{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1863, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005367686527106817, "grad_norm": 23.110759972569202, "learning_rate": 5.3475935828877005e-08, "loss": 1.3394, "step": 1 }, { "epoch": 0.0026838432635534087, "grad_norm": 22.925122994004756, "learning_rate": 2.6737967914438503e-07, "loss": 1.3151, "step": 5 }, { "epoch": 0.005367686527106817, "grad_norm": 14.852129539900352, "learning_rate": 5.347593582887701e-07, "loss": 1.2675, "step": 10 }, { "epoch": 0.008051529790660225, "grad_norm": 12.317661286648468, "learning_rate": 8.021390374331551e-07, "loss": 1.1403, "step": 15 }, { "epoch": 0.010735373054213635, "grad_norm": 7.224714479465641, "learning_rate": 1.0695187165775401e-06, "loss": 1.0275, "step": 20 }, { "epoch": 0.013419216317767043, "grad_norm": 3.6449885785262333, "learning_rate": 1.3368983957219254e-06, "loss": 0.9174, "step": 25 }, { "epoch": 0.01610305958132045, "grad_norm": 3.5335700341075187, "learning_rate": 1.6042780748663103e-06, "loss": 0.888, "step": 30 }, { "epoch": 0.01878690284487386, "grad_norm": 3.0479637649374047, "learning_rate": 1.8716577540106954e-06, "loss": 0.8425, "step": 35 }, { "epoch": 0.02147074610842727, "grad_norm": 2.9127033049894204, "learning_rate": 2.1390374331550802e-06, "loss": 0.8536, "step": 40 }, { "epoch": 0.024154589371980676, "grad_norm": 2.955411185718886, "learning_rate": 2.4064171122994653e-06, "loss": 0.8246, "step": 45 }, { "epoch": 0.026838432635534086, "grad_norm": 3.0538864870099256, "learning_rate": 2.673796791443851e-06, "loss": 0.8229, "step": 50 }, { "epoch": 0.029522275899087493, "grad_norm": 3.005959726162912, "learning_rate": 2.9411764705882355e-06, "loss": 0.794, "step": 55 }, { "epoch": 0.0322061191626409, "grad_norm": 2.9698740765231757, "learning_rate": 3.2085561497326205e-06, "loss": 0.7975, "step": 60 }, { "epoch": 0.03488996242619431, "grad_norm": 2.994204087977409, "learning_rate": 3.4759358288770056e-06, "loss": 0.7894, "step": 65 }, { "epoch": 0.03757380568974772, "grad_norm": 3.1033124975809074, "learning_rate": 3.7433155080213907e-06, "loss": 0.7815, "step": 70 }, { "epoch": 0.040257648953301126, "grad_norm": 3.2193535621925085, "learning_rate": 4.010695187165775e-06, "loss": 0.7817, "step": 75 }, { "epoch": 0.04294149221685454, "grad_norm": 3.235830874793306, "learning_rate": 4.2780748663101604e-06, "loss": 0.7612, "step": 80 }, { "epoch": 0.045625335480407946, "grad_norm": 3.13208883853292, "learning_rate": 4.5454545454545455e-06, "loss": 0.7505, "step": 85 }, { "epoch": 0.04830917874396135, "grad_norm": 3.0246804474347773, "learning_rate": 4.812834224598931e-06, "loss": 0.7641, "step": 90 }, { "epoch": 0.05099302200751476, "grad_norm": 3.064409482931746, "learning_rate": 5.0802139037433165e-06, "loss": 0.7431, "step": 95 }, { "epoch": 0.05367686527106817, "grad_norm": 2.9338902877933246, "learning_rate": 5.347593582887702e-06, "loss": 0.7324, "step": 100 }, { "epoch": 0.05636070853462158, "grad_norm": 2.953036769558524, "learning_rate": 5.614973262032086e-06, "loss": 0.7292, "step": 105 }, { "epoch": 0.059044551798174985, "grad_norm": 3.035878743482533, "learning_rate": 5.882352941176471e-06, "loss": 0.7251, "step": 110 }, { "epoch": 0.06172839506172839, "grad_norm": 2.952115899346688, "learning_rate": 6.149732620320856e-06, "loss": 0.7232, "step": 115 }, { "epoch": 0.0644122383252818, "grad_norm": 2.7758740988800326, "learning_rate": 6.417112299465241e-06, "loss": 0.7012, "step": 120 }, { "epoch": 0.06709608158883522, "grad_norm": 2.8578398858160012, "learning_rate": 6.684491978609626e-06, "loss": 0.7323, "step": 125 }, { "epoch": 0.06977992485238863, "grad_norm": 3.0026659384270666, "learning_rate": 6.951871657754011e-06, "loss": 0.702, "step": 130 }, { "epoch": 0.07246376811594203, "grad_norm": 2.818689680172409, "learning_rate": 7.219251336898396e-06, "loss": 0.7305, "step": 135 }, { "epoch": 0.07514761137949544, "grad_norm": 3.0129817059397555, "learning_rate": 7.486631016042781e-06, "loss": 0.6824, "step": 140 }, { "epoch": 0.07783145464304884, "grad_norm": 2.7719382192223367, "learning_rate": 7.754010695187166e-06, "loss": 0.7086, "step": 145 }, { "epoch": 0.08051529790660225, "grad_norm": 3.0117548462737633, "learning_rate": 8.02139037433155e-06, "loss": 0.6987, "step": 150 }, { "epoch": 0.08319914117015566, "grad_norm": 3.117756642769709, "learning_rate": 8.288770053475937e-06, "loss": 0.7029, "step": 155 }, { "epoch": 0.08588298443370908, "grad_norm": 2.753873126647003, "learning_rate": 8.556149732620321e-06, "loss": 0.7149, "step": 160 }, { "epoch": 0.08856682769726248, "grad_norm": 2.80142424622377, "learning_rate": 8.823529411764707e-06, "loss": 0.7061, "step": 165 }, { "epoch": 0.09125067096081589, "grad_norm": 2.907529190221545, "learning_rate": 9.090909090909091e-06, "loss": 0.6934, "step": 170 }, { "epoch": 0.0939345142243693, "grad_norm": 2.814192653475697, "learning_rate": 9.358288770053477e-06, "loss": 0.6944, "step": 175 }, { "epoch": 0.0966183574879227, "grad_norm": 2.8735128063109294, "learning_rate": 9.625668449197861e-06, "loss": 0.7097, "step": 180 }, { "epoch": 0.09930220075147611, "grad_norm": 2.956358157295863, "learning_rate": 9.893048128342247e-06, "loss": 0.6921, "step": 185 }, { "epoch": 0.10198604401502952, "grad_norm": 2.814113309865443, "learning_rate": 9.999920944317846e-06, "loss": 0.7104, "step": 190 }, { "epoch": 0.10466988727858294, "grad_norm": 2.8485042866415835, "learning_rate": 9.99943783531341e-06, "loss": 0.6826, "step": 195 }, { "epoch": 0.10735373054213634, "grad_norm": 2.73567463896316, "learning_rate": 9.998515579512446e-06, "loss": 0.6992, "step": 200 }, { "epoch": 0.11003757380568975, "grad_norm": 2.6995111015489117, "learning_rate": 9.997154257925199e-06, "loss": 0.6864, "step": 205 }, { "epoch": 0.11272141706924316, "grad_norm": 2.7633017806805173, "learning_rate": 9.995353990129115e-06, "loss": 0.6867, "step": 210 }, { "epoch": 0.11540526033279656, "grad_norm": 3.208294819337482, "learning_rate": 9.99311493425834e-06, "loss": 0.6996, "step": 215 }, { "epoch": 0.11808910359634997, "grad_norm": 3.0091543395842884, "learning_rate": 9.99043728698983e-06, "loss": 0.7038, "step": 220 }, { "epoch": 0.12077294685990338, "grad_norm": 2.5985119949576467, "learning_rate": 9.987321283526072e-06, "loss": 0.7013, "step": 225 }, { "epoch": 0.12345679012345678, "grad_norm": 2.60601633452578, "learning_rate": 9.983767197574432e-06, "loss": 0.6871, "step": 230 }, { "epoch": 0.1261406333870102, "grad_norm": 2.7495647322721757, "learning_rate": 9.979775341323097e-06, "loss": 0.6799, "step": 235 }, { "epoch": 0.1288244766505636, "grad_norm": 2.6491986807111134, "learning_rate": 9.975346065413673e-06, "loss": 0.6751, "step": 240 }, { "epoch": 0.13150831991411702, "grad_norm": 2.5726748610622914, "learning_rate": 9.970479758910365e-06, "loss": 0.684, "step": 245 }, { "epoch": 0.13419216317767044, "grad_norm": 2.623805490321599, "learning_rate": 9.965176849265814e-06, "loss": 0.6786, "step": 250 }, { "epoch": 0.13687600644122383, "grad_norm": 2.52007128379157, "learning_rate": 9.959437802283552e-06, "loss": 0.6851, "step": 255 }, { "epoch": 0.13955984970477725, "grad_norm": 2.453625823133244, "learning_rate": 9.953263122077077e-06, "loss": 0.683, "step": 260 }, { "epoch": 0.14224369296833064, "grad_norm": 2.4340394222869604, "learning_rate": 9.946653351025575e-06, "loss": 0.6615, "step": 265 }, { "epoch": 0.14492753623188406, "grad_norm": 2.6147228328901555, "learning_rate": 9.939609069726279e-06, "loss": 0.6714, "step": 270 }, { "epoch": 0.14761137949543746, "grad_norm": 2.6269616055305756, "learning_rate": 9.932130896943477e-06, "loss": 0.666, "step": 275 }, { "epoch": 0.15029522275899088, "grad_norm": 2.4724281775141264, "learning_rate": 9.924219489554145e-06, "loss": 0.662, "step": 280 }, { "epoch": 0.1529790660225443, "grad_norm": 2.5659933678791917, "learning_rate": 9.915875542490257e-06, "loss": 0.6739, "step": 285 }, { "epoch": 0.1556629092860977, "grad_norm": 2.5344597465249135, "learning_rate": 9.907099788677745e-06, "loss": 0.6526, "step": 290 }, { "epoch": 0.1583467525496511, "grad_norm": 2.394122458020706, "learning_rate": 9.897892998972113e-06, "loss": 0.6658, "step": 295 }, { "epoch": 0.1610305958132045, "grad_norm": 2.6297645216038665, "learning_rate": 9.888255982090728e-06, "loss": 0.6731, "step": 300 }, { "epoch": 0.16371443907675792, "grad_norm": 2.4753464250909842, "learning_rate": 9.878189584541783e-06, "loss": 0.6654, "step": 305 }, { "epoch": 0.16639828234031132, "grad_norm": 2.619944978101143, "learning_rate": 9.867694690549943e-06, "loss": 0.6692, "step": 310 }, { "epoch": 0.16908212560386474, "grad_norm": 2.4993316379340427, "learning_rate": 9.85677222197867e-06, "loss": 0.657, "step": 315 }, { "epoch": 0.17176596886741816, "grad_norm": 2.528839012072968, "learning_rate": 9.845423138249254e-06, "loss": 0.6631, "step": 320 }, { "epoch": 0.17444981213097155, "grad_norm": 2.4004766213125253, "learning_rate": 9.833648436256525e-06, "loss": 0.6532, "step": 325 }, { "epoch": 0.17713365539452497, "grad_norm": 2.518586056880346, "learning_rate": 9.821449150281308e-06, "loss": 0.6594, "step": 330 }, { "epoch": 0.17981749865807836, "grad_norm": 2.544140815715216, "learning_rate": 9.808826351899551e-06, "loss": 0.6592, "step": 335 }, { "epoch": 0.18250134192163178, "grad_norm": 2.5245630088604734, "learning_rate": 9.795781149888216e-06, "loss": 0.6292, "step": 340 }, { "epoch": 0.18518518518518517, "grad_norm": 2.5439203470356926, "learning_rate": 9.782314690127867e-06, "loss": 0.6484, "step": 345 }, { "epoch": 0.1878690284487386, "grad_norm": 2.5040989921138874, "learning_rate": 9.768428155502038e-06, "loss": 0.6395, "step": 350 }, { "epoch": 0.19055287171229202, "grad_norm": 2.393601235022955, "learning_rate": 9.754122765793306e-06, "loss": 0.6456, "step": 355 }, { "epoch": 0.1932367149758454, "grad_norm": 2.638262987889092, "learning_rate": 9.739399777576169e-06, "loss": 0.644, "step": 360 }, { "epoch": 0.19592055823939883, "grad_norm": 2.7569549053004883, "learning_rate": 9.72426048410665e-06, "loss": 0.6631, "step": 365 }, { "epoch": 0.19860440150295222, "grad_norm": 2.528928709578554, "learning_rate": 9.70870621520871e-06, "loss": 0.6614, "step": 370 }, { "epoch": 0.20128824476650564, "grad_norm": 2.5235297233746476, "learning_rate": 9.692738337157441e-06, "loss": 0.6277, "step": 375 }, { "epoch": 0.20397208803005903, "grad_norm": 2.3390770252414526, "learning_rate": 9.676358252559034e-06, "loss": 0.6391, "step": 380 }, { "epoch": 0.20665593129361245, "grad_norm": 2.547026548490698, "learning_rate": 9.6595674002276e-06, "loss": 0.6283, "step": 385 }, { "epoch": 0.20933977455716588, "grad_norm": 2.5417374262431514, "learning_rate": 9.642367255058767e-06, "loss": 0.6319, "step": 390 }, { "epoch": 0.21202361782071927, "grad_norm": 2.480085427573015, "learning_rate": 9.624759327900131e-06, "loss": 0.6353, "step": 395 }, { "epoch": 0.2147074610842727, "grad_norm": 2.3235442947827547, "learning_rate": 9.606745165418554e-06, "loss": 0.6284, "step": 400 }, { "epoch": 0.21739130434782608, "grad_norm": 2.7107934555661255, "learning_rate": 9.58832634996429e-06, "loss": 0.6188, "step": 405 }, { "epoch": 0.2200751476113795, "grad_norm": 2.487450305588197, "learning_rate": 9.569504499432005e-06, "loss": 0.6276, "step": 410 }, { "epoch": 0.2227589908749329, "grad_norm": 2.3987193787790915, "learning_rate": 9.550281267118659e-06, "loss": 0.6292, "step": 415 }, { "epoch": 0.22544283413848631, "grad_norm": 2.5508589467624834, "learning_rate": 9.530658341578276e-06, "loss": 0.6218, "step": 420 }, { "epoch": 0.2281266774020397, "grad_norm": 2.4158605522750625, "learning_rate": 9.510637446473633e-06, "loss": 0.6317, "step": 425 }, { "epoch": 0.23081052066559313, "grad_norm": 2.445524594115613, "learning_rate": 9.490220340424844e-06, "loss": 0.6092, "step": 430 }, { "epoch": 0.23349436392914655, "grad_norm": 2.400101432008715, "learning_rate": 9.469408816854898e-06, "loss": 0.6148, "step": 435 }, { "epoch": 0.23617820719269994, "grad_norm": 2.4509172847175287, "learning_rate": 9.448204703832102e-06, "loss": 0.6178, "step": 440 }, { "epoch": 0.23886205045625336, "grad_norm": 2.3235326521619837, "learning_rate": 9.426609863909537e-06, "loss": 0.6053, "step": 445 }, { "epoch": 0.24154589371980675, "grad_norm": 2.5243021146874627, "learning_rate": 9.404626193961427e-06, "loss": 0.6231, "step": 450 }, { "epoch": 0.24422973698336017, "grad_norm": 2.478238946101095, "learning_rate": 9.382255625016527e-06, "loss": 0.6138, "step": 455 }, { "epoch": 0.24691358024691357, "grad_norm": 2.403474222552862, "learning_rate": 9.359500122088511e-06, "loss": 0.616, "step": 460 }, { "epoch": 0.249597423510467, "grad_norm": 2.513962181210709, "learning_rate": 9.336361684003353e-06, "loss": 0.6069, "step": 465 }, { "epoch": 0.2522812667740204, "grad_norm": 2.5903112094260474, "learning_rate": 9.312842343223764e-06, "loss": 0.6051, "step": 470 }, { "epoch": 0.2549651100375738, "grad_norm": 2.6991873658550465, "learning_rate": 9.288944165670651e-06, "loss": 0.6068, "step": 475 }, { "epoch": 0.2576489533011272, "grad_norm": 2.371666862273313, "learning_rate": 9.264669250541658e-06, "loss": 0.6069, "step": 480 }, { "epoch": 0.2603327965646806, "grad_norm": 2.412799032379272, "learning_rate": 9.240019730126764e-06, "loss": 0.6053, "step": 485 }, { "epoch": 0.26301663982823403, "grad_norm": 2.338602369562366, "learning_rate": 9.214997769620998e-06, "loss": 0.6087, "step": 490 }, { "epoch": 0.26570048309178745, "grad_norm": 2.375919425974727, "learning_rate": 9.189605566934235e-06, "loss": 0.5954, "step": 495 }, { "epoch": 0.2683843263553409, "grad_norm": 2.456936633204222, "learning_rate": 9.163845352498141e-06, "loss": 0.5883, "step": 500 }, { "epoch": 0.27106816961889424, "grad_norm": 2.491833775729394, "learning_rate": 9.137719389070259e-06, "loss": 0.6044, "step": 505 }, { "epoch": 0.27375201288244766, "grad_norm": 2.6686273130637406, "learning_rate": 9.111229971535231e-06, "loss": 0.5898, "step": 510 }, { "epoch": 0.2764358561460011, "grad_norm": 2.6523362880972443, "learning_rate": 9.084379426703245e-06, "loss": 0.6047, "step": 515 }, { "epoch": 0.2791196994095545, "grad_norm": 2.3083390370799037, "learning_rate": 9.057170113105622e-06, "loss": 0.5837, "step": 520 }, { "epoch": 0.28180354267310787, "grad_norm": 2.4767833780981525, "learning_rate": 9.029604420787666e-06, "loss": 0.5769, "step": 525 }, { "epoch": 0.2844873859366613, "grad_norm": 2.428461072303662, "learning_rate": 9.001684771098709e-06, "loss": 0.59, "step": 530 }, { "epoch": 0.2871712292002147, "grad_norm": 2.2801805281947165, "learning_rate": 8.973413616479429e-06, "loss": 0.586, "step": 535 }, { "epoch": 0.2898550724637681, "grad_norm": 2.3036211885754683, "learning_rate": 8.944793440246435e-06, "loss": 0.5806, "step": 540 }, { "epoch": 0.29253891572732155, "grad_norm": 2.453752162913539, "learning_rate": 8.915826756374118e-06, "loss": 0.5823, "step": 545 }, { "epoch": 0.2952227589908749, "grad_norm": 2.368914385133046, "learning_rate": 8.88651610927384e-06, "loss": 0.5965, "step": 550 }, { "epoch": 0.29790660225442833, "grad_norm": 2.365826139655829, "learning_rate": 8.856864073570429e-06, "loss": 0.5822, "step": 555 }, { "epoch": 0.30059044551798175, "grad_norm": 2.3899003790290907, "learning_rate": 8.82687325387603e-06, "loss": 0.5793, "step": 560 }, { "epoch": 0.3032742887815352, "grad_norm": 2.549669992054601, "learning_rate": 8.796546284561307e-06, "loss": 0.5783, "step": 565 }, { "epoch": 0.3059581320450886, "grad_norm": 2.4702420198668724, "learning_rate": 8.765885829524059e-06, "loss": 0.5729, "step": 570 }, { "epoch": 0.30864197530864196, "grad_norm": 2.499938786523041, "learning_rate": 8.734894581955208e-06, "loss": 0.5894, "step": 575 }, { "epoch": 0.3113258185721954, "grad_norm": 2.340889756658331, "learning_rate": 8.703575264102245e-06, "loss": 0.5821, "step": 580 }, { "epoch": 0.3140096618357488, "grad_norm": 2.362311637854582, "learning_rate": 8.6719306270301e-06, "loss": 0.5727, "step": 585 }, { "epoch": 0.3166935050993022, "grad_norm": 2.2958777444156926, "learning_rate": 8.639963450379494e-06, "loss": 0.5703, "step": 590 }, { "epoch": 0.3193773483628556, "grad_norm": 2.507179937998802, "learning_rate": 8.607676542122782e-06, "loss": 0.575, "step": 595 }, { "epoch": 0.322061191626409, "grad_norm": 2.423849933926464, "learning_rate": 8.575072738317297e-06, "loss": 0.576, "step": 600 }, { "epoch": 0.3247450348899624, "grad_norm": 2.437623329716623, "learning_rate": 8.542154902856232e-06, "loss": 0.5804, "step": 605 }, { "epoch": 0.32742887815351585, "grad_norm": 2.2115580638755157, "learning_rate": 8.508925927217083e-06, "loss": 0.5576, "step": 610 }, { "epoch": 0.33011272141706927, "grad_norm": 2.2811473595343057, "learning_rate": 8.475388730207662e-06, "loss": 0.5713, "step": 615 }, { "epoch": 0.33279656468062263, "grad_norm": 2.9386402131334157, "learning_rate": 8.441546257709708e-06, "loss": 0.5778, "step": 620 }, { "epoch": 0.33548040794417605, "grad_norm": 2.342067746235464, "learning_rate": 8.407401482420129e-06, "loss": 0.5724, "step": 625 }, { "epoch": 0.33816425120772947, "grad_norm": 2.472976093583451, "learning_rate": 8.372957403589873e-06, "loss": 0.5362, "step": 630 }, { "epoch": 0.3408480944712829, "grad_norm": 2.406810916495276, "learning_rate": 8.33821704676049e-06, "loss": 0.5584, "step": 635 }, { "epoch": 0.3435319377348363, "grad_norm": 2.4216133440185836, "learning_rate": 8.303183463498357e-06, "loss": 0.5695, "step": 640 }, { "epoch": 0.3462157809983897, "grad_norm": 2.495271542527829, "learning_rate": 8.26785973112664e-06, "loss": 0.5451, "step": 645 }, { "epoch": 0.3488996242619431, "grad_norm": 2.2421708661276645, "learning_rate": 8.232248952454978e-06, "loss": 0.5702, "step": 650 }, { "epoch": 0.3515834675254965, "grad_norm": 2.417565948053365, "learning_rate": 8.196354255506937e-06, "loss": 0.5519, "step": 655 }, { "epoch": 0.35426731078904994, "grad_norm": 2.7393100167737034, "learning_rate": 8.160178793245254e-06, "loss": 0.5601, "step": 660 }, { "epoch": 0.3569511540526033, "grad_norm": 2.301896951332559, "learning_rate": 8.12372574329487e-06, "loss": 0.5425, "step": 665 }, { "epoch": 0.3596349973161567, "grad_norm": 2.4244722010442095, "learning_rate": 8.086998307663815e-06, "loss": 0.542, "step": 670 }, { "epoch": 0.36231884057971014, "grad_norm": 2.384385131758698, "learning_rate": 8.049999712461956e-06, "loss": 0.5472, "step": 675 }, { "epoch": 0.36500268384326356, "grad_norm": 2.305607323971358, "learning_rate": 8.012733207617602e-06, "loss": 0.5361, "step": 680 }, { "epoch": 0.367686527106817, "grad_norm": 2.536088265231215, "learning_rate": 7.975202066592038e-06, "loss": 0.5445, "step": 685 }, { "epoch": 0.37037037037037035, "grad_norm": 2.431118654215023, "learning_rate": 7.937409586091996e-06, "loss": 0.5411, "step": 690 }, { "epoch": 0.37305421363392377, "grad_norm": 2.4138272678093586, "learning_rate": 7.899359085780062e-06, "loss": 0.5519, "step": 695 }, { "epoch": 0.3757380568974772, "grad_norm": 2.7314497949142575, "learning_rate": 7.86105390798309e-06, "loss": 0.5095, "step": 700 }, { "epoch": 0.3784219001610306, "grad_norm": 2.400899875222358, "learning_rate": 7.822497417398607e-06, "loss": 0.5371, "step": 705 }, { "epoch": 0.38110574342458403, "grad_norm": 2.3269612477867594, "learning_rate": 7.783693000799263e-06, "loss": 0.5302, "step": 710 }, { "epoch": 0.3837895866881374, "grad_norm": 2.4169567626657433, "learning_rate": 7.744644066735335e-06, "loss": 0.5194, "step": 715 }, { "epoch": 0.3864734299516908, "grad_norm": 2.3153201550362232, "learning_rate": 7.705354045235335e-06, "loss": 0.5305, "step": 720 }, { "epoch": 0.38915727321524424, "grad_norm": 2.467841995467094, "learning_rate": 7.665826387504708e-06, "loss": 0.5329, "step": 725 }, { "epoch": 0.39184111647879766, "grad_norm": 2.2696522280120965, "learning_rate": 7.626064565622684e-06, "loss": 0.5366, "step": 730 }, { "epoch": 0.394524959742351, "grad_norm": 2.2727829847564376, "learning_rate": 7.586072072237291e-06, "loss": 0.512, "step": 735 }, { "epoch": 0.39720880300590444, "grad_norm": 2.3598027996508555, "learning_rate": 7.545852420258566e-06, "loss": 0.5112, "step": 740 }, { "epoch": 0.39989264626945786, "grad_norm": 2.368003064658677, "learning_rate": 7.505409142549987e-06, "loss": 0.5317, "step": 745 }, { "epoch": 0.4025764895330113, "grad_norm": 2.3103462558610177, "learning_rate": 7.464745791618138e-06, "loss": 0.5293, "step": 750 }, { "epoch": 0.4052603327965647, "grad_norm": 2.2786622682912143, "learning_rate": 7.423865939300674e-06, "loss": 0.497, "step": 755 }, { "epoch": 0.40794417606011807, "grad_norm": 2.53934845729529, "learning_rate": 7.382773176452561e-06, "loss": 0.5177, "step": 760 }, { "epoch": 0.4106280193236715, "grad_norm": 2.4684214956918895, "learning_rate": 7.341471112630667e-06, "loss": 0.5076, "step": 765 }, { "epoch": 0.4133118625872249, "grad_norm": 2.4508521497717073, "learning_rate": 7.2999633757766956e-06, "loss": 0.5096, "step": 770 }, { "epoch": 0.41599570585077833, "grad_norm": 2.3678505109019867, "learning_rate": 7.258253611898509e-06, "loss": 0.5056, "step": 775 }, { "epoch": 0.41867954911433175, "grad_norm": 2.2221596182982615, "learning_rate": 7.216345484749876e-06, "loss": 0.522, "step": 780 }, { "epoch": 0.4213633923778851, "grad_norm": 2.139260049879724, "learning_rate": 7.174242675508636e-06, "loss": 0.5005, "step": 785 }, { "epoch": 0.42404723564143854, "grad_norm": 2.3440581886927387, "learning_rate": 7.131948882453361e-06, "loss": 0.513, "step": 790 }, { "epoch": 0.42673107890499196, "grad_norm": 2.4623669294185673, "learning_rate": 7.089467820638491e-06, "loss": 0.5242, "step": 795 }, { "epoch": 0.4294149221685454, "grad_norm": 2.4426138559547312, "learning_rate": 7.0468032215680116e-06, "loss": 0.5235, "step": 800 }, { "epoch": 0.43209876543209874, "grad_norm": 2.3907694140611664, "learning_rate": 7.003958832867681e-06, "loss": 0.4924, "step": 805 }, { "epoch": 0.43478260869565216, "grad_norm": 2.356908207051785, "learning_rate": 6.960938417955841e-06, "loss": 0.5118, "step": 810 }, { "epoch": 0.4374664519592056, "grad_norm": 2.438370840563522, "learning_rate": 6.917745755712839e-06, "loss": 0.5029, "step": 815 }, { "epoch": 0.440150295222759, "grad_norm": 2.3167016934467917, "learning_rate": 6.874384640149101e-06, "loss": 0.5, "step": 820 }, { "epoch": 0.4428341384863124, "grad_norm": 2.4993615280751866, "learning_rate": 6.830858880071859e-06, "loss": 0.505, "step": 825 }, { "epoch": 0.4455179817498658, "grad_norm": 2.5024201225035347, "learning_rate": 6.7871722987505975e-06, "loss": 0.4775, "step": 830 }, { "epoch": 0.4482018250134192, "grad_norm": 2.391911071748609, "learning_rate": 6.743328733581211e-06, "loss": 0.5029, "step": 835 }, { "epoch": 0.45088566827697263, "grad_norm": 2.2256615676510263, "learning_rate": 6.6993320357489396e-06, "loss": 0.4956, "step": 840 }, { "epoch": 0.45356951154052605, "grad_norm": 2.427133491682211, "learning_rate": 6.6551860698900804e-06, "loss": 0.4852, "step": 845 }, { "epoch": 0.4562533548040794, "grad_norm": 2.479546455153262, "learning_rate": 6.610894713752513e-06, "loss": 0.4847, "step": 850 }, { "epoch": 0.45893719806763283, "grad_norm": 2.44396754275896, "learning_rate": 6.566461857855096e-06, "loss": 0.4848, "step": 855 }, { "epoch": 0.46162104133118625, "grad_norm": 2.2998770971513744, "learning_rate": 6.52189140514591e-06, "loss": 0.5043, "step": 860 }, { "epoch": 0.4643048845947397, "grad_norm": 2.3464162117554843, "learning_rate": 6.477187270659444e-06, "loss": 0.4892, "step": 865 }, { "epoch": 0.4669887278582931, "grad_norm": 2.3196241107572644, "learning_rate": 6.432353381172686e-06, "loss": 0.4898, "step": 870 }, { "epoch": 0.46967257112184646, "grad_norm": 2.459308414893301, "learning_rate": 6.387393674860205e-06, "loss": 0.4666, "step": 875 }, { "epoch": 0.4723564143853999, "grad_norm": 2.411953643312491, "learning_rate": 6.3423121009482226e-06, "loss": 0.5031, "step": 880 }, { "epoch": 0.4750402576489533, "grad_norm": 2.2569243344571475, "learning_rate": 6.297112619367721e-06, "loss": 0.4698, "step": 885 }, { "epoch": 0.4777241009125067, "grad_norm": 2.389598726091653, "learning_rate": 6.2517992004066e-06, "loss": 0.4862, "step": 890 }, { "epoch": 0.48040794417606014, "grad_norm": 2.2805769245442202, "learning_rate": 6.2063758243609275e-06, "loss": 0.4729, "step": 895 }, { "epoch": 0.4830917874396135, "grad_norm": 2.4478337689635623, "learning_rate": 6.160846481185326e-06, "loss": 0.4675, "step": 900 }, { "epoch": 0.4857756307031669, "grad_norm": 2.335115752689708, "learning_rate": 6.115215170142481e-06, "loss": 0.479, "step": 905 }, { "epoch": 0.48845947396672035, "grad_norm": 2.434287714107154, "learning_rate": 6.069485899451863e-06, "loss": 0.4693, "step": 910 }, { "epoch": 0.49114331723027377, "grad_norm": 2.3009707355593507, "learning_rate": 6.023662685937643e-06, "loss": 0.4652, "step": 915 }, { "epoch": 0.49382716049382713, "grad_norm": 2.38832033173472, "learning_rate": 5.9777495546758556e-06, "loss": 0.4772, "step": 920 }, { "epoch": 0.49651100375738055, "grad_norm": 2.226744897311866, "learning_rate": 5.9317505386408436e-06, "loss": 0.4663, "step": 925 }, { "epoch": 0.499194847020934, "grad_norm": 2.367817380610977, "learning_rate": 5.885669678350997e-06, "loss": 0.4728, "step": 930 }, { "epoch": 0.5018786902844874, "grad_norm": 2.3478927056419683, "learning_rate": 5.839511021513853e-06, "loss": 0.4758, "step": 935 }, { "epoch": 0.5045625335480408, "grad_norm": 2.318273549772175, "learning_rate": 5.793278622670527e-06, "loss": 0.4563, "step": 940 }, { "epoch": 0.5072463768115942, "grad_norm": 2.186215977425714, "learning_rate": 5.746976542839583e-06, "loss": 0.4707, "step": 945 }, { "epoch": 0.5099302200751477, "grad_norm": 2.3153563181524315, "learning_rate": 5.700608849160307e-06, "loss": 0.4628, "step": 950 }, { "epoch": 0.512614063338701, "grad_norm": 2.2860837953228708, "learning_rate": 5.654179614535457e-06, "loss": 0.4743, "step": 955 }, { "epoch": 0.5152979066022544, "grad_norm": 2.2059779887075206, "learning_rate": 5.607692917273499e-06, "loss": 0.4497, "step": 960 }, { "epoch": 0.5179817498658078, "grad_norm": 2.14636890882503, "learning_rate": 5.561152840730371e-06, "loss": 0.4502, "step": 965 }, { "epoch": 0.5206655931293612, "grad_norm": 2.294300860148226, "learning_rate": 5.514563472950812e-06, "loss": 0.4621, "step": 970 }, { "epoch": 0.5233494363929146, "grad_norm": 2.356049882596888, "learning_rate": 5.46792890630926e-06, "loss": 0.4535, "step": 975 }, { "epoch": 0.5260332796564681, "grad_norm": 2.3168946300960025, "learning_rate": 5.421253237150389e-06, "loss": 0.4558, "step": 980 }, { "epoch": 0.5287171229200215, "grad_norm": 2.3241483546240755, "learning_rate": 5.374540565429288e-06, "loss": 0.4482, "step": 985 }, { "epoch": 0.5314009661835749, "grad_norm": 2.351439191335833, "learning_rate": 5.327794994351321e-06, "loss": 0.4625, "step": 990 }, { "epoch": 0.5340848094471283, "grad_norm": 2.1875725633240473, "learning_rate": 5.281020630011703e-06, "loss": 0.4527, "step": 995 }, { "epoch": 0.5367686527106817, "grad_norm": 2.1471884171455753, "learning_rate": 5.234221581034834e-06, "loss": 0.4328, "step": 1000 }, { "epoch": 0.5394524959742351, "grad_norm": 2.347682490710178, "learning_rate": 5.187401958213391e-06, "loss": 0.4391, "step": 1005 }, { "epoch": 0.5421363392377885, "grad_norm": 2.6737067252166433, "learning_rate": 5.140565874147236e-06, "loss": 0.4606, "step": 1010 }, { "epoch": 0.5448201825013419, "grad_norm": 2.3143970904868123, "learning_rate": 5.093717442882185e-06, "loss": 0.4434, "step": 1015 }, { "epoch": 0.5475040257648953, "grad_norm": 2.192811491479885, "learning_rate": 5.046860779548613e-06, "loss": 0.4447, "step": 1020 }, { "epoch": 0.5501878690284487, "grad_norm": 2.2089396649322723, "learning_rate": 5e-06, "loss": 0.4405, "step": 1025 }, { "epoch": 0.5528717122920022, "grad_norm": 2.4898489440599785, "learning_rate": 4.953139220451386e-06, "loss": 0.4441, "step": 1030 }, { "epoch": 0.5555555555555556, "grad_norm": 2.1769574055024177, "learning_rate": 4.906282557117817e-06, "loss": 0.4389, "step": 1035 }, { "epoch": 0.558239398819109, "grad_norm": 2.2288345498166007, "learning_rate": 4.859434125852764e-06, "loss": 0.4539, "step": 1040 }, { "epoch": 0.5609232420826624, "grad_norm": 2.294217660395531, "learning_rate": 4.812598041786611e-06, "loss": 0.444, "step": 1045 }, { "epoch": 0.5636070853462157, "grad_norm": 2.405213559804565, "learning_rate": 4.765778418965168e-06, "loss": 0.4384, "step": 1050 }, { "epoch": 0.5662909286097692, "grad_norm": 2.287439029821135, "learning_rate": 4.718979369988299e-06, "loss": 0.4302, "step": 1055 }, { "epoch": 0.5689747718733226, "grad_norm": 2.209940083323156, "learning_rate": 4.672205005648681e-06, "loss": 0.4349, "step": 1060 }, { "epoch": 0.571658615136876, "grad_norm": 2.085775397869951, "learning_rate": 4.625459434570712e-06, "loss": 0.4258, "step": 1065 }, { "epoch": 0.5743424584004294, "grad_norm": 2.305735186475395, "learning_rate": 4.578746762849612e-06, "loss": 0.4339, "step": 1070 }, { "epoch": 0.5770263016639828, "grad_norm": 2.292516481711595, "learning_rate": 4.532071093690741e-06, "loss": 0.4256, "step": 1075 }, { "epoch": 0.5797101449275363, "grad_norm": 2.432951243765514, "learning_rate": 4.485436527049189e-06, "loss": 0.4312, "step": 1080 }, { "epoch": 0.5823939881910897, "grad_norm": 2.1804450539341467, "learning_rate": 4.438847159269631e-06, "loss": 0.4179, "step": 1085 }, { "epoch": 0.5850778314546431, "grad_norm": 2.2870488439776917, "learning_rate": 4.392307082726503e-06, "loss": 0.4143, "step": 1090 }, { "epoch": 0.5877616747181964, "grad_norm": 2.493059590364494, "learning_rate": 4.345820385464543e-06, "loss": 0.4334, "step": 1095 }, { "epoch": 0.5904455179817498, "grad_norm": 2.3289175976762464, "learning_rate": 4.299391150839694e-06, "loss": 0.4253, "step": 1100 }, { "epoch": 0.5931293612453032, "grad_norm": 2.3989830865234025, "learning_rate": 4.253023457160418e-06, "loss": 0.4208, "step": 1105 }, { "epoch": 0.5958132045088567, "grad_norm": 2.3227699603834724, "learning_rate": 4.2067213773294745e-06, "loss": 0.4246, "step": 1110 }, { "epoch": 0.5984970477724101, "grad_norm": 2.255884477618153, "learning_rate": 4.16048897848615e-06, "loss": 0.4236, "step": 1115 }, { "epoch": 0.6011808910359635, "grad_norm": 2.2826008434950262, "learning_rate": 4.114330321649004e-06, "loss": 0.4288, "step": 1120 }, { "epoch": 0.6038647342995169, "grad_norm": 2.2022418527394243, "learning_rate": 4.068249461359158e-06, "loss": 0.4211, "step": 1125 }, { "epoch": 0.6065485775630703, "grad_norm": 2.2527693003113494, "learning_rate": 4.022250445324145e-06, "loss": 0.412, "step": 1130 }, { "epoch": 0.6092324208266238, "grad_norm": 2.312675531959431, "learning_rate": 3.976337314062358e-06, "loss": 0.417, "step": 1135 }, { "epoch": 0.6119162640901772, "grad_norm": 2.3713378358296104, "learning_rate": 3.9305141005481385e-06, "loss": 0.399, "step": 1140 }, { "epoch": 0.6146001073537305, "grad_norm": 2.24595822570906, "learning_rate": 3.8847848298575205e-06, "loss": 0.4249, "step": 1145 }, { "epoch": 0.6172839506172839, "grad_norm": 2.1539069679484792, "learning_rate": 3.839153518814677e-06, "loss": 0.4025, "step": 1150 }, { "epoch": 0.6199677938808373, "grad_norm": 2.200782496023517, "learning_rate": 3.7936241756390746e-06, "loss": 0.4081, "step": 1155 }, { "epoch": 0.6226516371443908, "grad_norm": 2.2482447964846286, "learning_rate": 3.748200799593402e-06, "loss": 0.4054, "step": 1160 }, { "epoch": 0.6253354804079442, "grad_norm": 2.1836116896585773, "learning_rate": 3.7028873806322797e-06, "loss": 0.3997, "step": 1165 }, { "epoch": 0.6280193236714976, "grad_norm": 2.1840542950756943, "learning_rate": 3.6576878990517783e-06, "loss": 0.4063, "step": 1170 }, { "epoch": 0.630703166935051, "grad_norm": 2.248686475017599, "learning_rate": 3.6126063251397968e-06, "loss": 0.4083, "step": 1175 }, { "epoch": 0.6333870101986044, "grad_norm": 2.176167273096749, "learning_rate": 3.567646618827315e-06, "loss": 0.3959, "step": 1180 }, { "epoch": 0.6360708534621579, "grad_norm": 2.2132050473786937, "learning_rate": 3.522812729340557e-06, "loss": 0.3995, "step": 1185 }, { "epoch": 0.6387546967257112, "grad_norm": 2.148130147335481, "learning_rate": 3.4781085948540907e-06, "loss": 0.394, "step": 1190 }, { "epoch": 0.6414385399892646, "grad_norm": 2.1383422317634393, "learning_rate": 3.4335381421449056e-06, "loss": 0.4066, "step": 1195 }, { "epoch": 0.644122383252818, "grad_norm": 2.44274157346495, "learning_rate": 3.3891052862474884e-06, "loss": 0.4027, "step": 1200 }, { "epoch": 0.6468062265163714, "grad_norm": 2.1820050351983324, "learning_rate": 3.3448139301099212e-06, "loss": 0.4042, "step": 1205 }, { "epoch": 0.6494900697799249, "grad_norm": 2.3585852937353513, "learning_rate": 3.3006679642510596e-06, "loss": 0.3865, "step": 1210 }, { "epoch": 0.6521739130434783, "grad_norm": 2.338541385448513, "learning_rate": 3.2566712664187907e-06, "loss": 0.4134, "step": 1215 }, { "epoch": 0.6548577563070317, "grad_norm": 2.2164062324386467, "learning_rate": 3.2128277012494046e-06, "loss": 0.3976, "step": 1220 }, { "epoch": 0.6575415995705851, "grad_norm": 2.1733429518505187, "learning_rate": 3.169141119928142e-06, "loss": 0.3931, "step": 1225 }, { "epoch": 0.6602254428341385, "grad_norm": 2.110065764102904, "learning_rate": 3.125615359850902e-06, "loss": 0.3948, "step": 1230 }, { "epoch": 0.6629092860976918, "grad_norm": 2.3272167714466288, "learning_rate": 3.082254244287163e-06, "loss": 0.3961, "step": 1235 }, { "epoch": 0.6655931293612453, "grad_norm": 2.223215402926516, "learning_rate": 3.0390615820441605e-06, "loss": 0.3876, "step": 1240 }, { "epoch": 0.6682769726247987, "grad_norm": 2.26966085226159, "learning_rate": 2.9960411671323215e-06, "loss": 0.391, "step": 1245 }, { "epoch": 0.6709608158883521, "grad_norm": 2.192746796430763, "learning_rate": 2.9531967784319897e-06, "loss": 0.4038, "step": 1250 }, { "epoch": 0.6736446591519055, "grad_norm": 2.314392674212593, "learning_rate": 2.9105321793615106e-06, "loss": 0.4032, "step": 1255 }, { "epoch": 0.6763285024154589, "grad_norm": 2.3264830946407553, "learning_rate": 2.8680511175466384e-06, "loss": 0.3948, "step": 1260 }, { "epoch": 0.6790123456790124, "grad_norm": 2.375498185267021, "learning_rate": 2.8257573244913637e-06, "loss": 0.3917, "step": 1265 }, { "epoch": 0.6816961889425658, "grad_norm": 2.3150498477000023, "learning_rate": 2.783654515250126e-06, "loss": 0.3861, "step": 1270 }, { "epoch": 0.6843800322061192, "grad_norm": 2.219204721793084, "learning_rate": 2.741746388101493e-06, "loss": 0.3936, "step": 1275 }, { "epoch": 0.6870638754696726, "grad_norm": 2.4041046314657697, "learning_rate": 2.700036624223308e-06, "loss": 0.3793, "step": 1280 }, { "epoch": 0.6897477187332259, "grad_norm": 2.419940208841598, "learning_rate": 2.6585288873693355e-06, "loss": 0.3938, "step": 1285 }, { "epoch": 0.6924315619967794, "grad_norm": 2.135182214896721, "learning_rate": 2.6172268235474396e-06, "loss": 0.379, "step": 1290 }, { "epoch": 0.6951154052603328, "grad_norm": 2.209398798302135, "learning_rate": 2.576134060699328e-06, "loss": 0.3871, "step": 1295 }, { "epoch": 0.6977992485238862, "grad_norm": 2.224454024878489, "learning_rate": 2.5352542083818636e-06, "loss": 0.3877, "step": 1300 }, { "epoch": 0.7004830917874396, "grad_norm": 2.197665657140238, "learning_rate": 2.494590857450016e-06, "loss": 0.376, "step": 1305 }, { "epoch": 0.703166935050993, "grad_norm": 2.2482024472928868, "learning_rate": 2.454147579741436e-06, "loss": 0.3965, "step": 1310 }, { "epoch": 0.7058507783145465, "grad_norm": 2.227419822885104, "learning_rate": 2.4139279277627113e-06, "loss": 0.3858, "step": 1315 }, { "epoch": 0.7085346215780999, "grad_norm": 2.1612116182327687, "learning_rate": 2.373935434377316e-06, "loss": 0.3742, "step": 1320 }, { "epoch": 0.7112184648416533, "grad_norm": 2.2776030043981046, "learning_rate": 2.3341736124952924e-06, "loss": 0.3853, "step": 1325 }, { "epoch": 0.7139023081052066, "grad_norm": 2.268375126657082, "learning_rate": 2.294645954764666e-06, "loss": 0.3699, "step": 1330 }, { "epoch": 0.71658615136876, "grad_norm": 2.2357498168710426, "learning_rate": 2.2553559332646675e-06, "loss": 0.3717, "step": 1335 }, { "epoch": 0.7192699946323134, "grad_norm": 2.252470401205595, "learning_rate": 2.216306999200739e-06, "loss": 0.376, "step": 1340 }, { "epoch": 0.7219538378958669, "grad_norm": 2.2612747986853443, "learning_rate": 2.1775025826013953e-06, "loss": 0.3698, "step": 1345 }, { "epoch": 0.7246376811594203, "grad_norm": 2.1965941064581647, "learning_rate": 2.1389460920169105e-06, "loss": 0.3806, "step": 1350 }, { "epoch": 0.7273215244229737, "grad_norm": 2.3845204698608495, "learning_rate": 2.100640914219939e-06, "loss": 0.3861, "step": 1355 }, { "epoch": 0.7300053676865271, "grad_norm": 2.1385016278538425, "learning_rate": 2.062590413908007e-06, "loss": 0.3738, "step": 1360 }, { "epoch": 0.7326892109500805, "grad_norm": 2.332451579285504, "learning_rate": 2.0247979334079646e-06, "loss": 0.3819, "step": 1365 }, { "epoch": 0.735373054213634, "grad_norm": 2.237440412467856, "learning_rate": 1.9872667923823996e-06, "loss": 0.3673, "step": 1370 }, { "epoch": 0.7380568974771873, "grad_norm": 2.239705913805884, "learning_rate": 1.9500002875380458e-06, "loss": 0.3812, "step": 1375 }, { "epoch": 0.7407407407407407, "grad_norm": 2.352837542567985, "learning_rate": 1.9130016923361843e-06, "loss": 0.3773, "step": 1380 }, { "epoch": 0.7434245840042941, "grad_norm": 2.0641031090880957, "learning_rate": 1.8762742567051318e-06, "loss": 0.3689, "step": 1385 }, { "epoch": 0.7461084272678475, "grad_norm": 2.155612970100679, "learning_rate": 1.8398212067547455e-06, "loss": 0.3686, "step": 1390 }, { "epoch": 0.748792270531401, "grad_norm": 2.330836836061548, "learning_rate": 1.8036457444930643e-06, "loss": 0.3725, "step": 1395 }, { "epoch": 0.7514761137949544, "grad_norm": 2.0484588855195076, "learning_rate": 1.7677510475450244e-06, "loss": 0.3578, "step": 1400 }, { "epoch": 0.7541599570585078, "grad_norm": 2.156120575951097, "learning_rate": 1.7321402688733618e-06, "loss": 0.3639, "step": 1405 }, { "epoch": 0.7568438003220612, "grad_norm": 1.9550049410358357, "learning_rate": 1.6968165365016443e-06, "loss": 0.3563, "step": 1410 }, { "epoch": 0.7595276435856146, "grad_norm": 2.0686840366266, "learning_rate": 1.661782953239512e-06, "loss": 0.343, "step": 1415 }, { "epoch": 0.7622114868491681, "grad_norm": 2.3060037219643807, "learning_rate": 1.6270425964101272e-06, "loss": 0.3569, "step": 1420 }, { "epoch": 0.7648953301127214, "grad_norm": 2.1040795195596846, "learning_rate": 1.5925985175798741e-06, "loss": 0.3549, "step": 1425 }, { "epoch": 0.7675791733762748, "grad_norm": 2.122245904621032, "learning_rate": 1.5584537422902923e-06, "loss": 0.3642, "step": 1430 }, { "epoch": 0.7702630166398282, "grad_norm": 1.9864542739911943, "learning_rate": 1.5246112697923389e-06, "loss": 0.3756, "step": 1435 }, { "epoch": 0.7729468599033816, "grad_norm": 2.051986553063843, "learning_rate": 1.4910740727829176e-06, "loss": 0.3642, "step": 1440 }, { "epoch": 0.775630703166935, "grad_norm": 2.2606463357969293, "learning_rate": 1.457845097143769e-06, "loss": 0.3542, "step": 1445 }, { "epoch": 0.7783145464304885, "grad_norm": 2.0719715505765475, "learning_rate": 1.424927261682703e-06, "loss": 0.3488, "step": 1450 }, { "epoch": 0.7809983896940419, "grad_norm": 2.3533811054040275, "learning_rate": 1.3923234578772177e-06, "loss": 0.3628, "step": 1455 }, { "epoch": 0.7836822329575953, "grad_norm": 2.263543662697703, "learning_rate": 1.3600365496205059e-06, "loss": 0.3597, "step": 1460 }, { "epoch": 0.7863660762211487, "grad_norm": 2.2866732577397313, "learning_rate": 1.3280693729699018e-06, "loss": 0.3685, "step": 1465 }, { "epoch": 0.789049919484702, "grad_norm": 1.9800182040905552, "learning_rate": 1.2964247358977567e-06, "loss": 0.3482, "step": 1470 }, { "epoch": 0.7917337627482555, "grad_norm": 2.160414252037185, "learning_rate": 1.265105418044793e-06, "loss": 0.3514, "step": 1475 }, { "epoch": 0.7944176060118089, "grad_norm": 2.1739622467710493, "learning_rate": 1.2341141704759418e-06, "loss": 0.3605, "step": 1480 }, { "epoch": 0.7971014492753623, "grad_norm": 2.0687034435848286, "learning_rate": 1.2034537154386933e-06, "loss": 0.3404, "step": 1485 }, { "epoch": 0.7997852925389157, "grad_norm": 2.1974665421343453, "learning_rate": 1.173126746123972e-06, "loss": 0.3661, "step": 1490 }, { "epoch": 0.8024691358024691, "grad_norm": 2.0881095433825925, "learning_rate": 1.1431359264295717e-06, "loss": 0.3477, "step": 1495 }, { "epoch": 0.8051529790660226, "grad_norm": 2.1145126537022656, "learning_rate": 1.113483890726162e-06, "loss": 0.3623, "step": 1500 }, { "epoch": 0.807836822329576, "grad_norm": 2.096602228166432, "learning_rate": 1.084173243625884e-06, "loss": 0.3512, "step": 1505 }, { "epoch": 0.8105206655931294, "grad_norm": 2.00918141166385, "learning_rate": 1.0552065597535671e-06, "loss": 0.3451, "step": 1510 }, { "epoch": 0.8132045088566827, "grad_norm": 2.0153028062400695, "learning_rate": 1.0265863835205709e-06, "loss": 0.3598, "step": 1515 }, { "epoch": 0.8158883521202361, "grad_norm": 2.2189687378114846, "learning_rate": 9.983152289012926e-07, "loss": 0.3398, "step": 1520 }, { "epoch": 0.8185721953837896, "grad_norm": 2.1326182596624, "learning_rate": 9.70395579212336e-07, "loss": 0.3421, "step": 1525 }, { "epoch": 0.821256038647343, "grad_norm": 2.0826936088627024, "learning_rate": 9.428298868943791e-07, "loss": 0.3651, "step": 1530 }, { "epoch": 0.8239398819108964, "grad_norm": 1.9691104321642503, "learning_rate": 9.15620573296756e-07, "loss": 0.3398, "step": 1535 }, { "epoch": 0.8266237251744498, "grad_norm": 1.9849193731145134, "learning_rate": 8.887700284647699e-07, "loss": 0.3568, "step": 1540 }, { "epoch": 0.8293075684380032, "grad_norm": 2.2755367492353917, "learning_rate": 8.622806109297432e-07, "loss": 0.3447, "step": 1545 }, { "epoch": 0.8319914117015567, "grad_norm": 2.1843021123025794, "learning_rate": 8.361546475018589e-07, "loss": 0.3482, "step": 1550 }, { "epoch": 0.8346752549651101, "grad_norm": 2.1650103652741306, "learning_rate": 8.103944330657665e-07, "loss": 0.3588, "step": 1555 }, { "epoch": 0.8373590982286635, "grad_norm": 2.152542020465542, "learning_rate": 7.850022303790033e-07, "loss": 0.3499, "step": 1560 }, { "epoch": 0.8400429414922168, "grad_norm": 2.0389874782703163, "learning_rate": 7.599802698732356e-07, "loss": 0.3408, "step": 1565 }, { "epoch": 0.8427267847557702, "grad_norm": 2.021118284297251, "learning_rate": 7.353307494583445e-07, "loss": 0.3475, "step": 1570 }, { "epoch": 0.8454106280193237, "grad_norm": 2.056607841144872, "learning_rate": 7.1105583432935e-07, "loss": 0.3439, "step": 1575 }, { "epoch": 0.8480944712828771, "grad_norm": 2.068140196190409, "learning_rate": 6.871576567762373e-07, "loss": 0.3375, "step": 1580 }, { "epoch": 0.8507783145464305, "grad_norm": 2.300624139612673, "learning_rate": 6.63638315996647e-07, "loss": 0.3476, "step": 1585 }, { "epoch": 0.8534621578099839, "grad_norm": 2.2385858714676687, "learning_rate": 6.404998779114912e-07, "loss": 0.3372, "step": 1590 }, { "epoch": 0.8561460010735373, "grad_norm": 1.973212402814584, "learning_rate": 6.177443749834743e-07, "loss": 0.3373, "step": 1595 }, { "epoch": 0.8588298443370908, "grad_norm": 1.9786968800316662, "learning_rate": 5.953738060385761e-07, "loss": 0.3571, "step": 1600 }, { "epoch": 0.8615136876006442, "grad_norm": 1.9675354523408617, "learning_rate": 5.733901360904648e-07, "loss": 0.3464, "step": 1605 }, { "epoch": 0.8641975308641975, "grad_norm": 2.027073956445453, "learning_rate": 5.517952961678997e-07, "loss": 0.3359, "step": 1610 }, { "epoch": 0.8668813741277509, "grad_norm": 2.0402585297594347, "learning_rate": 5.305911831451044e-07, "loss": 0.331, "step": 1615 }, { "epoch": 0.8695652173913043, "grad_norm": 2.1626087079773164, "learning_rate": 5.097796595751564e-07, "loss": 0.3478, "step": 1620 }, { "epoch": 0.8722490606548577, "grad_norm": 2.1148294992033643, "learning_rate": 4.89362553526368e-07, "loss": 0.3536, "step": 1625 }, { "epoch": 0.8749329039184112, "grad_norm": 1.9220569930226101, "learning_rate": 4.6934165842172476e-07, "loss": 0.348, "step": 1630 }, { "epoch": 0.8776167471819646, "grad_norm": 2.0207032937657807, "learning_rate": 4.4971873288134237e-07, "loss": 0.3411, "step": 1635 }, { "epoch": 0.880300590445518, "grad_norm": 1.8962469162993538, "learning_rate": 4.304955005679962e-07, "loss": 0.3367, "step": 1640 }, { "epoch": 0.8829844337090714, "grad_norm": 2.0797413656102495, "learning_rate": 4.1167365003571047e-07, "loss": 0.3448, "step": 1645 }, { "epoch": 0.8856682769726248, "grad_norm": 2.1247816707137455, "learning_rate": 3.9325483458144684e-07, "loss": 0.3444, "step": 1650 }, { "epoch": 0.8883521202361782, "grad_norm": 2.4006636772524463, "learning_rate": 3.752406720998691e-07, "loss": 0.3364, "step": 1655 }, { "epoch": 0.8910359634997316, "grad_norm": 2.071268938017629, "learning_rate": 3.5763274494123424e-07, "loss": 0.3341, "step": 1660 }, { "epoch": 0.893719806763285, "grad_norm": 1.9640199390851907, "learning_rate": 3.404325997723995e-07, "loss": 0.3328, "step": 1665 }, { "epoch": 0.8964036500268384, "grad_norm": 2.0740873638861412, "learning_rate": 3.2364174744096587e-07, "loss": 0.3415, "step": 1670 }, { "epoch": 0.8990874932903918, "grad_norm": 1.8989778664336208, "learning_rate": 3.072616628425601e-07, "loss": 0.3432, "step": 1675 }, { "epoch": 0.9017713365539453, "grad_norm": 1.9734872353668054, "learning_rate": 2.9129378479129e-07, "loss": 0.3383, "step": 1680 }, { "epoch": 0.9044551798174987, "grad_norm": 2.047558212889419, "learning_rate": 2.7573951589335177e-07, "loss": 0.347, "step": 1685 }, { "epoch": 0.9071390230810521, "grad_norm": 2.0344276698492467, "learning_rate": 2.60600222423833e-07, "loss": 0.3309, "step": 1690 }, { "epoch": 0.9098228663446055, "grad_norm": 2.048785971989957, "learning_rate": 2.45877234206694e-07, "loss": 0.3438, "step": 1695 }, { "epoch": 0.9125067096081588, "grad_norm": 2.200847361671446, "learning_rate": 2.3157184449796365e-07, "loss": 0.3368, "step": 1700 }, { "epoch": 0.9151905528717122, "grad_norm": 2.01316266569961, "learning_rate": 2.1768530987213267e-07, "loss": 0.3442, "step": 1705 }, { "epoch": 0.9178743961352657, "grad_norm": 1.9145822539453043, "learning_rate": 2.0421885011178532e-07, "loss": 0.3505, "step": 1710 }, { "epoch": 0.9205582393988191, "grad_norm": 2.1144714054304563, "learning_rate": 1.911736481004489e-07, "loss": 0.3349, "step": 1715 }, { "epoch": 0.9232420826623725, "grad_norm": 2.0981605268272525, "learning_rate": 1.7855084971869385e-07, "loss": 0.3424, "step": 1720 }, { "epoch": 0.9259259259259259, "grad_norm": 2.0968262383390717, "learning_rate": 1.663515637434765e-07, "loss": 0.3471, "step": 1725 }, { "epoch": 0.9286097691894794, "grad_norm": 2.0763624895019333, "learning_rate": 1.5457686175074816e-07, "loss": 0.3361, "step": 1730 }, { "epoch": 0.9312936124530328, "grad_norm": 1.9756207657932199, "learning_rate": 1.432277780213298e-07, "loss": 0.3349, "step": 1735 }, { "epoch": 0.9339774557165862, "grad_norm": 2.119250023700252, "learning_rate": 1.3230530945005704e-07, "loss": 0.3383, "step": 1740 }, { "epoch": 0.9366612989801396, "grad_norm": 1.9692293196300776, "learning_rate": 1.2181041545821727e-07, "loss": 0.336, "step": 1745 }, { "epoch": 0.9393451422436929, "grad_norm": 1.9540830766787798, "learning_rate": 1.1174401790927325e-07, "loss": 0.3401, "step": 1750 }, { "epoch": 0.9420289855072463, "grad_norm": 1.9257788869336692, "learning_rate": 1.0210700102788796e-07, "loss": 0.333, "step": 1755 }, { "epoch": 0.9447128287707998, "grad_norm": 2.006775329335005, "learning_rate": 9.290021132225546e-08, "loss": 0.3464, "step": 1760 }, { "epoch": 0.9473966720343532, "grad_norm": 2.0435171268081658, "learning_rate": 8.412445750974385e-08, "loss": 0.3325, "step": 1765 }, { "epoch": 0.9500805152979066, "grad_norm": 2.023937980091131, "learning_rate": 7.578051044585644e-08, "loss": 0.3327, "step": 1770 }, { "epoch": 0.95276435856146, "grad_norm": 2.0405926009735937, "learning_rate": 6.786910305652373e-08, "loss": 0.3349, "step": 1775 }, { "epoch": 0.9554482018250134, "grad_norm": 1.9920486649415472, "learning_rate": 6.0390930273721e-08, "loss": 0.3272, "step": 1780 }, { "epoch": 0.9581320450885669, "grad_norm": 2.1761486764086517, "learning_rate": 5.334664897442721e-08, "loss": 0.3513, "step": 1785 }, { "epoch": 0.9608158883521203, "grad_norm": 1.966256421179389, "learning_rate": 4.673687792292436e-08, "loss": 0.3264, "step": 1790 }, { "epoch": 0.9634997316156736, "grad_norm": 2.0083028245123713, "learning_rate": 4.0562197716448316e-08, "loss": 0.3303, "step": 1795 }, { "epoch": 0.966183574879227, "grad_norm": 1.9587458286824233, "learning_rate": 3.4823150734186184e-08, "loss": 0.3298, "step": 1800 }, { "epoch": 0.9688674181427804, "grad_norm": 2.0080980579866363, "learning_rate": 2.9520241089636692e-08, "loss": 0.3362, "step": 1805 }, { "epoch": 0.9715512614063339, "grad_norm": 2.198284739864018, "learning_rate": 2.4653934586328365e-08, "loss": 0.3509, "step": 1810 }, { "epoch": 0.9742351046698873, "grad_norm": 1.999951422873387, "learning_rate": 2.022465867690282e-08, "loss": 0.3302, "step": 1815 }, { "epoch": 0.9769189479334407, "grad_norm": 2.151899177368404, "learning_rate": 1.6232802425568683e-08, "loss": 0.3467, "step": 1820 }, { "epoch": 0.9796027911969941, "grad_norm": 1.8566138184488445, "learning_rate": 1.2678716473927821e-08, "loss": 0.3313, "step": 1825 }, { "epoch": 0.9822866344605475, "grad_norm": 1.887709130179612, "learning_rate": 9.562713010171088e-09, "loss": 0.3397, "step": 1830 }, { "epoch": 0.984970477724101, "grad_norm": 1.9062599623387158, "learning_rate": 6.885065741661367e-09, "loss": 0.3287, "step": 1835 }, { "epoch": 0.9876543209876543, "grad_norm": 2.0316140944293153, "learning_rate": 4.646009870885593e-09, "loss": 0.337, "step": 1840 }, { "epoch": 0.9903381642512077, "grad_norm": 1.9272342232343023, "learning_rate": 2.845742074801261e-09, "loss": 0.3342, "step": 1845 }, { "epoch": 0.9930220075147611, "grad_norm": 2.1777366879760165, "learning_rate": 1.484420487553595e-09, "loss": 0.3485, "step": 1850 }, { "epoch": 0.9957058507783145, "grad_norm": 2.00381642147518, "learning_rate": 5.621646865899832e-10, "loss": 0.3348, "step": 1855 }, { "epoch": 0.998389694041868, "grad_norm": 2.0584544197883963, "learning_rate": 7.905568215504921e-11, "loss": 0.3413, "step": 1860 }, { "epoch": 1.0, "eval_runtime": 3.3989, "eval_samples_per_second": 2.942, "eval_steps_per_second": 0.883, "step": 1863 }, { "epoch": 1.0, "step": 1863, "total_flos": 195037149265920.0, "train_loss": 0.0, "train_runtime": 0.0084, "train_samples_per_second": 3564351.228, "train_steps_per_second": 222779.426 } ], "logging_steps": 5, "max_steps": 1863, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 195037149265920.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }