8.99393646977874e-06, "loss": 1.0365979671478271, "step": 486 }, { "epoch": 1.0317124735729386, "grad_norm": 1.401171088218689, "learning_rate": 8.983999399217536e-06, "loss": 0.8530629873275757, "step": 488 }, { "epoch": 1.0359408033826638, "grad_norm": 18.45070457458496, "learning_rate": 8.974019735363952e-06, "loss": 0.8255080580711365, "step": 490 }, { "epoch": 1.040169133192389, "grad_norm": 0.6856637597084045, "learning_rate": 8.963997600223387e-06, "loss": 0.7172267436981201, "step": 492 }, { "epoch": 1.0443974630021142, "grad_norm": 0.6630373597145081, "learning_rate": 8.953933116320474e-06, "loss": 1.1438912153244019, "step": 494 }, { "epoch": 1.0486257928118394, "grad_norm": 0.6837645769119263, "learning_rate": 8.943826406697569e-06, "loss": 0.958648145198822, "step": 496 }, { "epoch": 1.0528541226215644, "grad_norm": 1.070523977279663, "learning_rate": 8.93367759491326e-06, "loss": 0.7588282227516174, "step": 498 }, { "epoch": 1.0570824524312896, "grad_norm": 0.6902783513069153, "learning_rate": 8.923486805040845e-06, "loss": 0.8839633464813232, "step": 500 }, { "epoch": 1.0613107822410148, "grad_norm": 0.645658552646637, "learning_rate": 8.913254161666828e-06, "loss": 1.1252018213272095, "step": 502 }, { "epoch": 1.06553911205074, "grad_norm": 0.7490451335906982, "learning_rate": 8.902979789889382e-06, "loss": 1.162854552268982, "step": 504 }, { "epoch": 1.069767441860465, "grad_norm": 10.216524124145508, "learning_rate": 8.892663815316833e-06, "loss": 0.8035144209861755, "step": 506 }, { "epoch": 1.0739957716701902, "grad_norm": 0.7952625751495361, "learning_rate": 8.882306364066114e-06, "loss": 0.8197463750839233, "step": 508 }, { "epoch": 1.0782241014799154, "grad_norm": 1.6919180154800415, "learning_rate": 8.871907562761226e-06, "loss": 0.9620487689971924, "step": 510 }, { "epoch": 1.0824524312896406, "grad_norm": 1.5307462215423584, "learning_rate": 8.861467538531692e-06, "loss": 1.0218018293380737, "step": 512 }, { "epoch": 1.0866807610993658, "grad_norm": 0.9105727076530457, "learning_rate": 8.850986419011006e-06, "loss": 1.0973032712936401, "step": 514 }, { "epoch": 1.0909090909090908, "grad_norm": 1.4115995168685913, "learning_rate": 8.840464332335062e-06, "loss": 0.8785353899002075, "step": 516 }, { "epoch": 1.095137420718816, "grad_norm": 0.6940400004386902, "learning_rate": 8.829901407140599e-06, "loss": 0.861272931098938, "step": 518 }, { "epoch": 1.0993657505285412, "grad_norm": 1.932595133781433, "learning_rate": 8.81929777256362e-06, "loss": 0.6266706585884094, "step": 520 }, { "epoch": 1.1035940803382664, "grad_norm": 0.7717071771621704, "learning_rate": 8.808653558237818e-06, "loss": 1.304769515991211, "step": 522 }, { "epoch": 1.1078224101479917, "grad_norm": 2.265505790710449, "learning_rate": 8.797968894292992e-06, "loss": 0.7560991048812866, "step": 524 }, { "epoch": 1.1120507399577166, "grad_norm": 1.0455704927444458, "learning_rate": 8.787243911353447e-06, "loss": 1.3348989486694336, "step": 526 }, { "epoch": 1.1162790697674418, "grad_norm": 1.2992618083953857, "learning_rate": 8.776478740536409e-06, "loss": 0.8296196460723877, "step": 528 }, { "epoch": 1.120507399577167, "grad_norm": 1.7274901866912842, "learning_rate": 8.76567351345042e-06, "loss": 0.4661783277988434, "step": 530 }, { "epoch": 1.1247357293868923, "grad_norm": 1.1213003396987915, "learning_rate": 8.754828362193719e-06, "loss": 1.0078414678573608, "step": 532 }, { "epoch": 1.1289640591966172, "grad_norm": 0.5484246611595154, "learning_rate": 8.743943419352638e-06, "loss": 0.7887740731239319, "step": 534 }, { "epoch": 1.1331923890063424, "grad_norm": 1.3178303241729736, "learning_rate": 8.733018817999977e-06, "loss": 0.8570668697357178, "step": 536 }, { "epoch": 1.1374207188160677, "grad_norm": 1.8810722827911377, "learning_rate": 8.722054691693374e-06, "loss": 0.7170249223709106, "step": 538 }, { "epoch": 1.1416490486257929, "grad_norm": 1.204032063484192, "learning_rate": 8.711051174473682e-06, "loss": 0.7038702964782715, "step": 540 }, { "epoch": 1.145877378435518, "grad_norm": 0.8681644797325134, "learning_rate": 8.700008400863316e-06, "loss": 1.050874948501587, "step": 542 }, { "epoch": 1.150105708245243, "grad_norm": 1.311474084854126, "learning_rate": 8.688926505864624e-06, "loss": 0.7567013502120972, "step": 544 }, { "epoch": 1.1543340380549683, "grad_norm": 0.6653392910957336, "learning_rate": 8.67780562495822e-06, "loss": 1.1599386930465698, "step": 546 }, { "epoch": 1.1585623678646935, "grad_norm": 1.6653027534484863, "learning_rate": 8.666645894101346e-06, "loss": 1.2309300899505615, "step": 548 }, { "epoch": 1.1627906976744187, "grad_norm": 1.0250424146652222, "learning_rate": 8.655447449726189e-06, "loss": 0.7671850919723511, "step": 550 }, { "epoch": 1.1670190274841437, "grad_norm": 0.7034103870391846, "learning_rate": 8.644210428738237e-06, "loss": 1.033461332321167, "step": 552 }, { "epoch": 1.1712473572938689, "grad_norm": 0.9575777649879456, "learning_rate": 8.632934968514582e-06, "loss": 1.1345349550247192, "step": 554 }, { "epoch": 1.175475687103594, "grad_norm": 1.0800116062164307, "learning_rate": 8.621621206902256e-06, "loss": 1.0570917129516602, "step": 556 }, { "epoch": 1.1797040169133193, "grad_norm": 0.6489596962928772, "learning_rate": 8.61026928221654e-06, "loss": 1.0526567697525024, "step": 558 }, { "epoch": 1.1839323467230445, "grad_norm": 0.5726123452186584, "learning_rate": 8.598879333239274e-06, "loss": 1.017450213432312, "step": 560 }, { "epoch": 1.1881606765327695, "grad_norm": 0.6518921852111816, "learning_rate": 8.587451499217161e-06, "loss": 0.6855576634407043, "step": 562 }, { "epoch": 1.1923890063424947, "grad_norm": 0.7240839004516602, "learning_rate": 8.575985919860065e-06, "loss": 1.0725711584091187, "step": 564 }, { "epoch": 1.1966173361522199, "grad_norm": 1.0385645627975464, "learning_rate": 8.564482735339296e-06, "loss": 0.9034080505371094, "step": 566 }, { "epoch": 1.200845665961945, "grad_norm": 0.8748495578765869, "learning_rate": 8.552942086285909e-06, "loss": 1.2156535387039185, "step": 568 }, { "epoch": 1.20507399577167, "grad_norm": 1.3294693231582642, "learning_rate": 8.541364113788974e-06, "loss": 1.1595240831375122, "step": 570 }, { "epoch": 1.2093023255813953, "grad_norm": 1.0479997396469116, "learning_rate": 8.529748959393855e-06, "loss": 1.007725477218628, "step": 572 }, { "epoch": 1.2135306553911205, "grad_norm": 0.6284238696098328, "learning_rate": 8.518096765100485e-06, "loss": 0.8089824914932251, "step": 574 }, { "epoch": 1.2177589852008457, "grad_norm": 1.2860372066497803, "learning_rate": 8.50640767336162e-06, "loss": 0.7567947506904602, "step": 576 }, { "epoch": 1.221987315010571, "grad_norm": 0.8193660974502563, "learning_rate": 8.494681827081096e-06, "loss": 0.9203581213951111, "step": 578 }, { "epoch": 1.226215644820296, "grad_norm": 1.0734435319900513, "learning_rate": 8.482919369612103e-06, "loss": 0.7801018357276917, "step": 580 }, { "epoch": 1.230443974630021, "grad_norm": 0.8685236573219299, "learning_rate": 8.471120444755405e-06, "loss": 1.0735002756118774, "step": 582 }, { "epoch": 1.2346723044397463, "grad_norm": 6.773773193359375, "learning_rate": 8.4592851967576e-06, "loss": 0.8720724582672119, "step": 584 }, { "epoch": 1.2389006342494715, "grad_norm": 1.3109259605407715, "learning_rate": 8.447413770309349e-06, "loss": 0.832839846611023, "step": 586 }, { "epoch": 1.2431289640591967, "grad_norm": 1.3184690475463867, "learning_rate": 8.435506310543607e-06, "loss": 0.9906204342842102, "step": 588 }, { "epoch": 1.2473572938689217, "grad_norm": 0.45595452189445496, "learning_rate": 8.42356296303386e-06, "loss": 0.6442484855651855, "step": 590 }, { "epoch": 1.251585623678647, "grad_norm": 0.33540967106819153, "learning_rate": 8.411583873792325e-06, "loss": 0.866682231426239, "step": 592 }, { "epoch": 1.255813953488372, "grad_norm": 1.6199615001678467, "learning_rate": 8.399569189268182e-06, "loss": 1.0759512186050415, "step": 594 }, { "epoch": 1.2600422832980973, "grad_norm": 0.7049738168716431, "learning_rate": 8.387519056345778e-06, "loss": 0.6909711360931396, "step": 596 }, { "epoch": 1.2642706131078225, "grad_norm": 0.6753112077713013, "learning_rate": 8.375433622342824e-06, "loss": 1.0905535221099854, "step": 598 }, { "epoch": 1.2684989429175475, "grad_norm": 2.9911534786224365, "learning_rate": 8.363313035008613e-06, "loss": 1.2528599500656128, "step": 600 }, { "epoch": 1.2727272727272727, "grad_norm": 0.7724202275276184, "learning_rate": 8.351157442522187e-06, "loss": 0.9703590273857117, "step": 602 }, { "epoch": 1.276955602536998, "grad_norm": 0.9418428540229797, "learning_rate": 8.338966993490554e-06, "loss": 1.0988746881484985, "step": 604 }, { "epoch": 1.2811839323467231, "grad_norm": 1.554724097251892, "learning_rate": 8.326741836946852e-06, "loss": 0.7701537609100342, "step": 606 }, { "epoch": 1.285412262156448, "grad_norm": 0.7428291440010071, "learning_rate": 8.314482122348523e-06, "loss": 1.107397198677063, "step": 608 }, { "epoch": 1.2896405919661733, "grad_norm": 0.7416324615478516, "learning_rate": 8.30218799957551e-06, "loss": 0.721267819404602, "step": 610 }, { "epoch": 1.2938689217758985, "grad_norm": 0.7011500000953674, "learning_rate": 8.289859618928404e-06, "loss": 0.6388125419616699, "step": 612 }, { "epoch": 1.2980972515856237, "grad_norm": 0.6484890580177307, "learning_rate": 8.277497131126608e-06, "loss": 0.8539724946022034, "step": 614 }, { "epoch": 1.302325581395349, "grad_norm": 2.784458637237549, "learning_rate": 8.265100687306503e-06, "loss": 0.5695146322250366, "step": 616 }, { "epoch": 1.306553911205074, "grad_norm": 2.033276319503784, "learning_rate": 8.252670439019595e-06, "loss": 0.9038808345794678, "step": 618 }, { "epoch": 1.3107822410147991, "grad_norm": 0.7134523391723633, "learning_rate": 8.240206538230663e-06, "loss": 1.1141823530197144, "step": 620 }, { "epoch": 1.3150105708245243, "grad_norm": 0.7986293435096741, "learning_rate": 8.227709137315905e-06, "loss": 1.0307457447052002, "step": 622 }, { "epoch": 1.3192389006342495, "grad_norm": 2.133578300476074, "learning_rate": 8.215178389061064e-06, "loss": 0.755119264125824, "step": 624 }, { "epoch": 1.3234672304439745, "grad_norm": 1.6539106369018555, "learning_rate": 8.202614446659572e-06, "loss": 1.0942742824554443, "step": 626 }, { "epoch": 1.3276955602536997, "grad_norm": 1.206490159034729, "learning_rate": 8.190017463710675e-06, "loss": 1.2645890712738037, "step": 628 }, { "epoch": 1.331923890063425, "grad_norm": 0.7769160270690918, "learning_rate": 8.177387594217548e-06, "loss": 0.9681946635246277, "step": 630 }, { "epoch": 1.3361522198731501, "grad_norm": 1.0490977764129639, "learning_rate": 8.164724992585421e-06, "loss": 0.6947274208068848, "step": 632 }, { "epoch": 1.3403805496828753, "grad_norm": 0.790566086769104, "learning_rate": 8.152029813619685e-06, "loss": 0.7223414778709412, "step": 634 }, { "epoch": 1.3446088794926006, "grad_norm": 0.5555297136306763, "learning_rate": 8.139302212524006e-06, "loss": 0.7382919192314148, "step": 636 }, { "epoch": 1.3488372093023255, "grad_norm": 1.3161789178848267, "learning_rate": 8.126542344898419e-06, "loss": 0.9977390766143799, "step": 638 }, { "epoch": 1.3530655391120507, "grad_norm": 0.8468033075332642, "learning_rate": 8.113750366737431e-06, "loss": 0.7190608382225037, "step": 640 }, { "epoch": 1.357293868921776, "grad_norm": 0.5464400053024292, "learning_rate": 8.100926434428116e-06, "loss": 1.1817196607589722, "step": 642 }, { "epoch": 1.361522198731501, "grad_norm": 1.7523058652877808, "learning_rate": 8.0880707047482e-06, "loss": 1.064253807067871, "step": 644 }, { "epoch": 1.3657505285412261, "grad_norm": 1.9081772565841675, "learning_rate": 8.075183334864139e-06, "loss": 0.7208521366119385, "step": 646 }, { "epoch": 1.3699788583509513, "grad_norm": 1.2692513465881348, "learning_rate": 8.062264482329209e-06, "loss": 0.6858248710632324, "step": 648 }, { "epoch": 1.3742071881606766, "grad_norm": 2.8147478103637695, "learning_rate": 8.049314305081575e-06, "loss": 0.7705954313278198, "step": 650 }, { "epoch": 1.3784355179704018, "grad_norm": 3.870112419128418, "learning_rate": 8.036332961442355e-06, "loss": 0.7133288979530334, "step": 652 }, { "epoch": 1.382663847780127, "grad_norm": 0.5910788178443909, "learning_rate": 8.023320610113691e-06, "loss": 1.152907133102417, "step": 654 }, { "epoch": 1.386892177589852, "grad_norm": 0.48965322971343994, "learning_rate": 8.010277410176801e-06, "loss": 1.016326665878296, "step": 656 }, { "epoch": 1.3911205073995772, "grad_norm": 1.5643606185913086, "learning_rate": 7.997203521090053e-06, "loss": 0.8531705737113953, "step": 658 }, { "epoch": 1.3953488372093024, "grad_norm": 0.5423903465270996, "learning_rate": 7.984099102686986e-06, "loss": 0.9171060919761658, "step": 660 }, { "epoch": 1.3995771670190273, "grad_norm": 0.7497831583023071, "learning_rate": 7.970964315174384e-06, "loss": 1.0824397802352905, "step": 662 }, { "epoch": 1.4038054968287526, "grad_norm": 0.2594369649887085, "learning_rate": 7.9577993191303e-06, "loss": 0.9185059070587158, "step": 664 }, { "epoch": 1.4080338266384778, "grad_norm": 0.7158035039901733, "learning_rate": 7.944604275502102e-06, "loss": 1.2581110000610352, "step": 666 }, { "epoch": 1.412262156448203, "grad_norm": 0.5448182821273804, "learning_rate": 7.931379345604495e-06, "loss": 1.080849289894104, "step": 668 }, { "epoch": 1.4164904862579282, "grad_norm": 0.5859033465385437, "learning_rate": 7.918124691117563e-06, "loss": 0.703554630279541, "step": 670 }, { "epoch": 1.4207188160676534, "grad_norm": 20.444978713989258, "learning_rate": 7.904840474084783e-06, "loss": 1.0453234910964966, "step": 672 }, { "epoch": 1.4249471458773784, "grad_norm": 0.48923125863075256, "learning_rate": 7.891526856911046e-06, "loss": 0.5838836431503296, "step": 674 }, { "epoch": 1.4291754756871036, "grad_norm": 6.210752487182617, "learning_rate": 7.878184002360664e-06, "loss": 0.6894876956939697, "step": 676 }, { "epoch": 1.4334038054968288, "grad_norm": 0.9145434498786926, "learning_rate": 7.864812073555402e-06, "loss": 1.2583154439926147, "step": 678 }, { "epoch": 1.437632135306554, "grad_norm": 0.7431913018226624, "learning_rate": 7.851411233972461e-06, "loss": 1.1587738990783691, "step": 680 }, { "epoch": 1.441860465116279, "grad_norm": 1.0980017185211182, "learning_rate": 7.837981647442486e-06, "loss": 1.1265335083007812, "step": 682 }, { "epoch": 1.4460887949260042, "grad_norm": 0.5173488259315491, "learning_rate": 7.82452347814757e-06, "loss": 1.057129979133606, "step": 684 }, { "epoch": 1.4503171247357294, "grad_norm": 1.1598068475723267, "learning_rate": 7.811036890619239e-06, "loss": 1.362676978111267, "step": 686 }, { "epoch": 1.4545454545454546, "grad_norm": 0.6912574172019958, "learning_rate": 7.797522049736441e-06, "loss": 1.0552871227264404, "step": 688 }, { "epoch": 1.4587737843551798, "grad_norm": 1.028178095817566, "learning_rate": 7.78397912072354e-06, "loss": 0.4064818322658539, "step": 690 }, { "epoch": 1.463002114164905, "grad_norm": 0.7042977213859558, "learning_rate": 7.770408269148281e-06, "loss": 1.1370210647583008, "step": 692 }, { "epoch": 1.46723044397463, "grad_norm": 0.7910498976707458, "learning_rate": 7.756809660919778e-06, "loss": 0.5615589618682861, "step": 694 }, { "epoch": 1.4714587737843552, "grad_norm": 0.8000791072845459, "learning_rate": 7.74318346228648e-06, "loss": 1.05837881565094, "step": 696 }, { "epoch": 1.4756871035940804, "grad_norm": 0.5216151475906372, "learning_rate": 7.72952983983414e-06, "loss": 1.1063480377197266, "step": 698 }, { "epoch": 1.4799154334038054, "grad_norm": 1.8301907777786255, "learning_rate": 7.715848960483776e-06, "loss": 0.9082323312759399, "step": 700 }, { "epoch": 1.4841437632135306, "grad_norm": 0.6109437346458435, "learning_rate": 7.702140991489637e-06, "loss": 1.0499591827392578, "step": 702 }, { "epoch": 1.4883720930232558, "grad_norm": 0.9494948387145996, "learning_rate": 7.688406100437149e-06, "loss": 1.0240249633789062, "step": 704 }, { "epoch": 1.492600422832981, "grad_norm": 0.6281592845916748, "learning_rate": 7.674644455240878e-06, "loss": 0.7382880449295044, "step": 706 }, { "epoch": 1.4968287526427062, "grad_norm": 0.3081284463405609, "learning_rate": 7.660856224142456e-06, "loss": 0.24507500231266022, "step": 708 }, { "epoch": 1.5010570824524314, "grad_norm": 1.094086766242981, "learning_rate": 7.647041575708555e-06, "loss": 0.6077303886413574, "step": 710 }, { "epoch": 1.5052854122621564, "grad_norm": 1.780206561088562, "learning_rate": 7.633200678828804e-06, "loss": 0.5043145418167114, "step": 712 }, { "epoch": 1.5095137420718816, "grad_norm": 0.563587486743927, "learning_rate": 7.6193337027137215e-06, "loss": 0.8300334811210632, "step": 714 }, { "epoch": 1.5137420718816068, "grad_norm": 1.3600208759307861, "learning_rate": 7.605440816892667e-06, "loss": 1.0690257549285889, "step": 716 }, { "epoch": 1.5179704016913318, "grad_norm": 1.6465442180633545, "learning_rate": 7.591522191211746e-06, "loss": 0.902448296546936, "step": 718 }, { "epoch": 1.522198731501057, "grad_norm": 0.3158721625804901, "learning_rate": 7.577577995831755e-06, "loss": 0.8883390426635742, "step": 720 }, { "epoch": 1.5264270613107822, "grad_norm": 2.353653907775879, "learning_rate": 7.563608401226081e-06, "loss": 0.8452302813529968, "step": 722 }, { "epoch": 1.5306553911205074, "grad_norm": 0.6037604212760925, "learning_rate": 7.549613578178632e-06, "loss": 0.8907937407493591, "step": 724 }, { "epoch": 1.5348837209302326, "grad_norm": 1.6640311479568481, "learning_rate": 7.535593697781741e-06, "loss": 0.904115617275238, "step": 726 }, { "epoch": 1.5391120507399578, "grad_norm": 1.110495686531067, "learning_rate": 7.52154893143408e-06, "loss": 0.6306935548782349, "step": 728 }, { "epoch": 1.543340380549683, "grad_norm": 1.428308367729187, "learning_rate": 7.50747945083856e-06, "loss": 0.8169469237327576, "step": 730 }, { "epoch": 1.547568710359408, "grad_norm": 0.6837590336799622, "learning_rate": 7.493385428000234e-06, "loss": 1.0594215393066406, "step": 732 }, { "epoch": 1.5517970401691332, "grad_norm": 0.3673056960105896, "learning_rate": 7.479267035224191e-06, "loss": 0.23039767146110535, "step": 734 }, { "epoch": 1.5560253699788582, "grad_norm": 0.6057469248771667, "learning_rate": 7.465124445113459e-06, "loss": 0.9881829619407654, "step": 736 }, { "epoch": 1.5602536997885834, "grad_norm": 0.25152888894081116, "learning_rate": 7.450957830566878e-06, "loss": 0.7413854002952576, "step": 738 }, { "epoch": 1.5644820295983086, "grad_norm": 0.424793004989624, "learning_rate": 7.436767364777009e-06, "loss": 1.1149650812149048, "step": 740 }, { "epoch": 1.5687103594080338, "grad_norm": 1.2502988576889038, "learning_rate": 7.422553221227993e-06, "loss": 0.7535862922668457, "step": 742 }, { "epoch": 1.572938689217759, "grad_norm": 1.3932405710220337, "learning_rate": 7.4083155736934484e-06, "loss": 1.1075509786605835, "step": 744 }, { "epoch": 1.5771670190274842, "grad_norm": 1.375607967376709, "learning_rate": 7.394054596234336e-06, "loss": 1.1646960973739624, "step": 746 }, { "epoch": 1.5813953488372094, "grad_norm": 0.572155237197876, "learning_rate": 7.379770463196831e-06, "loss": 0.9123924374580383, "step": 748 }, { "epoch": 1.5856236786469344, "grad_norm": 0.19384686648845673, "learning_rate": 7.365463349210203e-06, "loss": 0.10290507227182388, "step": 750 }, { "epoch": 1.5898520084566596, "grad_norm": 2.1665472984313965, "learning_rate": 7.351133429184666e-06, "loss": 0.8750689625740051, "step": 752 }, { "epoch": 1.5940803382663846, "grad_norm": 0.8769041895866394, "learning_rate": 7.336780878309251e-06, "loss": 1.1258633136749268, "step": 754 }, { "epoch": 1.5983086680761098, "grad_norm": 0.6586044430732727, "learning_rate": 7.322405872049657e-06, "loss": 1.1040945053100586, "step": 756 }, { "epoch": 1.602536997885835, "grad_norm": 0.9873610734939575, "learning_rate": 7.308008586146111e-06, "loss": 1.1133191585540771, "step": 758 }, { "epoch": 1.6067653276955602, "grad_norm": 0.9443269371986389, "learning_rate": 7.293589196611221e-06, "loss": 1.0808392763137817, "step": 760 }, { "epoch": 1.6109936575052854, "grad_norm": 0.8102638125419617, "learning_rate": 7.279147879727811e-06, "loss": 1.1142152547836304, "step": 762 }, { "epoch": 1.6152219873150107, "grad_norm": 1.1252881288528442, "learning_rate": 7.264684812046787e-06, "loss": 1.1062783002853394, "step": 764 }, { "epoch": 1.6194503171247359, "grad_norm": 1.064736247062683, "learning_rate": 7.250200170384961e-06, "loss": 0.7885035276412964, "step": 766 }, { "epoch": 1.6236786469344608, "grad_norm": 0.9809871912002563, "learning_rate": 7.235694131822894e-06, "loss": 1.0891193151474, "step": 768 }, { "epoch": 1.627906976744186, "grad_norm": 1.5109798908233643, "learning_rate": 7.221166873702738e-06, "loss": 1.0620685815811157, "step": 770 }, { "epoch": 1.6321353065539113, "grad_norm": 0.5466718077659607, "learning_rate": 7.206618573626058e-06, "loss": 1.089674949645996, "step": 772 }, { "epoch": 1.6363636363636362, "grad_norm": 0.6056283712387085, "learning_rate": 7.19204940945167e-06, "loss": 0.7608787417411804, "step": 774 }, { "epoch": 1.6405919661733614, "grad_norm": 0.705392599105835, "learning_rate": 7.177459559293456e-06, "loss": 1.111889362335205, "step": 776 }, { "epoch": 1.6448202959830867, "grad_norm": 0.8870161771774292, "learning_rate": 7.162849201518198e-06, "loss": 0.6739569306373596, "step": 778 }, { "epoch": 1.6490486257928119, "grad_norm": 0.6942276954650879, "learning_rate": 7.1482185147433905e-06, "loss": 1.046175241470337, "step": 780 }, { "epoch": 1.653276955602537, "grad_norm": 0.6807941794395447, "learning_rate": 7.133567677835055e-06, "loss": 0.8236555457115173, "step": 782 }, { "epoch": 1.6575052854122623, "grad_norm": 0.8403719663619995, "learning_rate": 7.11889686990556e-06, "loss": 1.185294270515442, "step": 784 }, { "epoch": 1.6617336152219875, "grad_norm": 4.393839359283447, "learning_rate": 7.104206270311423e-06, "loss": 0.5078250169754028, "step": 786 }, { "epoch": 1.6659619450317125, "grad_norm": 0.6424494981765747, "learning_rate": 7.089496058651133e-06, "loss": 1.1155799627304077, "step": 788 }, { "epoch": 1.6701902748414377, "grad_norm": 0.49682241678237915, "learning_rate": 7.0747664147629335e-06, "loss": 0.7395763993263245, "step": 790 }, { "epoch": 1.6744186046511627, "grad_norm": 0.42382878065109253, "learning_rate": 7.060017518722637e-06, "loss": 0.40569525957107544, "step": 792 }, { "epoch": 1.6786469344608879, "grad_norm": 0.8390569686889648, "learning_rate": 7.0452495508414276e-06, "loss": 1.0769119262695312, "step": 794 }, { "epoch": 1.682875264270613, "grad_norm": 0.40442875027656555, "learning_rate": 7.030462691663641e-06, "loss": 0.6114833950996399, "step": 796 }, { "epoch": 1.6871035940803383, "grad_norm": 0.44755929708480835, "learning_rate": 7.015657121964575e-06, "loss": 1.1810165643692017, "step": 798 }, { "epoch": 1.6913319238900635, "grad_norm": 0.527320384979248, "learning_rate": 7.000833022748267e-06, "loss": 1.072128176689148, "step": 800 }, { "epoch": 1.6955602536997887, "grad_norm": 4.611921787261963, "learning_rate": 6.985990575245283e-06, "loss": 0.5809746980667114, "step": 802 }, { "epoch": 1.699788583509514, "grad_norm": 0.42148807644844055, "learning_rate": 6.97112996091051e-06, "loss": 1.053298830986023, "step": 804 }, { "epoch": 1.7040169133192389, "grad_norm": 3.425072431564331, "learning_rate": 6.956251361420926e-06, "loss": 0.8129485845565796, "step": 806 }, { "epoch": 1.708245243128964, "grad_norm": 1.2476472854614258, "learning_rate": 6.94135495867339e-06, "loss": 0.7263811230659485, "step": 808 }, { "epoch": 1.712473572938689, "grad_norm": 1.6771245002746582, "learning_rate": 6.926440934782407e-06, "loss": 1.1060547828674316, "step": 810 }, { "epoch": 1.7167019027484143, "grad_norm": 2.214505195617676, "learning_rate": 6.9115094720779155e-06, "loss": 1.3158310651779175, "step": 812 }, { "epoch": 1.7209302325581395, "grad_norm": 0.5428487062454224, "learning_rate": 6.896560753103041e-06, "loss": 1.039423942565918, "step": 814 }, { "epoch": 1.7251585623678647, "grad_norm": 0.7045199871063232, "learning_rate": 6.881594960611881e-06, "loss": 1.1292474269866943, "step": 816 }, { "epoch": 1.72938689217759, "grad_norm": 1.1411083936691284, "learning_rate": 6.866612277567261e-06, "loss": 0.9374118447303772, "step": 818 }, { "epoch": 1.733615221987315, "grad_norm": 5.835515022277832, "learning_rate": 6.851612887138501e-06, "loss": 0.982239842414856, "step": 820 }, { "epoch": 1.7378435517970403, "grad_norm": 0.4945686459541321, "learning_rate": 6.836596972699175e-06, "loss": 0.6540818810462952, "step": 822 }, { "epoch": 1.7420718816067653, "grad_norm": 0.8004485964775085, "learning_rate": 6.82156471782487e-06, "loss": 0.6552245616912842, "step": 824 }, { "epoch": 1.7463002114164905, "grad_norm": 3.4864680767059326, "learning_rate": 6.806516306290942e-06, "loss": 0.8940937519073486, "step": 826 }, { "epoch": 1.7505285412262155, "grad_norm": 0.4634850323200226, "learning_rate": 6.791451922070265e-06, "loss": 0.884535551071167, "step": 828 }, { "epoch": 1.7547568710359407, "grad_norm": 0.9890514016151428, "learning_rate": 6.77637174933099e-06, "loss": 0.7590419054031372, "step": 830 }, { "epoch": 1.758985200845666, "grad_norm": 1.0166455507278442, "learning_rate": 6.7612759724342895e-06, "loss": 1.1585743427276611, "step": 832 }, { "epoch": 1.763213530655391, "grad_norm": 7.651342391967773, "learning_rate": 6.746164775932096e-06, "loss": 0.8045985698699951, "step": 834 }, { "epoch": 1.7674418604651163, "grad_norm": 0.581699013710022, "learning_rate": 6.731038344564862e-06, "loss": 0.7906743884086609, "step": 836 }, { "epoch": 1.7716701902748415, "grad_norm": 0.5245794057846069, "learning_rate": 6.715896863259286e-06, "loss": 1.1179639101028442, "step": 838 }, { "epoch": 1.7758985200845667, "grad_norm": 0.9436385035514832, "learning_rate": 6.700740517126061e-06, "loss": 0.8209047317504883, "step": 840 }, { "epoch": 1.7801268498942917, "grad_norm": 2.1427574157714844, "learning_rate": 6.685569491457608e-06, "loss": 0.3800247311592102, "step": 842 }, { "epoch": 1.784355179704017, "grad_norm": 0.6596232652664185, "learning_rate": 6.670383971725809e-06, "loss": 0.6930893063545227, "step": 844 }, { "epoch": 1.7885835095137421, "grad_norm": 2.8469529151916504, "learning_rate": 6.655184143579746e-06, "loss": 0.9458221793174744, "step": 846 }, { "epoch": 1.792811839323467, "grad_norm": 1.49416983127594, "learning_rate": 6.639970192843423e-06, "loss": 0.7403481006622314, "step": 848 }, { "epoch": 1.7970401691331923, "grad_norm": 2.6232669353485107, "learning_rate": 6.624742305513502e-06, "loss": 0.6847668886184692, "step": 850 }, { "epoch": 1.8012684989429175, "grad_norm": 0.7676483392715454, "learning_rate": 6.609500667757022e-06, "loss": 0.9342989325523376, "step": 852 }, { "epoch": 1.8054968287526427, "grad_norm": 0.8810073137283325, "learning_rate": 6.594245465909127e-06, "loss": 0.7572864890098572, "step": 854 }, { "epoch": 1.809725158562368, "grad_norm": 0.5721503496170044, "learning_rate": 6.578976886470791e-06, "loss": 1.052355408668518, "step": 856 }, { "epoch": 1.8139534883720931, "grad_norm": 0.5520162582397461, "learning_rate": 6.56369511610653e-06, "loss": 0.5999872088432312, "step": 858 }, { "epoch": 1.8181818181818183, "grad_norm": 0.9520819187164307, "learning_rate": 6.548400341642128e-06, "loss": 1.050502896308899, "step": 860 }, { "epoch": 1.8224101479915433, "grad_norm": 0.5526043176651001, "learning_rate": 6.533092750062345e-06, "loss": 1.0451221466064453, "step": 862 }, { "epoch": 1.8266384778012685, "grad_norm": 0.696395993232727, "learning_rate": 6.5177725285086416e-06, "loss": 0.5881604552268982, "step": 864 }, { "epoch": 1.8308668076109935, "grad_norm": 0.6110039353370667, "learning_rate": 6.5024398642768785e-06, "loss": 0.7557898163795471, "step": 866 }, { "epoch": 1.8350951374207187, "grad_norm": 0.5088884234428406, "learning_rate": 6.487094944815036e-06, "loss": 1.0823222398757935, "step": 868 }, { "epoch": 1.839323467230444, "grad_norm": 1.0750072002410889, "learning_rate": 6.47173795772092e-06, "loss": 1.0935083627700806, "step": 870 }, { "epoch": 1.8435517970401691, "grad_norm": 0.28848883509635925, "learning_rate": 6.456369090739869e-06, "loss": 0.7627519369125366, "step": 872 }, { "epoch": 1.8477801268498943, "grad_norm": 0.6725155115127563, "learning_rate": 6.440988531762454e-06, "loss": 1.1057088375091553, "step": 874 }, { "epoch": 1.8520084566596196, "grad_norm": 1.8453751802444458, "learning_rate": 6.42559646882219e-06, "loss": 0.873634397983551, "step": 876 }, { "epoch": 1.8562367864693448, "grad_norm": 2.4322872161865234, "learning_rate": 6.410193090093227e-06, "loss": 0.3047733008861542, "step": 878 }, { "epoch": 1.8604651162790697, "grad_norm": 1.3105032444000244, "learning_rate": 6.394778583888064e-06, "loss": 0.7178741693496704, "step": 880 }, { "epoch": 1.864693446088795, "grad_norm": 1.2071388959884644, "learning_rate": 6.379353138655227e-06, "loss": 1.110272765159607, "step": 882 }, { "epoch": 1.86892177589852, "grad_norm": 0.8797225952148438, "learning_rate": 6.3639169429769805e-06, "loss": 0.7329269647598267, "step": 884 }, { "epoch": 1.8731501057082451, "grad_norm": 3.42655086517334, "learning_rate": 6.348470185567025e-06, "loss": 1.1439217329025269, "step": 886 }, { "epoch": 1.8773784355179703, "grad_norm": 0.5335652828216553, "learning_rate": 6.333013055268169e-06, "loss": 1.1082477569580078, "step": 888 }, { "epoch": 1.8816067653276956, "grad_norm": 3.26548433303833, "learning_rate": 6.317545741050044e-06, "loss": 0.6481310725212097, "step": 890 }, { "epoch": 1.8858350951374208, "grad_norm": 1.7353861331939697, "learning_rate": 6.3020684320067805e-06, "loss": 0.7864089608192444, "step": 892 }, { "epoch": 1.890063424947146, "grad_norm": 1.2937991619110107, "learning_rate": 6.2865813173546976e-06, "loss": 1.11574387550354, "step": 894 }, { "epoch": 1.8942917547568712, "grad_norm": 1.2202117443084717, "learning_rate": 6.271084586429994e-06, "loss": 1.3662776947021484, "step": 896 }, { "epoch": 1.8985200845665962, "grad_norm": 0.6188715696334839, "learning_rate": 6.255578428686433e-06, "loss": 1.0432673692703247, "step": 898 }, { "epoch": 1.9027484143763214, "grad_norm": 2.3999335765838623, "learning_rate": 6.240063033693023e-06, "loss": 0.4890569746494293, "step": 900 }, { "epoch": 1.9069767441860463, "grad_norm": 5.765149116516113, "learning_rate": 6.2245385911316994e-06, "loss": 1.0591330528259277, "step": 902 }, { "epoch": 1.9112050739957716, "grad_norm": 4.306301593780518, "learning_rate": 6.2090052907950096e-06, "loss": 0.5486176013946533, "step": 904 }, { "epoch": 1.9154334038054968, "grad_norm": 0.5568671226501465, "learning_rate": 6.193463322583792e-06, "loss": 0.8711650967597961, "step": 906 }, { "epoch": 1.919661733615222, "grad_norm": 0.9368557333946228, "learning_rate": 6.177912876504851e-06, "loss": 1.1886277198791504, "step": 908 }, { "epoch": 1.9238900634249472, "grad_norm": 1.2915819883346558, "learning_rate": 6.16235414266864e-06, "loss": 0.8123524188995361, "step": 910 }, { "epoch": 1.9281183932346724, "grad_norm": 0.7841312885284424, "learning_rate": 6.146787311286927e-06, "loss": 1.0567268133163452, "step": 912 }, { "epoch": 1.9323467230443976, "grad_norm": 0.8721857666969299, "learning_rate": 6.131212572670483e-06, "loss": 0.6849409937858582, "step": 914 }, { "epoch": 1.9365750528541226, "grad_norm": 0.5539165139198303, "learning_rate": 6.115630117226741e-06, "loss": 1.0969229936599731, "step": 916 }, { "epoch": 1.9408033826638478, "grad_norm": 0.6441904902458191, "learning_rate": 6.1000401354574855e-06, "loss": 0.6425963640213013, "step": 918 }, { "epoch": 1.945031712473573, "grad_norm": 2.0100107192993164, "learning_rate": 6.084442817956502e-06, "loss": 0.9008411169052124, "step": 920 }, { "epoch": 1.949260042283298, "grad_norm": 0.5583478808403015, "learning_rate": 6.0688383554072625e-06, "loss": 0.9682831764221191, "step": 922 }, { "epoch": 1.9534883720930232, "grad_norm": 0.6045987010002136, "learning_rate": 6.053226938580596e-06, "loss": 0.9832097291946411, "step": 924 }, { "epoch": 1.9577167019027484, "grad_norm": 0.36139747500419617, "learning_rate": 6.03760875833234e-06, "loss": 0.8807600736618042, "step": 926 }, { "epoch": 1.9619450317124736, "grad_norm": 1.0740067958831787, "learning_rate": 6.021984005601027e-06, "loss": 1.1585499048233032, "step": 928 }, { "epoch": 1.9661733615221988, "grad_norm": 0.8910236358642578, "learning_rate": 6.006352871405534e-06, "loss": 0.8231717348098755, "step": 930 }, { "epoch": 1.970401691331924, "grad_norm": 1.0428776741027832, "learning_rate": 5.990715546842755e-06, "loss": 1.228318691253662, "step": 932 }, { "epoch": 1.9746300211416492, "grad_norm": 1.5089360475540161, "learning_rate": 5.9750722230852694e-06, "loss": 0.8693381547927856, "step": 934 }, { "epoch": 1.9788583509513742, "grad_norm": 0.9107832908630371, "learning_rate": 5.959423091378992e-06, "loss": 0.7001117467880249, "step": 936 }, { "epoch": 1.9830866807610994, "grad_norm": 8.807775497436523, "learning_rate": 5.943768343040845e-06, "loss": 0.7743115425109863, "step": 938 }, { "epoch": 1.9873150105708244, "grad_norm": 0.7729356288909912, "learning_rate": 5.928108169456419e-06, "loss": 1.056190848350525, "step": 940 }, { "epoch": 1.9915433403805496, "grad_norm": 0.6299241781234741, "learning_rate": 5.912442762077624e-06, "loss": 1.0633841753005981, "step": 942 }, { "epoch": 1.9957716701902748, "grad_norm": 0.45847564935684204, "learning_rate": 5.89677231242036e-06, "loss": 1.0876084566116333, "step": 944 }, { "epoch": 2.0, "grad_norm": 0.8876862525939941, "learning_rate": 5.8810970120621714e-06, "loss": 0.4923701286315918, "step": 946 }, { "epoch": 2.004228329809725, "grad_norm": 30.97492218017578, "learning_rate": 5.8654170526399014e-06, "loss": 0.7388001084327698, "step": 948 }, { "epoch": 2.0084566596194504, "grad_norm": 1.121238350868225, "learning_rate": 5.849732625847354e-06, "loss": 0.9629300236701965, "step": 950 }, { "epoch": 2.0126849894291756, "grad_norm": 0.7477766871452332, "learning_rate": 5.834043923432947e-06, "loss": 0.9182472825050354, "step": 952 }, { "epoch": 2.016913319238901, "grad_norm": 0.5724676847457886, "learning_rate": 5.818351137197373e-06, "loss": 1.010575532913208, "step": 954 }, { "epoch": 2.0211416490486256, "grad_norm": 0.8635369539260864, "learning_rate": 5.802654458991245e-06, "loss": 1.1136103868484497, "step": 956 }, { "epoch": 2.025369978858351, "grad_norm": 0.5300254225730896, "learning_rate": 5.786954080712763e-06, "loss": 0.698776364326477, "step": 958 }, { "epoch": 2.029598308668076, "grad_norm": 0.9135218858718872, "learning_rate": 5.7712501943053576e-06, "loss": 0.9391481876373291, "step": 960 }, { "epoch": 2.033826638477801, "grad_norm": 3.698072910308838, "learning_rate": 5.755542991755352e-06, "loss": 0.8788146376609802, "step": 962 }, { "epoch": 2.0380549682875264, "grad_norm": 1.0173090696334839, "learning_rate": 5.739832665089604e-06, "loss": 0.7509766817092896, "step": 964 }, { "epoch": 2.0422832980972516, "grad_norm": 1.3024694919586182, "learning_rate": 5.724119406373171e-06, "loss": 0.6607835292816162, "step": 966 }, { "epoch": 2.046511627906977, "grad_norm": 3.309645414352417, "learning_rate": 5.708403407706954e-06, "loss": 0.6546986699104309, "step": 968 }, { "epoch": 2.050739957716702, "grad_norm": 0.6194641590118408, "learning_rate": 5.692684861225349e-06, "loss": 0.9780763983726501, "step": 970 }, { "epoch": 2.0549682875264272, "grad_norm": 5.071075439453125, "learning_rate": 5.676963959093904e-06, "loss": 0.4349742829799652, "step": 972 }, { "epoch": 2.059196617336152, "grad_norm": 0.9067067503929138, "learning_rate": 5.66124089350696e-06, "loss": 0.9252787828445435, "step": 974 }, { "epoch": 2.063424947145877, "grad_norm": 0.7849780321121216, "learning_rate": 5.645515856685316e-06, "loss": 0.9430543780326843, "step": 976 }, { "epoch": 2.0676532769556024, "grad_norm": 1.2118703126907349, "learning_rate": 5.629789040873862e-06, "loss": 0.9624269604682922, "step": 978 }, { "epoch": 2.0718816067653276, "grad_norm": 5.212878704071045, "learning_rate": 5.614060638339238e-06, "loss": 0.7365391254425049, "step": 980 }, { "epoch": 2.076109936575053, "grad_norm": 3.2754108905792236, "learning_rate": 5.598330841367487e-06, "loss": 0.7081872224807739, "step": 982 }, { "epoch": 2.080338266384778, "grad_norm": 0.4842812716960907, "learning_rate": 5.582599842261693e-06, "loss": 0.7261295914649963, "step": 984 }, { "epoch": 2.0845665961945032, "grad_norm": 1.0085281133651733, "learning_rate": 5.566867833339644e-06, "loss": 0.8238586187362671, "step": 986 }, { "epoch": 2.0887949260042284, "grad_norm": 0.7246492505073547, "learning_rate": 5.551135006931467e-06, "loss": 0.9454484581947327, "step": 988 }, { "epoch": 2.0930232558139537, "grad_norm": 0.7532749176025391, "learning_rate": 5.535401555377287e-06, "loss": 0.876262366771698, "step": 990 }, { "epoch": 2.097251585623679, "grad_norm": 1.657408595085144, "learning_rate": 5.51966767102487e-06, "loss": 0.5936261415481567, "step": 992 }, { "epoch": 2.1014799154334036, "grad_norm": 1.6842647790908813, "learning_rate": 5.503933546227273e-06, "loss": 0.7082334160804749, "step": 994 }, { "epoch": 2.105708245243129, "grad_norm": 0.5524448156356812, "learning_rate": 5.4881993733404916e-06, "loss": 0.7404530644416809, "step": 996 }, { "epoch": 2.109936575052854, "grad_norm": 1.3093129396438599, "learning_rate": 5.472465344721113e-06, "loss": 0.9283185005187988, "step": 998 }, { "epoch": 2.1141649048625792, "grad_norm": 1.196323275566101, "learning_rate": 5.456731652723959e-06, "loss": 0.8905725479125977, "step": 1000 }, { "epoch": 2.1183932346723044, "grad_norm": 0.6400330662727356, "learning_rate": 5.440998489699731e-06, "loss": 0.24109074473381042, "step": 1002 }, { "epoch": 2.1226215644820297, "grad_norm": 3.808913469314575, "learning_rate": 5.425266047992672e-06, "loss": 0.6522191762924194, "step": 1004 }, { "epoch": 2.126849894291755, "grad_norm": 0.5903002023696899, "learning_rate": 5.4095345199382e-06, "loss": 0.910293459892273, "step": 1006 }, { "epoch": 2.13107822410148, "grad_norm": 1.13662588596344, "learning_rate": 5.393804097860568e-06, "loss": 0.833383321762085, "step": 1008 }, { "epoch": 2.1353065539112053, "grad_norm": 1.0298562049865723, "learning_rate": 5.3780749740705065e-06, "loss": 0.6212067604064941, "step": 1010 }, { "epoch": 2.13953488372093, "grad_norm": 0.5126671195030212, "learning_rate": 5.362347340862869e-06, "loss": 0.5482521653175354, "step": 1012 }, { "epoch": 2.1437632135306552, "grad_norm": 0.5542948842048645, "learning_rate": 5.3466213905142935e-06, "loss": 0.6081077456474304, "step": 1014 }, { "epoch": 2.1479915433403804, "grad_norm": 0.667399525642395, "learning_rate": 5.3308973152808395e-06, "loss": 0.7646819949150085, "step": 1016 }, { "epoch": 2.1522198731501057, "grad_norm": 1.3126075267791748, "learning_rate": 5.315175307395644e-06, "loss": 0.8908743262290955, "step": 1018 }, { "epoch": 2.156448202959831, "grad_norm": 1.3381482362747192, "learning_rate": 5.299455559066571e-06, "loss": 0.7117832899093628, "step": 1020 }, { "epoch": 2.160676532769556, "grad_norm": 0.5555500388145447, "learning_rate": 5.283738262473859e-06, "loss": 0.6557780504226685, "step": 1022 }, { "epoch": 2.1649048625792813, "grad_norm": 0.6875596046447754, "learning_rate": 5.268023609767772e-06, "loss": 0.9180653691291809, "step": 1024 }, { "epoch": 2.1691331923890065, "grad_norm": 0.5114744305610657, "learning_rate": 5.2523117930662545e-06, "loss": 0.9426715970039368, "step": 1026 }, { "epoch": 2.1733615221987317, "grad_norm": 0.8016918897628784, "learning_rate": 5.2366030044525785e-06, "loss": 1.0160022974014282, "step": 1028 }, { "epoch": 2.177589852008457, "grad_norm": 0.664639949798584, "learning_rate": 5.220897435972992e-06, "loss": 0.9374679327011108, "step": 1030 }, { "epoch": 2.1818181818181817, "grad_norm": 0.8410804271697998, "learning_rate": 5.205195279634385e-06, "loss": 0.9438706040382385, "step": 1032 }, { "epoch": 2.186046511627907, "grad_norm": 0.6709905862808228, "learning_rate": 5.1894967274019245e-06, "loss": 0.9935900568962097, "step": 1034 }, { "epoch": 2.190274841437632, "grad_norm": 0.6367090344429016, "learning_rate": 5.173801971196716e-06, "loss": 0.6655043959617615, "step": 1036 }, { "epoch": 2.1945031712473573, "grad_norm": 4.230550289154053, "learning_rate": 5.158111202893464e-06, "loss": 0.35415753722190857, "step": 1038 }, { "epoch": 2.1987315010570825, "grad_norm": 0.7429682612419128, "learning_rate": 5.142424614318112e-06, "loss": 0.9756222367286682, "step": 1040 }, { "epoch": 2.2029598308668077, "grad_norm": 6.087325096130371, "learning_rate": 5.12674239724551e-06, "loss": 0.3032646179199219, "step": 1042 }, { "epoch": 2.207188160676533, "grad_norm": 0.9910244345664978, "learning_rate": 5.111064743397061e-06, "loss": 0.9804587364196777, "step": 1044 }, { "epoch": 2.211416490486258, "grad_norm": 0.6226437091827393, "learning_rate": 5.09539184443838e-06, "loss": 0.5167152285575867, "step": 1046 }, { "epoch": 2.2156448202959833, "grad_norm": 3.445274591445923, "learning_rate": 5.079723891976956e-06, "loss": 0.7733212113380432, "step": 1048 }, { "epoch": 2.219873150105708, "grad_norm": 2.0134127140045166, "learning_rate": 5.064061077559803e-06, "loss": 0.5894641876220703, "step": 1050 }, { "epoch": 2.2241014799154333, "grad_norm": 1.4332314729690552, "learning_rate": 5.048403592671116e-06, "loss": 0.7874913215637207, "step": 1052 }, { "epoch": 2.2283298097251585, "grad_norm": 1.122257947921753, "learning_rate": 5.032751628729943e-06, "loss": 0.9522119760513306, "step": 1054 }, { "epoch": 2.2325581395348837, "grad_norm": 0.741966962814331, "learning_rate": 5.017105377087829e-06, "loss": 0.9521563053131104, "step": 1056 }, { "epoch": 2.236786469344609, "grad_norm": 0.3313559293746948, "learning_rate": 5.0014650290264854e-06, "loss": 0.6805707216262817, "step": 1058 }, { "epoch": 2.241014799154334, "grad_norm": 0.5800691843032837, "learning_rate": 4.9858307757554536e-06, "loss": 0.759727954864502, "step": 1060 }, { "epoch": 2.2452431289640593, "grad_norm": 0.9093447923660278, "learning_rate": 4.97020280840976e-06, "loss": 0.9344936013221741, "step": 1062 }, { "epoch": 2.2494714587737845, "grad_norm": 1.0423702001571655, "learning_rate": 4.954581318047582e-06, "loss": 0.8695020079612732, "step": 1064 }, { "epoch": 2.2536997885835097, "grad_norm": 1.9365214109420776, "learning_rate": 4.938966495647918e-06, "loss": 0.542430579662323, "step": 1066 }, { "epoch": 2.2579281183932345, "grad_norm": 0.6056095361709595, "learning_rate": 4.923358532108244e-06, "loss": 0.8178219795227051, "step": 1068 }, { "epoch": 2.2621564482029597, "grad_norm": 2.5407559871673584, "learning_rate": 4.907757618242186e-06, "loss": 0.6770350337028503, "step": 1070 }, { "epoch": 2.266384778012685, "grad_norm": 0.6252725720405579, "learning_rate": 4.892163944777181e-06, "loss": 0.9717943668365479, "step": 1072 }, { "epoch": 2.27061310782241, "grad_norm": 0.42637455463409424, "learning_rate": 4.876577702352155e-06, "loss": 0.6377326250076294, "step": 1074 }, { "epoch": 2.2748414376321353, "grad_norm": 3.716885566711426, "learning_rate": 4.860999081515183e-06, "loss": 0.7123830914497375, "step": 1076 }, { "epoch": 2.2790697674418605, "grad_norm": 1.23655104637146, "learning_rate": 4.845428272721161e-06, "loss": 0.2273055464029312, "step": 1078 }, { "epoch": 2.2832980972515857, "grad_norm": 0.37076041102409363, "learning_rate": 4.8298654663294865e-06, "loss": 0.12106815725564957, "step": 1080 }, { "epoch": 2.287526427061311, "grad_norm": 0.6062988042831421, "learning_rate": 4.814310852601717e-06, "loss": 0.4892716109752655, "step": 1082 }, { "epoch": 2.291754756871036, "grad_norm": 0.713954746723175, "learning_rate": 4.7987646216992545e-06, "loss": 0.3308049142360687, "step": 1084 }, { "epoch": 2.295983086680761, "grad_norm": 0.4922694265842438, "learning_rate": 4.783226963681018e-06, "loss": 0.14864258468151093, "step": 1086 }, { "epoch": 2.300211416490486, "grad_norm": 42.06053924560547, "learning_rate": 4.76769806850112e-06, "loss": 0.6442570686340332, "step": 1088 }, { "epoch": 2.3044397463002113, "grad_norm": 0.8329454660415649, "learning_rate": 4.752178126006544e-06, "loss": 0.8334766626358032, "step": 1090 }, { "epoch": 2.3086680761099365, "grad_norm": 1.1945240497589111, "learning_rate": 4.736667325934819e-06, "loss": 0.652392566204071, "step": 1092 }, { "epoch": 2.3128964059196617, "grad_norm": 0.701427698135376, "learning_rate": 4.721165857911709e-06, "loss": 0.9152230620384216, "step": 1094 }, { "epoch": 2.317124735729387, "grad_norm": 0.95479416847229, "learning_rate": 4.705673911448891e-06, "loss": 0.8755677342414856, "step": 1096 }, { "epoch": 2.321353065539112, "grad_norm": 0.9657679796218872, "learning_rate": 4.690191675941631e-06, "loss": 0.8886753916740417, "step": 1098 }, { "epoch": 2.3255813953488373, "grad_norm": 2.5783119201660156, "learning_rate": 4.674719340666477e-06, "loss": 0.5045087337493896, "step": 1100 }, { "epoch": 2.3298097251585626, "grad_norm": 0.6372756361961365, "learning_rate": 4.659257094778949e-06, "loss": 0.691253125667572, "step": 1102 }, { "epoch": 2.3340380549682873, "grad_norm": 1.0967471599578857, "learning_rate": 4.643805127311212e-06, "loss": 0.9556361436843872, "step": 1104 }, { "epoch": 2.3382663847780125, "grad_norm": 1.0436038970947266, "learning_rate": 4.628363627169774e-06, "loss": 0.888778567314148, "step": 1106 }, { "epoch": 2.3424947145877377, "grad_norm": 0.7186304330825806, "learning_rate": 4.612932783133182e-06, "loss": 0.852042555809021, "step": 1108 }, { "epoch": 2.346723044397463, "grad_norm": 1.2672243118286133, "learning_rate": 4.5975127838497036e-06, "loss": 1.0449351072311401, "step": 1110 }, { "epoch": 2.350951374207188, "grad_norm": 1.355370044708252, "learning_rate": 4.582103817835021e-06, "loss": 0.597102701663971, "step": 1112 }, { "epoch": 2.3551797040169133, "grad_norm": 2.839750289916992, "learning_rate": 4.566706073469938e-06, "loss": 0.7668895125389099, "step": 1114 }, { "epoch": 2.3594080338266386, "grad_norm": 1.4695847034454346, "learning_rate": 4.551319738998067e-06, "loss": 0.5695499181747437, "step": 1116 }, { "epoch": 2.3636363636363638, "grad_norm": 3.9198238849639893, "learning_rate": 4.535945002523524e-06, "loss": 1.0125648975372314, "step": 1118 }, { "epoch": 2.367864693446089, "grad_norm": 0.7557876110076904, "learning_rate": 4.5205820520086415e-06, "loss": 0.9332593083381653, "step": 1120 }, { "epoch": 2.3720930232558137, "grad_norm": 0.5043232440948486, "learning_rate": 4.505231075271662e-06, "loss": 0.8402242660522461, "step": 1122 }, { "epoch": 2.376321353065539, "grad_norm": 0.9241620302200317, "learning_rate": 4.489892259984446e-06, "loss": 0.607761025428772, "step": 1124 }, { "epoch": 2.380549682875264, "grad_norm": 1.9049075841903687, "learning_rate": 4.474565793670167e-06, "loss": 0.7773751020431519, "step": 1126 }, { "epoch": 2.3847780126849893, "grad_norm": 5.811763286590576, "learning_rate": 4.459251863701038e-06, "loss": 0.6147076487541199, "step": 1128 }, { "epoch": 2.3890063424947146, "grad_norm": 4.413387298583984, "learning_rate": 4.443950657296004e-06, "loss": 0.7182481288909912, "step": 1130 }, { "epoch": 2.3932346723044398, "grad_norm": 6.594907760620117, "learning_rate": 4.4286623615184585e-06, "loss": 0.5292147397994995, "step": 1132 }, { "epoch": 2.397463002114165, "grad_norm": 0.5823398232460022, "learning_rate": 4.413387163273964e-06, "loss": 0.9658170938491821, "step": 1134 }, { "epoch": 2.40169133192389, "grad_norm": 1.8569353818893433, "learning_rate": 4.3981252493079506e-06, "loss": 0.6759036779403687, "step": 1136 }, { "epoch": 2.4059196617336154, "grad_norm": 5.227511405944824, "learning_rate": 4.382876806203453e-06, "loss": 0.7729136943817139, "step": 1138 }, { "epoch": 2.41014799154334, "grad_norm": 0.6373514533042908, "learning_rate": 4.3676420203788125e-06, "loss": 0.9397667646408081, "step": 1140 }, { "epoch": 2.4143763213530653, "grad_norm": 0.5432982444763184, "learning_rate": 4.352421078085405e-06, "loss": 1.0088902711868286, "step": 1142 }, { "epoch": 2.4186046511627906, "grad_norm": 0.9690803289413452, "learning_rate": 4.337214165405368e-06, "loss": 0.4879336655139923, "step": 1144 }, { "epoch": 2.4228329809725158, "grad_norm": 2.288316249847412, "learning_rate": 4.322021468249316e-06, "loss": 0.6819209456443787, "step": 1146 }, { "epoch": 2.427061310782241, "grad_norm": 1.671682357788086, "learning_rate": 4.306843172354076e-06, "loss": 0.7601984739303589, "step": 1148 }, { "epoch": 2.431289640591966, "grad_norm": 1.0260653495788574, "learning_rate": 4.291679463280416e-06, "loss": 0.45934075117111206, "step": 1150 }, { "epoch": 2.4355179704016914, "grad_norm": 1.7110512256622314, "learning_rate": 4.276530526410768e-06, "loss": 0.5771675109863281, "step": 1152 }, { "epoch": 2.4397463002114166, "grad_norm": 0.38674408197402954, "learning_rate": 4.261396546946972e-06, "loss": 0.4827878773212433, "step": 1154 }, { "epoch": 2.443974630021142, "grad_norm": 1.2068623304367065, "learning_rate": 4.246277709908009e-06, "loss": 0.8348107933998108, "step": 1156 }, { "epoch": 2.448202959830867, "grad_norm": 0.8439732789993286, "learning_rate": 4.231174200127736e-06, "loss": 0.5334876179695129, "step": 1158 }, { "epoch": 2.452431289640592, "grad_norm": 0.47613054513931274, "learning_rate": 4.216086202252624e-06, "loss": 0.9284610748291016, "step": 1160 }, { "epoch": 2.456659619450317, "grad_norm": 0.7516986131668091, "learning_rate": 4.201013900739513e-06, "loss": 0.915778636932373, "step": 1162 }, { "epoch": 2.460887949260042, "grad_norm": 0.9380217790603638, "learning_rate": 4.185957479853344e-06, "loss": 0.6841413378715515, "step": 1164 }, { "epoch": 2.4651162790697674, "grad_norm": 0.9076225161552429, "learning_rate": 4.1709171236649096e-06, "loss": 1.002259373664856, "step": 1166 }, { "epoch": 2.4693446088794926, "grad_norm": 1.0005605220794678, "learning_rate": 4.155893016048607e-06, "loss": 1.1612303256988525, "step": 1168 }, { "epoch": 2.473572938689218, "grad_norm": 0.7159266471862793, "learning_rate": 4.140885340680189e-06, "loss": 0.6536337733268738, "step": 1170 }, { "epoch": 2.477801268498943, "grad_norm": 2.118730068206787, "learning_rate": 4.125894281034517e-06, "loss": 0.7673131227493286, "step": 1172 }, { "epoch": 2.482029598308668, "grad_norm": 0.6753649115562439, "learning_rate": 4.110920020383316e-06, "loss": 0.7120599150657654, "step": 1174 }, { "epoch": 2.4862579281183934, "grad_norm": 0.9139197468757629, "learning_rate": 4.0959627417929386e-06, "loss": 0.7065567374229431, "step": 1176 }, { "epoch": 2.4904862579281186, "grad_norm": 1.5965232849121094, "learning_rate": 4.081022628122127e-06, "loss": 0.7578078508377075, "step": 1178 }, { "epoch": 2.4947145877378434, "grad_norm": 1.408253788948059, "learning_rate": 4.06609986201977e-06, "loss": 0.5925859212875366, "step": 1180 }, { "epoch": 2.4989429175475686, "grad_norm": 0.46419283747673035, "learning_rate": 4.051194625922681e-06, "loss": 0.4587797522544861, "step": 1182 }, { "epoch": 2.503171247357294, "grad_norm": 0.6330340504646301, "learning_rate": 4.036307102053359e-06, "loss": 0.11168936640024185, "step": 1184 }, { "epoch": 2.507399577167019, "grad_norm": 1.6745115518569946, "learning_rate": 4.021437472417763e-06, "loss": 0.8709131479263306, "step": 1186 }, { "epoch": 2.511627906976744, "grad_norm": 17.842241287231445, "learning_rate": 4.006585918803091e-06, "loss": 0.6913301944732666, "step": 1188 }, { "epoch": 2.5158562367864694, "grad_norm": 1.5969452857971191, "learning_rate": 3.991752622775551e-06, "loss": 0.5852769017219543, "step": 1190 }, { "epoch": 2.5200845665961946, "grad_norm": 0.7198762893676758, "learning_rate": 3.97693776567815e-06, "loss": 0.9364661574363708, "step": 1192 }, { "epoch": 2.52431289640592, "grad_norm": 0.8717184066772461, "learning_rate": 3.962141528628465e-06, "loss": 0.5808508396148682, "step": 1194 }, { "epoch": 2.528541226215645, "grad_norm": 5.840766429901123, "learning_rate": 3.947364092516437e-06, "loss": 0.8575798273086548, "step": 1196 }, { "epoch": 2.53276955602537, "grad_norm": 0.6181642413139343, "learning_rate": 3.932605638002163e-06, "loss": 0.9035545587539673, "step": 1198 }, { "epoch": 2.536997885835095, "grad_norm": 2.034467935562134, "learning_rate": 3.917866345513677e-06, "loss": 0.6786800026893616, "step": 1200 }, { "epoch": 2.54122621564482, "grad_norm": 0.6932312846183777, "learning_rate": 3.903146395244749e-06, "loss": 0.8922795057296753, "step": 1202 }, { "epoch": 2.5454545454545454, "grad_norm": 1.945586919784546, "learning_rate": 3.888445967152691e-06, "loss": 0.37132975459098816, "step": 1204 }, { "epoch": 2.5496828752642706, "grad_norm": 0.6736026406288147, "learning_rate": 3.873765240956138e-06, "loss": 0.9939403533935547, "step": 1206 }, { "epoch": 2.553911205073996, "grad_norm": 0.546970784664154, "learning_rate": 3.859104396132863e-06, "loss": 0.9657546877861023, "step": 1208 }, { "epoch": 2.558139534883721, "grad_norm": 0.8349957466125488, "learning_rate": 3.84446361191759e-06, "loss": 0.9398714900016785, "step": 1210 }, { "epoch": 2.5623678646934462, "grad_norm": 0.9163470268249512, "learning_rate": 3.829843067299788e-06, "loss": 0.6566909551620483, "step": 1212 }, { "epoch": 2.5665961945031714, "grad_norm": 0.8621496558189392, "learning_rate": 3.8152429410214834e-06, "loss": 0.9173173904418945, "step": 1214 }, { "epoch": 2.570824524312896, "grad_norm": 1.340057134628296, "learning_rate": 3.8006634115750886e-06, "loss": 0.5776484608650208, "step": 1216 }, { "epoch": 2.5750528541226214, "grad_norm": 1.6031118631362915, "learning_rate": 3.7861046572012105e-06, "loss": 0.5216265916824341, "step": 1218 }, { "epoch": 2.5792811839323466, "grad_norm": 1.0857218503952026, "learning_rate": 3.771566855886467e-06, "loss": 0.47422534227371216, "step": 1220 }, { "epoch": 2.583509513742072, "grad_norm": 2.884624481201172, "learning_rate": 3.7570501853613227e-06, "loss": 0.5570884346961975, "step": 1222 }, { "epoch": 2.587737843551797, "grad_norm": 4.1100993156433105, "learning_rate": 3.742554823097905e-06, "loss": 0.8588721752166748, "step": 1224 }, { "epoch": 2.5919661733615222, "grad_norm": 0.2905360758304596, "learning_rate": 3.7280809463078436e-06, "loss": 0.3534935712814331, "step": 1226 }, { "epoch": 2.5961945031712474, "grad_norm": 0.6426495313644409, "learning_rate": 3.7136287319400944e-06, "loss": 0.7040010690689087, "step": 1228 }, { "epoch": 2.6004228329809727, "grad_norm": 2.311009168624878, "learning_rate": 3.6991983566787847e-06, "loss": 0.7547330260276794, "step": 1230 }, { "epoch": 2.604651162790698, "grad_norm": 9.141519546508789, "learning_rate": 3.6847899969410515e-06, "loss": 0.7063798308372498, "step": 1232 }, { "epoch": 2.6088794926004226, "grad_norm": 1.2885082960128784, "learning_rate": 3.6704038288748812e-06, "loss": 0.7670626640319824, "step": 1234 }, { "epoch": 2.613107822410148, "grad_norm": 0.5779919624328613, "learning_rate": 3.6560400283569543e-06, "loss": 0.7829570174217224, "step": 1236 }, { "epoch": 2.617336152219873, "grad_norm": 3.22723650932312, "learning_rate": 3.641698770990507e-06, "loss": 0.816627025604248, "step": 1238 }, { "epoch": 2.6215644820295982, "grad_norm": 0.5778287649154663, "learning_rate": 3.6273802321031738e-06, "loss": 0.6943777799606323, "step": 1240 }, { "epoch": 2.6257928118393234, "grad_norm": 0.7096527218818665, "learning_rate": 3.6130845867448384e-06, "loss": 0.7963392734527588, "step": 1242 }, { "epoch": 2.6300211416490487, "grad_norm": 2.49165678024292, "learning_rate": 3.598812009685514e-06, "loss": 0.9108496308326721, "step": 1244 }, { "epoch": 2.634249471458774, "grad_norm": 2.79050350189209, "learning_rate": 3.584562675413189e-06, "loss": 0.6753231287002563, "step": 1246 }, { "epoch": 2.638477801268499, "grad_norm": 1.7486052513122559, "learning_rate": 3.5703367581316985e-06, "loss": 0.44615814089775085, "step": 1248 }, { "epoch": 2.6427061310782243, "grad_norm": 0.6540852785110474, "learning_rate": 3.5561344317585957e-06, "loss": 0.9385300278663635, "step": 1250 }, { "epoch": 2.646934460887949, "grad_norm": 8.63803482055664, "learning_rate": 3.5419558699230305e-06, "loss": 0.44542282819747925, "step": 1252 }, { "epoch": 2.6511627906976747, "grad_norm": 5.931276798248291, "learning_rate": 3.52780124596361e-06, "loss": 0.6263750195503235, "step": 1254 }, { "epoch": 2.6553911205073994, "grad_norm": 0.5771086812019348, "learning_rate": 3.5136707329263055e-06, "loss": 0.9163082242012024, "step": 1256 }, { "epoch": 2.6596194503171247, "grad_norm": 0.6170768737792969, "learning_rate": 3.499564503562315e-06, "loss": 0.21917259693145752, "step": 1258 }, { "epoch": 2.66384778012685, "grad_norm": 0.3818674087524414, "learning_rate": 3.4854827303259575e-06, "loss": 0.4561626613140106, "step": 1260 }, { "epoch": 2.668076109936575, "grad_norm": 7.052920341491699, "learning_rate": 3.47142558537257e-06, "loss": 0.6176928281784058, "step": 1262 }, { "epoch": 2.6723044397463003, "grad_norm": 2.3205859661102295, "learning_rate": 3.4573932405563966e-06, "loss": 0.6451160311698914, "step": 1264 }, { "epoch": 2.6765327695560255, "grad_norm": 1.9360634088516235, "learning_rate": 3.4433858674284894e-06, "loss": 0.3469844460487366, "step": 1266 }, { "epoch": 2.6807610993657507, "grad_norm": 1.1347569227218628, "learning_rate": 3.429403637234614e-06, "loss": 0.6708723902702332, "step": 1268 }, { "epoch": 2.6849894291754755, "grad_norm": 0.726165771484375, "learning_rate": 3.4154467209131515e-06, "loss": 0.9065659642219543, "step": 1270 }, { "epoch": 2.689217758985201, "grad_norm": 1.6492167711257935, "learning_rate": 3.401515289093011e-06, "loss": 0.6738967299461365, "step": 1272 }, { "epoch": 2.693446088794926, "grad_norm": 0.43170294165611267, "learning_rate": 3.3876095120915433e-06, "loss": 0.4017610251903534, "step": 1274 }, { "epoch": 2.697674418604651, "grad_norm": 1.2748513221740723, "learning_rate": 3.3737295599124592e-06, "loss": 0.4568636119365692, "step": 1276 }, { "epoch": 2.7019027484143763, "grad_norm": 1.0479854345321655, "learning_rate": 3.3598756022437507e-06, "loss": 0.9143987894058228, "step": 1278 }, { "epoch": 2.7061310782241015, "grad_norm": 0.6926357746124268, "learning_rate": 3.3460478084556157e-06, "loss": 0.6025747060775757, "step": 1280 }, { "epoch": 2.7103594080338267, "grad_norm": 0.4956757724285126, "learning_rate": 3.33224634759839e-06, "loss": 0.9949999451637268, "step": 1282 }, { "epoch": 2.714587737843552, "grad_norm": 14.328939437866211, "learning_rate": 3.318471388400476e-06, "loss": 0.6738043427467346, "step": 1284 }, { "epoch": 2.718816067653277, "grad_norm": 0.1694031059741974, "learning_rate": 3.3047230992662834e-06, "loss": 1.0150436162948608, "step": 1286 }, { "epoch": 2.723044397463002, "grad_norm": 0.42077353596687317, "learning_rate": 3.291001648274175e-06, "loss": 0.4722650945186615, "step": 1288 }, { "epoch": 2.7272727272727275, "grad_norm": 0.546546220779419, "learning_rate": 3.277307203174395e-06, "loss": 0.9117059707641602, "step": 1290 }, { "epoch": 2.7315010570824523, "grad_norm": 0.5688716769218445, "learning_rate": 3.263639931387039e-06, "loss": 0.9608585238456726, "step": 1292 }, { "epoch": 2.7357293868921775, "grad_norm": 1.4636285305023193, "learning_rate": 3.2500000000000015e-06, "loss": 0.8858906626701355, "step": 1294 }, { "epoch": 2.7399577167019027, "grad_norm": 0.3925884962081909, "learning_rate": 3.236387575766916e-06, "loss": 0.2969858646392822, "step": 1296 }, { "epoch": 2.744186046511628, "grad_norm": 0.7721077799797058, "learning_rate": 3.222802825105138e-06, "loss": 0.5420318245887756, "step": 1298 }, { "epoch": 2.748414376321353, "grad_norm": 0.7165651917457581, "learning_rate": 3.209245914093708e-06, "loss": 0.6247003674507141, "step": 1300 }, { "epoch": 2.7526427061310783, "grad_norm": 0.7919058799743652, "learning_rate": 3.1957170084713053e-06, "loss": 0.7403091788291931, "step": 1302 }, { "epoch": 2.7568710359408035, "grad_norm": 1.9444713592529297, "learning_rate": 3.182216273634235e-06, "loss": 0.5224264860153198, "step": 1304 }, { "epoch": 2.7610993657505283, "grad_norm": 1.2281345129013062, "learning_rate": 3.1687438746344086e-06, "loss": 0.7813040614128113, "step": 1306 }, { "epoch": 2.765327695560254, "grad_norm": 4.363501071929932, "learning_rate": 3.1552999761773166e-06, "loss": 0.7680379748344421, "step": 1308 }, { "epoch": 2.7695560253699787, "grad_norm": 1.1411948204040527, "learning_rate": 3.141884742620013e-06, "loss": 0.9268274903297424, "step": 1310 }, { "epoch": 2.773784355179704, "grad_norm": 0.7298506498336792, "learning_rate": 3.1284983379691247e-06, "loss": 0.7121368646621704, "step": 1312 }, { "epoch": 2.778012684989429, "grad_norm": 0.24272526800632477, "learning_rate": 3.1151409258788235e-06, "loss": 0.4666304290294647, "step": 1314 }, { "epoch": 2.7822410147991543, "grad_norm": 0.763480007648468, "learning_rate": 3.101812669648838e-06, "loss": 0.8377182483673096, "step": 1316 }, { "epoch": 2.7864693446088795, "grad_norm": 0.4666755199432373, "learning_rate": 3.0885137322224546e-06, "loss": 0.4907030463218689, "step": 1318 }, { "epoch": 2.7906976744186047, "grad_norm": 1.2374683618545532, "learning_rate": 3.075244276184529e-06, "loss": 0.786038339138031, "step": 1320 }, { "epoch": 2.79492600422833, "grad_norm": 2.4183313846588135, "learning_rate": 3.0620044637594936e-06, "loss": 0.47882896661758423, "step": 1322 }, { "epoch": 2.7991543340380547, "grad_norm": 0.6164536476135254, "learning_rate": 3.0487944568093685e-06, "loss": 0.965308666229248, "step": 1324 }, { "epoch": 2.8033826638477803, "grad_norm": 1.176335096359253, "learning_rate": 3.035614416831801e-06, "loss": 0.2657644748687744, "step": 1326 }, { "epoch": 2.807610993657505, "grad_norm": 10.388093948364258, "learning_rate": 3.0224645049580746e-06, "loss": 0.4449101388454437, "step": 1328 }, { "epoch": 2.8118393234672303, "grad_norm": 0.5235056281089783, "learning_rate": 3.0093448819511416e-06, "loss": 0.5318148136138916, "step": 1330 }, { "epoch": 2.8160676532769555, "grad_norm": 0.5244578719139099, "learning_rate": 2.9962557082036677e-06, "loss": 0.9637982845306396, "step": 1332 }, { "epoch": 2.8202959830866807, "grad_norm": 0.5162270069122314, "learning_rate": 2.9831971437360606e-06, "loss": 0.5877452492713928, "step": 1334 }, { "epoch": 2.824524312896406, "grad_norm": 0.7031766772270203, "learning_rate": 2.9701693481945132e-06, "loss": 0.964709997177124, "step": 1336 }, { "epoch": 2.828752642706131, "grad_norm": 0.7961280345916748, "learning_rate": 2.957172480849064e-06, "loss": 0.936155378818512, "step": 1338 }, { "epoch": 2.8329809725158563, "grad_norm": 0.5453387498855591, "learning_rate": 2.9442067005916375e-06, "loss": 0.6408176422119141, "step": 1340 }, { "epoch": 2.8372093023255816, "grad_norm": 0.6556735634803772, "learning_rate": 2.931272165934105e-06, "loss": 0.9994575381278992, "step": 1342 }, { "epoch": 2.8414376321353068, "grad_norm": 0.9036626219749451, "learning_rate": 2.918369035006351e-06, "loss": 0.6383472681045532, "step": 1344 }, { "epoch": 2.8456659619450315, "grad_norm": 1.7746022939682007, "learning_rate": 2.9054974655543335e-06, "loss": 0.7216110229492188, "step": 1346 }, { "epoch": 2.8498942917547567, "grad_norm": 0.5420008897781372, "learning_rate": 2.89265761493816e-06, "loss": 0.811105489730835, "step": 1348 }, { "epoch": 2.854122621564482, "grad_norm": 1.6720713376998901, "learning_rate": 2.8798496401301644e-06, "loss": 0.5354399085044861, "step": 1350 }, { "epoch": 2.858350951374207, "grad_norm": 2.1013383865356445, "learning_rate": 2.8670736977129843e-06, "loss": 0.7998499274253845, "step": 1352 }, { "epoch": 2.8625792811839323, "grad_norm": 0.5114390254020691, "learning_rate": 2.854329943877647e-06, "loss": 0.9000284671783447, "step": 1354 }, { "epoch": 2.8668076109936576, "grad_norm": 1.0974289178848267, "learning_rate": 2.841618534421664e-06, "loss": 0.38514694571495056, "step": 1356 }, { "epoch": 2.8710359408033828, "grad_norm": 0.8061960935592651, "learning_rate": 2.8289396247471227e-06, "loss": 0.9419484734535217, "step": 1358 }, { "epoch": 2.875264270613108, "grad_norm": 1.9654678106307983, "learning_rate": 2.816293369858788e-06, "loss": 0.6914476752281189, "step": 1360 }, { "epoch": 2.879492600422833, "grad_norm": 0.39243558049201965, "learning_rate": 2.803679924362206e-06, "loss": 0.596655011177063, "step": 1362 }, { "epoch": 2.883720930232558, "grad_norm": 0.802558958530426, "learning_rate": 2.7910994424618165e-06, "loss": 1.0268882513046265, "step": 1364 }, { "epoch": 2.887949260042283, "grad_norm": 3.4329564571380615, "learning_rate": 2.778552077959064e-06, "loss": 0.7781391143798828, "step": 1366 }, { "epoch": 2.8921775898520083, "grad_norm": 0.3626936674118042, "learning_rate": 2.766037984250521e-06, "loss": 0.922453761100769, "step": 1368 }, { "epoch": 2.8964059196617336, "grad_norm": 0.530470609664917, "learning_rate": 2.753557314326011e-06, "loss": 0.918528139591217, "step": 1370 }, { "epoch": 2.9006342494714588, "grad_norm": 0.9835408329963684, "learning_rate": 2.7411102207667373e-06, "loss": 0.9388396143913269, "step": 1372 }, { "epoch": 2.904862579281184, "grad_norm": 0.7426559329032898, "learning_rate": 2.728696855743418e-06, "loss": 0.7643646597862244, "step": 1374 }, { "epoch": 2.909090909090909, "grad_norm": 0.8638247847557068, "learning_rate": 2.7163173710144323e-06, "loss": 0.9589405059814453, "step": 1376 }, { "epoch": 2.9133192389006344, "grad_norm": 1.8436757326126099, "learning_rate": 2.703971917923951e-06, "loss": 0.5900381207466125, "step": 1378 }, { "epoch": 2.9175475687103596, "grad_norm": 0.6242554783821106, "learning_rate": 2.6916606474000965e-06, "loss": 0.6310076117515564, "step": 1380 }, { "epoch": 2.9217758985200843, "grad_norm": 1.9490702152252197, "learning_rate": 2.679383709953103e-06, "loss": 0.9625915884971619, "step": 1382 }, { "epoch": 2.92600422832981, "grad_norm": 1.426056981086731, "learning_rate": 2.6671412556734578e-06, "loss": 0.790015697479248, "step": 1384 }, { "epoch": 2.9302325581395348, "grad_norm": 0.7446538209915161, "learning_rate": 2.6549334342300844e-06, "loss": 0.6157321333885193, "step": 1386 }, { "epoch": 2.93446088794926, "grad_norm": 0.9662436842918396, "learning_rate": 2.642760394868503e-06, "loss": 0.8995580077171326, "step": 1388 }, { "epoch": 2.938689217758985, "grad_norm": 0.1636676788330078, "learning_rate": 2.6306222864090157e-06, "loss": 0.7162589430809021, "step": 1390 }, { "epoch": 2.9429175475687104, "grad_norm": 0.5341367721557617, "learning_rate": 2.61851925724487e-06, "loss": 0.9481911659240723, "step": 1392 }, { "epoch": 2.9471458773784356, "grad_norm": 0.24322892725467682, "learning_rate": 2.606451455340459e-06, "loss": 0.2592424750328064, "step": 1394 }, { "epoch": 2.951374207188161, "grad_norm": 0.47246232628822327, "learning_rate": 2.5944190282295155e-06, "loss": 0.47894513607025146, "step": 1396 }, { "epoch": 2.955602536997886, "grad_norm": 1.1216708421707153, "learning_rate": 2.5824221230132895e-06, "loss": 0.8182187080383301, "step": 1398 }, { "epoch": 2.9598308668076108, "grad_norm": 0.6486838459968567, "learning_rate": 2.5704608863587676e-06, "loss": 0.9932674169540405, "step": 1400 }, { "epoch": 2.9640591966173364, "grad_norm": 3.1482739448547363, "learning_rate": 2.558535464496877e-06, "loss": 0.7923304438591003, "step": 1402 }, { "epoch": 2.968287526427061, "grad_norm": 0.4015442132949829, "learning_rate": 2.5466460032206872e-06, "loss": 0.44513118267059326, "step": 1404 }, { "epoch": 2.9725158562367864, "grad_norm": 4.7295331954956055, "learning_rate": 2.53479264788364e-06, "loss": 0.8289566040039062, "step": 1406 }, { "epoch": 2.9767441860465116, "grad_norm": 0.6188860535621643, "learning_rate": 2.522975543397769e-06, "loss": 0.7704756855964661, "step": 1408 }, { "epoch": 2.980972515856237, "grad_norm": 1.6783899068832397, "learning_rate": 2.511194834231922e-06, "loss": 0.7189264297485352, "step": 1410 }, { "epoch": 2.985200845665962, "grad_norm": 0.5423654913902283, "learning_rate": 2.49945066441e-06, "loss": 0.9147735834121704, "step": 1412 }, { "epoch": 2.989429175475687, "grad_norm": 0.5348056554794312, "learning_rate": 2.4877431775092004e-06, "loss": 0.6833301782608032, "step": 1414 }, { "epoch": 2.9936575052854124, "grad_norm": 3.807912588119507, "learning_rate": 2.4760725166582544e-06, "loss": 0.8869065642356873, "step": 1416 }, { "epoch": 2.997885835095137, "grad_norm": 0.8176599144935608, "learning_rate": 2.464438824535675e-06, "loss": 0.47630202770233154, "step": 1418 }, { "epoch": 3.0021141649048624, "grad_norm": 0.5347883105278015, "learning_rate": 2.452842243368028e-06, "loss": 0.8811054229736328, "step": 1420 }, { "epoch": 3.0063424947145876, "grad_norm": 0.7508466839790344, "learning_rate": 2.4412829149281735e-06, "loss": 0.4740794599056244, "step": 1422 }, { "epoch": 3.010570824524313, "grad_norm": 1.979899525642395, "learning_rate": 2.4297609805335472e-06, "loss": 0.9109249114990234, "step": 1424 }, { "epoch": 3.014799154334038, "grad_norm": 1.673256754875183, "learning_rate": 2.4182765810444263e-06, "loss": 0.3574182391166687, "step": 1426 }, { "epoch": 3.019027484143763, "grad_norm": 0.597726583480835, "learning_rate": 2.4068298568622083e-06, "loss": 0.5223789811134338, "step": 1428 }, { "epoch": 3.0232558139534884, "grad_norm": 0.5907129049301147, "learning_rate": 2.395420947927694e-06, "loss": 0.7532718181610107, "step": 1430 }, { "epoch": 3.0274841437632136, "grad_norm": 0.5962886810302734, "learning_rate": 2.3840499937193804e-06, "loss": 0.8148324489593506, "step": 1432 }, { "epoch": 3.031712473572939, "grad_norm": 0.5221508145332336, "learning_rate": 2.3727171332517496e-06, "loss": 0.7622570991516113, "step": 1434 }, { "epoch": 3.035940803382664, "grad_norm": 2.456155776977539, "learning_rate": 2.361422505073575e-06, "loss": 0.5890013575553894, "step": 1436 }, { "epoch": 3.040169133192389, "grad_norm": 0.35271134972572327, "learning_rate": 2.3501662472662233e-06, "loss": 0.17637419700622559, "step": 1438 }, { "epoch": 3.044397463002114, "grad_norm": 0.7209294438362122, "learning_rate": 2.3389484974419685e-06, "loss": 0.7976908087730408, "step": 1440 }, { "epoch": 3.048625792811839, "grad_norm": 0.6704209446907043, "learning_rate": 2.327769392742309e-06, "loss": 0.5822479724884033, "step": 1442 }, { "epoch": 3.0528541226215644, "grad_norm": 16.698678970336914, "learning_rate": 2.316629069836291e-06, "loss": 0.15618830919265747, "step": 1444 }, { "epoch": 3.0570824524312896, "grad_norm": 1.150067687034607, "learning_rate": 2.305527664918838e-06, "loss": 0.46259307861328125, "step": 1446 }, { "epoch": 3.061310782241015, "grad_norm": 1.5562708377838135, "learning_rate": 2.294465313709085e-06, "loss": 0.5446912050247192, "step": 1448 }, { "epoch": 3.06553911205074, "grad_norm": 0.639706552028656, "learning_rate": 2.2834421514487205e-06, "loss": 0.5113627910614014, "step": 1450 }, { "epoch": 3.0697674418604652, "grad_norm": 3.0295112133026123, "learning_rate": 2.27245831290033e-06, "loss": 0.6176190376281738, "step": 1452 }, { "epoch": 3.0739957716701904, "grad_norm": 0.6498733162879944, "learning_rate": 2.261513932345755e-06, "loss": 0.7461786866188049, "step": 1454 }, { "epoch": 3.0782241014799157, "grad_norm": 0.2336254119873047, "learning_rate": 2.250609143584443e-06, "loss": 0.21532724797725677, "step": 1456 }, { "epoch": 3.0824524312896404, "grad_norm": 0.2933042645454407, "learning_rate": 2.239744079931818e-06, "loss": 0.4857647716999054, "step": 1458 }, { "epoch": 3.0866807610993656, "grad_norm": 0.6210364699363708, "learning_rate": 2.228918874217649e-06, "loss": 0.7847075462341309, "step": 1460 }, { "epoch": 3.090909090909091, "grad_norm": 0.49971577525138855, "learning_rate": 2.2181336587844244e-06, "loss": 0.8046977519989014, "step": 1462 }, { "epoch": 3.095137420718816, "grad_norm": 0.7083837985992432, "learning_rate": 2.207388565485736e-06, "loss": 0.5487635731697083, "step": 1464 }, { "epoch": 3.0993657505285412, "grad_norm": 0.771369993686676, "learning_rate": 2.196683725684666e-06, "loss": 0.682548999786377, "step": 1466 }, { "epoch": 3.1035940803382664, "grad_norm": 0.6805517673492432, "learning_rate": 2.1860192702521826e-06, "loss": 0.87738037109375, "step": 1468 }, { "epoch": 3.1078224101479917, "grad_norm": 0.7333028316497803, "learning_rate": 2.1753953295655354e-06, "loss": 0.8108183145523071, "step": 1470 }, { "epoch": 3.112050739957717, "grad_norm": 2.33878231048584, "learning_rate": 2.164812033506673e-06, "loss": 0.5281031131744385, "step": 1472 }, { "epoch": 3.116279069767442, "grad_norm": 0.5589327812194824, "learning_rate": 2.1542695114606367e-06, "loss": 0.8572843074798584, "step": 1474 }, { "epoch": 3.120507399577167, "grad_norm": 0.6607449054718018, "learning_rate": 2.1437678923139944e-06, "loss": 0.8003775477409363, "step": 1476 }, { "epoch": 3.124735729386892, "grad_norm": 21.184663772583008, "learning_rate": 2.1333073044532628e-06, "loss": 0.3766254484653473, "step": 1478 }, { "epoch": 3.1289640591966172, "grad_norm": 0.8753629922866821, "learning_rate": 2.122887875763327e-06, "loss": 0.7876757383346558, "step": 1480 }, { "epoch": 3.1331923890063424, "grad_norm": 0.7183106541633606, "learning_rate": 2.1125097336258897e-06, "loss": 0.7673516273498535, "step": 1482 }, { "epoch": 3.1374207188160677, "grad_norm": 0.4325995147228241, "learning_rate": 2.1021730049179117e-06, "loss": 0.2292463481426239, "step": 1484 }, { "epoch": 3.141649048625793, "grad_norm": 5.6108269691467285, "learning_rate": 2.09187781601005e-06, "loss": 0.7191312313079834, "step": 1486 }, { "epoch": 3.145877378435518, "grad_norm": 0.7772470712661743, "learning_rate": 2.0816242927651254e-06, "loss": 0.9005565047264099, "step": 1488 }, { "epoch": 3.1501057082452433, "grad_norm": 4.918927192687988, "learning_rate": 2.071412560536581e-06, "loss": 0.685893714427948, "step": 1490 }, { "epoch": 3.1543340380549685, "grad_norm": 3.08353328704834, "learning_rate": 2.0612427441669475e-06, "loss": 0.6022601127624512, "step": 1492 }, { "epoch": 3.1585623678646932, "grad_norm": 1.8396400213241577, "learning_rate": 2.051114967986311e-06, "loss": 0.37677979469299316, "step": 1494 }, { "epoch": 3.1627906976744184, "grad_norm": 0.15926599502563477, "learning_rate": 2.0410293558108074e-06, "loss": 0.5826849341392517, "step": 1496 }, { "epoch": 3.1670190274841437, "grad_norm": 0.5507872700691223, "learning_rate": 2.0309860309410986e-06, "loss": 0.7842580676078796, "step": 1498 }, { "epoch": 3.171247357293869, "grad_norm": 0.48856478929519653, "learning_rate": 2.0209851161608613e-06, "loss": 0.8684639930725098, "step": 1500 }, { "epoch": 3.175475687103594, "grad_norm": 1.4167568683624268, "learning_rate": 2.011026733735301e-06, "loss": 0.2424730360507965, "step": 1502 }, { "epoch": 3.1797040169133193, "grad_norm": 0.5894184112548828, "learning_rate": 2.001111005409643e-06, "loss": 0.42941153049468994, "step": 1504 }, { "epoch": 3.1839323467230445, "grad_norm": 0.8752439022064209, "learning_rate": 1.9912380524076503e-06, "loss": 0.6384761333465576, "step": 1506 }, { "epoch": 3.1881606765327697, "grad_norm": 1.6139200925827026, "learning_rate": 1.981407995430136e-06, "loss": 0.3339318633079529, "step": 1508 }, { "epoch": 3.192389006342495, "grad_norm": 2.3417136669158936, "learning_rate": 1.9716209546535e-06, "loss": 0.3422594666481018, "step": 1510 }, { "epoch": 3.1966173361522197, "grad_norm": 0.18520565330982208, "learning_rate": 1.9618770497282487e-06, "loss": 0.06635133922100067, "step": 1512 }, { "epoch": 3.200845665961945, "grad_norm": 1.2493771314620972, "learning_rate": 1.9521763997775294e-06, "loss": 0.7406595945358276, "step": 1514 }, { "epoch": 3.20507399577167, "grad_norm": 1.0728957653045654, "learning_rate": 1.942519123395689e-06, "loss": 0.8073416948318481, "step": 1516 }, { "epoch": 3.2093023255813953, "grad_norm": 1.0175617933273315, "learning_rate": 1.932905338646812e-06, "loss": 0.479559987783432, "step": 1518 }, { "epoch": 3.2135306553911205, "grad_norm": 0.5045363306999207, "learning_rate": 1.9233351630632747e-06, "loss": 0.6859887838363647, "step": 1520 }, { "epoch": 3.2177589852008457, "grad_norm": 0.6776877045631409, "learning_rate": 1.9138087136443227e-06, "loss": 0.744087278842926, "step": 1522 }, { "epoch": 3.221987315010571, "grad_norm": 1.2866824865341187, "learning_rate": 1.904326106854626e-06, "loss": 0.7924530506134033, "step": 1524 }, { "epoch": 3.226215644820296, "grad_norm": 0.5151466727256775, "learning_rate": 1.8948874586228622e-06, "loss": 0.7691396474838257, "step": 1526 }, { "epoch": 3.2304439746300213, "grad_norm": 1.185268521308899, "learning_rate": 1.8854928843402987e-06, "loss": 0.11905823647975922, "step": 1528 }, { "epoch": 3.234672304439746, "grad_norm": 1.3089765310287476, "learning_rate": 1.8761424988593796e-06, "loss": 0.6736167669296265, "step": 1530 }, { "epoch": 3.2389006342494713, "grad_norm": 1.214754343032837, "learning_rate": 1.8668364164923248e-06, "loss": 0.654792845249176, "step": 1532 }, { "epoch": 3.2431289640591965, "grad_norm": 0.704034149646759, "learning_rate": 1.8575747510097294e-06, "loss": 0.8160040974617004, "step": 1534 }, { "epoch": 3.2473572938689217, "grad_norm": 0.730758011341095, "learning_rate": 1.8483576156391747e-06, "loss": 0.528414785861969, "step": 1536 }, { "epoch": 3.251585623678647, "grad_norm": 0.5425379276275635, "learning_rate": 1.8391851230638443e-06, "loss": 0.5372763872146606, "step": 1538 }, { "epoch": 3.255813953488372, "grad_norm": 0.5301923751831055, "learning_rate": 1.8300573854211452e-06, "loss": 0.45242756605148315, "step": 1540 }, { "epoch": 3.2600422832980973, "grad_norm": 1.9838603734970093, "learning_rate": 1.8209745143013363e-06, "loss": 0.7830596566200256, "step": 1542 }, { "epoch": 3.2642706131078225, "grad_norm": 0.9704765677452087, "learning_rate": 1.811936620746167e-06, "loss": 0.8070287108421326, "step": 1544 }, { "epoch": 3.2684989429175477, "grad_norm": 1.1180484294891357, "learning_rate": 1.8029438152475159e-06, "loss": 0.703566312789917, "step": 1546 }, { "epoch": 3.2727272727272725, "grad_norm": 0.43579116463661194, "learning_rate": 1.7939962077460448e-06, "loss": 0.14839768409729004, "step": 1548 }, { "epoch": 3.276955602536998, "grad_norm": 0.8753741383552551, "learning_rate": 1.785093907629849e-06, "loss": 0.7331667542457581, "step": 1550 }, { "epoch": 3.281183932346723, "grad_norm": 0.7363839149475098, "learning_rate": 1.7762370237331233e-06, "loss": 0.834587812423706, "step": 1552 }, { "epoch": 3.285412262156448, "grad_norm": 0.0855717658996582, "learning_rate": 1.7674256643348348e-06, "loss": 0.09367389976978302, "step": 1554 }, { "epoch": 3.2896405919661733, "grad_norm": 0.5846360921859741, "learning_rate": 1.7586599371573887e-06, "loss": 0.7191219329833984, "step": 1556 }, { "epoch": 3.2938689217758985, "grad_norm": 0.5940054059028625, "learning_rate": 1.7499399493653225e-06, "loss": 0.426492840051651, "step": 1558 }, { "epoch": 3.2980972515856237, "grad_norm": 5.685873985290527, "learning_rate": 1.7412658075639921e-06, "loss": 0.8922783136367798, "step": 1560 }, { "epoch": 3.302325581395349, "grad_norm": 16.20218849182129, "learning_rate": 1.7326376177982635e-06, "loss": 0.5691681504249573, "step": 1562 }, { "epoch": 3.306553911205074, "grad_norm": 0.8330562710762024, "learning_rate": 1.7240554855512225e-06, "loss": 0.38691553473472595, "step": 1564 }, { "epoch": 3.3107822410147993, "grad_norm": 0.6537200212478638, "learning_rate": 1.7155195157428878e-06, "loss": 0.5346977114677429, "step": 1566 }, { "epoch": 3.3150105708245245, "grad_norm": 0.2761213481426239, "learning_rate": 1.707029812728916e-06, "loss": 0.10800652951002121, "step": 1568 }, { "epoch": 3.3192389006342493, "grad_norm": 0.9342727065086365, "learning_rate": 1.6985864802993366e-06, "loss": 0.46171727776527405, "step": 1570 }, { "epoch": 3.3234672304439745, "grad_norm": 3.019517421722412, "learning_rate": 1.690189621677284e-06, "loss": 0.5780071020126343, "step": 1572 }, { "epoch": 3.3276955602536997, "grad_norm": 1.4273282289505005, "learning_rate": 1.681839339517728e-06, "loss": 0.16791722178459167, "step": 1574 }, { "epoch": 3.331923890063425, "grad_norm": 1.1448655128479004, "learning_rate": 1.67353573590622e-06, "loss": 0.2885700762271881, "step": 1576 }, { "epoch": 3.33615221987315, "grad_norm": 0.5603737831115723, "learning_rate": 1.6652789123576513e-06, "loss": 0.4562610685825348, "step": 1578 }, { "epoch": 3.3403805496828753, "grad_norm": 0.511721670627594, "learning_rate": 1.6570689698150094e-06, "loss": 0.5023640990257263, "step": 1580 }, { "epoch": 3.3446088794926006, "grad_norm": 0.6595059633255005, "learning_rate": 1.6489060086481373e-06, "loss": 0.8846491575241089, "step": 1582 }, { "epoch": 3.3488372093023258, "grad_norm": 2.6087253093719482, "learning_rate": 1.6407901286525152e-06, "loss": 0.5563831925392151, "step": 1584 }, { "epoch": 3.353065539112051, "grad_norm": 0.606498658657074, "learning_rate": 1.6327214290480382e-06, "loss": 0.4892018437385559, "step": 1586 }, { "epoch": 3.3572938689217757, "grad_norm": 1.33845853805542, "learning_rate": 1.6247000084778006e-06, "loss": 0.8378742933273315, "step": 1588 }, { "epoch": 3.361522198731501, "grad_norm": 0.5669885277748108, "learning_rate": 1.6167259650068887e-06, "loss": 0.2973576784133911, "step": 1590 }, { "epoch": 3.365750528541226, "grad_norm": 0.5756183862686157, "learning_rate": 1.6087993961211904e-06, "loss": 0.6423325538635254, "step": 1592 }, { "epoch": 3.3699788583509513, "grad_norm": 0.8195279836654663, "learning_rate": 1.6009203987261957e-06, "loss": 0.27564576268196106, "step": 1594 }, { "epoch": 3.3742071881606766, "grad_norm": 0.5971675515174866, "learning_rate": 1.593089069145809e-06, "loss": 0.7789900302886963, "step": 1596 }, { "epoch": 3.3784355179704018, "grad_norm": 1.3379855155944824, "learning_rate": 1.5853055031211844e-06, "loss": 0.5074257254600525, "step": 1598 }, { "epoch": 3.382663847780127, "grad_norm": 0.38119375705718994, "learning_rate": 1.577569795809544e-06, "loss": 0.2607685625553131, "step": 1600 }, { "epoch": 3.386892177589852, "grad_norm": 0.9026830196380615, "learning_rate": 1.5698820417830137e-06, "loss": 0.5245527625083923, "step": 1602 }, { "epoch": 3.3911205073995774, "grad_norm": 0.8339282870292664, "learning_rate": 1.5622423350274784e-06, "loss": 0.8080227971076965, "step": 1604 }, { "epoch": 3.395348837209302, "grad_norm": 0.654216468334198, "learning_rate": 1.5546507689414217e-06, "loss": 0.8545297384262085, "step": 1606 }, { "epoch": 3.3995771670190273, "grad_norm": 4.353316307067871, "learning_rate": 1.5471074363347894e-06, "loss": 0.4326980710029602, "step": 1608 }, { "epoch": 3.4038054968287526, "grad_norm": 0.4745010435581207, "learning_rate": 1.539612429427852e-06, "loss": 0.8205713629722595, "step": 1610 }, { "epoch": 3.4080338266384778, "grad_norm": 0.5275663137435913, "learning_rate": 1.5321658398500808e-06, "loss": 0.7244023680686951, "step": 1612 }, { "epoch": 3.412262156448203, "grad_norm": 0.876323401927948, "learning_rate": 1.5247677586390255e-06, "loss": 0.6330902576446533, "step": 1614 }, { "epoch": 3.416490486257928, "grad_norm": 0.7790511846542358, "learning_rate": 1.5174182762392007e-06, "loss": 0.7890173196792603, "step": 1616 }, { "epoch": 3.4207188160676534, "grad_norm": 0.7576814889907837, "learning_rate": 1.5101174825009815e-06, "loss": 0.8212699890136719, "step": 1618 }, { "epoch": 3.4249471458773786, "grad_norm": 0.4849609136581421, "learning_rate": 1.5028654666795042e-06, "loss": 0.7752748727798462, "step": 1620 }, { "epoch": 3.429175475687104, "grad_norm": 1.3400230407714844, "learning_rate": 1.495662317433576e-06, "loss": 0.5360914468765259, "step": 1622 }, { "epoch": 3.4334038054968286, "grad_norm": 2.1691901683807373, "learning_rate": 1.4885081228245909e-06, "loss": 0.7797468900680542, "step": 1624 }, { "epoch": 3.4376321353065538, "grad_norm": 0.7433999180793762, "learning_rate": 1.4814029703154515e-06, "loss": 0.5227027535438538, "step": 1626 }, { "epoch": 3.441860465116279, "grad_norm": 0.8282102942466736, "learning_rate": 1.4743469467695017e-06, "loss": 0.8936291933059692, "step": 1628 }, { "epoch": 3.446088794926004, "grad_norm": 2.6265172958374023, "learning_rate": 1.4673401384494651e-06, "loss": 0.43022099137306213, "step": 1630 }, { "epoch": 3.4503171247357294, "grad_norm": 0.8742415904998779, "learning_rate": 1.4603826310163874e-06, "loss": 0.7152241468429565, "step": 1632 }, { "epoch": 3.4545454545454546, "grad_norm": 0.6871761083602905, "learning_rate": 1.453474509528593e-06, "loss": 0.4893222749233246, "step": 1634 }, { "epoch": 3.45877378435518, "grad_norm": 0.7918784022331238, "learning_rate": 1.446615858440642e-06, "loss": 0.7473881244659424, "step": 1636 }, { "epoch": 3.463002114164905, "grad_norm": 0.15924090147018433, "learning_rate": 1.4398067616022993e-06, "loss": 0.25529974699020386, "step": 1638 }, { "epoch": 3.46723044397463, "grad_norm": 0.47457703948020935, "learning_rate": 1.43304730225751e-06, "loss": 0.46837541460990906, "step": 1640 }, { "epoch": 3.471458773784355, "grad_norm": 0.8605097532272339, "learning_rate": 1.4263375630433802e-06, "loss": 0.24951256811618805, "step": 1642 }, { "epoch": 3.47568710359408, "grad_norm": 0.5765727758407593, "learning_rate": 1.4196776259891665e-06, "loss": 0.788293719291687, "step": 1644 }, { "epoch": 3.4799154334038054, "grad_norm": 0.7365961670875549, "learning_rate": 1.4130675725152762e-06, "loss": 0.660286545753479, "step": 1646 }, { "epoch": 3.4841437632135306, "grad_norm": 0.12560750544071198, "learning_rate": 1.4065074834322677e-06, "loss": 0.45965394377708435, "step": 1648 }, { "epoch": 3.488372093023256, "grad_norm": 0.614321231842041, "learning_rate": 1.3999974389398669e-06, "loss": 0.4378893971443176, "step": 1650 }, { "epoch": 3.492600422832981, "grad_norm": 2.5098178386688232, "learning_rate": 1.3935375186259817e-06, "loss": 0.4187197685241699, "step": 1652 }, { "epoch": 3.496828752642706, "grad_norm": 1.288038969039917, "learning_rate": 1.3871278014657332e-06, "loss": 0.7457848191261292, "step": 1654 }, { "epoch": 3.5010570824524314, "grad_norm": 0.6148707866668701, "learning_rate": 1.3807683658204915e-06, "loss": 0.7514063119888306, "step": 1656 }, { "epoch": 3.5052854122621566, "grad_norm": 0.2492813616991043, "learning_rate": 1.3744592894369093e-06, "loss": 0.462161123752594, "step": 1658 }, { "epoch": 3.5095137420718814, "grad_norm": 0.39551863074302673, "learning_rate": 1.3682006494459806e-06, "loss": 0.555620014667511, "step": 1660 }, { "epoch": 3.513742071881607, "grad_norm": 4.405650615692139, "learning_rate": 1.361992522362096e-06, "loss": 0.5125894546508789, "step": 1662 }, { "epoch": 3.517970401691332, "grad_norm": 0.6411206126213074, "learning_rate": 1.355834984082101e-06, "loss": 0.7557477355003357, "step": 1664 }, { "epoch": 3.522198731501057, "grad_norm": 1.730056643486023, "learning_rate": 1.3497281098843746e-06, "loss": 0.7412624955177307, "step": 1666 }, { "epoch": 3.526427061310782, "grad_norm": 0.17836298048496246, "learning_rate": 1.34367197442791e-06, "loss": 0.164866641163826, "step": 1668 }, { "epoch": 3.5306553911205074, "grad_norm": 0.22004663944244385, "learning_rate": 1.3376666517513931e-06, "loss": 0.6337510347366333, "step": 1670 }, { "epoch": 3.5348837209302326, "grad_norm": 0.7251442670822144, "learning_rate": 1.3317122152723078e-06, "loss": 0.49543118476867676, "step": 1672 }, { "epoch": 3.539112050739958, "grad_norm": 0.5675739049911499, "learning_rate": 1.3258087377860323e-06, "loss": 0.7474437952041626, "step": 1674 }, { "epoch": 3.543340380549683, "grad_norm": 3.3841161727905273, "learning_rate": 1.3199562914649519e-06, "loss": 0.43814244866371155, "step": 1676 }, { "epoch": 3.547568710359408, "grad_norm": 0.6816301941871643, "learning_rate": 1.314154947857571e-06, "loss": 0.7525407671928406, "step": 1678 }, { "epoch": 3.5517970401691334, "grad_norm": 0.6903603672981262, "learning_rate": 1.3084047778876487e-06, "loss": 0.5105797648429871, "step": 1680 }, { "epoch": 3.556025369978858, "grad_norm": 0.5235387682914734, "learning_rate": 1.3027058518533228e-06, "loss": 0.4686659872531891, "step": 1682 }, { "epoch": 3.5602536997885834, "grad_norm": 0.9544976353645325, "learning_rate": 1.2970582394262516e-06, "loss": 0.4570730924606323, "step": 1684 }, { "epoch": 3.5644820295983086, "grad_norm": 1.0277490615844727, "learning_rate": 1.291462009650768e-06, "loss": 0.2640705108642578, "step": 1686 }, { "epoch": 3.568710359408034, "grad_norm": 0.5556883215904236, "learning_rate": 1.2859172309430285e-06, "loss": 0.5416086316108704, "step": 1688 }, { "epoch": 3.572938689217759, "grad_norm": 0.052497394382953644, "learning_rate": 1.280423971090181e-06, "loss": 0.20976774394512177, "step": 1690 }, { "epoch": 3.5771670190274842, "grad_norm": 0.9812293648719788, "learning_rate": 1.2749822972495333e-06, "loss": 0.336683452129364, "step": 1692 }, { "epoch": 3.5813953488372094, "grad_norm": 0.9204544425010681, "learning_rate": 1.2695922759477356e-06, "loss": 0.486004501581192, "step": 1694 }, { "epoch": 3.585623678646934, "grad_norm": 1.3403997421264648, "learning_rate": 1.2642539730799622e-06, "loss": 0.29541391134262085, "step": 1696 }, { "epoch": 3.58985200845666, "grad_norm": 0.6753963232040405, "learning_rate": 1.2589674539091115e-06, "loss": 0.7681332230567932, "step": 1698 }, { "epoch": 3.5940803382663846, "grad_norm": 0.8763320446014404, "learning_rate": 1.2537327830650042e-06, "loss": 0.9110218286514282, "step": 1700 }, { "epoch": 3.59830866807611, "grad_norm": 1.326659917831421, "learning_rate": 1.248550024543594e-06, "loss": 0.7413162589073181, "step": 1702 }, { "epoch": 3.602536997885835, "grad_norm": 1.5853239297866821, "learning_rate": 1.2434192417061862e-06, "loss": 0.22896696627140045, "step": 1704 }, { "epoch": 3.6067653276955602, "grad_norm": 0.6515389084815979, "learning_rate": 1.2383404972786625e-06, "loss": 0.4268551766872406, "step": 1706 }, { "epoch": 3.6109936575052854, "grad_norm": 7.213520526885986, "learning_rate": 1.2333138533507139e-06, "loss": 0.652518630027771, "step": 1708 }, { "epoch": 3.6152219873150107, "grad_norm": 0.892566978931427, "learning_rate": 1.2283393713750816e-06, "loss": 0.5081558227539062, "step": 1710 }, { "epoch": 3.619450317124736, "grad_norm": 0.6494478583335876, "learning_rate": 1.2234171121668069e-06, "loss": 0.40064775943756104, "step": 1712 }, { "epoch": 3.6236786469344606, "grad_norm": 0.22923864424228668, "learning_rate": 1.2185471359024855e-06, "loss": 0.2788720726966858, "step": 1714 }, { "epoch": 3.6279069767441863, "grad_norm": 5.971065998077393, "learning_rate": 1.2137295021195341e-06, "loss": 0.6276031136512756, "step": 1716 }, { "epoch": 3.632135306553911, "grad_norm": 0.5167627930641174, "learning_rate": 1.2089642697154613e-06, "loss": 0.4265766441822052, "step": 1718 }, { "epoch": 3.6363636363636362, "grad_norm": 1.3780224323272705, "learning_rate": 1.2042514969471475e-06, "loss": 0.35583245754241943, "step": 1720 }, { "epoch": 3.6405919661733614, "grad_norm": 0.5640789270401001, "learning_rate": 1.1995912414301329e-06, "loss": 0.6183260679244995, "step": 1722 }, { "epoch": 3.6448202959830867, "grad_norm": 0.8287678360939026, "learning_rate": 1.1949835601379144e-06, "loss": 0.5412572622299194, "step": 1724 }, { "epoch": 3.649048625792812, "grad_norm": 0.7322806119918823, "learning_rate": 1.1904285094012463e-06, "loss": 0.8397457599639893, "step": 1726 }, { "epoch": 3.653276955602537, "grad_norm": 0.664240837097168, "learning_rate": 1.185926144907454e-06, "loss": 0.862804114818573, "step": 1728 }, { "epoch": 3.6575052854122623, "grad_norm": 9.177942276000977, "learning_rate": 1.1814765216997522e-06, "loss": 0.7075401544570923, "step": 1730 }, { "epoch": 3.6617336152219875, "grad_norm": 1.1146337985992432, "learning_rate": 1.1770796941765727e-06, "loss": 0.7143962979316711, "step": 1732 }, { "epoch": 3.6659619450317127, "grad_norm": 0.8190587759017944, "learning_rate": 1.1727357160908978e-06, "loss": 0.7297363877296448, "step": 1734 }, { "epoch": 3.6701902748414374, "grad_norm": 1.230346918106079, "learning_rate": 1.1684446405496052e-06, "loss": 0.8038426637649536, "step": 1736 }, { "epoch": 3.6744186046511627, "grad_norm": 2.0446665287017822, "learning_rate": 1.1642065200128179e-06, "loss": 0.18586766719818115, "step": 1738 }, { "epoch": 3.678646934460888, "grad_norm": 1.1482292413711548, "learning_rate": 1.1600214062932613e-06, "loss": 0.40937185287475586, "step": 1740 }, { "epoch": 3.682875264270613, "grad_norm": 1.0397467613220215, "learning_rate": 1.1558893505556315e-06, "loss": 0.3153565526008606, "step": 1742 }, { "epoch": 3.6871035940803383, "grad_norm": 0.5952998995780945, "learning_rate": 1.1518104033159715e-06, "loss": 0.7531910538673401, "step": 1744 }, { "epoch": 3.6913319238900635, "grad_norm": 0.1816006302833557, "learning_rate": 1.1477846144410493e-06, "loss": 0.39744868874549866, "step": 1746 }, { "epoch": 3.6955602536997887, "grad_norm": 1.9531266689300537, "learning_rate": 1.1438120331477506e-06, "loss": 0.43866536021232605, "step": 1748 }, { "epoch": 3.699788583509514, "grad_norm": 0.9578500986099243, "learning_rate": 1.1398927080024796e-06, "loss": 0.9380204081535339, "step": 1750 }, { "epoch": 3.704016913319239, "grad_norm": 1.5280166864395142, "learning_rate": 1.1360266869205593e-06, "loss": 0.34832873940467834, "step": 1752 }, { "epoch": 3.708245243128964, "grad_norm": 2.1192808151245117, "learning_rate": 1.1322140171656507e-06, "loss": 0.5118672251701355, "step": 1754 }, { "epoch": 3.712473572938689, "grad_norm": 0.5815062522888184, "learning_rate": 1.1284547453491734e-06, "loss": 0.6748945713043213, "step": 1756 }, { "epoch": 3.7167019027484143, "grad_norm": 1.7530949115753174, "learning_rate": 1.1247489174297372e-06, "loss": 0.4095591604709625, "step": 1758 }, { "epoch": 3.7209302325581395, "grad_norm": 0.10765009373426437, "learning_rate": 1.1210965787125743e-06, "loss": 0.4029945135116577, "step": 1760 }, { "epoch": 3.7251585623678647, "grad_norm": 0.7308849096298218, "learning_rate": 1.1174977738489955e-06, "loss": 0.7451815605163574, "step": 1762 }, { "epoch": 3.72938689217759, "grad_norm": 0.6930791735649109, "learning_rate": 1.113952546835835e-06, "loss": 0.4407256543636322, "step": 1764 }, { "epoch": 3.733615221987315, "grad_norm": 1.11472749710083, "learning_rate": 1.1104609410149174e-06, "loss": 0.7251062393188477, "step": 1766 }, { "epoch": 3.7378435517970403, "grad_norm": 1.2439417839050293, "learning_rate": 1.1070229990725262e-06, "loss": 0.6750838160514832, "step": 1768 }, { "epoch": 3.7420718816067655, "grad_norm": 0.1913423389196396, "learning_rate": 1.1036387630388841e-06, "loss": 0.17793335020542145, "step": 1770 }, { "epoch": 3.7463002114164903, "grad_norm": 0.93876051902771, "learning_rate": 1.100308274287636e-06, "loss": 0.42213642597198486, "step": 1772 }, { "epoch": 3.7505285412262155, "grad_norm": 1.9084138870239258, "learning_rate": 1.0970315735353434e-06, "loss": 0.9261226654052734, "step": 1774 }, { "epoch": 3.7547568710359407, "grad_norm": 0.6595978140830994, "learning_rate": 1.0938087008409909e-06, "loss": 0.7292943596839905, "step": 1776 }, { "epoch": 3.758985200845666, "grad_norm": 0.7210798263549805, "learning_rate": 1.0906396956054919e-06, "loss": 0.8342658281326294, "step": 1778 }, { "epoch": 3.763213530655391, "grad_norm": 1.0401872396469116, "learning_rate": 1.0875245965712077e-06, "loss": 0.8826445937156677, "step": 1780 }, { "epoch": 3.7674418604651163, "grad_norm": 0.7973780632019043, "learning_rate": 1.0844634418214763e-06, "loss": 0.7034344673156738, "step": 1782 }, { "epoch": 3.7716701902748415, "grad_norm": 0.9849272966384888, "learning_rate": 1.0814562687801448e-06, "loss": 0.08771834522485733, "step": 1784 }, { "epoch": 3.7758985200845667, "grad_norm": 1.0446085929870605, "learning_rate": 1.0785031142111103e-06, "loss": 0.6218074560165405, "step": 1786 }, { "epoch": 3.780126849894292, "grad_norm": 1.0609960556030273, "learning_rate": 1.075604014217875e-06, "loss": 0.4520392119884491, "step": 1788 }, { "epoch": 3.7843551797040167, "grad_norm": 1.3537647724151611, "learning_rate": 1.0727590042431009e-06, "loss": 0.14752379059791565, "step": 1790 }, { "epoch": 3.7885835095137423, "grad_norm": 0.2052919566631317, "learning_rate": 1.0699681190681777e-06, "loss": 0.6634056568145752, "step": 1792 }, { "epoch": 3.792811839323467, "grad_norm": 1.1699483394622803, "learning_rate": 1.067231392812798e-06, "loss": 0.7590288519859314, "step": 1794 }, { "epoch": 3.7970401691331923, "grad_norm": 1.1282999515533447, "learning_rate": 1.0645488589345396e-06, "loss": 0.4387762248516083, "step": 1796 }, { "epoch": 3.8012684989429175, "grad_norm": 1.2183369398117065, "learning_rate": 1.0619205502284574e-06, "loss": 0.5932766795158386, "step": 1798 }, { "epoch": 3.8054968287526427, "grad_norm": 0.7450636029243469, "learning_rate": 1.0593464988266811e-06, "loss": 0.8486042022705078, "step": 1800 }, { "epoch": 3.809725158562368, "grad_norm": 0.6482730507850647, "learning_rate": 1.0568267361980225e-06, "loss": 0.5628738403320312, "step": 1802 }, { "epoch": 3.813953488372093, "grad_norm": 0.583836555480957, "learning_rate": 1.0543612931475935e-06, "loss": 0.7584009170532227, "step": 1804 }, { "epoch": 3.8181818181818183, "grad_norm": 0.9632444977760315, "learning_rate": 1.0519501998164247e-06, "loss": 0.8446902632713318, "step": 1806 }, { "epoch": 3.822410147991543, "grad_norm": 1.254462480545044, "learning_rate": 1.049593485681101e-06, "loss": 0.15652018785476685, "step": 1808 }, { "epoch": 3.8266384778012688, "grad_norm": 1.1484737396240234, "learning_rate": 1.0472911795533997e-06, "loss": 0.8680257201194763, "step": 1810 }, { "epoch": 3.8308668076109935, "grad_norm": 2.7658069133758545, "learning_rate": 1.045043309579938e-06, "loss": 0.7872487902641296, "step": 1812 }, { "epoch": 3.8350951374207187, "grad_norm": 0.6242542862892151, "learning_rate": 1.0428499032418297e-06, "loss": 0.6809377074241638, "step": 1814 }, { "epoch": 3.839323467230444, "grad_norm": 0.49033528566360474, "learning_rate": 1.0407109873543484e-06, "loss": 0.499438613653183, "step": 1816 }, { "epoch": 3.843551797040169, "grad_norm": 1.332689642906189, "learning_rate": 1.0386265880665996e-06, "loss": 0.480955570936203, "step": 1818 }, { "epoch": 3.8477801268498943, "grad_norm": 0.5686059594154358, "learning_rate": 1.036596730861203e-06, "loss": 0.5239531397819519, "step": 1820 }, { "epoch": 3.8520084566596196, "grad_norm": 0.2690507471561432, "learning_rate": 1.0346214405539783e-06, "loss": 0.5307909846305847, "step": 1822 }, { "epoch": 3.8562367864693448, "grad_norm": 0.5634549856185913, "learning_rate": 1.0327007412936419e-06, "loss": 0.4868367910385132, "step": 1824 }, { "epoch": 3.8604651162790695, "grad_norm": 1.5844804048538208, "learning_rate": 1.0308346565615158e-06, "loss": 0.42393574118614197, "step": 1826 }, { "epoch": 3.864693446088795, "grad_norm": 0.6295269131660461, "learning_rate": 1.0290232091712337e-06, "loss": 0.8385677933692932, "step": 1828 }, { "epoch": 3.86892177589852, "grad_norm": 0.8205349445343018, "learning_rate": 1.0272664212684687e-06, "loss": 0.8098199963569641, "step": 1830 }, { "epoch": 3.873150105708245, "grad_norm": 0.5298824310302734, "learning_rate": 1.025564314330659e-06, "loss": 0.49209269881248474, "step": 1832 }, { "epoch": 3.8773784355179703, "grad_norm": 0.9415776133537292, "learning_rate": 1.0239169091667447e-06, "loss": 0.4232519268989563, "step": 1834 }, { "epoch": 3.8816067653276956, "grad_norm": 0.24776436388492584, "learning_rate": 1.022324225916917e-06, "loss": 0.3875177800655365, "step": 1836 }, { "epoch": 3.8858350951374208, "grad_norm": 0.0747380256652832, "learning_rate": 1.0207862840523672e-06, "loss": 0.40923503041267395, "step": 1838 }, { "epoch": 3.890063424947146, "grad_norm": 0.6147421002388, "learning_rate": 1.0193031023750534e-06, "loss": 0.6663722395896912, "step": 1840 }, { "epoch": 3.894291754756871, "grad_norm": 0.5905871987342834, "learning_rate": 1.017874699017468e-06, "loss": 0.7557142972946167, "step": 1842 }, { "epoch": 3.898520084566596, "grad_norm": 0.6456781029701233, "learning_rate": 1.0165010914424142e-06, "loss": 0.47357022762298584, "step": 1844 }, { "epoch": 3.9027484143763216, "grad_norm": 1.2691642045974731, "learning_rate": 1.015182296442798e-06, "loss": 0.4522860646247864, "step": 1846 }, { "epoch": 3.9069767441860463, "grad_norm": 1.0089086294174194, "learning_rate": 1.0139183301414176e-06, "loss": 0.13496319949626923, "step": 1848 }, { "epoch": 3.9112050739957716, "grad_norm": 0.6533223986625671, "learning_rate": 1.0127092079907682e-06, "loss": 0.704232931137085, "step": 1850 }, { "epoch": 3.9154334038054968, "grad_norm": 0.47021999955177307, "learning_rate": 1.0115549447728551e-06, "loss": 0.48939523100852966, "step": 1852 }, { "epoch": 3.919661733615222, "grad_norm": 0.4720703959465027, "learning_rate": 1.0104555545990088e-06, "loss": 0.7670784592628479, "step": 1854 }, { "epoch": 3.923890063424947, "grad_norm": 0.9229042530059814, "learning_rate": 1.009411050909716e-06, "loss": 0.4503980576992035, "step": 1856 }, { "epoch": 3.9281183932346724, "grad_norm": 0.8781830668449402, "learning_rate": 1.008421446474455e-06, "loss": 0.6185179352760315, "step": 1858 }, { "epoch": 3.9323467230443976, "grad_norm": 2.2009589672088623, "learning_rate": 1.0074867533915367e-06, "loss": 0.31048187613487244, "step": 1860 }, { "epoch": 3.9365750528541223, "grad_norm": 1.511147379875183, "learning_rate": 1.0066069830879593e-06, "loss": 0.6718884706497192, "step": 1862 }, { "epoch": 3.940803382663848, "grad_norm": 0.5847153067588806, "learning_rate": 1.0057821463192687e-06, "loss": 0.7651690244674683, "step": 1864 }, { "epoch": 3.9450317124735728, "grad_norm": 0.640338122844696, "learning_rate": 1.005012253169426e-06, "loss": 0.6931731700897217, "step": 1866 }, { "epoch": 3.949260042283298, "grad_norm": 0.07513075321912766, "learning_rate": 1.0042973130506839e-06, "loss": 0.015569097362458706, "step": 1868 }, { "epoch": 3.953488372093023, "grad_norm": 0.608818769454956, "learning_rate": 1.003637334703472e-06, "loss": 0.8720670938491821, "step": 1870 }, { "epoch": 3.9577167019027484, "grad_norm": 0.7820308804512024, "learning_rate": 1.0030323261962922e-06, "loss": 0.5503110289573669, "step": 1872 }, { "epoch": 3.9619450317124736, "grad_norm": 1.5642873048782349, "learning_rate": 1.002482294925615e-06, "loss": 0.453378826379776, "step": 1874 }, { "epoch": 3.966173361522199, "grad_norm": 0.5773085355758667, "learning_rate": 1.0019872476157952e-06, "loss": 0.7782825827598572, "step": 1876 }, { "epoch": 3.970401691331924, "grad_norm": 2.9013774394989014, "learning_rate": 1.0015471903189834e-06, "loss": 0.3082369863986969, "step": 1878 }, { "epoch": 3.974630021141649, "grad_norm": 0.6316245198249817, "learning_rate": 1.0011621284150583e-06, "loss": 0.4108630418777466, "step": 1880 }, { "epoch": 3.9788583509513744, "grad_norm": 0.9112673401832581, "learning_rate": 1.000832066611556e-06, "loss": 0.715188205242157, "step": 1882 }, { "epoch": 3.983086680761099, "grad_norm": 0.7631689310073853, "learning_rate": 1.0005570089436137e-06, "loss": 0.8756908178329468, "step": 1884 }, { "epoch": 3.9873150105708244, "grad_norm": 0.6057588458061218, "learning_rate": 1.0003369587739234e-06, "loss": 0.6971763372421265, "step": 1886 }, { "epoch": 3.9915433403805496, "grad_norm": 0.5287474989891052, "learning_rate": 1.0001719187926854e-06, "loss": 0.7656105756759644, "step": 1888 }, { "epoch": 3.995771670190275, "grad_norm": 1.1572192907333374, "learning_rate": 1.0000618910175811e-06, "loss": 0.7712121605873108, "step": 1890 }, { "epoch": 4.0, "grad_norm": 0.7201916575431824, "learning_rate": 1.000006876793743e-06, "loss": 0.4180610477924347, "step": 1892 }, { "epoch": 4.0, "step": 1892, "total_flos": 3.554237146892075e+18, "train_loss": 0.8412088291359234, "train_runtime": 19567.1939, "train_samples_per_second": 2.901, "train_steps_per_second": 0.097 } ], "logging_steps": 2, "max_steps": 1892, "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": 3.554237146892075e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }