{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 8.0, "eval_steps": 500, "global_step": 22928, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.034891835310537335, "grad_norm": 4.449178218841553, "learning_rate": 4.9784106769016056e-05, "loss": 7.4361, "step": 100 }, { "epoch": 0.06978367062107467, "grad_norm": 4.605655670166016, "learning_rate": 4.95660327983252e-05, "loss": 5.6934, "step": 200 }, { "epoch": 0.104675505931612, "grad_norm": 5.126296520233154, "learning_rate": 4.9347958827634335e-05, "loss": 5.1849, "step": 300 }, { "epoch": 0.13956734124214934, "grad_norm": 5.184763431549072, "learning_rate": 4.912988485694348e-05, "loss": 4.9327, "step": 400 }, { "epoch": 0.17445917655268667, "grad_norm": 4.761885643005371, "learning_rate": 4.891181088625262e-05, "loss": 4.7416, "step": 500 }, { "epoch": 0.209351011863224, "grad_norm": 4.478248596191406, "learning_rate": 4.869373691556176e-05, "loss": 4.5712, "step": 600 }, { "epoch": 0.24424284717376135, "grad_norm": 4.7443928718566895, "learning_rate": 4.84756629448709e-05, "loss": 4.4319, "step": 700 }, { "epoch": 0.2791346824842987, "grad_norm": 4.571919918060303, "learning_rate": 4.8257588974180044e-05, "loss": 4.3216, "step": 800 }, { "epoch": 0.31402651779483604, "grad_norm": 4.504453182220459, "learning_rate": 4.803951500348919e-05, "loss": 4.1818, "step": 900 }, { "epoch": 0.34891835310537334, "grad_norm": 4.749291896820068, "learning_rate": 4.782144103279832e-05, "loss": 4.0893, "step": 1000 }, { "epoch": 0.3838101884159107, "grad_norm": 4.697039604187012, "learning_rate": 4.7603367062107466e-05, "loss": 4.0596, "step": 1100 }, { "epoch": 0.418702023726448, "grad_norm": 4.919949054718018, "learning_rate": 4.738529309141661e-05, "loss": 4.0145, "step": 1200 }, { "epoch": 0.45359385903698535, "grad_norm": 4.816226482391357, "learning_rate": 4.716721912072575e-05, "loss": 3.9097, "step": 1300 }, { "epoch": 0.4884856943475227, "grad_norm": 4.794589519500732, "learning_rate": 4.6949145150034896e-05, "loss": 3.8486, "step": 1400 }, { "epoch": 0.5233775296580601, "grad_norm": 4.941982269287109, "learning_rate": 4.673107117934404e-05, "loss": 3.8414, "step": 1500 }, { "epoch": 0.5582693649685974, "grad_norm": 4.8971452713012695, "learning_rate": 4.6512997208653175e-05, "loss": 3.7677, "step": 1600 }, { "epoch": 0.5931612002791347, "grad_norm": 4.788393974304199, "learning_rate": 4.629492323796232e-05, "loss": 3.7563, "step": 1700 }, { "epoch": 0.6280530355896721, "grad_norm": 8.283535957336426, "learning_rate": 4.607684926727146e-05, "loss": 3.702, "step": 1800 }, { "epoch": 0.6629448709002094, "grad_norm": 4.443343639373779, "learning_rate": 4.5858775296580604e-05, "loss": 3.6575, "step": 1900 }, { "epoch": 0.6978367062107467, "grad_norm": 4.8935956954956055, "learning_rate": 4.564070132588975e-05, "loss": 3.6542, "step": 2000 }, { "epoch": 0.732728541521284, "grad_norm": 4.706109523773193, "learning_rate": 4.542262735519889e-05, "loss": 3.588, "step": 2100 }, { "epoch": 0.7676203768318214, "grad_norm": 5.829479694366455, "learning_rate": 4.520455338450803e-05, "loss": 3.5628, "step": 2200 }, { "epoch": 0.8025122121423587, "grad_norm": 5.121861457824707, "learning_rate": 4.498647941381717e-05, "loss": 3.5284, "step": 2300 }, { "epoch": 0.837404047452896, "grad_norm": 9.078815460205078, "learning_rate": 4.476840544312631e-05, "loss": 3.5192, "step": 2400 }, { "epoch": 0.8722958827634334, "grad_norm": 4.904483318328857, "learning_rate": 4.455033147243545e-05, "loss": 3.4818, "step": 2500 }, { "epoch": 0.9071877180739707, "grad_norm": 4.965977668762207, "learning_rate": 4.433225750174459e-05, "loss": 3.4393, "step": 2600 }, { "epoch": 0.942079553384508, "grad_norm": 4.89396858215332, "learning_rate": 4.4114183531053736e-05, "loss": 3.4231, "step": 2700 }, { "epoch": 0.9769713886950454, "grad_norm": 5.0034661293029785, "learning_rate": 4.389610956036287e-05, "loss": 3.3895, "step": 2800 }, { "epoch": 1.0118632240055827, "grad_norm": 4.820219039916992, "learning_rate": 4.3678035589672015e-05, "loss": 3.2998, "step": 2900 }, { "epoch": 1.0467550593161201, "grad_norm": 4.667869567871094, "learning_rate": 4.345996161898116e-05, "loss": 3.172, "step": 3000 }, { "epoch": 1.0816468946266573, "grad_norm": 4.847691059112549, "learning_rate": 4.32418876482903e-05, "loss": 3.1746, "step": 3100 }, { "epoch": 1.1165387299371947, "grad_norm": 4.929681301116943, "learning_rate": 4.3023813677599444e-05, "loss": 3.1565, "step": 3200 }, { "epoch": 1.1514305652477321, "grad_norm": 5.4113359451293945, "learning_rate": 4.280573970690859e-05, "loss": 3.1381, "step": 3300 }, { "epoch": 1.1863224005582693, "grad_norm": 5.372176647186279, "learning_rate": 4.2587665736217724e-05, "loss": 3.1268, "step": 3400 }, { "epoch": 1.2212142358688067, "grad_norm": 5.134545803070068, "learning_rate": 4.236959176552687e-05, "loss": 3.1067, "step": 3500 }, { "epoch": 1.2561060711793441, "grad_norm": 5.3275861740112305, "learning_rate": 4.215151779483601e-05, "loss": 3.0777, "step": 3600 }, { "epoch": 1.2909979064898813, "grad_norm": 5.151634216308594, "learning_rate": 4.193344382414515e-05, "loss": 3.067, "step": 3700 }, { "epoch": 1.3258897418004187, "grad_norm": 5.169743061065674, "learning_rate": 4.1715369853454296e-05, "loss": 3.0564, "step": 3800 }, { "epoch": 1.3607815771109562, "grad_norm": 4.969324588775635, "learning_rate": 4.149729588276344e-05, "loss": 3.0547, "step": 3900 }, { "epoch": 1.3956734124214933, "grad_norm": 4.806005477905273, "learning_rate": 4.1279221912072576e-05, "loss": 3.0324, "step": 4000 }, { "epoch": 1.4305652477320308, "grad_norm": 5.4942426681518555, "learning_rate": 4.106114794138172e-05, "loss": 3.0307, "step": 4100 }, { "epoch": 1.4654570830425682, "grad_norm": 5.495986461639404, "learning_rate": 4.084307397069086e-05, "loss": 3.0058, "step": 4200 }, { "epoch": 1.5003489183531054, "grad_norm": 4.752720355987549, "learning_rate": 4.0625000000000005e-05, "loss": 2.9856, "step": 4300 }, { "epoch": 1.5352407536636425, "grad_norm": 4.929941654205322, "learning_rate": 4.040692602930914e-05, "loss": 2.9931, "step": 4400 }, { "epoch": 1.5701325889741802, "grad_norm": 4.883072853088379, "learning_rate": 4.0188852058618284e-05, "loss": 2.9824, "step": 4500 }, { "epoch": 1.6050244242847174, "grad_norm": 5.3392333984375, "learning_rate": 3.997077808792743e-05, "loss": 2.9538, "step": 4600 }, { "epoch": 1.6399162595952546, "grad_norm": 5.304770469665527, "learning_rate": 3.9752704117236564e-05, "loss": 2.9584, "step": 4700 }, { "epoch": 1.6748080949057922, "grad_norm": 5.055889129638672, "learning_rate": 3.953463014654571e-05, "loss": 2.9221, "step": 4800 }, { "epoch": 1.7096999302163294, "grad_norm": 5.006368637084961, "learning_rate": 3.931655617585485e-05, "loss": 2.9154, "step": 4900 }, { "epoch": 1.7445917655268666, "grad_norm": 5.258544921875, "learning_rate": 3.909848220516399e-05, "loss": 2.9123, "step": 5000 }, { "epoch": 1.7794836008374042, "grad_norm": 4.940785884857178, "learning_rate": 3.8880408234473136e-05, "loss": 2.8721, "step": 5100 }, { "epoch": 1.8143754361479414, "grad_norm": 5.046368598937988, "learning_rate": 3.866233426378228e-05, "loss": 2.8598, "step": 5200 }, { "epoch": 1.8492672714584786, "grad_norm": 5.59748649597168, "learning_rate": 3.8444260293091416e-05, "loss": 2.8819, "step": 5300 }, { "epoch": 1.8841591067690162, "grad_norm": 5.261348247528076, "learning_rate": 3.822618632240056e-05, "loss": 2.8284, "step": 5400 }, { "epoch": 1.9190509420795534, "grad_norm": 5.169360160827637, "learning_rate": 3.80081123517097e-05, "loss": 2.8456, "step": 5500 }, { "epoch": 1.9539427773900906, "grad_norm": 5.436888694763184, "learning_rate": 3.7790038381018845e-05, "loss": 2.8561, "step": 5600 }, { "epoch": 1.988834612700628, "grad_norm": 5.126554489135742, "learning_rate": 3.757196441032799e-05, "loss": 2.8151, "step": 5700 }, { "epoch": 2.0237264480111654, "grad_norm": 4.704784870147705, "learning_rate": 3.735389043963713e-05, "loss": 2.674, "step": 5800 }, { "epoch": 2.0586182833217026, "grad_norm": 5.37230920791626, "learning_rate": 3.713581646894627e-05, "loss": 2.608, "step": 5900 }, { "epoch": 2.0935101186322402, "grad_norm": 4.852290630340576, "learning_rate": 3.691774249825541e-05, "loss": 2.591, "step": 6000 }, { "epoch": 2.1284019539427774, "grad_norm": 5.700033664703369, "learning_rate": 3.6699668527564554e-05, "loss": 2.5985, "step": 6100 }, { "epoch": 2.1632937892533146, "grad_norm": 5.340079307556152, "learning_rate": 3.64815945568737e-05, "loss": 2.5871, "step": 6200 }, { "epoch": 2.1981856245638522, "grad_norm": 5.0922532081604, "learning_rate": 3.626352058618284e-05, "loss": 2.5762, "step": 6300 }, { "epoch": 2.2330774598743894, "grad_norm": 5.114669322967529, "learning_rate": 3.6045446615491976e-05, "loss": 2.5665, "step": 6400 }, { "epoch": 2.2679692951849266, "grad_norm": 5.286740303039551, "learning_rate": 3.582737264480112e-05, "loss": 2.5635, "step": 6500 }, { "epoch": 2.3028611304954643, "grad_norm": 5.458755016326904, "learning_rate": 3.5609298674110256e-05, "loss": 2.5559, "step": 6600 }, { "epoch": 2.3377529658060014, "grad_norm": 5.574306488037109, "learning_rate": 3.53912247034194e-05, "loss": 2.5386, "step": 6700 }, { "epoch": 2.3726448011165386, "grad_norm": 5.048354148864746, "learning_rate": 3.517315073272854e-05, "loss": 2.5325, "step": 6800 }, { "epoch": 2.407536636427076, "grad_norm": 5.464790344238281, "learning_rate": 3.4955076762037685e-05, "loss": 2.5501, "step": 6900 }, { "epoch": 2.4424284717376135, "grad_norm": 5.763171672821045, "learning_rate": 3.473700279134683e-05, "loss": 2.5496, "step": 7000 }, { "epoch": 2.4773203070481506, "grad_norm": 5.179362773895264, "learning_rate": 3.4518928820655964e-05, "loss": 2.5447, "step": 7100 }, { "epoch": 2.5122121423586883, "grad_norm": 5.075343132019043, "learning_rate": 3.430085484996511e-05, "loss": 2.5568, "step": 7200 }, { "epoch": 2.5471039776692255, "grad_norm": 5.105709552764893, "learning_rate": 3.408278087927425e-05, "loss": 2.5631, "step": 7300 }, { "epoch": 2.5819958129797627, "grad_norm": 5.484874248504639, "learning_rate": 3.3864706908583394e-05, "loss": 2.5462, "step": 7400 }, { "epoch": 2.6168876482903, "grad_norm": 5.008668422698975, "learning_rate": 3.364663293789254e-05, "loss": 2.5169, "step": 7500 }, { "epoch": 2.6517794836008375, "grad_norm": 5.086187362670898, "learning_rate": 3.342855896720168e-05, "loss": 2.5182, "step": 7600 }, { "epoch": 2.6866713189113747, "grad_norm": 5.237493991851807, "learning_rate": 3.3210484996510816e-05, "loss": 2.5152, "step": 7700 }, { "epoch": 2.7215631542219123, "grad_norm": 4.8399977684021, "learning_rate": 3.299241102581996e-05, "loss": 2.5159, "step": 7800 }, { "epoch": 2.7564549895324495, "grad_norm": 5.455721378326416, "learning_rate": 3.27743370551291e-05, "loss": 2.5059, "step": 7900 }, { "epoch": 2.7913468248429867, "grad_norm": 4.843439102172852, "learning_rate": 3.2556263084438245e-05, "loss": 2.5007, "step": 8000 }, { "epoch": 2.826238660153524, "grad_norm": 5.252379417419434, "learning_rate": 3.233818911374739e-05, "loss": 2.4966, "step": 8100 }, { "epoch": 2.8611304954640615, "grad_norm": 4.738300800323486, "learning_rate": 3.212011514305653e-05, "loss": 2.5076, "step": 8200 }, { "epoch": 2.8960223307745987, "grad_norm": 4.630394458770752, "learning_rate": 3.190204117236567e-05, "loss": 2.5125, "step": 8300 }, { "epoch": 2.9309141660851363, "grad_norm": 5.112858772277832, "learning_rate": 3.168396720167481e-05, "loss": 2.496, "step": 8400 }, { "epoch": 2.9658060013956735, "grad_norm": 4.9403510093688965, "learning_rate": 3.146589323098395e-05, "loss": 2.4916, "step": 8500 }, { "epoch": 3.0006978367062107, "grad_norm": 4.983951091766357, "learning_rate": 3.124781926029309e-05, "loss": 2.4925, "step": 8600 }, { "epoch": 3.035589672016748, "grad_norm": 4.399389743804932, "learning_rate": 3.1029745289602233e-05, "loss": 2.27, "step": 8700 }, { "epoch": 3.0704815073272855, "grad_norm": 5.247836589813232, "learning_rate": 3.0811671318911377e-05, "loss": 2.283, "step": 8800 }, { "epoch": 3.1053733426378227, "grad_norm": 5.457115173339844, "learning_rate": 3.059359734822051e-05, "loss": 2.2568, "step": 8900 }, { "epoch": 3.14026517794836, "grad_norm": 4.6203179359436035, "learning_rate": 3.037552337752966e-05, "loss": 2.2618, "step": 9000 }, { "epoch": 3.1751570132588975, "grad_norm": 5.432634353637695, "learning_rate": 3.01574494068388e-05, "loss": 2.2945, "step": 9100 }, { "epoch": 3.2100488485694347, "grad_norm": 5.295199871063232, "learning_rate": 2.9939375436147942e-05, "loss": 2.2687, "step": 9200 }, { "epoch": 3.244940683879972, "grad_norm": 5.510141849517822, "learning_rate": 2.9721301465457085e-05, "loss": 2.2846, "step": 9300 }, { "epoch": 3.2798325191905096, "grad_norm": 5.49964714050293, "learning_rate": 2.950322749476623e-05, "loss": 2.2727, "step": 9400 }, { "epoch": 3.3147243545010467, "grad_norm": 5.006816864013672, "learning_rate": 2.928515352407537e-05, "loss": 2.27, "step": 9500 }, { "epoch": 3.349616189811584, "grad_norm": 4.75443172454834, "learning_rate": 2.9067079553384508e-05, "loss": 2.2896, "step": 9600 }, { "epoch": 3.3845080251221216, "grad_norm": 5.43818473815918, "learning_rate": 2.884900558269365e-05, "loss": 2.2823, "step": 9700 }, { "epoch": 3.4193998604326588, "grad_norm": 5.078537940979004, "learning_rate": 2.8630931612002794e-05, "loss": 2.2689, "step": 9800 }, { "epoch": 3.454291695743196, "grad_norm": 5.591304302215576, "learning_rate": 2.8412857641311934e-05, "loss": 2.2915, "step": 9900 }, { "epoch": 3.4891835310537336, "grad_norm": 5.2217559814453125, "learning_rate": 2.8194783670621077e-05, "loss": 2.268, "step": 10000 }, { "epoch": 3.5240753663642708, "grad_norm": 5.424462795257568, "learning_rate": 2.797670969993022e-05, "loss": 2.2562, "step": 10100 }, { "epoch": 3.558967201674808, "grad_norm": 5.45490837097168, "learning_rate": 2.7758635729239356e-05, "loss": 2.2699, "step": 10200 }, { "epoch": 3.5938590369853456, "grad_norm": 5.29006814956665, "learning_rate": 2.75405617585485e-05, "loss": 2.2875, "step": 10300 }, { "epoch": 3.628750872295883, "grad_norm": 5.640931606292725, "learning_rate": 2.7322487787857642e-05, "loss": 2.277, "step": 10400 }, { "epoch": 3.66364270760642, "grad_norm": 5.791449069976807, "learning_rate": 2.7104413817166786e-05, "loss": 2.289, "step": 10500 }, { "epoch": 3.698534542916957, "grad_norm": 5.233780860900879, "learning_rate": 2.688633984647593e-05, "loss": 2.2559, "step": 10600 }, { "epoch": 3.733426378227495, "grad_norm": 4.809124946594238, "learning_rate": 2.6668265875785072e-05, "loss": 2.2699, "step": 10700 }, { "epoch": 3.768318213538032, "grad_norm": 5.174726963043213, "learning_rate": 2.6450191905094208e-05, "loss": 2.2584, "step": 10800 }, { "epoch": 3.8032100488485696, "grad_norm": 5.181713104248047, "learning_rate": 2.623211793440335e-05, "loss": 2.2426, "step": 10900 }, { "epoch": 3.838101884159107, "grad_norm": 5.212897777557373, "learning_rate": 2.601404396371249e-05, "loss": 2.2257, "step": 11000 }, { "epoch": 3.872993719469644, "grad_norm": 5.191478252410889, "learning_rate": 2.5795969993021634e-05, "loss": 2.2468, "step": 11100 }, { "epoch": 3.907885554780181, "grad_norm": 5.237133979797363, "learning_rate": 2.5577896022330777e-05, "loss": 2.2529, "step": 11200 }, { "epoch": 3.942777390090719, "grad_norm": 5.110697269439697, "learning_rate": 2.535982205163992e-05, "loss": 2.2403, "step": 11300 }, { "epoch": 3.977669225401256, "grad_norm": 5.379474639892578, "learning_rate": 2.5141748080949056e-05, "loss": 2.2432, "step": 11400 }, { "epoch": 4.012561060711794, "grad_norm": 5.239147663116455, "learning_rate": 2.49236741102582e-05, "loss": 2.1658, "step": 11500 }, { "epoch": 4.047452896022331, "grad_norm": 5.401543140411377, "learning_rate": 2.4705600139567343e-05, "loss": 2.0642, "step": 11600 }, { "epoch": 4.082344731332868, "grad_norm": 5.2488322257995605, "learning_rate": 2.4487526168876486e-05, "loss": 2.0671, "step": 11700 }, { "epoch": 4.117236566643405, "grad_norm": 5.270359039306641, "learning_rate": 2.4269452198185625e-05, "loss": 2.0655, "step": 11800 }, { "epoch": 4.152128401953942, "grad_norm": 5.2798614501953125, "learning_rate": 2.4051378227494765e-05, "loss": 2.0595, "step": 11900 }, { "epoch": 4.1870202372644805, "grad_norm": 5.490713119506836, "learning_rate": 2.3833304256803908e-05, "loss": 2.076, "step": 12000 }, { "epoch": 4.221912072575018, "grad_norm": 5.069546699523926, "learning_rate": 2.361523028611305e-05, "loss": 2.0744, "step": 12100 }, { "epoch": 4.256803907885555, "grad_norm": 5.110651016235352, "learning_rate": 2.339715631542219e-05, "loss": 2.058, "step": 12200 }, { "epoch": 4.291695743196092, "grad_norm": 5.666290760040283, "learning_rate": 2.3179082344731334e-05, "loss": 2.111, "step": 12300 }, { "epoch": 4.326587578506629, "grad_norm": 5.498898983001709, "learning_rate": 2.2961008374040477e-05, "loss": 2.0557, "step": 12400 }, { "epoch": 4.361479413817166, "grad_norm": 5.75054407119751, "learning_rate": 2.2742934403349617e-05, "loss": 2.0703, "step": 12500 }, { "epoch": 4.3963712491277045, "grad_norm": 5.280162811279297, "learning_rate": 2.252486043265876e-05, "loss": 2.0588, "step": 12600 }, { "epoch": 4.431263084438242, "grad_norm": 5.701440334320068, "learning_rate": 2.2306786461967903e-05, "loss": 2.0804, "step": 12700 }, { "epoch": 4.466154919748779, "grad_norm": 5.908513069152832, "learning_rate": 2.2088712491277043e-05, "loss": 2.0645, "step": 12800 }, { "epoch": 4.501046755059316, "grad_norm": 4.762182712554932, "learning_rate": 2.1870638520586183e-05, "loss": 2.0615, "step": 12900 }, { "epoch": 4.535938590369853, "grad_norm": 5.06411075592041, "learning_rate": 2.1652564549895326e-05, "loss": 2.0684, "step": 13000 }, { "epoch": 4.57083042568039, "grad_norm": 5.691733360290527, "learning_rate": 2.1434490579204465e-05, "loss": 2.0636, "step": 13100 }, { "epoch": 4.6057222609909285, "grad_norm": 5.261690139770508, "learning_rate": 2.121641660851361e-05, "loss": 2.0679, "step": 13200 }, { "epoch": 4.640614096301466, "grad_norm": 5.58465051651001, "learning_rate": 2.099834263782275e-05, "loss": 2.086, "step": 13300 }, { "epoch": 4.675505931612003, "grad_norm": 5.2169952392578125, "learning_rate": 2.078026866713189e-05, "loss": 2.0703, "step": 13400 }, { "epoch": 4.71039776692254, "grad_norm": 5.576324939727783, "learning_rate": 2.0562194696441034e-05, "loss": 2.0862, "step": 13500 }, { "epoch": 4.745289602233077, "grad_norm": 5.461946964263916, "learning_rate": 2.0344120725750178e-05, "loss": 2.0627, "step": 13600 }, { "epoch": 4.7801814375436145, "grad_norm": 5.098294258117676, "learning_rate": 2.0126046755059317e-05, "loss": 2.0736, "step": 13700 }, { "epoch": 4.815073272854152, "grad_norm": 5.7679853439331055, "learning_rate": 1.990797278436846e-05, "loss": 2.0635, "step": 13800 }, { "epoch": 4.84996510816469, "grad_norm": 5.441159725189209, "learning_rate": 1.96898988136776e-05, "loss": 2.1033, "step": 13900 }, { "epoch": 4.884856943475227, "grad_norm": 6.114187717437744, "learning_rate": 1.947182484298674e-05, "loss": 2.0641, "step": 14000 }, { "epoch": 4.919748778785764, "grad_norm": 5.230809688568115, "learning_rate": 1.9253750872295883e-05, "loss": 2.0742, "step": 14100 }, { "epoch": 4.954640614096301, "grad_norm": 5.573941707611084, "learning_rate": 1.9035676901605026e-05, "loss": 2.0967, "step": 14200 }, { "epoch": 4.9895324494068385, "grad_norm": 5.449982166290283, "learning_rate": 1.8817602930914166e-05, "loss": 2.0524, "step": 14300 }, { "epoch": 5.024424284717377, "grad_norm": 5.071106433868408, "learning_rate": 1.859952896022331e-05, "loss": 1.9743, "step": 14400 }, { "epoch": 5.059316120027914, "grad_norm": 5.510537624359131, "learning_rate": 1.8381454989532452e-05, "loss": 1.8963, "step": 14500 }, { "epoch": 5.094207955338451, "grad_norm": 5.249537467956543, "learning_rate": 1.816338101884159e-05, "loss": 1.9142, "step": 14600 }, { "epoch": 5.129099790648988, "grad_norm": 6.67589807510376, "learning_rate": 1.7945307048150735e-05, "loss": 1.888, "step": 14700 }, { "epoch": 5.163991625959525, "grad_norm": 5.381292819976807, "learning_rate": 1.7727233077459874e-05, "loss": 1.9226, "step": 14800 }, { "epoch": 5.1988834612700625, "grad_norm": 5.443178653717041, "learning_rate": 1.7509159106769018e-05, "loss": 1.901, "step": 14900 }, { "epoch": 5.2337752965806, "grad_norm": 5.7889018058776855, "learning_rate": 1.7291085136078157e-05, "loss": 1.9326, "step": 15000 }, { "epoch": 5.268667131891138, "grad_norm": 5.440788745880127, "learning_rate": 1.70730111653873e-05, "loss": 1.9295, "step": 15100 }, { "epoch": 5.303558967201675, "grad_norm": 5.275712490081787, "learning_rate": 1.685493719469644e-05, "loss": 1.9146, "step": 15200 }, { "epoch": 5.338450802512212, "grad_norm": 5.518808841705322, "learning_rate": 1.6636863224005583e-05, "loss": 1.9308, "step": 15300 }, { "epoch": 5.373342637822749, "grad_norm": 5.810028553009033, "learning_rate": 1.6418789253314726e-05, "loss": 1.9393, "step": 15400 }, { "epoch": 5.4082344731332865, "grad_norm": 5.17830753326416, "learning_rate": 1.6200715282623866e-05, "loss": 1.9166, "step": 15500 }, { "epoch": 5.443126308443825, "grad_norm": 5.424782752990723, "learning_rate": 1.598264131193301e-05, "loss": 1.8713, "step": 15600 }, { "epoch": 5.478018143754362, "grad_norm": 5.202701568603516, "learning_rate": 1.5764567341242152e-05, "loss": 1.9279, "step": 15700 }, { "epoch": 5.512909979064899, "grad_norm": 5.875789642333984, "learning_rate": 1.5546493370551292e-05, "loss": 1.9216, "step": 15800 }, { "epoch": 5.547801814375436, "grad_norm": 5.769129276275635, "learning_rate": 1.532841939986043e-05, "loss": 1.9097, "step": 15900 }, { "epoch": 5.582693649685973, "grad_norm": 5.4025421142578125, "learning_rate": 1.5110345429169576e-05, "loss": 1.9151, "step": 16000 }, { "epoch": 5.617585484996511, "grad_norm": 4.817849636077881, "learning_rate": 1.4892271458478716e-05, "loss": 1.9122, "step": 16100 }, { "epoch": 5.652477320307048, "grad_norm": 5.83222770690918, "learning_rate": 1.4674197487787857e-05, "loss": 1.9219, "step": 16200 }, { "epoch": 5.687369155617586, "grad_norm": 5.329492092132568, "learning_rate": 1.4456123517097e-05, "loss": 1.9142, "step": 16300 }, { "epoch": 5.722260990928123, "grad_norm": 5.5221686363220215, "learning_rate": 1.423804954640614e-05, "loss": 1.9194, "step": 16400 }, { "epoch": 5.75715282623866, "grad_norm": 6.1820197105407715, "learning_rate": 1.4019975575715283e-05, "loss": 1.937, "step": 16500 }, { "epoch": 5.792044661549197, "grad_norm": 5.7394232749938965, "learning_rate": 1.3801901605024425e-05, "loss": 1.919, "step": 16600 }, { "epoch": 5.826936496859735, "grad_norm": 5.4087042808532715, "learning_rate": 1.3583827634333568e-05, "loss": 1.9118, "step": 16700 }, { "epoch": 5.861828332170272, "grad_norm": 5.745779037475586, "learning_rate": 1.3365753663642708e-05, "loss": 1.934, "step": 16800 }, { "epoch": 5.89672016748081, "grad_norm": 5.784609794616699, "learning_rate": 1.314767969295185e-05, "loss": 1.9248, "step": 16900 }, { "epoch": 5.931612002791347, "grad_norm": 7.318721294403076, "learning_rate": 1.2929605722260992e-05, "loss": 1.9192, "step": 17000 }, { "epoch": 5.966503838101884, "grad_norm": 5.4304304122924805, "learning_rate": 1.2711531751570133e-05, "loss": 1.948, "step": 17100 }, { "epoch": 6.001395673412421, "grad_norm": 5.5656609535217285, "learning_rate": 1.2493457780879275e-05, "loss": 1.9194, "step": 17200 }, { "epoch": 6.036287508722959, "grad_norm": 5.588869094848633, "learning_rate": 1.2275383810188416e-05, "loss": 1.78, "step": 17300 }, { "epoch": 6.071179344033496, "grad_norm": 5.662446975708008, "learning_rate": 1.2057309839497558e-05, "loss": 1.7815, "step": 17400 }, { "epoch": 6.106071179344034, "grad_norm": 5.681488037109375, "learning_rate": 1.18392358688067e-05, "loss": 1.7902, "step": 17500 }, { "epoch": 6.140963014654571, "grad_norm": 5.237543106079102, "learning_rate": 1.162116189811584e-05, "loss": 1.7949, "step": 17600 }, { "epoch": 6.175854849965108, "grad_norm": 6.3692474365234375, "learning_rate": 1.1403087927424982e-05, "loss": 1.7712, "step": 17700 }, { "epoch": 6.210746685275645, "grad_norm": 5.9078049659729, "learning_rate": 1.1185013956734125e-05, "loss": 1.7964, "step": 17800 }, { "epoch": 6.245638520586183, "grad_norm": 5.628890037536621, "learning_rate": 1.0966939986043266e-05, "loss": 1.7937, "step": 17900 }, { "epoch": 6.28053035589672, "grad_norm": 5.680924415588379, "learning_rate": 1.074886601535241e-05, "loss": 1.8011, "step": 18000 }, { "epoch": 6.315422191207258, "grad_norm": 5.3683857917785645, "learning_rate": 1.053079204466155e-05, "loss": 1.8093, "step": 18100 }, { "epoch": 6.350314026517795, "grad_norm": 6.106055736541748, "learning_rate": 1.031271807397069e-05, "loss": 1.8021, "step": 18200 }, { "epoch": 6.385205861828332, "grad_norm": 5.841535568237305, "learning_rate": 1.0094644103279834e-05, "loss": 1.8266, "step": 18300 }, { "epoch": 6.4200976971388695, "grad_norm": 5.864353179931641, "learning_rate": 9.876570132588975e-06, "loss": 1.8075, "step": 18400 }, { "epoch": 6.454989532449407, "grad_norm": 8.195747375488281, "learning_rate": 9.658496161898117e-06, "loss": 1.8123, "step": 18500 }, { "epoch": 6.489881367759944, "grad_norm": 6.448851585388184, "learning_rate": 9.440422191207258e-06, "loss": 1.7956, "step": 18600 }, { "epoch": 6.524773203070481, "grad_norm": 5.370660305023193, "learning_rate": 9.2223482205164e-06, "loss": 1.7862, "step": 18700 }, { "epoch": 6.559665038381019, "grad_norm": 5.711855411529541, "learning_rate": 9.00427424982554e-06, "loss": 1.8082, "step": 18800 }, { "epoch": 6.594556873691556, "grad_norm": 5.534999847412109, "learning_rate": 8.786200279134684e-06, "loss": 1.8117, "step": 18900 }, { "epoch": 6.6294487090020935, "grad_norm": 5.1350789070129395, "learning_rate": 8.568126308443825e-06, "loss": 1.8072, "step": 19000 }, { "epoch": 6.664340544312631, "grad_norm": 5.525078773498535, "learning_rate": 8.350052337752965e-06, "loss": 1.7891, "step": 19100 }, { "epoch": 6.699232379623168, "grad_norm": 5.587681293487549, "learning_rate": 8.131978367062108e-06, "loss": 1.786, "step": 19200 }, { "epoch": 6.734124214933706, "grad_norm": 5.702240467071533, "learning_rate": 7.91390439637125e-06, "loss": 1.8239, "step": 19300 }, { "epoch": 6.769016050244243, "grad_norm": 6.304993152618408, "learning_rate": 7.695830425680391e-06, "loss": 1.8181, "step": 19400 }, { "epoch": 6.80390788555478, "grad_norm": 5.786768913269043, "learning_rate": 7.477756454989533e-06, "loss": 1.8127, "step": 19500 }, { "epoch": 6.8387997208653175, "grad_norm": 5.68336820602417, "learning_rate": 7.2596824842986745e-06, "loss": 1.7917, "step": 19600 }, { "epoch": 6.873691556175855, "grad_norm": 5.827804088592529, "learning_rate": 7.041608513607816e-06, "loss": 1.8309, "step": 19700 }, { "epoch": 6.908583391486392, "grad_norm": 5.98842716217041, "learning_rate": 6.823534542916958e-06, "loss": 1.7808, "step": 19800 }, { "epoch": 6.943475226796929, "grad_norm": 5.252569198608398, "learning_rate": 6.6054605722261e-06, "loss": 1.8115, "step": 19900 }, { "epoch": 6.978367062107467, "grad_norm": 5.1013288497924805, "learning_rate": 6.38738660153524e-06, "loss": 1.7922, "step": 20000 }, { "epoch": 7.013258897418004, "grad_norm": 5.664073467254639, "learning_rate": 6.169312630844383e-06, "loss": 1.7694, "step": 20100 }, { "epoch": 7.0481507327285415, "grad_norm": 5.690623760223389, "learning_rate": 5.951238660153524e-06, "loss": 1.7241, "step": 20200 }, { "epoch": 7.083042568039079, "grad_norm": 5.286320209503174, "learning_rate": 5.733164689462666e-06, "loss": 1.7105, "step": 20300 }, { "epoch": 7.117934403349616, "grad_norm": 5.791104793548584, "learning_rate": 5.515090718771808e-06, "loss": 1.7085, "step": 20400 }, { "epoch": 7.152826238660153, "grad_norm": 5.083521366119385, "learning_rate": 5.297016748080949e-06, "loss": 1.7011, "step": 20500 }, { "epoch": 7.187718073970691, "grad_norm": 5.443909645080566, "learning_rate": 5.078942777390091e-06, "loss": 1.7239, "step": 20600 }, { "epoch": 7.222609909281228, "grad_norm": 6.203304767608643, "learning_rate": 4.8608688066992325e-06, "loss": 1.7177, "step": 20700 }, { "epoch": 7.257501744591766, "grad_norm": 6.1620564460754395, "learning_rate": 4.642794836008374e-06, "loss": 1.6979, "step": 20800 }, { "epoch": 7.292393579902303, "grad_norm": 6.96720027923584, "learning_rate": 4.424720865317516e-06, "loss": 1.7266, "step": 20900 }, { "epoch": 7.32728541521284, "grad_norm": 6.198672771453857, "learning_rate": 4.206646894626658e-06, "loss": 1.7106, "step": 21000 }, { "epoch": 7.362177250523377, "grad_norm": 5.367521286010742, "learning_rate": 3.9885729239358e-06, "loss": 1.7188, "step": 21100 }, { "epoch": 7.397069085833915, "grad_norm": 5.912238597869873, "learning_rate": 3.770498953244941e-06, "loss": 1.7194, "step": 21200 }, { "epoch": 7.431960921144452, "grad_norm": 5.624551296234131, "learning_rate": 3.5524249825540826e-06, "loss": 1.7169, "step": 21300 }, { "epoch": 7.46685275645499, "grad_norm": 5.592011451721191, "learning_rate": 3.3343510118632245e-06, "loss": 1.7247, "step": 21400 }, { "epoch": 7.501744591765527, "grad_norm": 5.727781295776367, "learning_rate": 3.116277041172366e-06, "loss": 1.7231, "step": 21500 }, { "epoch": 7.536636427076064, "grad_norm": 5.530336856842041, "learning_rate": 2.8982030704815073e-06, "loss": 1.7057, "step": 21600 }, { "epoch": 7.571528262386601, "grad_norm": 6.076034069061279, "learning_rate": 2.680129099790649e-06, "loss": 1.7196, "step": 21700 }, { "epoch": 7.606420097697139, "grad_norm": 5.994781017303467, "learning_rate": 2.462055129099791e-06, "loss": 1.7241, "step": 21800 }, { "epoch": 7.641311933007676, "grad_norm": 5.7654948234558105, "learning_rate": 2.2439811584089323e-06, "loss": 1.7211, "step": 21900 }, { "epoch": 7.676203768318214, "grad_norm": 5.507397174835205, "learning_rate": 2.025907187718074e-06, "loss": 1.7044, "step": 22000 }, { "epoch": 7.711095603628751, "grad_norm": 5.571853160858154, "learning_rate": 1.8078332170272158e-06, "loss": 1.7384, "step": 22100 }, { "epoch": 7.745987438939288, "grad_norm": 5.2521867752075195, "learning_rate": 1.5897592463363572e-06, "loss": 1.7174, "step": 22200 }, { "epoch": 7.780879274249825, "grad_norm": 26.5225887298584, "learning_rate": 1.371685275645499e-06, "loss": 1.7183, "step": 22300 }, { "epoch": 7.815771109560363, "grad_norm": 6.7133307456970215, "learning_rate": 1.1536113049546406e-06, "loss": 1.7281, "step": 22400 }, { "epoch": 7.8506629448709, "grad_norm": 5.532526016235352, "learning_rate": 9.355373342637824e-07, "loss": 1.7132, "step": 22500 }, { "epoch": 7.885554780181438, "grad_norm": 5.792304992675781, "learning_rate": 7.17463363572924e-07, "loss": 1.6923, "step": 22600 }, { "epoch": 7.920446615491975, "grad_norm": 6.1261210441589355, "learning_rate": 4.993893928820656e-07, "loss": 1.7188, "step": 22700 }, { "epoch": 7.955338450802512, "grad_norm": 5.306552410125732, "learning_rate": 2.8131542219120726e-07, "loss": 1.7141, "step": 22800 }, { "epoch": 7.990230286113049, "grad_norm": 5.88728141784668, "learning_rate": 6.324145150034892e-08, "loss": 1.7307, "step": 22900 } ], "logging_steps": 100, "max_steps": 22928, "num_input_tokens_seen": 0, "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 50, "trial_name": null, "trial_params": null }