{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4706254289173163, "eval_steps": 500, "global_step": 30517, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004780741323340042, "grad_norm": 3.1866345405578613, "learning_rate": 1.0157273918741808e-06, "loss": 1.194, "step": 31 }, { "epoch": 0.0009561482646680084, "grad_norm": 1.7708723545074463, "learning_rate": 2.0314547837483616e-06, "loss": 1.1124, "step": 62 }, { "epoch": 0.0014342223970020126, "grad_norm": 1.6835601329803467, "learning_rate": 3.0471821756225426e-06, "loss": 1.0585, "step": 93 }, { "epoch": 0.0019122965293360168, "grad_norm": 1.642537236213684, "learning_rate": 4.062909567496723e-06, "loss": 1.0213, "step": 124 }, { "epoch": 0.002390370661670021, "grad_norm": 1.8476150035858154, "learning_rate": 5.078636959370905e-06, "loss": 1.0024, "step": 155 }, { "epoch": 0.0028684447940040252, "grad_norm": 1.96336829662323, "learning_rate": 6.094364351245085e-06, "loss": 0.9938, "step": 186 }, { "epoch": 0.0033465189263380294, "grad_norm": 1.8158528804779053, "learning_rate": 7.110091743119267e-06, "loss": 0.969, "step": 217 }, { "epoch": 0.0038245930586720336, "grad_norm": 1.9796783924102783, "learning_rate": 8.125819134993446e-06, "loss": 0.9573, "step": 248 }, { "epoch": 0.004302667191006038, "grad_norm": 1.8192514181137085, "learning_rate": 9.141546526867629e-06, "loss": 0.9498, "step": 279 }, { "epoch": 0.004780741323340042, "grad_norm": 2.1396358013153076, "learning_rate": 1.015727391874181e-05, "loss": 0.9294, "step": 310 }, { "epoch": 0.005258815455674046, "grad_norm": 2.0807156562805176, "learning_rate": 1.117300131061599e-05, "loss": 0.9186, "step": 341 }, { "epoch": 0.0057368895880080505, "grad_norm": 2.002887010574341, "learning_rate": 1.218872870249017e-05, "loss": 0.9149, "step": 372 }, { "epoch": 0.006214963720342055, "grad_norm": 2.240675687789917, "learning_rate": 1.3204456094364351e-05, "loss": 0.9139, "step": 403 }, { "epoch": 0.006693037852676059, "grad_norm": 1.9016591310501099, "learning_rate": 1.4220183486238533e-05, "loss": 0.8946, "step": 434 }, { "epoch": 0.007171111985010063, "grad_norm": 1.6729310750961304, "learning_rate": 1.5235910878112714e-05, "loss": 0.8959, "step": 465 }, { "epoch": 0.007649186117344067, "grad_norm": 2.2607779502868652, "learning_rate": 1.6251638269986893e-05, "loss": 0.8847, "step": 496 }, { "epoch": 0.00812726024967807, "grad_norm": 1.699507236480713, "learning_rate": 1.7267365661861077e-05, "loss": 0.8773, "step": 527 }, { "epoch": 0.008605334382012076, "grad_norm": 1.93502938747406, "learning_rate": 1.8283093053735257e-05, "loss": 0.8773, "step": 558 }, { "epoch": 0.009083408514346079, "grad_norm": 2.1234281063079834, "learning_rate": 1.9298820445609438e-05, "loss": 0.8669, "step": 589 }, { "epoch": 0.009561482646680084, "grad_norm": 1.7465944290161133, "learning_rate": 2.031454783748362e-05, "loss": 0.8536, "step": 620 }, { "epoch": 0.010039556779014087, "grad_norm": 1.7039932012557983, "learning_rate": 2.13302752293578e-05, "loss": 0.8624, "step": 651 }, { "epoch": 0.010517630911348093, "grad_norm": 1.551837682723999, "learning_rate": 2.234600262123198e-05, "loss": 0.8555, "step": 682 }, { "epoch": 0.010995705043682096, "grad_norm": 1.7622497081756592, "learning_rate": 2.336173001310616e-05, "loss": 0.8475, "step": 713 }, { "epoch": 0.011473779176016101, "grad_norm": 2.000936269760132, "learning_rate": 2.437745740498034e-05, "loss": 0.852, "step": 744 }, { "epoch": 0.011951853308350104, "grad_norm": 1.6770379543304443, "learning_rate": 2.5393184796854525e-05, "loss": 0.8455, "step": 775 }, { "epoch": 0.01242992744068411, "grad_norm": 1.746506929397583, "learning_rate": 2.6408912188728702e-05, "loss": 0.8406, "step": 806 }, { "epoch": 0.012908001573018113, "grad_norm": 1.507759690284729, "learning_rate": 2.7424639580602886e-05, "loss": 0.8556, "step": 837 }, { "epoch": 0.013386075705352118, "grad_norm": 1.6984492540359497, "learning_rate": 2.8440366972477066e-05, "loss": 0.8281, "step": 868 }, { "epoch": 0.013864149837686121, "grad_norm": 1.5145736932754517, "learning_rate": 2.9456094364351244e-05, "loss": 0.8359, "step": 899 }, { "epoch": 0.014342223970020126, "grad_norm": 1.5700000524520874, "learning_rate": 3.0471821756225428e-05, "loss": 0.8305, "step": 930 }, { "epoch": 0.01482029810235413, "grad_norm": 1.6657596826553345, "learning_rate": 3.148754914809961e-05, "loss": 0.8263, "step": 961 }, { "epoch": 0.015298372234688135, "grad_norm": 1.527628779411316, "learning_rate": 3.2503276539973785e-05, "loss": 0.8318, "step": 992 }, { "epoch": 0.015776446367022138, "grad_norm": 1.8353967666625977, "learning_rate": 3.351900393184797e-05, "loss": 0.8192, "step": 1023 }, { "epoch": 0.01625452049935614, "grad_norm": 1.2118042707443237, "learning_rate": 3.453473132372215e-05, "loss": 0.819, "step": 1054 }, { "epoch": 0.016732594631690145, "grad_norm": 1.3235970735549927, "learning_rate": 3.555045871559633e-05, "loss": 0.8176, "step": 1085 }, { "epoch": 0.01721066876402415, "grad_norm": 1.6729888916015625, "learning_rate": 3.6566186107470514e-05, "loss": 0.8202, "step": 1116 }, { "epoch": 0.017688742896358155, "grad_norm": 1.3251298666000366, "learning_rate": 3.7581913499344695e-05, "loss": 0.8104, "step": 1147 }, { "epoch": 0.018166817028692158, "grad_norm": 1.5231342315673828, "learning_rate": 3.8597640891218876e-05, "loss": 0.8113, "step": 1178 }, { "epoch": 0.01864489116102616, "grad_norm": 1.3263883590698242, "learning_rate": 3.9613368283093056e-05, "loss": 0.7981, "step": 1209 }, { "epoch": 0.019122965293360168, "grad_norm": 1.317791223526001, "learning_rate": 4.062909567496724e-05, "loss": 0.7962, "step": 1240 }, { "epoch": 0.01960103942569417, "grad_norm": 1.566698670387268, "learning_rate": 4.164482306684142e-05, "loss": 0.8072, "step": 1271 }, { "epoch": 0.020079113558028175, "grad_norm": 1.2935110330581665, "learning_rate": 4.26605504587156e-05, "loss": 0.7818, "step": 1302 }, { "epoch": 0.020557187690362178, "grad_norm": 1.336227536201477, "learning_rate": 4.367627785058978e-05, "loss": 0.7917, "step": 1333 }, { "epoch": 0.021035261822696185, "grad_norm": 1.5656548738479614, "learning_rate": 4.469200524246396e-05, "loss": 0.7785, "step": 1364 }, { "epoch": 0.02151333595503019, "grad_norm": 1.5208159685134888, "learning_rate": 4.570773263433814e-05, "loss": 0.7839, "step": 1395 }, { "epoch": 0.02199141008736419, "grad_norm": 1.4816375970840454, "learning_rate": 4.672346002621232e-05, "loss": 0.7789, "step": 1426 }, { "epoch": 0.022469484219698195, "grad_norm": 1.402166485786438, "learning_rate": 4.77391874180865e-05, "loss": 0.7803, "step": 1457 }, { "epoch": 0.022947558352032202, "grad_norm": 1.2986265420913696, "learning_rate": 4.875491480996068e-05, "loss": 0.7739, "step": 1488 }, { "epoch": 0.023425632484366205, "grad_norm": 1.3171271085739136, "learning_rate": 4.977064220183487e-05, "loss": 0.7694, "step": 1519 }, { "epoch": 0.02390370661670021, "grad_norm": 1.4870030879974365, "learning_rate": 4.9999915451558777e-05, "loss": 0.7663, "step": 1550 }, { "epoch": 0.024381780749034212, "grad_norm": 1.7419476509094238, "learning_rate": 4.999955597496219e-05, "loss": 0.7731, "step": 1581 }, { "epoch": 0.02485985488136822, "grad_norm": 1.109238624572754, "learning_rate": 4.9998914381774255e-05, "loss": 0.7704, "step": 1612 }, { "epoch": 0.025337929013702222, "grad_norm": 1.3478920459747314, "learning_rate": 4.999799067923527e-05, "loss": 0.7723, "step": 1643 }, { "epoch": 0.025816003146036225, "grad_norm": 1.2739650011062622, "learning_rate": 4.999678487776908e-05, "loss": 0.7699, "step": 1674 }, { "epoch": 0.02629407727837023, "grad_norm": 1.3892935514450073, "learning_rate": 4.9995296990983006e-05, "loss": 0.7709, "step": 1705 }, { "epoch": 0.026772151410704235, "grad_norm": 1.2031512260437012, "learning_rate": 4.999352703566763e-05, "loss": 0.7557, "step": 1736 }, { "epoch": 0.02725022554303824, "grad_norm": 1.185471773147583, "learning_rate": 4.999147503179668e-05, "loss": 0.7645, "step": 1767 }, { "epoch": 0.027728299675372242, "grad_norm": 1.2331740856170654, "learning_rate": 4.998914100252672e-05, "loss": 0.7655, "step": 1798 }, { "epoch": 0.028206373807706245, "grad_norm": 1.1817049980163574, "learning_rate": 4.998652497419696e-05, "loss": 0.7617, "step": 1829 }, { "epoch": 0.028684447940040252, "grad_norm": 1.2225860357284546, "learning_rate": 4.9983626976328927e-05, "loss": 0.7558, "step": 1860 }, { "epoch": 0.029162522072374256, "grad_norm": 1.6452528238296509, "learning_rate": 4.998044704162613e-05, "loss": 0.7566, "step": 1891 }, { "epoch": 0.02964059620470826, "grad_norm": 1.3764828443527222, "learning_rate": 4.9976985205973705e-05, "loss": 0.7545, "step": 1922 }, { "epoch": 0.030118670337042262, "grad_norm": 1.6581465005874634, "learning_rate": 4.997324150843799e-05, "loss": 0.7519, "step": 1953 }, { "epoch": 0.03059674446937627, "grad_norm": 1.1065036058425903, "learning_rate": 4.99692159912661e-05, "loss": 0.7579, "step": 1984 }, { "epoch": 0.031074818601710272, "grad_norm": 2.6465444564819336, "learning_rate": 4.996490869988546e-05, "loss": 0.7538, "step": 2015 }, { "epoch": 0.031552892734044276, "grad_norm": 1.3028968572616577, "learning_rate": 4.996031968290326e-05, "loss": 0.7522, "step": 2046 }, { "epoch": 0.03203096686637828, "grad_norm": 1.0450382232666016, "learning_rate": 4.995544899210594e-05, "loss": 0.742, "step": 2077 }, { "epoch": 0.03250904099871228, "grad_norm": 0.9411994814872742, "learning_rate": 4.9950296682458583e-05, "loss": 0.7401, "step": 2108 }, { "epoch": 0.03298711513104629, "grad_norm": 1.0501608848571777, "learning_rate": 4.994486281210429e-05, "loss": 0.7455, "step": 2139 }, { "epoch": 0.03346518926338029, "grad_norm": 1.266400694847107, "learning_rate": 4.9939147442363566e-05, "loss": 0.7391, "step": 2170 }, { "epoch": 0.033943263395714296, "grad_norm": 1.2862213850021362, "learning_rate": 4.9933150637733574e-05, "loss": 0.7397, "step": 2201 }, { "epoch": 0.0344213375280483, "grad_norm": 1.2715409994125366, "learning_rate": 4.992687246588743e-05, "loss": 0.7467, "step": 2232 }, { "epoch": 0.0348994116603823, "grad_norm": 1.3290003538131714, "learning_rate": 4.992031299767347e-05, "loss": 0.7432, "step": 2263 }, { "epoch": 0.03537748579271631, "grad_norm": 1.0561761856079102, "learning_rate": 4.9913472307114386e-05, "loss": 0.7336, "step": 2294 }, { "epoch": 0.035855559925050316, "grad_norm": 1.3272422552108765, "learning_rate": 4.9906350471406446e-05, "loss": 0.7251, "step": 2325 }, { "epoch": 0.036333634057384316, "grad_norm": 1.0749491453170776, "learning_rate": 4.989894757091861e-05, "loss": 0.7205, "step": 2356 }, { "epoch": 0.03681170818971832, "grad_norm": 1.1581461429595947, "learning_rate": 4.989126368919158e-05, "loss": 0.7311, "step": 2387 }, { "epoch": 0.03728978232205232, "grad_norm": 1.0796961784362793, "learning_rate": 4.988329891293693e-05, "loss": 0.7259, "step": 2418 }, { "epoch": 0.03776785645438633, "grad_norm": 1.1916818618774414, "learning_rate": 4.987505333203608e-05, "loss": 0.7258, "step": 2449 }, { "epoch": 0.038245930586720336, "grad_norm": 0.9515872001647949, "learning_rate": 4.9866527039539276e-05, "loss": 0.7273, "step": 2480 }, { "epoch": 0.038724004719054336, "grad_norm": 1.1217246055603027, "learning_rate": 4.9857720131664594e-05, "loss": 0.7269, "step": 2511 }, { "epoch": 0.03920207885138834, "grad_norm": 0.9570199847221375, "learning_rate": 4.9848632707796773e-05, "loss": 0.7289, "step": 2542 }, { "epoch": 0.03968015298372235, "grad_norm": 1.2980682849884033, "learning_rate": 4.9839264870486155e-05, "loss": 0.7382, "step": 2573 }, { "epoch": 0.04015822711605635, "grad_norm": 2.1257143020629883, "learning_rate": 4.9829616725447526e-05, "loss": 0.8112, "step": 2604 }, { "epoch": 0.04063630124839036, "grad_norm": 1.5091110467910767, "learning_rate": 4.981968838155888e-05, "loss": 0.7451, "step": 2635 }, { "epoch": 0.041114375380724356, "grad_norm": 2.4548749923706055, "learning_rate": 4.980947995086024e-05, "loss": 0.7358, "step": 2666 }, { "epoch": 0.04159244951305836, "grad_norm": 1.176115870475769, "learning_rate": 4.979899154855234e-05, "loss": 0.7368, "step": 2697 }, { "epoch": 0.04207052364539237, "grad_norm": 1.063672661781311, "learning_rate": 4.9788223292995386e-05, "loss": 0.7465, "step": 2728 }, { "epoch": 0.04254859777772637, "grad_norm": 1.3062779903411865, "learning_rate": 4.977717530570768e-05, "loss": 0.7413, "step": 2759 }, { "epoch": 0.04302667191006038, "grad_norm": 1.5550280809402466, "learning_rate": 4.976584771136425e-05, "loss": 0.724, "step": 2790 }, { "epoch": 0.043504746042394384, "grad_norm": 1.2525728940963745, "learning_rate": 4.975424063779547e-05, "loss": 0.7216, "step": 2821 }, { "epoch": 0.04398282017472838, "grad_norm": 1.158134937286377, "learning_rate": 4.974235421598557e-05, "loss": 0.728, "step": 2852 }, { "epoch": 0.04446089430706239, "grad_norm": 1.262291669845581, "learning_rate": 4.973018858007122e-05, "loss": 0.7191, "step": 2883 }, { "epoch": 0.04493896843939639, "grad_norm": 2.826028347015381, "learning_rate": 4.9717743867339963e-05, "loss": 0.7211, "step": 2914 }, { "epoch": 0.0454170425717304, "grad_norm": 1.0346958637237549, "learning_rate": 4.9705020218228695e-05, "loss": 0.7268, "step": 2945 }, { "epoch": 0.045895116704064404, "grad_norm": 1.4338330030441284, "learning_rate": 4.969201777632205e-05, "loss": 0.7154, "step": 2976 }, { "epoch": 0.046373190836398404, "grad_norm": 0.9223676919937134, "learning_rate": 4.9678736688350846e-05, "loss": 0.7195, "step": 3007 }, { "epoch": 0.04685126496873241, "grad_norm": 0.9936623573303223, "learning_rate": 4.966517710419033e-05, "loss": 0.7194, "step": 3038 }, { "epoch": 0.04732933910106642, "grad_norm": 1.017962098121643, "learning_rate": 4.965133917685858e-05, "loss": 0.713, "step": 3069 }, { "epoch": 0.04780741323340042, "grad_norm": 0.9654473662376404, "learning_rate": 4.9637223062514714e-05, "loss": 0.7096, "step": 3100 }, { "epoch": 0.048285487365734424, "grad_norm": 0.9372695684432983, "learning_rate": 4.962282892045718e-05, "loss": 0.7116, "step": 3131 }, { "epoch": 0.048763561498068424, "grad_norm": 0.9450846910476685, "learning_rate": 4.9608156913121904e-05, "loss": 0.7129, "step": 3162 }, { "epoch": 0.04924163563040243, "grad_norm": 1.0803054571151733, "learning_rate": 4.959320720608049e-05, "loss": 0.706, "step": 3193 }, { "epoch": 0.04971970976273644, "grad_norm": 1.2218348979949951, "learning_rate": 4.9577979968038354e-05, "loss": 0.7076, "step": 3224 }, { "epoch": 0.05019778389507044, "grad_norm": 1.0429767370224, "learning_rate": 4.956247537083282e-05, "loss": 0.7089, "step": 3255 }, { "epoch": 0.050675858027404444, "grad_norm": 0.9912049770355225, "learning_rate": 4.9546693589431145e-05, "loss": 0.7016, "step": 3286 }, { "epoch": 0.051153932159738444, "grad_norm": 0.9687103033065796, "learning_rate": 4.9530634801928595e-05, "loss": 0.7071, "step": 3317 }, { "epoch": 0.05163200629207245, "grad_norm": 0.8178670406341553, "learning_rate": 4.9514299189546395e-05, "loss": 0.6991, "step": 3348 }, { "epoch": 0.05211008042440646, "grad_norm": 0.8601382374763489, "learning_rate": 4.949768693662973e-05, "loss": 0.6978, "step": 3379 }, { "epoch": 0.05258815455674046, "grad_norm": 1.076370120048523, "learning_rate": 4.948079823064559e-05, "loss": 0.7044, "step": 3410 }, { "epoch": 0.053066228689074464, "grad_norm": 3.9457356929779053, "learning_rate": 4.946363326218074e-05, "loss": 0.6978, "step": 3441 }, { "epoch": 0.05354430282140847, "grad_norm": 0.8186474442481995, "learning_rate": 4.9446192224939525e-05, "loss": 0.6974, "step": 3472 }, { "epoch": 0.05402237695374247, "grad_norm": 0.9643816947937012, "learning_rate": 4.942847531574167e-05, "loss": 0.7025, "step": 3503 }, { "epoch": 0.05450045108607648, "grad_norm": 1.024248480796814, "learning_rate": 4.941048273452008e-05, "loss": 0.7006, "step": 3534 }, { "epoch": 0.05497852521841048, "grad_norm": 0.7718949317932129, "learning_rate": 4.9392214684318605e-05, "loss": 0.7024, "step": 3565 }, { "epoch": 0.055456599350744484, "grad_norm": 1.1313899755477905, "learning_rate": 4.93736713712897e-05, "loss": 0.701, "step": 3596 }, { "epoch": 0.05593467348307849, "grad_norm": 1.0118827819824219, "learning_rate": 4.9354853004692124e-05, "loss": 0.7036, "step": 3627 }, { "epoch": 0.05641274761541249, "grad_norm": 0.9465724229812622, "learning_rate": 4.93357597968886e-05, "loss": 0.6869, "step": 3658 }, { "epoch": 0.0568908217477465, "grad_norm": 1.0233882665634155, "learning_rate": 4.931639196334338e-05, "loss": 0.6944, "step": 3689 }, { "epoch": 0.057368895880080505, "grad_norm": 1.008609652519226, "learning_rate": 4.9296749722619826e-05, "loss": 0.6916, "step": 3720 }, { "epoch": 0.057846970012414504, "grad_norm": 1.0083181858062744, "learning_rate": 4.9276833296377966e-05, "loss": 0.6886, "step": 3751 }, { "epoch": 0.05832504414474851, "grad_norm": 0.9374220967292786, "learning_rate": 4.925664290937196e-05, "loss": 0.6976, "step": 3782 }, { "epoch": 0.05880311827708251, "grad_norm": 0.9066904783248901, "learning_rate": 4.9236178789447576e-05, "loss": 0.6911, "step": 3813 }, { "epoch": 0.05928119240941652, "grad_norm": 0.9702699780464172, "learning_rate": 4.921544116753962e-05, "loss": 0.6959, "step": 3844 }, { "epoch": 0.059759266541750525, "grad_norm": 0.8405037522315979, "learning_rate": 4.919443027766935e-05, "loss": 0.6896, "step": 3875 }, { "epoch": 0.060237340674084525, "grad_norm": 0.9460383653640747, "learning_rate": 4.91731463569418e-05, "loss": 0.6871, "step": 3906 }, { "epoch": 0.06071541480641853, "grad_norm": 0.9355078339576721, "learning_rate": 4.915158964554312e-05, "loss": 0.6843, "step": 3937 }, { "epoch": 0.06119348893875254, "grad_norm": 0.7211058735847473, "learning_rate": 4.912976038673786e-05, "loss": 0.6861, "step": 3968 }, { "epoch": 0.06167156307108654, "grad_norm": 0.8674766421318054, "learning_rate": 4.9107658826866254e-05, "loss": 0.6939, "step": 3999 }, { "epoch": 0.062149637203420545, "grad_norm": 0.8166181445121765, "learning_rate": 4.908528521534139e-05, "loss": 0.692, "step": 4030 }, { "epoch": 0.06262771133575455, "grad_norm": 0.841305136680603, "learning_rate": 4.906263980464644e-05, "loss": 0.6855, "step": 4061 }, { "epoch": 0.06310578546808855, "grad_norm": 0.8942857384681702, "learning_rate": 4.903972285033178e-05, "loss": 0.6946, "step": 4092 }, { "epoch": 0.06358385960042255, "grad_norm": 0.8595120310783386, "learning_rate": 4.901653461101213e-05, "loss": 0.6825, "step": 4123 }, { "epoch": 0.06406193373275657, "grad_norm": 0.8155812621116638, "learning_rate": 4.8993075348363626e-05, "loss": 0.6821, "step": 4154 }, { "epoch": 0.06454000786509057, "grad_norm": 0.8901113271713257, "learning_rate": 4.896934532712084e-05, "loss": 0.6898, "step": 4185 }, { "epoch": 0.06501808199742456, "grad_norm": 0.9637976288795471, "learning_rate": 4.8945344815073846e-05, "loss": 0.6829, "step": 4216 }, { "epoch": 0.06549615612975858, "grad_norm": 0.7048139572143555, "learning_rate": 4.892107408306516e-05, "loss": 0.6834, "step": 4247 }, { "epoch": 0.06597423026209258, "grad_norm": 0.8655612468719482, "learning_rate": 4.889653340498669e-05, "loss": 0.6778, "step": 4278 }, { "epoch": 0.06645230439442658, "grad_norm": 0.8204261064529419, "learning_rate": 4.8871723057776664e-05, "loss": 0.6672, "step": 4309 }, { "epoch": 0.06693037852676058, "grad_norm": 0.9259466528892517, "learning_rate": 4.8846643321416476e-05, "loss": 0.6778, "step": 4340 }, { "epoch": 0.06740845265909459, "grad_norm": 0.9826278686523438, "learning_rate": 4.882129447892753e-05, "loss": 0.6882, "step": 4371 }, { "epoch": 0.06788652679142859, "grad_norm": 0.7376586198806763, "learning_rate": 4.8795676816368076e-05, "loss": 0.6802, "step": 4402 }, { "epoch": 0.06836460092376259, "grad_norm": 0.6778755784034729, "learning_rate": 4.876979062282995e-05, "loss": 0.6814, "step": 4433 }, { "epoch": 0.0688426750560966, "grad_norm": 0.8117042183876038, "learning_rate": 4.8743636190435325e-05, "loss": 0.6759, "step": 4464 }, { "epoch": 0.0693207491884306, "grad_norm": 0.9493227005004883, "learning_rate": 4.871721381433344e-05, "loss": 0.6744, "step": 4495 }, { "epoch": 0.0697988233207646, "grad_norm": 1.3356900215148926, "learning_rate": 4.869052379269719e-05, "loss": 0.6763, "step": 4526 }, { "epoch": 0.07027689745309862, "grad_norm": 1.1542543172836304, "learning_rate": 4.866356642671985e-05, "loss": 0.6788, "step": 4557 }, { "epoch": 0.07075497158543262, "grad_norm": 0.785176157951355, "learning_rate": 4.8636342020611634e-05, "loss": 0.6853, "step": 4588 }, { "epoch": 0.07123304571776662, "grad_norm": 0.8102776408195496, "learning_rate": 4.860885088159626e-05, "loss": 0.6794, "step": 4619 }, { "epoch": 0.07171111985010063, "grad_norm": 0.9685975313186646, "learning_rate": 4.858109331990751e-05, "loss": 0.6823, "step": 4650 }, { "epoch": 0.07218919398243463, "grad_norm": 0.7929072976112366, "learning_rate": 4.855306964878567e-05, "loss": 0.6781, "step": 4681 }, { "epoch": 0.07266726811476863, "grad_norm": 0.8171564340591431, "learning_rate": 4.8524780184474084e-05, "loss": 0.6685, "step": 4712 }, { "epoch": 0.07314534224710265, "grad_norm": 0.9218119382858276, "learning_rate": 4.8496225246215496e-05, "loss": 0.6796, "step": 4743 }, { "epoch": 0.07362341637943665, "grad_norm": 3.1681158542633057, "learning_rate": 4.8467405156248505e-05, "loss": 0.676, "step": 4774 }, { "epoch": 0.07410149051177065, "grad_norm": 0.9336240887641907, "learning_rate": 4.843832023980392e-05, "loss": 0.6734, "step": 4805 }, { "epoch": 0.07457956464410465, "grad_norm": 0.8264138102531433, "learning_rate": 4.840897082510106e-05, "loss": 0.6905, "step": 4836 }, { "epoch": 0.07505763877643866, "grad_norm": 0.819663405418396, "learning_rate": 4.8379357243344084e-05, "loss": 0.6814, "step": 4867 }, { "epoch": 0.07553571290877266, "grad_norm": 3.124502420425415, "learning_rate": 4.8349479828718236e-05, "loss": 0.6704, "step": 4898 }, { "epoch": 0.07601378704110666, "grad_norm": 0.7769860625267029, "learning_rate": 4.8319338918386075e-05, "loss": 0.6728, "step": 4929 }, { "epoch": 0.07649186117344067, "grad_norm": 0.8232171535491943, "learning_rate": 4.828893485248369e-05, "loss": 0.6798, "step": 4960 }, { "epoch": 0.07696993530577467, "grad_norm": 0.8771420121192932, "learning_rate": 4.825826797411682e-05, "loss": 0.6722, "step": 4991 }, { "epoch": 0.07744800943810867, "grad_norm": 0.8321033716201782, "learning_rate": 4.822733862935702e-05, "loss": 0.6724, "step": 5022 }, { "epoch": 0.07792608357044269, "grad_norm": 0.9346029162406921, "learning_rate": 4.819614716723775e-05, "loss": 0.6764, "step": 5053 }, { "epoch": 0.07840415770277669, "grad_norm": 0.9193580150604248, "learning_rate": 4.8164693939750425e-05, "loss": 0.6789, "step": 5084 }, { "epoch": 0.07888223183511069, "grad_norm": 1.0850661993026733, "learning_rate": 4.813297930184042e-05, "loss": 0.6685, "step": 5115 }, { "epoch": 0.0793603059674447, "grad_norm": 0.6851856708526611, "learning_rate": 4.810100361140314e-05, "loss": 0.6621, "step": 5146 }, { "epoch": 0.0798383800997787, "grad_norm": 0.7950114607810974, "learning_rate": 4.8068767229279885e-05, "loss": 0.6642, "step": 5177 }, { "epoch": 0.0803164542321127, "grad_norm": 0.9632556438446045, "learning_rate": 4.8036270519253854e-05, "loss": 0.6628, "step": 5208 }, { "epoch": 0.0807945283644467, "grad_norm": 0.7066652178764343, "learning_rate": 4.8003513848046e-05, "loss": 0.6642, "step": 5239 }, { "epoch": 0.08127260249678071, "grad_norm": 0.7749651670455933, "learning_rate": 4.79704975853109e-05, "loss": 0.6633, "step": 5270 }, { "epoch": 0.08175067662911471, "grad_norm": 1.702022671699524, "learning_rate": 4.793722210363262e-05, "loss": 0.6745, "step": 5301 }, { "epoch": 0.08222875076144871, "grad_norm": 0.8134759068489075, "learning_rate": 4.7903687778520414e-05, "loss": 0.659, "step": 5332 }, { "epoch": 0.08270682489378273, "grad_norm": 0.8805097341537476, "learning_rate": 4.7869894988404593e-05, "loss": 0.6779, "step": 5363 }, { "epoch": 0.08318489902611673, "grad_norm": 0.9312698841094971, "learning_rate": 4.783584411463221e-05, "loss": 0.6634, "step": 5394 }, { "epoch": 0.08366297315845073, "grad_norm": 0.7013948559761047, "learning_rate": 4.780153554146274e-05, "loss": 0.6589, "step": 5425 }, { "epoch": 0.08414104729078474, "grad_norm": 0.8027428388595581, "learning_rate": 4.7766969656063766e-05, "loss": 0.6603, "step": 5456 }, { "epoch": 0.08461912142311874, "grad_norm": 1.0179306268692017, "learning_rate": 4.773214684850662e-05, "loss": 0.6595, "step": 5487 }, { "epoch": 0.08509719555545274, "grad_norm": 0.8512592911720276, "learning_rate": 4.769706751176193e-05, "loss": 0.6659, "step": 5518 }, { "epoch": 0.08557526968778675, "grad_norm": 0.8476304411888123, "learning_rate": 4.7661732041695264e-05, "loss": 0.6658, "step": 5549 }, { "epoch": 0.08605334382012075, "grad_norm": 0.771584153175354, "learning_rate": 4.762614083706258e-05, "loss": 0.6622, "step": 5580 }, { "epoch": 0.08653141795245475, "grad_norm": 0.8719794154167175, "learning_rate": 4.759029429950581e-05, "loss": 0.661, "step": 5611 }, { "epoch": 0.08700949208478877, "grad_norm": 0.9247443675994873, "learning_rate": 4.7554192833548235e-05, "loss": 0.6475, "step": 5642 }, { "epoch": 0.08748756621712277, "grad_norm": 0.9540857672691345, "learning_rate": 4.751783684659e-05, "loss": 0.662, "step": 5673 }, { "epoch": 0.08796564034945677, "grad_norm": 0.7939008474349976, "learning_rate": 4.748122674890348e-05, "loss": 0.6514, "step": 5704 }, { "epoch": 0.08844371448179077, "grad_norm": 0.613531768321991, "learning_rate": 4.7444362953628654e-05, "loss": 0.6513, "step": 5735 }, { "epoch": 0.08892178861412478, "grad_norm": 0.8084924817085266, "learning_rate": 4.7407245876768424e-05, "loss": 0.6465, "step": 5766 }, { "epoch": 0.08939986274645878, "grad_norm": 0.7709007263183594, "learning_rate": 4.736987593718397e-05, "loss": 0.6618, "step": 5797 }, { "epoch": 0.08987793687879278, "grad_norm": 0.6461811065673828, "learning_rate": 4.733225355658999e-05, "loss": 0.6516, "step": 5828 }, { "epoch": 0.0903560110111268, "grad_norm": 0.6879326105117798, "learning_rate": 4.7294379159549926e-05, "loss": 0.655, "step": 5859 }, { "epoch": 0.0908340851434608, "grad_norm": 0.7594075798988342, "learning_rate": 4.725625317347119e-05, "loss": 0.655, "step": 5890 }, { "epoch": 0.0913121592757948, "grad_norm": 0.774758517742157, "learning_rate": 4.7217876028600374e-05, "loss": 0.6697, "step": 5921 }, { "epoch": 0.09179023340812881, "grad_norm": 0.9164844155311584, "learning_rate": 4.717924815801832e-05, "loss": 0.6483, "step": 5952 }, { "epoch": 0.09226830754046281, "grad_norm": 0.792631208896637, "learning_rate": 4.714036999763532e-05, "loss": 0.6644, "step": 5983 }, { "epoch": 0.09274638167279681, "grad_norm": 0.7735174298286438, "learning_rate": 4.7101241986186116e-05, "loss": 0.6545, "step": 6014 }, { "epoch": 0.09322445580513082, "grad_norm": 0.725825309753418, "learning_rate": 4.7061864565225e-05, "loss": 0.6579, "step": 6045 }, { "epoch": 0.09370252993746482, "grad_norm": 0.7191294431686401, "learning_rate": 4.702223817912081e-05, "loss": 0.6509, "step": 6076 }, { "epoch": 0.09418060406979882, "grad_norm": 0.8470766544342041, "learning_rate": 4.698236327505195e-05, "loss": 0.6515, "step": 6107 }, { "epoch": 0.09465867820213283, "grad_norm": 0.7250267863273621, "learning_rate": 4.694224030300127e-05, "loss": 0.6484, "step": 6138 }, { "epoch": 0.09513675233446683, "grad_norm": 0.7370029091835022, "learning_rate": 4.690186971575107e-05, "loss": 0.6639, "step": 6169 }, { "epoch": 0.09561482646680083, "grad_norm": 0.7768808007240295, "learning_rate": 4.6861251968877916e-05, "loss": 0.657, "step": 6200 }, { "epoch": 0.09609290059913483, "grad_norm": 0.770039439201355, "learning_rate": 4.68203875207476e-05, "loss": 0.6588, "step": 6231 }, { "epoch": 0.09657097473146885, "grad_norm": 0.637853741645813, "learning_rate": 4.677927683250983e-05, "loss": 0.6438, "step": 6262 }, { "epoch": 0.09704904886380285, "grad_norm": 0.6896365284919739, "learning_rate": 4.6737920368093156e-05, "loss": 0.6493, "step": 6293 }, { "epoch": 0.09752712299613685, "grad_norm": 0.721318781375885, "learning_rate": 4.669631859419965e-05, "loss": 0.6427, "step": 6324 }, { "epoch": 0.09800519712847086, "grad_norm": 0.7492154836654663, "learning_rate": 4.6654471980299676e-05, "loss": 0.6474, "step": 6355 }, { "epoch": 0.09848327126080486, "grad_norm": 0.8512872457504272, "learning_rate": 4.661238099862658e-05, "loss": 0.6423, "step": 6386 }, { "epoch": 0.09896134539313886, "grad_norm": 0.6349690556526184, "learning_rate": 4.657004612417138e-05, "loss": 0.6499, "step": 6417 }, { "epoch": 0.09943941952547287, "grad_norm": 0.8040255904197693, "learning_rate": 4.6527467834677374e-05, "loss": 0.6495, "step": 6448 }, { "epoch": 0.09991749365780687, "grad_norm": 0.6428426504135132, "learning_rate": 4.648464661063478e-05, "loss": 0.6565, "step": 6479 }, { "epoch": 0.10039556779014087, "grad_norm": 0.8141711950302124, "learning_rate": 4.6441582935275264e-05, "loss": 0.6592, "step": 6510 }, { "epoch": 0.10087364192247489, "grad_norm": 0.8665099740028381, "learning_rate": 4.6398277294566586e-05, "loss": 0.6497, "step": 6541 }, { "epoch": 0.10135171605480889, "grad_norm": 0.709786057472229, "learning_rate": 4.6354730177207e-05, "loss": 0.6546, "step": 6572 }, { "epoch": 0.10182979018714289, "grad_norm": 0.8345597982406616, "learning_rate": 4.6310942074619787e-05, "loss": 0.6547, "step": 6603 }, { "epoch": 0.10230786431947689, "grad_norm": 0.746769905090332, "learning_rate": 4.626691348094777e-05, "loss": 0.6526, "step": 6634 }, { "epoch": 0.1027859384518109, "grad_norm": 0.7869583368301392, "learning_rate": 4.622264489304762e-05, "loss": 0.6458, "step": 6665 }, { "epoch": 0.1032640125841449, "grad_norm": 0.5438331365585327, "learning_rate": 4.617813681048434e-05, "loss": 0.6468, "step": 6696 }, { "epoch": 0.1037420867164789, "grad_norm": 0.7230411171913147, "learning_rate": 4.61333897355256e-05, "loss": 0.6435, "step": 6727 }, { "epoch": 0.10422016084881291, "grad_norm": 0.9861361384391785, "learning_rate": 4.608840417313604e-05, "loss": 0.6488, "step": 6758 }, { "epoch": 0.10469823498114691, "grad_norm": 0.7873183488845825, "learning_rate": 4.6043180630971646e-05, "loss": 0.6485, "step": 6789 }, { "epoch": 0.10517630911348091, "grad_norm": 0.7746345400810242, "learning_rate": 4.599771961937391e-05, "loss": 0.6384, "step": 6820 }, { "epoch": 0.10565438324581493, "grad_norm": 0.8218130469322205, "learning_rate": 4.5952021651364204e-05, "loss": 0.6434, "step": 6851 }, { "epoch": 0.10613245737814893, "grad_norm": 0.7047727108001709, "learning_rate": 4.590608724263786e-05, "loss": 0.6562, "step": 6882 }, { "epoch": 0.10661053151048293, "grad_norm": 0.9560827612876892, "learning_rate": 4.585991691155845e-05, "loss": 0.6422, "step": 6913 }, { "epoch": 0.10708860564281694, "grad_norm": 1.1834834814071655, "learning_rate": 4.581351117915188e-05, "loss": 0.6525, "step": 6944 }, { "epoch": 0.10756667977515094, "grad_norm": 0.8007238507270813, "learning_rate": 4.5766870569100534e-05, "loss": 0.6575, "step": 6975 }, { "epoch": 0.10804475390748494, "grad_norm": 0.6816396713256836, "learning_rate": 4.571999560773736e-05, "loss": 0.6453, "step": 7006 }, { "epoch": 0.10852282803981896, "grad_norm": 0.7240257859230042, "learning_rate": 4.5672886824039915e-05, "loss": 0.6542, "step": 7037 }, { "epoch": 0.10900090217215296, "grad_norm": 0.6335741877555847, "learning_rate": 4.5625544749624435e-05, "loss": 0.6449, "step": 7068 }, { "epoch": 0.10947897630448696, "grad_norm": 0.6071763038635254, "learning_rate": 4.5577969918739794e-05, "loss": 0.6572, "step": 7099 }, { "epoch": 0.10995705043682096, "grad_norm": 0.8242653608322144, "learning_rate": 4.5530162868261486e-05, "loss": 0.6483, "step": 7130 }, { "epoch": 0.11043512456915497, "grad_norm": 0.7106221318244934, "learning_rate": 4.548212413768558e-05, "loss": 0.6376, "step": 7161 }, { "epoch": 0.11091319870148897, "grad_norm": 0.6587203145027161, "learning_rate": 4.543385426912261e-05, "loss": 0.6426, "step": 7192 }, { "epoch": 0.11139127283382297, "grad_norm": 0.8035815954208374, "learning_rate": 4.53853538072915e-05, "loss": 0.6428, "step": 7223 }, { "epoch": 0.11186934696615698, "grad_norm": 0.6661431193351746, "learning_rate": 4.533662329951336e-05, "loss": 0.6431, "step": 7254 }, { "epoch": 0.11234742109849098, "grad_norm": 0.5891786813735962, "learning_rate": 4.528766329570536e-05, "loss": 0.6356, "step": 7285 }, { "epoch": 0.11282549523082498, "grad_norm": 0.7475966811180115, "learning_rate": 4.523847434837447e-05, "loss": 0.6348, "step": 7316 }, { "epoch": 0.113303569363159, "grad_norm": 0.7461502552032471, "learning_rate": 4.518905701261128e-05, "loss": 0.639, "step": 7347 }, { "epoch": 0.113781643495493, "grad_norm": 0.7351141571998596, "learning_rate": 4.5139411846083715e-05, "loss": 0.6473, "step": 7378 }, { "epoch": 0.114259717627827, "grad_norm": 0.7713771462440491, "learning_rate": 4.508953940903073e-05, "loss": 0.6433, "step": 7409 }, { "epoch": 0.11473779176016101, "grad_norm": 0.639986515045166, "learning_rate": 4.5039440264255994e-05, "loss": 0.6411, "step": 7440 }, { "epoch": 0.11521586589249501, "grad_norm": 0.8399244546890259, "learning_rate": 4.498911497712155e-05, "loss": 0.6421, "step": 7471 }, { "epoch": 0.11569394002482901, "grad_norm": 0.7681542634963989, "learning_rate": 4.493856411554142e-05, "loss": 0.6371, "step": 7502 }, { "epoch": 0.11617201415716301, "grad_norm": 0.6907945275306702, "learning_rate": 4.4887788249975206e-05, "loss": 0.6446, "step": 7533 }, { "epoch": 0.11665008828949702, "grad_norm": 0.7653492093086243, "learning_rate": 4.4836787953421656e-05, "loss": 0.6407, "step": 7564 }, { "epoch": 0.11712816242183102, "grad_norm": 0.6535690426826477, "learning_rate": 4.478556380141218e-05, "loss": 0.6388, "step": 7595 }, { "epoch": 0.11760623655416502, "grad_norm": 2.6184701919555664, "learning_rate": 4.4734116372004375e-05, "loss": 0.6382, "step": 7626 }, { "epoch": 0.11808431068649904, "grad_norm": 0.7846981287002563, "learning_rate": 4.4682446245775477e-05, "loss": 0.6364, "step": 7657 }, { "epoch": 0.11856238481883304, "grad_norm": 0.8151688575744629, "learning_rate": 4.463055400581586e-05, "loss": 0.6427, "step": 7688 }, { "epoch": 0.11904045895116704, "grad_norm": 0.7663447856903076, "learning_rate": 4.4578440237722374e-05, "loss": 0.643, "step": 7719 }, { "epoch": 0.11951853308350105, "grad_norm": 0.7225657105445862, "learning_rate": 4.452610552959183e-05, "loss": 0.6395, "step": 7750 }, { "epoch": 0.11999660721583505, "grad_norm": 0.7033439874649048, "learning_rate": 4.447355047201428e-05, "loss": 0.6354, "step": 7781 }, { "epoch": 0.12047468134816905, "grad_norm": 0.7693649530410767, "learning_rate": 4.4420775658066414e-05, "loss": 0.6436, "step": 7812 }, { "epoch": 0.12095275548050306, "grad_norm": 0.7597894668579102, "learning_rate": 4.436778168330484e-05, "loss": 0.6411, "step": 7843 }, { "epoch": 0.12143082961283706, "grad_norm": 0.7899183630943298, "learning_rate": 4.4314569145759353e-05, "loss": 0.6381, "step": 7874 }, { "epoch": 0.12190890374517106, "grad_norm": 0.7656906247138977, "learning_rate": 4.42611386459262e-05, "loss": 0.6386, "step": 7905 }, { "epoch": 0.12238697787750508, "grad_norm": 0.8353867530822754, "learning_rate": 4.420749078676133e-05, "loss": 0.6386, "step": 7936 }, { "epoch": 0.12286505200983908, "grad_norm": 0.6712770462036133, "learning_rate": 4.4153626173673516e-05, "loss": 0.6438, "step": 7967 }, { "epoch": 0.12334312614217308, "grad_norm": 0.8008986115455627, "learning_rate": 4.409954541451762e-05, "loss": 0.6384, "step": 7998 }, { "epoch": 0.12382120027450708, "grad_norm": 0.6632928252220154, "learning_rate": 4.404524911958764e-05, "loss": 0.629, "step": 8029 }, { "epoch": 0.12429927440684109, "grad_norm": 0.6943359971046448, "learning_rate": 4.399073790160989e-05, "loss": 0.6456, "step": 8060 }, { "epoch": 0.12477734853917509, "grad_norm": 0.6177495718002319, "learning_rate": 4.393601237573607e-05, "loss": 0.6426, "step": 8091 }, { "epoch": 0.1252554226715091, "grad_norm": 0.6089790463447571, "learning_rate": 4.388107315953628e-05, "loss": 0.6396, "step": 8122 }, { "epoch": 0.1257334968038431, "grad_norm": 0.6960969567298889, "learning_rate": 4.382592087299212e-05, "loss": 0.6293, "step": 8153 }, { "epoch": 0.1262115709361771, "grad_norm": 0.6519069075584412, "learning_rate": 4.377055613848964e-05, "loss": 0.6284, "step": 8184 }, { "epoch": 0.1266896450685111, "grad_norm": 0.6861445903778076, "learning_rate": 4.3714979580812355e-05, "loss": 0.6386, "step": 8215 }, { "epoch": 0.1271677192008451, "grad_norm": 0.7522263526916504, "learning_rate": 4.365919182713416e-05, "loss": 0.6424, "step": 8246 }, { "epoch": 0.1276457933331791, "grad_norm": 0.6868363618850708, "learning_rate": 4.360319350701226e-05, "loss": 0.6367, "step": 8277 }, { "epoch": 0.12812386746551313, "grad_norm": 0.5939040780067444, "learning_rate": 4.3546985252380115e-05, "loss": 0.6406, "step": 8308 }, { "epoch": 0.12860194159784713, "grad_norm": 0.7341668605804443, "learning_rate": 4.349056769754021e-05, "loss": 0.6346, "step": 8339 }, { "epoch": 0.12908001573018113, "grad_norm": 0.7468376755714417, "learning_rate": 4.3433941479156994e-05, "loss": 0.6398, "step": 8370 }, { "epoch": 0.12955808986251513, "grad_norm": 0.6253494024276733, "learning_rate": 4.3377107236249647e-05, "loss": 0.6375, "step": 8401 }, { "epoch": 0.13003616399484913, "grad_norm": 0.6635178923606873, "learning_rate": 4.332006561018488e-05, "loss": 0.6299, "step": 8432 }, { "epoch": 0.13051423812718313, "grad_norm": 0.584648609161377, "learning_rate": 4.3262817244669683e-05, "loss": 0.6277, "step": 8463 }, { "epoch": 0.13099231225951716, "grad_norm": 0.5907359719276428, "learning_rate": 4.3205362785744083e-05, "loss": 0.6328, "step": 8494 }, { "epoch": 0.13147038639185116, "grad_norm": 0.7864153385162354, "learning_rate": 4.314770288177384e-05, "loss": 0.6365, "step": 8525 }, { "epoch": 0.13194846052418516, "grad_norm": 0.6572133302688599, "learning_rate": 4.308983818344313e-05, "loss": 0.6312, "step": 8556 }, { "epoch": 0.13242653465651916, "grad_norm": 0.7108786702156067, "learning_rate": 4.3031769343747206e-05, "loss": 0.6355, "step": 8587 }, { "epoch": 0.13290460878885316, "grad_norm": 0.6737267374992371, "learning_rate": 4.297349701798505e-05, "loss": 0.6256, "step": 8618 }, { "epoch": 0.13338268292118716, "grad_norm": 0.6710911989212036, "learning_rate": 4.2915021863751916e-05, "loss": 0.632, "step": 8649 }, { "epoch": 0.13386075705352116, "grad_norm": 0.6295626759529114, "learning_rate": 4.285634454093198e-05, "loss": 0.6372, "step": 8680 }, { "epoch": 0.13433883118585518, "grad_norm": 0.6405526399612427, "learning_rate": 4.279746571169086e-05, "loss": 0.6364, "step": 8711 }, { "epoch": 0.13481690531818918, "grad_norm": 0.6847979426383972, "learning_rate": 4.2738386040468136e-05, "loss": 0.6246, "step": 8742 }, { "epoch": 0.13529497945052318, "grad_norm": 0.7338352799415588, "learning_rate": 4.2679106193969866e-05, "loss": 0.6373, "step": 8773 }, { "epoch": 0.13577305358285718, "grad_norm": 0.6530189514160156, "learning_rate": 4.261962684116106e-05, "loss": 0.6217, "step": 8804 }, { "epoch": 0.13625112771519118, "grad_norm": 0.6450487375259399, "learning_rate": 4.2559948653258145e-05, "loss": 0.6365, "step": 8835 }, { "epoch": 0.13672920184752518, "grad_norm": 0.706732988357544, "learning_rate": 4.250007230372134e-05, "loss": 0.6294, "step": 8866 }, { "epoch": 0.1372072759798592, "grad_norm": 0.687240481376648, "learning_rate": 4.2439998468247126e-05, "loss": 0.6332, "step": 8897 }, { "epoch": 0.1376853501121932, "grad_norm": 0.6686804890632629, "learning_rate": 4.2379727824760566e-05, "loss": 0.6334, "step": 8928 }, { "epoch": 0.1381634242445272, "grad_norm": 0.8371458649635315, "learning_rate": 4.231926105340768e-05, "loss": 0.6249, "step": 8959 }, { "epoch": 0.1386414983768612, "grad_norm": 0.7204101085662842, "learning_rate": 4.225859883654776e-05, "loss": 0.6309, "step": 8990 }, { "epoch": 0.1391195725091952, "grad_norm": 0.8539360165596008, "learning_rate": 4.219774185874569e-05, "loss": 0.6326, "step": 9021 }, { "epoch": 0.1395976466415292, "grad_norm": 0.7264754176139832, "learning_rate": 4.213669080676418e-05, "loss": 0.6342, "step": 9052 }, { "epoch": 0.14007572077386324, "grad_norm": 0.6681591868400574, "learning_rate": 4.2075446369556056e-05, "loss": 0.6295, "step": 9083 }, { "epoch": 0.14055379490619724, "grad_norm": 0.6293045282363892, "learning_rate": 4.201400923825648e-05, "loss": 0.6304, "step": 9114 }, { "epoch": 0.14103186903853124, "grad_norm": 0.6432914137840271, "learning_rate": 4.195238010617511e-05, "loss": 0.6215, "step": 9145 }, { "epoch": 0.14150994317086524, "grad_norm": 0.7524629235267639, "learning_rate": 4.1890559668788344e-05, "loss": 0.625, "step": 9176 }, { "epoch": 0.14198801730319924, "grad_norm": 0.7128170728683472, "learning_rate": 4.1828548623731405e-05, "loss": 0.6342, "step": 9207 }, { "epoch": 0.14246609143553324, "grad_norm": 0.651841938495636, "learning_rate": 4.1766347670790506e-05, "loss": 0.6303, "step": 9238 }, { "epoch": 0.14294416556786724, "grad_norm": 0.6290706396102905, "learning_rate": 4.170395751189495e-05, "loss": 0.6297, "step": 9269 }, { "epoch": 0.14342223970020127, "grad_norm": 0.6372231841087341, "learning_rate": 4.164137885110921e-05, "loss": 0.6244, "step": 9300 }, { "epoch": 0.14390031383253526, "grad_norm": 0.8424429297447205, "learning_rate": 4.157861239462495e-05, "loss": 0.6363, "step": 9331 }, { "epoch": 0.14437838796486926, "grad_norm": 0.7121688723564148, "learning_rate": 4.1515658850753114e-05, "loss": 0.63, "step": 9362 }, { "epoch": 0.14485646209720326, "grad_norm": 0.7196950316429138, "learning_rate": 4.145251892991588e-05, "loss": 0.6254, "step": 9393 }, { "epoch": 0.14533453622953726, "grad_norm": 0.6595038175582886, "learning_rate": 4.138919334463868e-05, "loss": 0.6207, "step": 9424 }, { "epoch": 0.14581261036187126, "grad_norm": 0.6118171811103821, "learning_rate": 4.1325682809542124e-05, "loss": 0.6233, "step": 9455 }, { "epoch": 0.1462906844942053, "grad_norm": 0.7232321500778198, "learning_rate": 4.126198804133398e-05, "loss": 0.6328, "step": 9486 }, { "epoch": 0.1467687586265393, "grad_norm": 0.691681981086731, "learning_rate": 4.1198109758801055e-05, "loss": 0.634, "step": 9517 }, { "epoch": 0.1472468327588733, "grad_norm": 0.6887443661689758, "learning_rate": 4.113404868280107e-05, "loss": 0.6275, "step": 9548 }, { "epoch": 0.1477249068912073, "grad_norm": 0.6932326555252075, "learning_rate": 4.106980553625457e-05, "loss": 0.6233, "step": 9579 }, { "epoch": 0.1482029810235413, "grad_norm": 0.7189227342605591, "learning_rate": 4.100538104413674e-05, "loss": 0.6229, "step": 9610 }, { "epoch": 0.1486810551558753, "grad_norm": 0.6898639798164368, "learning_rate": 4.09407759334692e-05, "loss": 0.6251, "step": 9641 }, { "epoch": 0.1491591292882093, "grad_norm": 0.6311922669410706, "learning_rate": 4.087599093331186e-05, "loss": 0.6249, "step": 9672 }, { "epoch": 0.14963720342054332, "grad_norm": 0.5781577825546265, "learning_rate": 4.081102677475462e-05, "loss": 0.6337, "step": 9703 }, { "epoch": 0.15011527755287732, "grad_norm": 0.6525286436080933, "learning_rate": 4.0745884190909194e-05, "loss": 0.6347, "step": 9734 }, { "epoch": 0.15059335168521132, "grad_norm": 0.6761188507080078, "learning_rate": 4.0680563916900796e-05, "loss": 0.6267, "step": 9765 }, { "epoch": 0.15107142581754532, "grad_norm": 0.674532413482666, "learning_rate": 4.0615066689859815e-05, "loss": 0.6303, "step": 9796 }, { "epoch": 0.15154949994987932, "grad_norm": 0.5923493504524231, "learning_rate": 4.0549393248913584e-05, "loss": 0.6241, "step": 9827 }, { "epoch": 0.15202757408221332, "grad_norm": 0.6309007406234741, "learning_rate": 4.048354433517794e-05, "loss": 0.6231, "step": 9858 }, { "epoch": 0.15250564821454735, "grad_norm": 0.7521491050720215, "learning_rate": 4.0417520691748916e-05, "loss": 0.6214, "step": 9889 }, { "epoch": 0.15298372234688135, "grad_norm": 0.8196119666099548, "learning_rate": 4.035132306369438e-05, "loss": 0.6254, "step": 9920 }, { "epoch": 0.15346179647921535, "grad_norm": 0.6895152926445007, "learning_rate": 4.028495219804555e-05, "loss": 0.6227, "step": 9951 }, { "epoch": 0.15393987061154935, "grad_norm": 0.6823534369468689, "learning_rate": 4.021840884378864e-05, "loss": 0.6281, "step": 9982 }, { "epoch": 0.15441794474388335, "grad_norm": 0.6531606912612915, "learning_rate": 4.015169375185633e-05, "loss": 0.6259, "step": 10013 }, { "epoch": 0.15489601887621735, "grad_norm": 0.5898056626319885, "learning_rate": 4.0084807675119396e-05, "loss": 0.6184, "step": 10044 }, { "epoch": 0.15537409300855134, "grad_norm": 0.6368978023529053, "learning_rate": 4.0017751368378106e-05, "loss": 0.6196, "step": 10075 }, { "epoch": 0.15585216714088537, "grad_norm": 0.8086898922920227, "learning_rate": 3.995052558835377e-05, "loss": 0.6226, "step": 10106 }, { "epoch": 0.15633024127321937, "grad_norm": 0.6620404124259949, "learning_rate": 3.988313109368017e-05, "loss": 0.6146, "step": 10137 }, { "epoch": 0.15680831540555337, "grad_norm": 0.6264041662216187, "learning_rate": 3.981556864489504e-05, "loss": 0.6254, "step": 10168 }, { "epoch": 0.15728638953788737, "grad_norm": 0.6619133353233337, "learning_rate": 3.974783900443142e-05, "loss": 0.6233, "step": 10199 }, { "epoch": 0.15776446367022137, "grad_norm": 0.6223868131637573, "learning_rate": 3.9679942936609095e-05, "loss": 0.6232, "step": 10230 }, { "epoch": 0.15824253780255537, "grad_norm": 0.7436427474021912, "learning_rate": 3.961188120762596e-05, "loss": 0.6194, "step": 10261 }, { "epoch": 0.1587206119348894, "grad_norm": 0.7166286110877991, "learning_rate": 3.954365458554938e-05, "loss": 0.6267, "step": 10292 }, { "epoch": 0.1591986860672234, "grad_norm": 0.6377813220024109, "learning_rate": 3.947526384030751e-05, "loss": 0.6145, "step": 10323 }, { "epoch": 0.1596767601995574, "grad_norm": 1.5197011232376099, "learning_rate": 3.9406709743680624e-05, "loss": 0.6261, "step": 10354 }, { "epoch": 0.1601548343318914, "grad_norm": 0.6208730340003967, "learning_rate": 3.9337993069292366e-05, "loss": 0.6201, "step": 10385 }, { "epoch": 0.1606329084642254, "grad_norm": 0.6887170076370239, "learning_rate": 3.926911459260109e-05, "loss": 0.6235, "step": 10416 }, { "epoch": 0.1611109825965594, "grad_norm": 0.6381047368049622, "learning_rate": 3.920007509089102e-05, "loss": 0.6189, "step": 10447 }, { "epoch": 0.1615890567288934, "grad_norm": 0.6249068379402161, "learning_rate": 3.913087534326357e-05, "loss": 0.6222, "step": 10478 }, { "epoch": 0.16206713086122743, "grad_norm": 0.659757137298584, "learning_rate": 3.9061516130628475e-05, "loss": 0.6345, "step": 10509 }, { "epoch": 0.16254520499356143, "grad_norm": 0.6268470883369446, "learning_rate": 3.8991998235695025e-05, "loss": 0.6197, "step": 10540 }, { "epoch": 0.16302327912589543, "grad_norm": 0.6520307660102844, "learning_rate": 3.8922322442963224e-05, "loss": 0.6122, "step": 10571 }, { "epoch": 0.16350135325822943, "grad_norm": 0.5919711589813232, "learning_rate": 3.885248953871491e-05, "loss": 0.6237, "step": 10602 }, { "epoch": 0.16397942739056343, "grad_norm": 0.6761168837547302, "learning_rate": 3.8782500311004915e-05, "loss": 0.615, "step": 10633 }, { "epoch": 0.16445750152289743, "grad_norm": 0.7123913168907166, "learning_rate": 3.871235554965218e-05, "loss": 0.6178, "step": 10664 }, { "epoch": 0.16493557565523145, "grad_norm": 0.5414535403251648, "learning_rate": 3.864205604623078e-05, "loss": 0.6319, "step": 10695 }, { "epoch": 0.16541364978756545, "grad_norm": 0.741256594657898, "learning_rate": 3.857160259406107e-05, "loss": 0.6102, "step": 10726 }, { "epoch": 0.16589172391989945, "grad_norm": 0.6938264966011047, "learning_rate": 3.8500995988200674e-05, "loss": 0.6127, "step": 10757 }, { "epoch": 0.16636979805223345, "grad_norm": 0.7152143716812134, "learning_rate": 3.843023702543556e-05, "loss": 0.6119, "step": 10788 }, { "epoch": 0.16684787218456745, "grad_norm": 0.6516321897506714, "learning_rate": 3.8359326504270984e-05, "loss": 0.6224, "step": 10819 }, { "epoch": 0.16732594631690145, "grad_norm": 0.6300469040870667, "learning_rate": 3.828826522492255e-05, "loss": 0.6229, "step": 10850 }, { "epoch": 0.16780402044923548, "grad_norm": 0.645636260509491, "learning_rate": 3.821705398930713e-05, "loss": 0.6284, "step": 10881 }, { "epoch": 0.16828209458156948, "grad_norm": 0.5895135402679443, "learning_rate": 3.814569360103385e-05, "loss": 0.6142, "step": 10912 }, { "epoch": 0.16876016871390348, "grad_norm": 0.6440445184707642, "learning_rate": 3.807418486539499e-05, "loss": 0.6158, "step": 10943 }, { "epoch": 0.16923824284623748, "grad_norm": 0.6739510893821716, "learning_rate": 3.80025285893569e-05, "loss": 0.6149, "step": 10974 }, { "epoch": 0.16971631697857148, "grad_norm": 0.627185046672821, "learning_rate": 3.793072558155093e-05, "loss": 0.614, "step": 11005 }, { "epoch": 0.17019439111090548, "grad_norm": 0.710350513458252, "learning_rate": 3.785877665226426e-05, "loss": 0.6214, "step": 11036 }, { "epoch": 0.17067246524323948, "grad_norm": 0.6784375309944153, "learning_rate": 3.778668261343079e-05, "loss": 0.6123, "step": 11067 }, { "epoch": 0.1711505393755735, "grad_norm": 0.6646184325218201, "learning_rate": 3.771444427862192e-05, "loss": 0.6178, "step": 11098 }, { "epoch": 0.1716286135079075, "grad_norm": 0.7227056622505188, "learning_rate": 3.7642062463037465e-05, "loss": 0.6158, "step": 11129 }, { "epoch": 0.1721066876402415, "grad_norm": 0.5937723517417908, "learning_rate": 3.7569537983496373e-05, "loss": 0.6194, "step": 11160 }, { "epoch": 0.1725847617725755, "grad_norm": 0.6352291703224182, "learning_rate": 3.749687165842753e-05, "loss": 0.6286, "step": 11191 }, { "epoch": 0.1730628359049095, "grad_norm": 0.5864464044570923, "learning_rate": 3.7424064307860536e-05, "loss": 0.6186, "step": 11222 }, { "epoch": 0.1735409100372435, "grad_norm": 0.5402609705924988, "learning_rate": 3.735111675341645e-05, "loss": 0.6072, "step": 11253 }, { "epoch": 0.17401898416957753, "grad_norm": 0.6429933905601501, "learning_rate": 3.7278029818298524e-05, "loss": 0.608, "step": 11284 }, { "epoch": 0.17449705830191153, "grad_norm": 0.5420451164245605, "learning_rate": 3.720480432728287e-05, "loss": 0.6174, "step": 11315 }, { "epoch": 0.17497513243424553, "grad_norm": 0.5691730380058289, "learning_rate": 3.71314411067092e-05, "loss": 0.6138, "step": 11346 }, { "epoch": 0.17545320656657953, "grad_norm": 0.6198572516441345, "learning_rate": 3.70579409844715e-05, "loss": 0.6166, "step": 11377 }, { "epoch": 0.17593128069891353, "grad_norm": 0.6781229972839355, "learning_rate": 3.698430479000865e-05, "loss": 0.6083, "step": 11408 }, { "epoch": 0.17640935483124753, "grad_norm": 0.6572268605232239, "learning_rate": 3.691053335429509e-05, "loss": 0.6179, "step": 11439 }, { "epoch": 0.17688742896358153, "grad_norm": 0.6720935702323914, "learning_rate": 3.683662750983147e-05, "loss": 0.6039, "step": 11470 }, { "epoch": 0.17736550309591556, "grad_norm": 0.6098059415817261, "learning_rate": 3.676258809063518e-05, "loss": 0.608, "step": 11501 }, { "epoch": 0.17784357722824956, "grad_norm": 0.6108371615409851, "learning_rate": 3.6688415932231004e-05, "loss": 0.6147, "step": 11532 }, { "epoch": 0.17832165136058356, "grad_norm": 0.8087718486785889, "learning_rate": 3.661411187164166e-05, "loss": 0.6091, "step": 11563 }, { "epoch": 0.17879972549291756, "grad_norm": 0.719902753829956, "learning_rate": 3.65396767473784e-05, "loss": 0.6107, "step": 11594 }, { "epoch": 0.17927779962525156, "grad_norm": 0.5758282542228699, "learning_rate": 3.6465111399431465e-05, "loss": 0.6236, "step": 11625 }, { "epoch": 0.17975587375758556, "grad_norm": 0.5602071285247803, "learning_rate": 3.6390416669260674e-05, "loss": 0.611, "step": 11656 }, { "epoch": 0.1802339478899196, "grad_norm": 0.6070683002471924, "learning_rate": 3.63155933997859e-05, "loss": 0.609, "step": 11687 }, { "epoch": 0.1807120220222536, "grad_norm": 0.64506596326828, "learning_rate": 3.624064243537758e-05, "loss": 0.605, "step": 11718 }, { "epoch": 0.1811900961545876, "grad_norm": 0.6906920075416565, "learning_rate": 3.616556462184716e-05, "loss": 0.6168, "step": 11749 }, { "epoch": 0.1816681702869216, "grad_norm": 0.6724758148193359, "learning_rate": 3.609036080643755e-05, "loss": 0.6143, "step": 11780 }, { "epoch": 0.1821462444192556, "grad_norm": 0.6033251881599426, "learning_rate": 3.60150318378136e-05, "loss": 0.6161, "step": 11811 }, { "epoch": 0.1826243185515896, "grad_norm": 0.6713966727256775, "learning_rate": 3.5939578566052465e-05, "loss": 0.619, "step": 11842 }, { "epoch": 0.1831023926839236, "grad_norm": 0.6794861555099487, "learning_rate": 3.586400184263408e-05, "loss": 0.6116, "step": 11873 }, { "epoch": 0.18358046681625761, "grad_norm": 0.5780847668647766, "learning_rate": 3.578830252043148e-05, "loss": 0.6159, "step": 11904 }, { "epoch": 0.18405854094859161, "grad_norm": 0.6031593680381775, "learning_rate": 3.571248145370125e-05, "loss": 0.6135, "step": 11935 }, { "epoch": 0.18453661508092561, "grad_norm": 0.6339271664619446, "learning_rate": 3.5636539498073794e-05, "loss": 0.6113, "step": 11966 }, { "epoch": 0.18501468921325961, "grad_norm": 0.6663223505020142, "learning_rate": 3.556047751054378e-05, "loss": 0.6184, "step": 11997 }, { "epoch": 0.18549276334559361, "grad_norm": 0.9799377918243408, "learning_rate": 3.548429634946039e-05, "loss": 0.6103, "step": 12028 }, { "epoch": 0.18597083747792761, "grad_norm": 0.7260358929634094, "learning_rate": 3.540799687451768e-05, "loss": 0.6245, "step": 12059 }, { "epoch": 0.18644891161026164, "grad_norm": 0.7097154259681702, "learning_rate": 3.533157994674485e-05, "loss": 0.6194, "step": 12090 }, { "epoch": 0.18692698574259564, "grad_norm": 0.5897482633590698, "learning_rate": 3.5255046428496546e-05, "loss": 0.6171, "step": 12121 }, { "epoch": 0.18740505987492964, "grad_norm": 0.6374841332435608, "learning_rate": 3.517839718344311e-05, "loss": 0.6141, "step": 12152 }, { "epoch": 0.18788313400726364, "grad_norm": 0.6854335069656372, "learning_rate": 3.510163307656086e-05, "loss": 0.6077, "step": 12183 }, { "epoch": 0.18836120813959764, "grad_norm": 0.6838460564613342, "learning_rate": 3.5024754974122324e-05, "loss": 0.6129, "step": 12214 }, { "epoch": 0.18883928227193164, "grad_norm": 0.6604870557785034, "learning_rate": 3.494776374368643e-05, "loss": 0.6193, "step": 12245 }, { "epoch": 0.18931735640426567, "grad_norm": 0.5817708373069763, "learning_rate": 3.4870660254088724e-05, "loss": 0.6086, "step": 12276 }, { "epoch": 0.18979543053659967, "grad_norm": 0.5379335284233093, "learning_rate": 3.479344537543164e-05, "loss": 0.6088, "step": 12307 }, { "epoch": 0.19027350466893367, "grad_norm": 0.6126767992973328, "learning_rate": 3.4716119979074565e-05, "loss": 0.6131, "step": 12338 }, { "epoch": 0.19075157880126767, "grad_norm": 0.609724223613739, "learning_rate": 3.463868493762412e-05, "loss": 0.6106, "step": 12369 }, { "epoch": 0.19122965293360167, "grad_norm": 0.6327598094940186, "learning_rate": 3.456114112492418e-05, "loss": 0.6134, "step": 12400 }, { "epoch": 0.19170772706593567, "grad_norm": 0.5619271993637085, "learning_rate": 3.4483489416046164e-05, "loss": 0.6161, "step": 12431 }, { "epoch": 0.19218580119826967, "grad_norm": 0.6915563344955444, "learning_rate": 3.440573068727905e-05, "loss": 0.6046, "step": 12462 }, { "epoch": 0.1926638753306037, "grad_norm": 0.7094136476516724, "learning_rate": 3.4327865816119495e-05, "loss": 0.6087, "step": 12493 }, { "epoch": 0.1931419494629377, "grad_norm": 0.627680778503418, "learning_rate": 3.4249895681262025e-05, "loss": 0.604, "step": 12524 }, { "epoch": 0.1936200235952717, "grad_norm": 0.6224892735481262, "learning_rate": 3.417182116258899e-05, "loss": 0.6047, "step": 12555 }, { "epoch": 0.1940980977276057, "grad_norm": 0.5795034766197205, "learning_rate": 3.409364314116074e-05, "loss": 0.6111, "step": 12586 }, { "epoch": 0.1945761718599397, "grad_norm": 0.7537661194801331, "learning_rate": 3.401536249920559e-05, "loss": 0.6079, "step": 12617 }, { "epoch": 0.1950542459922737, "grad_norm": 0.838455319404602, "learning_rate": 3.393698012010998e-05, "loss": 0.6036, "step": 12648 }, { "epoch": 0.19553232012460772, "grad_norm": 0.650592029094696, "learning_rate": 3.385849688840839e-05, "loss": 0.6088, "step": 12679 }, { "epoch": 0.19601039425694172, "grad_norm": 0.7277738451957703, "learning_rate": 3.3779913689773414e-05, "loss": 0.6073, "step": 12710 }, { "epoch": 0.19648846838927572, "grad_norm": 0.6338685154914856, "learning_rate": 3.370123141100578e-05, "loss": 0.6085, "step": 12741 }, { "epoch": 0.19696654252160972, "grad_norm": 0.5530194044113159, "learning_rate": 3.3622450940024305e-05, "loss": 0.6063, "step": 12772 }, { "epoch": 0.19744461665394372, "grad_norm": 0.634303867816925, "learning_rate": 3.35435731658559e-05, "loss": 0.6036, "step": 12803 }, { "epoch": 0.19792269078627772, "grad_norm": 0.6769723892211914, "learning_rate": 3.346459897862552e-05, "loss": 0.6094, "step": 12834 }, { "epoch": 0.19840076491861172, "grad_norm": 0.5914043188095093, "learning_rate": 3.338552926954613e-05, "loss": 0.6093, "step": 12865 }, { "epoch": 0.19887883905094575, "grad_norm": 0.6945207118988037, "learning_rate": 3.330636493090868e-05, "loss": 0.609, "step": 12896 }, { "epoch": 0.19935691318327975, "grad_norm": 0.7246667742729187, "learning_rate": 3.322710685607193e-05, "loss": 0.6245, "step": 12927 }, { "epoch": 0.19983498731561375, "grad_norm": 0.5429117679595947, "learning_rate": 3.314775593945251e-05, "loss": 0.6112, "step": 12958 }, { "epoch": 0.20031306144794775, "grad_norm": 0.5964083671569824, "learning_rate": 3.3068313076514714e-05, "loss": 0.6037, "step": 12989 }, { "epoch": 0.20079113558028175, "grad_norm": 0.6770813465118408, "learning_rate": 3.298877916376047e-05, "loss": 0.6046, "step": 13020 }, { "epoch": 0.20126920971261575, "grad_norm": 0.5819186568260193, "learning_rate": 3.290915509871915e-05, "loss": 0.6102, "step": 13051 }, { "epoch": 0.20174728384494978, "grad_norm": 0.6465575098991394, "learning_rate": 3.282944177993753e-05, "loss": 0.6082, "step": 13082 }, { "epoch": 0.20222535797728378, "grad_norm": 0.607782244682312, "learning_rate": 3.274964010696957e-05, "loss": 0.6067, "step": 13113 }, { "epoch": 0.20270343210961778, "grad_norm": 0.6200498938560486, "learning_rate": 3.266975098036629e-05, "loss": 0.6096, "step": 13144 }, { "epoch": 0.20318150624195178, "grad_norm": 0.6002140045166016, "learning_rate": 3.258977530166562e-05, "loss": 0.6029, "step": 13175 }, { "epoch": 0.20365958037428578, "grad_norm": 0.6123709082603455, "learning_rate": 3.250971397338227e-05, "loss": 0.6067, "step": 13206 }, { "epoch": 0.20413765450661978, "grad_norm": 0.5950725078582764, "learning_rate": 3.2429567898997404e-05, "loss": 0.6123, "step": 13237 }, { "epoch": 0.20461572863895378, "grad_norm": 0.5370542407035828, "learning_rate": 3.234933798294859e-05, "loss": 0.6037, "step": 13268 }, { "epoch": 0.2050938027712878, "grad_norm": 0.6526908874511719, "learning_rate": 3.2269025130619535e-05, "loss": 0.6093, "step": 13299 }, { "epoch": 0.2055718769036218, "grad_norm": 0.6925700306892395, "learning_rate": 3.218863024832985e-05, "loss": 0.6077, "step": 13330 }, { "epoch": 0.2060499510359558, "grad_norm": 0.6531749367713928, "learning_rate": 3.2108154243324864e-05, "loss": 0.6126, "step": 13361 }, { "epoch": 0.2065280251682898, "grad_norm": 0.7173174023628235, "learning_rate": 3.2027598023765345e-05, "loss": 0.5991, "step": 13392 }, { "epoch": 0.2070060993006238, "grad_norm": 0.7028422355651855, "learning_rate": 3.194696249871729e-05, "loss": 0.6037, "step": 13423 }, { "epoch": 0.2074841734329578, "grad_norm": 0.5837274193763733, "learning_rate": 3.186624857814164e-05, "loss": 0.6135, "step": 13454 }, { "epoch": 0.20796224756529183, "grad_norm": 0.6421070098876953, "learning_rate": 3.178545717288401e-05, "loss": 0.6095, "step": 13485 }, { "epoch": 0.20844032169762583, "grad_norm": 0.6141335964202881, "learning_rate": 3.170458919466444e-05, "loss": 0.6161, "step": 13516 }, { "epoch": 0.20891839582995983, "grad_norm": 0.6881201267242432, "learning_rate": 3.1623645556067063e-05, "loss": 0.6053, "step": 13547 }, { "epoch": 0.20939646996229383, "grad_norm": 0.655423104763031, "learning_rate": 3.154262717052985e-05, "loss": 0.6037, "step": 13578 }, { "epoch": 0.20987454409462783, "grad_norm": 0.5702130198478699, "learning_rate": 3.146153495233426e-05, "loss": 0.603, "step": 13609 }, { "epoch": 0.21035261822696183, "grad_norm": 0.6374569535255432, "learning_rate": 3.1380369816594944e-05, "loss": 0.6048, "step": 13640 }, { "epoch": 0.21083069235929583, "grad_norm": 0.6103787422180176, "learning_rate": 3.129913267924946e-05, "loss": 0.608, "step": 13671 }, { "epoch": 0.21130876649162986, "grad_norm": 0.6299352049827576, "learning_rate": 3.121782445704782e-05, "loss": 0.5993, "step": 13702 }, { "epoch": 0.21178684062396386, "grad_norm": 0.6262964010238647, "learning_rate": 3.11364460675423e-05, "loss": 0.6085, "step": 13733 }, { "epoch": 0.21226491475629786, "grad_norm": 0.5756493210792542, "learning_rate": 3.1054998429076934e-05, "loss": 0.6051, "step": 13764 }, { "epoch": 0.21274298888863186, "grad_norm": 0.5393940806388855, "learning_rate": 3.097348246077728e-05, "loss": 0.6072, "step": 13795 }, { "epoch": 0.21322106302096586, "grad_norm": 0.5831958651542664, "learning_rate": 3.0891899082539924e-05, "loss": 0.6015, "step": 13826 }, { "epoch": 0.21369913715329986, "grad_norm": 0.6049664616584778, "learning_rate": 3.0810249215022233e-05, "loss": 0.6136, "step": 13857 }, { "epoch": 0.21417721128563388, "grad_norm": 0.6627909541130066, "learning_rate": 3.0728533779631865e-05, "loss": 0.6027, "step": 13888 }, { "epoch": 0.21465528541796788, "grad_norm": 0.568748950958252, "learning_rate": 3.064675369851637e-05, "loss": 0.601, "step": 13919 }, { "epoch": 0.21513335955030188, "grad_norm": 0.6373331546783447, "learning_rate": 3.056490989455289e-05, "loss": 0.606, "step": 13950 }, { "epoch": 0.21561143368263588, "grad_norm": 0.5549852252006531, "learning_rate": 3.0483003291337596e-05, "loss": 0.5931, "step": 13981 }, { "epoch": 0.21608950781496988, "grad_norm": 0.5983837246894836, "learning_rate": 3.040103481317539e-05, "loss": 0.6023, "step": 14012 }, { "epoch": 0.21656758194730388, "grad_norm": 0.6063233017921448, "learning_rate": 3.03190053850694e-05, "loss": 0.5974, "step": 14043 }, { "epoch": 0.2170456560796379, "grad_norm": 3.3559274673461914, "learning_rate": 3.0236915932710573e-05, "loss": 0.6057, "step": 14074 }, { "epoch": 0.2175237302119719, "grad_norm": 0.5984488725662231, "learning_rate": 3.0154767382467232e-05, "loss": 0.5953, "step": 14105 }, { "epoch": 0.2180018043443059, "grad_norm": 0.5625097751617432, "learning_rate": 3.0072560661374582e-05, "loss": 0.6029, "step": 14136 }, { "epoch": 0.2184798784766399, "grad_norm": 0.6621974110603333, "learning_rate": 2.999029669712431e-05, "loss": 0.6042, "step": 14167 }, { "epoch": 0.2189579526089739, "grad_norm": 0.7209954857826233, "learning_rate": 2.990797641805408e-05, "loss": 0.6069, "step": 14198 }, { "epoch": 0.2194360267413079, "grad_norm": 0.4810869097709656, "learning_rate": 2.982560075313704e-05, "loss": 0.6131, "step": 14229 }, { "epoch": 0.2199141008736419, "grad_norm": 0.6061887145042419, "learning_rate": 2.9743170631971368e-05, "loss": 0.6012, "step": 14260 }, { "epoch": 0.22039217500597594, "grad_norm": 0.5912594795227051, "learning_rate": 2.9660686984769792e-05, "loss": 0.6042, "step": 14291 }, { "epoch": 0.22087024913830994, "grad_norm": 0.5847635269165039, "learning_rate": 2.9578150742349047e-05, "loss": 0.5945, "step": 14322 }, { "epoch": 0.22134832327064394, "grad_norm": 0.617660403251648, "learning_rate": 2.949556283611942e-05, "loss": 0.6008, "step": 14353 }, { "epoch": 0.22182639740297794, "grad_norm": 0.6549617052078247, "learning_rate": 2.9412924198074206e-05, "loss": 0.6055, "step": 14384 }, { "epoch": 0.22230447153531194, "grad_norm": 0.6084825396537781, "learning_rate": 2.9330235760779208e-05, "loss": 0.6059, "step": 14415 }, { "epoch": 0.22278254566764594, "grad_norm": 0.619442880153656, "learning_rate": 2.9247498457362188e-05, "loss": 0.6003, "step": 14446 }, { "epoch": 0.22326061979997996, "grad_norm": 0.5925353169441223, "learning_rate": 2.9164713221502373e-05, "loss": 0.6064, "step": 14477 }, { "epoch": 0.22373869393231396, "grad_norm": 0.6110435724258423, "learning_rate": 2.9081880987419912e-05, "loss": 0.5992, "step": 14508 }, { "epoch": 0.22421676806464796, "grad_norm": 0.5053293108940125, "learning_rate": 2.8999002689865296e-05, "loss": 0.5938, "step": 14539 }, { "epoch": 0.22469484219698196, "grad_norm": 0.6076425909996033, "learning_rate": 2.8916079264108852e-05, "loss": 0.6055, "step": 14570 }, { "epoch": 0.22517291632931596, "grad_norm": 0.6807154417037964, "learning_rate": 2.883311164593017e-05, "loss": 0.602, "step": 14601 }, { "epoch": 0.22565099046164996, "grad_norm": 0.6125125885009766, "learning_rate": 2.875010077160754e-05, "loss": 0.6044, "step": 14632 }, { "epoch": 0.22612906459398396, "grad_norm": 0.6103615164756775, "learning_rate": 2.866704757790741e-05, "loss": 0.5956, "step": 14663 }, { "epoch": 0.226607138726318, "grad_norm": 0.6321137547492981, "learning_rate": 2.858395300207376e-05, "loss": 0.6033, "step": 14694 }, { "epoch": 0.227085212858652, "grad_norm": 0.5844994783401489, "learning_rate": 2.8500817981817607e-05, "loss": 0.6015, "step": 14725 }, { "epoch": 0.227563286990986, "grad_norm": 0.648857593536377, "learning_rate": 2.8417643455306336e-05, "loss": 0.5939, "step": 14756 }, { "epoch": 0.22804136112332, "grad_norm": 0.6076569557189941, "learning_rate": 2.8334430361153185e-05, "loss": 0.5999, "step": 14787 }, { "epoch": 0.228519435255654, "grad_norm": 0.5311121344566345, "learning_rate": 2.8251179638406612e-05, "loss": 0.5961, "step": 14818 }, { "epoch": 0.228997509387988, "grad_norm": 0.6423148512840271, "learning_rate": 2.8167892226539704e-05, "loss": 0.5965, "step": 14849 }, { "epoch": 0.22947558352032202, "grad_norm": 0.6332517266273499, "learning_rate": 2.8084569065439588e-05, "loss": 0.5934, "step": 14880 }, { "epoch": 0.22995365765265602, "grad_norm": 0.6193598508834839, "learning_rate": 2.8001211095396807e-05, "loss": 0.6075, "step": 14911 }, { "epoch": 0.23043173178499002, "grad_norm": 0.6870059967041016, "learning_rate": 2.791781925709473e-05, "loss": 0.6044, "step": 14942 }, { "epoch": 0.23090980591732402, "grad_norm": 0.5324540138244629, "learning_rate": 2.7834394491598908e-05, "loss": 0.5908, "step": 14973 }, { "epoch": 0.23138788004965802, "grad_norm": 1.536717414855957, "learning_rate": 2.7750937740346485e-05, "loss": 0.5953, "step": 15004 }, { "epoch": 0.23186595418199202, "grad_norm": 0.550554096698761, "learning_rate": 2.7667449945135564e-05, "loss": 0.5952, "step": 15035 }, { "epoch": 0.23234402831432602, "grad_norm": 1.174824833869934, "learning_rate": 2.7583932048114557e-05, "loss": 0.6065, "step": 15066 }, { "epoch": 0.23282210244666005, "grad_norm": 0.6926533579826355, "learning_rate": 2.7500384991771587e-05, "loss": 0.6031, "step": 15097 }, { "epoch": 0.23330017657899405, "grad_norm": 0.6488378047943115, "learning_rate": 2.7416809718923825e-05, "loss": 0.5977, "step": 15128 }, { "epoch": 0.23377825071132805, "grad_norm": 0.5631073713302612, "learning_rate": 2.7333207172706864e-05, "loss": 0.6024, "step": 15159 }, { "epoch": 0.23425632484366204, "grad_norm": 0.5837413668632507, "learning_rate": 2.7249578296564088e-05, "loss": 0.5961, "step": 15190 }, { "epoch": 0.23473439897599604, "grad_norm": 0.5875633955001831, "learning_rate": 2.7165924034235973e-05, "loss": 0.6027, "step": 15221 }, { "epoch": 0.23521247310833004, "grad_norm": 0.5024504661560059, "learning_rate": 2.708224532974953e-05, "loss": 0.5951, "step": 15252 }, { "epoch": 0.23569054724066407, "grad_norm": 0.5877059698104858, "learning_rate": 2.6998543127407538e-05, "loss": 0.5953, "step": 15283 }, { "epoch": 0.23616862137299807, "grad_norm": 0.593683660030365, "learning_rate": 2.6914818371777988e-05, "loss": 0.5921, "step": 15314 }, { "epoch": 0.23664669550533207, "grad_norm": 0.6094300150871277, "learning_rate": 2.6831072007683373e-05, "loss": 0.6037, "step": 15345 }, { "epoch": 0.23712476963766607, "grad_norm": 0.5903526544570923, "learning_rate": 2.6747304980190018e-05, "loss": 0.5937, "step": 15376 }, { "epoch": 0.23760284377000007, "grad_norm": 0.5828642845153809, "learning_rate": 2.6663518234597453e-05, "loss": 0.5991, "step": 15407 }, { "epoch": 0.23808091790233407, "grad_norm": 0.728405237197876, "learning_rate": 2.6579712716427696e-05, "loss": 0.5882, "step": 15438 }, { "epoch": 0.2385589920346681, "grad_norm": 0.535317599773407, "learning_rate": 2.6495889371414652e-05, "loss": 0.6042, "step": 15469 }, { "epoch": 0.2390370661670021, "grad_norm": 0.6083411574363708, "learning_rate": 2.6412049145493367e-05, "loss": 0.601, "step": 15500 }, { "epoch": 0.2395151402993361, "grad_norm": 0.6077481508255005, "learning_rate": 2.632819298478939e-05, "loss": 0.5932, "step": 15531 }, { "epoch": 0.2399932144316701, "grad_norm": 0.7210131883621216, "learning_rate": 2.6244321835608105e-05, "loss": 0.602, "step": 15562 }, { "epoch": 0.2404712885640041, "grad_norm": 0.7543363571166992, "learning_rate": 2.6160436644424024e-05, "loss": 0.5919, "step": 15593 }, { "epoch": 0.2409493626963381, "grad_norm": 0.6915935277938843, "learning_rate": 2.6076538357870133e-05, "loss": 0.5992, "step": 15624 }, { "epoch": 0.2414274368286721, "grad_norm": 0.5868044495582581, "learning_rate": 2.5992627922727196e-05, "loss": 0.5909, "step": 15655 }, { "epoch": 0.24190551096100613, "grad_norm": 0.5753960013389587, "learning_rate": 2.5908706285913066e-05, "loss": 0.5996, "step": 15686 }, { "epoch": 0.24238358509334013, "grad_norm": 0.602874219417572, "learning_rate": 2.5824774394472008e-05, "loss": 0.5925, "step": 15717 }, { "epoch": 0.24286165922567413, "grad_norm": 0.6005914211273193, "learning_rate": 2.5740833195563996e-05, "loss": 0.5965, "step": 15748 }, { "epoch": 0.24333973335800813, "grad_norm": 0.6699410676956177, "learning_rate": 2.5656883636454067e-05, "loss": 0.5926, "step": 15779 }, { "epoch": 0.24381780749034213, "grad_norm": 0.6079136729240417, "learning_rate": 2.557292666450159e-05, "loss": 0.5895, "step": 15810 }, { "epoch": 0.24429588162267613, "grad_norm": 0.5411943197250366, "learning_rate": 2.5488963227149566e-05, "loss": 0.5982, "step": 15841 }, { "epoch": 0.24477395575501015, "grad_norm": 1.2917388677597046, "learning_rate": 2.5404994271913983e-05, "loss": 0.6009, "step": 15872 }, { "epoch": 0.24525202988734415, "grad_norm": 0.6021159887313843, "learning_rate": 2.5321020746373085e-05, "loss": 0.5942, "step": 15903 }, { "epoch": 0.24573010401967815, "grad_norm": 0.6222237944602966, "learning_rate": 2.52370435981567e-05, "loss": 0.5879, "step": 15934 }, { "epoch": 0.24620817815201215, "grad_norm": 0.609616756439209, "learning_rate": 2.5153063774935533e-05, "loss": 0.5977, "step": 15965 }, { "epoch": 0.24668625228434615, "grad_norm": 0.5242776274681091, "learning_rate": 2.506908222441045e-05, "loss": 0.5942, "step": 15996 }, { "epoch": 0.24716432641668015, "grad_norm": 0.5265721082687378, "learning_rate": 2.498509989430187e-05, "loss": 0.5886, "step": 16027 }, { "epoch": 0.24764240054901415, "grad_norm": 0.6138966679573059, "learning_rate": 2.4901117732338958e-05, "loss": 0.5978, "step": 16058 }, { "epoch": 0.24812047468134818, "grad_norm": 0.6608225107192993, "learning_rate": 2.481713668624899e-05, "loss": 0.59, "step": 16089 }, { "epoch": 0.24859854881368218, "grad_norm": 0.6166261434555054, "learning_rate": 2.4733157703746663e-05, "loss": 0.5953, "step": 16120 }, { "epoch": 0.24907662294601618, "grad_norm": 0.5305414795875549, "learning_rate": 2.4649181732523392e-05, "loss": 0.5977, "step": 16151 }, { "epoch": 0.24955469707835018, "grad_norm": 0.5814329981803894, "learning_rate": 2.4565209720236582e-05, "loss": 0.5871, "step": 16182 }, { "epoch": 0.2500327712106842, "grad_norm": 0.7118150591850281, "learning_rate": 2.4481242614498975e-05, "loss": 0.6003, "step": 16213 }, { "epoch": 0.2505108453430182, "grad_norm": 0.4954952597618103, "learning_rate": 2.439728136286796e-05, "loss": 0.5929, "step": 16244 }, { "epoch": 0.2509889194753522, "grad_norm": 0.5879791975021362, "learning_rate": 2.4313326912834852e-05, "loss": 0.5851, "step": 16275 }, { "epoch": 0.2514669936076862, "grad_norm": 0.5314292311668396, "learning_rate": 2.4229380211814206e-05, "loss": 0.593, "step": 16306 }, { "epoch": 0.2519450677400202, "grad_norm": 0.6319591403007507, "learning_rate": 2.4145442207133124e-05, "loss": 0.5925, "step": 16337 }, { "epoch": 0.2524231418723542, "grad_norm": 0.5172461867332458, "learning_rate": 2.406151384602059e-05, "loss": 0.5959, "step": 16368 }, { "epoch": 0.25290121600468823, "grad_norm": 0.5364922285079956, "learning_rate": 2.3977596075596747e-05, "loss": 0.6051, "step": 16399 }, { "epoch": 0.2533792901370222, "grad_norm": 0.5659622550010681, "learning_rate": 2.3893689842862223e-05, "loss": 0.5937, "step": 16430 }, { "epoch": 0.25385736426935623, "grad_norm": 0.7728786468505859, "learning_rate": 2.3809796094687475e-05, "loss": 0.5978, "step": 16461 }, { "epoch": 0.2543354384016902, "grad_norm": 0.5832898616790771, "learning_rate": 2.372591577780202e-05, "loss": 0.5965, "step": 16492 }, { "epoch": 0.25481351253402423, "grad_norm": 0.7000778913497925, "learning_rate": 2.3642049838783838e-05, "loss": 0.5914, "step": 16523 }, { "epoch": 0.2552915866663582, "grad_norm": 0.6954141855239868, "learning_rate": 2.3558199224048666e-05, "loss": 0.5936, "step": 16554 }, { "epoch": 0.25576966079869223, "grad_norm": 0.5859754681587219, "learning_rate": 2.347436487983929e-05, "loss": 0.5913, "step": 16585 }, { "epoch": 0.25624773493102626, "grad_norm": 0.6719058156013489, "learning_rate": 2.3390547752214888e-05, "loss": 0.5896, "step": 16616 }, { "epoch": 0.25672580906336023, "grad_norm": 0.5692052841186523, "learning_rate": 2.330674878704035e-05, "loss": 0.5912, "step": 16647 }, { "epoch": 0.25720388319569426, "grad_norm": 0.5615118145942688, "learning_rate": 2.322296892997561e-05, "loss": 0.5913, "step": 16678 }, { "epoch": 0.25768195732802823, "grad_norm": 0.6449048519134521, "learning_rate": 2.313920912646497e-05, "loss": 0.5933, "step": 16709 }, { "epoch": 0.25816003146036226, "grad_norm": 0.5827602744102478, "learning_rate": 2.305547032172643e-05, "loss": 0.5912, "step": 16740 }, { "epoch": 0.2586381055926963, "grad_norm": 0.6197795271873474, "learning_rate": 2.2971753460741014e-05, "loss": 0.5911, "step": 16771 }, { "epoch": 0.25911617972503026, "grad_norm": 0.6223908066749573, "learning_rate": 2.288805948824212e-05, "loss": 0.5971, "step": 16802 }, { "epoch": 0.2595942538573643, "grad_norm": 0.5632069706916809, "learning_rate": 2.2804389348704858e-05, "loss": 0.5942, "step": 16833 }, { "epoch": 0.26007232798969826, "grad_norm": 0.5121845006942749, "learning_rate": 2.2720743986335374e-05, "loss": 0.5891, "step": 16864 }, { "epoch": 0.2605504021220323, "grad_norm": 0.5367355942726135, "learning_rate": 2.2637124345060233e-05, "loss": 0.5904, "step": 16895 }, { "epoch": 0.26102847625436626, "grad_norm": 0.5924873948097229, "learning_rate": 2.2553531368515695e-05, "loss": 0.5883, "step": 16926 }, { "epoch": 0.2615065503867003, "grad_norm": 0.5673496127128601, "learning_rate": 2.2469966000037144e-05, "loss": 0.5938, "step": 16957 }, { "epoch": 0.2619846245190343, "grad_norm": 0.5983547568321228, "learning_rate": 2.2386429182648417e-05, "loss": 0.5857, "step": 16988 }, { "epoch": 0.2624626986513683, "grad_norm": 0.6841906905174255, "learning_rate": 2.230292185905114e-05, "loss": 0.6016, "step": 17019 }, { "epoch": 0.2629407727837023, "grad_norm": 0.5953052639961243, "learning_rate": 2.2219444971614116e-05, "loss": 0.6035, "step": 17050 }, { "epoch": 0.2634188469160363, "grad_norm": 0.6069731116294861, "learning_rate": 2.2135999462362655e-05, "loss": 0.5854, "step": 17081 }, { "epoch": 0.2638969210483703, "grad_norm": 0.5507410168647766, "learning_rate": 2.2052586272968003e-05, "loss": 0.5892, "step": 17112 }, { "epoch": 0.2643749951807043, "grad_norm": 0.5835263133049011, "learning_rate": 2.196920634473666e-05, "loss": 0.596, "step": 17143 }, { "epoch": 0.2648530693130383, "grad_norm": 0.5266990065574646, "learning_rate": 2.1885860618599787e-05, "loss": 0.584, "step": 17174 }, { "epoch": 0.26533114344537234, "grad_norm": 0.5418040156364441, "learning_rate": 2.1802550035102577e-05, "loss": 0.5954, "step": 17205 }, { "epoch": 0.2658092175777063, "grad_norm": 0.5487755537033081, "learning_rate": 2.171927553439363e-05, "loss": 0.5948, "step": 17236 }, { "epoch": 0.26628729171004034, "grad_norm": 0.6113549470901489, "learning_rate": 2.1636038056214376e-05, "loss": 0.5889, "step": 17267 }, { "epoch": 0.2667653658423743, "grad_norm": 0.7934780716896057, "learning_rate": 2.155283853988844e-05, "loss": 0.5891, "step": 17298 }, { "epoch": 0.26724343997470834, "grad_norm": 0.5100197792053223, "learning_rate": 2.146967792431106e-05, "loss": 0.5926, "step": 17329 }, { "epoch": 0.2677215141070423, "grad_norm": 0.5467435121536255, "learning_rate": 2.138655714793849e-05, "loss": 0.5923, "step": 17360 }, { "epoch": 0.26819958823937634, "grad_norm": 0.557858407497406, "learning_rate": 2.1303477148777367e-05, "loss": 0.5983, "step": 17391 }, { "epoch": 0.26867766237171037, "grad_norm": 0.5128514170646667, "learning_rate": 2.122043886437421e-05, "loss": 0.592, "step": 17422 }, { "epoch": 0.26915573650404434, "grad_norm": 0.5660766363143921, "learning_rate": 2.1137443231804765e-05, "loss": 0.5865, "step": 17453 }, { "epoch": 0.26963381063637837, "grad_norm": 0.6714511513710022, "learning_rate": 2.105449118766347e-05, "loss": 0.5902, "step": 17484 }, { "epoch": 0.27011188476871234, "grad_norm": 0.6227546334266663, "learning_rate": 2.097158366805287e-05, "loss": 0.5884, "step": 17515 }, { "epoch": 0.27058995890104637, "grad_norm": 0.5964284539222717, "learning_rate": 2.0888721608573047e-05, "loss": 0.5815, "step": 17546 }, { "epoch": 0.2710680330333804, "grad_norm": 0.6127567887306213, "learning_rate": 2.0805905944311087e-05, "loss": 0.5927, "step": 17577 }, { "epoch": 0.27154610716571437, "grad_norm": 0.5167319178581238, "learning_rate": 2.0723137609830497e-05, "loss": 0.5934, "step": 17608 }, { "epoch": 0.2720241812980484, "grad_norm": 0.6052663326263428, "learning_rate": 2.0640417539160686e-05, "loss": 0.5927, "step": 17639 }, { "epoch": 0.27250225543038237, "grad_norm": 0.6475414633750916, "learning_rate": 2.0557746665786427e-05, "loss": 0.5927, "step": 17670 }, { "epoch": 0.2729803295627164, "grad_norm": 0.5984682440757751, "learning_rate": 2.0475125922637256e-05, "loss": 0.5902, "step": 17701 }, { "epoch": 0.27345840369505037, "grad_norm": 0.5002421140670776, "learning_rate": 2.0392556242077047e-05, "loss": 0.6001, "step": 17732 }, { "epoch": 0.2739364778273844, "grad_norm": 0.6157301664352417, "learning_rate": 2.031003855589343e-05, "loss": 0.5844, "step": 17763 }, { "epoch": 0.2744145519597184, "grad_norm": 0.6168811321258545, "learning_rate": 2.022757379528727e-05, "loss": 0.5906, "step": 17794 }, { "epoch": 0.2748926260920524, "grad_norm": 0.5338504910469055, "learning_rate": 2.0145162890862184e-05, "loss": 0.5824, "step": 17825 }, { "epoch": 0.2753707002243864, "grad_norm": 0.5488714575767517, "learning_rate": 2.0062806772614022e-05, "loss": 0.5879, "step": 17856 }, { "epoch": 0.2758487743567204, "grad_norm": 0.5172461271286011, "learning_rate": 1.9980506369920392e-05, "loss": 0.5877, "step": 17887 }, { "epoch": 0.2763268484890544, "grad_norm": 0.5921024084091187, "learning_rate": 1.989826261153015e-05, "loss": 0.5922, "step": 17918 }, { "epoch": 0.2768049226213884, "grad_norm": 0.5407642126083374, "learning_rate": 1.9816076425552923e-05, "loss": 0.5897, "step": 17949 }, { "epoch": 0.2772829967537224, "grad_norm": 0.536432147026062, "learning_rate": 1.9733948739448676e-05, "loss": 0.5915, "step": 17980 }, { "epoch": 0.27776107088605645, "grad_norm": 0.6100837588310242, "learning_rate": 1.9651880480017155e-05, "loss": 0.5899, "step": 18011 }, { "epoch": 0.2782391450183904, "grad_norm": 0.5521765351295471, "learning_rate": 1.9569872573387516e-05, "loss": 0.5875, "step": 18042 }, { "epoch": 0.27871721915072445, "grad_norm": 0.5669123530387878, "learning_rate": 1.9487925945007854e-05, "loss": 0.5915, "step": 18073 }, { "epoch": 0.2791952932830584, "grad_norm": 0.5691494345664978, "learning_rate": 1.9406041519634726e-05, "loss": 0.5813, "step": 18104 }, { "epoch": 0.27967336741539245, "grad_norm": 0.6357378959655762, "learning_rate": 1.932422022132275e-05, "loss": 0.5832, "step": 18135 }, { "epoch": 0.2801514415477265, "grad_norm": 0.6269022822380066, "learning_rate": 1.924246297341414e-05, "loss": 0.5878, "step": 18166 }, { "epoch": 0.28062951568006045, "grad_norm": 0.5049974322319031, "learning_rate": 1.9160770698528338e-05, "loss": 0.5791, "step": 18197 }, { "epoch": 0.2811075898123945, "grad_norm": 0.5020114779472351, "learning_rate": 1.907914431855156e-05, "loss": 0.5804, "step": 18228 }, { "epoch": 0.28158566394472845, "grad_norm": 0.6124894022941589, "learning_rate": 1.8997584754626412e-05, "loss": 0.582, "step": 18259 }, { "epoch": 0.2820637380770625, "grad_norm": 0.532447099685669, "learning_rate": 1.8916092927141486e-05, "loss": 0.5836, "step": 18290 }, { "epoch": 0.28254181220939645, "grad_norm": 0.6032750010490417, "learning_rate": 1.883466975572098e-05, "loss": 0.5814, "step": 18321 }, { "epoch": 0.2830198863417305, "grad_norm": 0.5806031227111816, "learning_rate": 1.8753316159214312e-05, "loss": 0.5784, "step": 18352 }, { "epoch": 0.2834979604740645, "grad_norm": 0.6188846826553345, "learning_rate": 1.8672033055685766e-05, "loss": 0.5795, "step": 18383 }, { "epoch": 0.2839760346063985, "grad_norm": 0.5964253544807434, "learning_rate": 1.8590821362404116e-05, "loss": 0.5859, "step": 18414 }, { "epoch": 0.2844541087387325, "grad_norm": 0.5597705245018005, "learning_rate": 1.8509681995832294e-05, "loss": 0.5877, "step": 18445 }, { "epoch": 0.2849321828710665, "grad_norm": 0.5870900750160217, "learning_rate": 1.8428615871617004e-05, "loss": 0.5879, "step": 18476 }, { "epoch": 0.2854102570034005, "grad_norm": 0.6172513961791992, "learning_rate": 1.8347623904578448e-05, "loss": 0.5825, "step": 18507 }, { "epoch": 0.2858883311357345, "grad_norm": 0.6141090989112854, "learning_rate": 1.8266707008699975e-05, "loss": 0.5794, "step": 18538 }, { "epoch": 0.2863664052680685, "grad_norm": 0.5404875874519348, "learning_rate": 1.818586609711774e-05, "loss": 0.5779, "step": 18569 }, { "epoch": 0.28684447940040253, "grad_norm": 0.5638667941093445, "learning_rate": 1.8105102082110462e-05, "loss": 0.5907, "step": 18600 }, { "epoch": 0.2873225535327365, "grad_norm": 0.6166080236434937, "learning_rate": 1.8024415875089058e-05, "loss": 0.5787, "step": 18631 }, { "epoch": 0.28780062766507053, "grad_norm": 0.6575906872749329, "learning_rate": 1.7943808386586407e-05, "loss": 0.5868, "step": 18662 }, { "epoch": 0.2882787017974045, "grad_norm": 0.6117292046546936, "learning_rate": 1.7863280526247073e-05, "loss": 0.586, "step": 18693 }, { "epoch": 0.28875677592973853, "grad_norm": 0.5406068563461304, "learning_rate": 1.7782833202817003e-05, "loss": 0.5828, "step": 18724 }, { "epoch": 0.2892348500620725, "grad_norm": 0.5712701678276062, "learning_rate": 1.7702467324133327e-05, "loss": 0.585, "step": 18755 }, { "epoch": 0.28971292419440653, "grad_norm": 0.602117121219635, "learning_rate": 1.7622183797114042e-05, "loss": 0.5862, "step": 18786 }, { "epoch": 0.29019099832674056, "grad_norm": 0.5379143953323364, "learning_rate": 1.7541983527747838e-05, "loss": 0.5868, "step": 18817 }, { "epoch": 0.29066907245907453, "grad_norm": 0.5759631991386414, "learning_rate": 1.746186742108387e-05, "loss": 0.586, "step": 18848 }, { "epoch": 0.29114714659140856, "grad_norm": 0.543383002281189, "learning_rate": 1.73818363812215e-05, "loss": 0.5849, "step": 18879 }, { "epoch": 0.29162522072374253, "grad_norm": 0.6425350308418274, "learning_rate": 1.7301891311300153e-05, "loss": 0.5888, "step": 18910 }, { "epoch": 0.29210329485607656, "grad_norm": 0.5259391069412231, "learning_rate": 1.7222033113489055e-05, "loss": 0.5846, "step": 18941 }, { "epoch": 0.2925813689884106, "grad_norm": 0.5230016708374023, "learning_rate": 1.7142262688977127e-05, "loss": 0.5836, "step": 18972 }, { "epoch": 0.29305944312074456, "grad_norm": 0.5167984962463379, "learning_rate": 1.7062580937962764e-05, "loss": 0.5839, "step": 19003 }, { "epoch": 0.2935375172530786, "grad_norm": 0.6248798370361328, "learning_rate": 1.698298875964369e-05, "loss": 0.5826, "step": 19034 }, { "epoch": 0.29401559138541256, "grad_norm": 0.5567784309387207, "learning_rate": 1.690348705220684e-05, "loss": 0.5798, "step": 19065 }, { "epoch": 0.2944936655177466, "grad_norm": 0.6178439855575562, "learning_rate": 1.6824076712818156e-05, "loss": 0.5872, "step": 19096 }, { "epoch": 0.29497173965008056, "grad_norm": 0.5599183440208435, "learning_rate": 1.6744758637612533e-05, "loss": 0.5912, "step": 19127 }, { "epoch": 0.2954498137824146, "grad_norm": 0.5310354828834534, "learning_rate": 1.6665533721683664e-05, "loss": 0.5825, "step": 19158 }, { "epoch": 0.2959278879147486, "grad_norm": 0.477606862783432, "learning_rate": 1.6586402859073974e-05, "loss": 0.5834, "step": 19189 }, { "epoch": 0.2964059620470826, "grad_norm": 0.6715511679649353, "learning_rate": 1.6507366942764463e-05, "loss": 0.587, "step": 19220 }, { "epoch": 0.2968840361794166, "grad_norm": 0.6267414689064026, "learning_rate": 1.6428426864664732e-05, "loss": 0.5748, "step": 19251 }, { "epoch": 0.2973621103117506, "grad_norm": 0.5867800712585449, "learning_rate": 1.6349583515602816e-05, "loss": 0.5847, "step": 19282 }, { "epoch": 0.2978401844440846, "grad_norm": 0.6102165579795837, "learning_rate": 1.6270837785315208e-05, "loss": 0.585, "step": 19313 }, { "epoch": 0.2983182585764186, "grad_norm": 0.5824636816978455, "learning_rate": 1.619219056243676e-05, "loss": 0.5791, "step": 19344 }, { "epoch": 0.2987963327087526, "grad_norm": 0.558809757232666, "learning_rate": 1.6113642734490698e-05, "loss": 0.5746, "step": 19375 }, { "epoch": 0.29927440684108664, "grad_norm": 0.5723096132278442, "learning_rate": 1.6035195187878577e-05, "loss": 0.5808, "step": 19406 }, { "epoch": 0.2997524809734206, "grad_norm": 0.5783522725105286, "learning_rate": 1.5956848807870305e-05, "loss": 0.5909, "step": 19437 }, { "epoch": 0.30023055510575464, "grad_norm": 0.605096697807312, "learning_rate": 1.587860447859413e-05, "loss": 0.5827, "step": 19468 }, { "epoch": 0.3007086292380886, "grad_norm": 0.5810924768447876, "learning_rate": 1.5800463083026686e-05, "loss": 0.5874, "step": 19499 }, { "epoch": 0.30118670337042264, "grad_norm": 0.5270748734474182, "learning_rate": 1.572242550298298e-05, "loss": 0.5724, "step": 19530 }, { "epoch": 0.30166477750275666, "grad_norm": 0.6422134041786194, "learning_rate": 1.56444926191065e-05, "loss": 0.5879, "step": 19561 }, { "epoch": 0.30214285163509064, "grad_norm": 0.5272889733314514, "learning_rate": 1.5566665310859257e-05, "loss": 0.5772, "step": 19592 }, { "epoch": 0.30262092576742466, "grad_norm": 0.7464088201522827, "learning_rate": 1.5488944456511846e-05, "loss": 0.5874, "step": 19623 }, { "epoch": 0.30309899989975864, "grad_norm": 0.5078160166740417, "learning_rate": 1.5411330933133546e-05, "loss": 0.5781, "step": 19654 }, { "epoch": 0.30357707403209266, "grad_norm": 0.56827712059021, "learning_rate": 1.533382561658241e-05, "loss": 0.579, "step": 19685 }, { "epoch": 0.30405514816442664, "grad_norm": 0.5845567584037781, "learning_rate": 1.525642938149541e-05, "loss": 0.5774, "step": 19716 }, { "epoch": 0.30453322229676066, "grad_norm": 0.5950722694396973, "learning_rate": 1.5179143101278536e-05, "loss": 0.576, "step": 19747 }, { "epoch": 0.3050112964290947, "grad_norm": 0.5643905997276306, "learning_rate": 1.5101967648096955e-05, "loss": 0.5803, "step": 19778 }, { "epoch": 0.30548937056142866, "grad_norm": 0.6215445399284363, "learning_rate": 1.5024903892865172e-05, "loss": 0.579, "step": 19809 }, { "epoch": 0.3059674446937627, "grad_norm": 0.5208318829536438, "learning_rate": 1.4947952705237184e-05, "loss": 0.5777, "step": 19840 }, { "epoch": 0.30644551882609666, "grad_norm": 0.6431962251663208, "learning_rate": 1.4871114953596682e-05, "loss": 0.5829, "step": 19871 }, { "epoch": 0.3069235929584307, "grad_norm": 0.4828816056251526, "learning_rate": 1.4794391505047256e-05, "loss": 0.5742, "step": 19902 }, { "epoch": 0.30740166709076466, "grad_norm": 0.6670913696289062, "learning_rate": 1.4717783225402596e-05, "loss": 0.5793, "step": 19933 }, { "epoch": 0.3078797412230987, "grad_norm": 0.5313072204589844, "learning_rate": 1.4641290979176735e-05, "loss": 0.5847, "step": 19964 }, { "epoch": 0.3083578153554327, "grad_norm": 0.5336267948150635, "learning_rate": 1.4564915629574246e-05, "loss": 0.5844, "step": 19995 }, { "epoch": 0.3088358894877667, "grad_norm": 0.6394053101539612, "learning_rate": 1.4488658038480601e-05, "loss": 0.5807, "step": 20026 }, { "epoch": 0.3093139636201007, "grad_norm": 0.6073569059371948, "learning_rate": 1.4412519066452323e-05, "loss": 0.5844, "step": 20057 }, { "epoch": 0.3097920377524347, "grad_norm": 0.6105561852455139, "learning_rate": 1.4336499572707373e-05, "loss": 0.5829, "step": 20088 }, { "epoch": 0.3102701118847687, "grad_norm": 0.6145188212394714, "learning_rate": 1.4260600415115433e-05, "loss": 0.5847, "step": 20119 }, { "epoch": 0.3107481860171027, "grad_norm": 0.5367770195007324, "learning_rate": 1.4184822450188137e-05, "loss": 0.5873, "step": 20150 }, { "epoch": 0.3112262601494367, "grad_norm": 0.6103881001472473, "learning_rate": 1.410916653306954e-05, "loss": 0.5772, "step": 20181 }, { "epoch": 0.31170433428177075, "grad_norm": 0.5279451012611389, "learning_rate": 1.403363351752639e-05, "loss": 0.5724, "step": 20212 }, { "epoch": 0.3121824084141047, "grad_norm": 0.5088768005371094, "learning_rate": 1.3958224255938485e-05, "loss": 0.5799, "step": 20243 }, { "epoch": 0.31266048254643874, "grad_norm": 0.6134737730026245, "learning_rate": 1.388293959928911e-05, "loss": 0.5876, "step": 20274 }, { "epoch": 0.3131385566787727, "grad_norm": 0.5696072578430176, "learning_rate": 1.3807780397155379e-05, "loss": 0.5768, "step": 20305 }, { "epoch": 0.31361663081110674, "grad_norm": 0.6008872389793396, "learning_rate": 1.3732747497698655e-05, "loss": 0.5863, "step": 20336 }, { "epoch": 0.3140947049434408, "grad_norm": 0.5617655515670776, "learning_rate": 1.3657841747655038e-05, "loss": 0.577, "step": 20367 }, { "epoch": 0.31457277907577474, "grad_norm": 0.6002852320671082, "learning_rate": 1.3583063992325706e-05, "loss": 0.5812, "step": 20398 }, { "epoch": 0.31505085320810877, "grad_norm": 0.5778743028640747, "learning_rate": 1.3508415075567496e-05, "loss": 0.5813, "step": 20429 }, { "epoch": 0.31552892734044274, "grad_norm": 0.5733532309532166, "learning_rate": 1.343389583978327e-05, "loss": 0.589, "step": 20460 }, { "epoch": 0.31600700147277677, "grad_norm": 0.5163986682891846, "learning_rate": 1.3359507125912468e-05, "loss": 0.575, "step": 20491 }, { "epoch": 0.31648507560511074, "grad_norm": 0.5018510818481445, "learning_rate": 1.3285249773421627e-05, "loss": 0.5791, "step": 20522 }, { "epoch": 0.31696314973744477, "grad_norm": 0.53333979845047, "learning_rate": 1.3211124620294884e-05, "loss": 0.5869, "step": 20553 }, { "epoch": 0.3174412238697788, "grad_norm": 0.6099141240119934, "learning_rate": 1.313713250302451e-05, "loss": 0.5796, "step": 20584 }, { "epoch": 0.31791929800211277, "grad_norm": 0.6042903065681458, "learning_rate": 1.3063274256601479e-05, "loss": 0.5694, "step": 20615 }, { "epoch": 0.3183973721344468, "grad_norm": 0.5727267265319824, "learning_rate": 1.2989550714506086e-05, "loss": 0.5802, "step": 20646 }, { "epoch": 0.31887544626678077, "grad_norm": 0.5630910396575928, "learning_rate": 1.291596270869846e-05, "loss": 0.5629, "step": 20677 }, { "epoch": 0.3193535203991148, "grad_norm": 0.5013255476951599, "learning_rate": 1.284251106960927e-05, "loss": 0.5829, "step": 20708 }, { "epoch": 0.31983159453144877, "grad_norm": 0.5741969347000122, "learning_rate": 1.2769196626130263e-05, "loss": 0.5744, "step": 20739 }, { "epoch": 0.3203096686637828, "grad_norm": 0.552740216255188, "learning_rate": 1.2696020205604969e-05, "loss": 0.5808, "step": 20770 }, { "epoch": 0.3207877427961168, "grad_norm": 0.6418048739433289, "learning_rate": 1.2622982633819359e-05, "loss": 0.5871, "step": 20801 }, { "epoch": 0.3212658169284508, "grad_norm": 0.6518685817718506, "learning_rate": 1.2550084734992484e-05, "loss": 0.572, "step": 20832 }, { "epoch": 0.3217438910607848, "grad_norm": 0.535139262676239, "learning_rate": 1.247732733176724e-05, "loss": 0.5768, "step": 20863 }, { "epoch": 0.3222219651931188, "grad_norm": 0.579274594783783, "learning_rate": 1.2404711245201044e-05, "loss": 0.5803, "step": 20894 }, { "epoch": 0.3227000393254528, "grad_norm": 0.5379701256752014, "learning_rate": 1.2332237294756535e-05, "loss": 0.5844, "step": 20925 }, { "epoch": 0.3231781134577868, "grad_norm": 0.48069506883621216, "learning_rate": 1.225990629829241e-05, "loss": 0.5728, "step": 20956 }, { "epoch": 0.3236561875901208, "grad_norm": 0.576770007610321, "learning_rate": 1.2187719072054136e-05, "loss": 0.5838, "step": 20987 }, { "epoch": 0.32413426172245485, "grad_norm": 0.6682817339897156, "learning_rate": 1.2115676430664735e-05, "loss": 0.5746, "step": 21018 }, { "epoch": 0.3246123358547888, "grad_norm": 0.576655387878418, "learning_rate": 1.2043779187115647e-05, "loss": 0.5776, "step": 21049 }, { "epoch": 0.32509040998712285, "grad_norm": 0.5452989935874939, "learning_rate": 1.1972028152757476e-05, "loss": 0.5862, "step": 21080 }, { "epoch": 0.3255684841194568, "grad_norm": 0.5150167942047119, "learning_rate": 1.1900424137290889e-05, "loss": 0.5903, "step": 21111 }, { "epoch": 0.32604655825179085, "grad_norm": 0.5409998297691345, "learning_rate": 1.1828967948757482e-05, "loss": 0.5776, "step": 21142 }, { "epoch": 0.3265246323841249, "grad_norm": 0.5723608136177063, "learning_rate": 1.175766039353062e-05, "loss": 0.5832, "step": 21173 }, { "epoch": 0.32700270651645885, "grad_norm": 0.5304202437400818, "learning_rate": 1.1686502276306382e-05, "loss": 0.5797, "step": 21204 }, { "epoch": 0.3274807806487929, "grad_norm": 0.5880327820777893, "learning_rate": 1.1615494400094445e-05, "loss": 0.5807, "step": 21235 }, { "epoch": 0.32795885478112685, "grad_norm": 0.5001874566078186, "learning_rate": 1.1544637566209029e-05, "loss": 0.5784, "step": 21266 }, { "epoch": 0.3284369289134609, "grad_norm": 0.6035870909690857, "learning_rate": 1.1473932574259886e-05, "loss": 0.5758, "step": 21297 }, { "epoch": 0.32891500304579485, "grad_norm": 0.5601738691329956, "learning_rate": 1.1403380222143247e-05, "loss": 0.5805, "step": 21328 }, { "epoch": 0.3293930771781289, "grad_norm": 0.5500284433364868, "learning_rate": 1.1332981306032808e-05, "loss": 0.5744, "step": 21359 }, { "epoch": 0.3298711513104629, "grad_norm": 0.515215277671814, "learning_rate": 1.1262736620370762e-05, "loss": 0.58, "step": 21390 }, { "epoch": 0.3303492254427969, "grad_norm": 0.6095441579818726, "learning_rate": 1.1192646957858854e-05, "loss": 0.5731, "step": 21421 }, { "epoch": 0.3308272995751309, "grad_norm": 0.5884034633636475, "learning_rate": 1.1122713109449381e-05, "loss": 0.5769, "step": 21452 }, { "epoch": 0.3313053737074649, "grad_norm": 0.49037814140319824, "learning_rate": 1.105293586433634e-05, "loss": 0.5812, "step": 21483 }, { "epoch": 0.3317834478397989, "grad_norm": 0.5256391167640686, "learning_rate": 1.0983316009946446e-05, "loss": 0.5807, "step": 21514 }, { "epoch": 0.3322615219721329, "grad_norm": 0.6110324263572693, "learning_rate": 1.0913854331930282e-05, "loss": 0.5735, "step": 21545 }, { "epoch": 0.3327395961044669, "grad_norm": 0.5897322297096252, "learning_rate": 1.0844551614153456e-05, "loss": 0.5748, "step": 21576 }, { "epoch": 0.33321767023680093, "grad_norm": 0.5892772078514099, "learning_rate": 1.0775408638687725e-05, "loss": 0.5733, "step": 21607 }, { "epoch": 0.3336957443691349, "grad_norm": 0.5256847739219666, "learning_rate": 1.0706426185802165e-05, "loss": 0.5786, "step": 21638 }, { "epoch": 0.33417381850146893, "grad_norm": 0.5861433744430542, "learning_rate": 1.0637605033954371e-05, "loss": 0.5749, "step": 21669 }, { "epoch": 0.3346518926338029, "grad_norm": 0.5262039303779602, "learning_rate": 1.05689459597817e-05, "loss": 0.5675, "step": 21700 }, { "epoch": 0.33512996676613693, "grad_norm": 0.5511645674705505, "learning_rate": 1.050044973809246e-05, "loss": 0.5802, "step": 21731 }, { "epoch": 0.33560804089847096, "grad_norm": 0.5599253177642822, "learning_rate": 1.043211714185722e-05, "loss": 0.5825, "step": 21762 }, { "epoch": 0.33608611503080493, "grad_norm": 0.5281076431274414, "learning_rate": 1.036394894220003e-05, "loss": 0.5801, "step": 21793 }, { "epoch": 0.33656418916313896, "grad_norm": 0.5938977599143982, "learning_rate": 1.0295945908389751e-05, "loss": 0.5782, "step": 21824 }, { "epoch": 0.33704226329547293, "grad_norm": 0.5920172929763794, "learning_rate": 1.0228108807831393e-05, "loss": 0.5703, "step": 21855 }, { "epoch": 0.33752033742780696, "grad_norm": 0.5725109577178955, "learning_rate": 1.01604384060574e-05, "loss": 0.5764, "step": 21886 }, { "epoch": 0.33799841156014093, "grad_norm": 0.5738679766654968, "learning_rate": 1.009293546671907e-05, "loss": 0.5726, "step": 21917 }, { "epoch": 0.33847648569247496, "grad_norm": 0.5508648753166199, "learning_rate": 1.002560075157791e-05, "loss": 0.5698, "step": 21948 }, { "epoch": 0.338954559824809, "grad_norm": 0.5032240748405457, "learning_rate": 9.958435020496995e-06, "loss": 0.5765, "step": 21979 }, { "epoch": 0.33943263395714296, "grad_norm": 0.5450903177261353, "learning_rate": 9.89143903143249e-06, "loss": 0.5723, "step": 22010 }, { "epoch": 0.339910708089477, "grad_norm": 0.5665742754936218, "learning_rate": 9.824613540425038e-06, "loss": 0.5696, "step": 22041 }, { "epoch": 0.34038878222181096, "grad_norm": 0.572994589805603, "learning_rate": 9.757959301591197e-06, "loss": 0.5768, "step": 22072 }, { "epoch": 0.340866856354145, "grad_norm": 0.5740769505500793, "learning_rate": 9.691477067115017e-06, "loss": 0.5748, "step": 22103 }, { "epoch": 0.34134493048647896, "grad_norm": 0.5839989185333252, "learning_rate": 9.625167587239467e-06, "loss": 0.5764, "step": 22134 }, { "epoch": 0.341823004618813, "grad_norm": 5.201451778411865, "learning_rate": 9.559031610258007e-06, "loss": 0.5676, "step": 22165 }, { "epoch": 0.342301078751147, "grad_norm": 0.5265706181526184, "learning_rate": 9.493069882506164e-06, "loss": 0.5733, "step": 22196 }, { "epoch": 0.342779152883481, "grad_norm": 0.596712052822113, "learning_rate": 9.427283148353056e-06, "loss": 0.575, "step": 22227 }, { "epoch": 0.343257227015815, "grad_norm": 0.6111375093460083, "learning_rate": 9.361672150193052e-06, "loss": 0.5784, "step": 22258 }, { "epoch": 0.343735301148149, "grad_norm": 0.5548860430717468, "learning_rate": 9.29623762843734e-06, "loss": 0.5689, "step": 22289 }, { "epoch": 0.344213375280483, "grad_norm": 0.5465906858444214, "learning_rate": 9.230980321505594e-06, "loss": 0.58, "step": 22320 }, { "epoch": 0.344691449412817, "grad_norm": 0.589872419834137, "learning_rate": 9.165900965817668e-06, "loss": 0.5717, "step": 22351 }, { "epoch": 0.345169523545151, "grad_norm": 0.581211268901825, "learning_rate": 9.101000295785245e-06, "loss": 0.5736, "step": 22382 }, { "epoch": 0.34564759767748504, "grad_norm": 0.6026866436004639, "learning_rate": 9.036279043803565e-06, "loss": 0.5763, "step": 22413 }, { "epoch": 0.346125671809819, "grad_norm": 0.6060176491737366, "learning_rate": 8.971737940243147e-06, "loss": 0.572, "step": 22444 }, { "epoch": 0.34660374594215304, "grad_norm": 0.5560024976730347, "learning_rate": 8.907377713441592e-06, "loss": 0.5705, "step": 22475 }, { "epoch": 0.347081820074487, "grad_norm": 0.6205755472183228, "learning_rate": 8.843199089695293e-06, "loss": 0.5685, "step": 22506 }, { "epoch": 0.34755989420682104, "grad_norm": 0.5278075337409973, "learning_rate": 8.779202793251311e-06, "loss": 0.5688, "step": 22537 }, { "epoch": 0.34803796833915507, "grad_norm": 0.5662840008735657, "learning_rate": 8.715389546299149e-06, "loss": 0.5853, "step": 22568 }, { "epoch": 0.34851604247148904, "grad_norm": 0.5269712209701538, "learning_rate": 8.651760068962617e-06, "loss": 0.5802, "step": 22599 }, { "epoch": 0.34899411660382307, "grad_norm": 0.5230329632759094, "learning_rate": 8.588315079291733e-06, "loss": 0.568, "step": 22630 }, { "epoch": 0.34947219073615704, "grad_norm": 0.627826988697052, "learning_rate": 8.52505529325457e-06, "loss": 0.568, "step": 22661 }, { "epoch": 0.34995026486849107, "grad_norm": 0.6054178476333618, "learning_rate": 8.461981424729216e-06, "loss": 0.5756, "step": 22692 }, { "epoch": 0.35042833900082504, "grad_norm": 0.47537288069725037, "learning_rate": 8.399094185495725e-06, "loss": 0.5667, "step": 22723 }, { "epoch": 0.35090641313315907, "grad_norm": 0.5262076258659363, "learning_rate": 8.336394285228017e-06, "loss": 0.5807, "step": 22754 }, { "epoch": 0.3513844872654931, "grad_norm": 0.6217135190963745, "learning_rate": 8.273882431485952e-06, "loss": 0.5706, "step": 22785 }, { "epoch": 0.35186256139782707, "grad_norm": 0.5373092889785767, "learning_rate": 8.211559329707316e-06, "loss": 0.5743, "step": 22816 }, { "epoch": 0.3523406355301611, "grad_norm": 0.5938353538513184, "learning_rate": 8.149425683199823e-06, "loss": 0.5811, "step": 22847 }, { "epoch": 0.35281870966249507, "grad_norm": 0.654653787612915, "learning_rate": 8.08748219313325e-06, "loss": 0.5772, "step": 22878 }, { "epoch": 0.3532967837948291, "grad_norm": 0.589327335357666, "learning_rate": 8.025729558531453e-06, "loss": 0.5715, "step": 22909 }, { "epoch": 0.35377485792716307, "grad_norm": 0.6570223569869995, "learning_rate": 7.964168476264508e-06, "loss": 0.5807, "step": 22940 }, { "epoch": 0.3542529320594971, "grad_norm": 0.6160106658935547, "learning_rate": 7.902799641040884e-06, "loss": 0.5641, "step": 22971 }, { "epoch": 0.3547310061918311, "grad_norm": 0.5942509770393372, "learning_rate": 7.841623745399523e-06, "loss": 0.566, "step": 23002 }, { "epoch": 0.3552090803241651, "grad_norm": 0.6464576125144958, "learning_rate": 7.780641479702114e-06, "loss": 0.5736, "step": 23033 }, { "epoch": 0.3556871544564991, "grad_norm": 0.5047611594200134, "learning_rate": 7.719853532125227e-06, "loss": 0.5745, "step": 23064 }, { "epoch": 0.3561652285888331, "grad_norm": 0.6161003112792969, "learning_rate": 7.65926058865258e-06, "loss": 0.5723, "step": 23095 }, { "epoch": 0.3566433027211671, "grad_norm": 0.6291042566299438, "learning_rate": 7.598863333067313e-06, "loss": 0.5709, "step": 23126 }, { "epoch": 0.35712137685350115, "grad_norm": 0.4892687499523163, "learning_rate": 7.538662446944253e-06, "loss": 0.5624, "step": 23157 }, { "epoch": 0.3575994509858351, "grad_norm": 0.5112323760986328, "learning_rate": 7.478658609642211e-06, "loss": 0.5727, "step": 23188 }, { "epoch": 0.35807752511816915, "grad_norm": 0.5709079504013062, "learning_rate": 7.418852498296327e-06, "loss": 0.571, "step": 23219 }, { "epoch": 0.3585555992505031, "grad_norm": 0.5238727927207947, "learning_rate": 7.359244787810457e-06, "loss": 0.57, "step": 23250 }, { "epoch": 0.35903367338283715, "grad_norm": 0.5535005331039429, "learning_rate": 7.299836150849493e-06, "loss": 0.5727, "step": 23281 }, { "epoch": 0.3595117475151711, "grad_norm": 0.5350549817085266, "learning_rate": 7.240627257831847e-06, "loss": 0.5719, "step": 23312 }, { "epoch": 0.35998982164750515, "grad_norm": 0.5879747271537781, "learning_rate": 7.1816187769218195e-06, "loss": 0.5773, "step": 23343 }, { "epoch": 0.3604678957798392, "grad_norm": 0.5242079496383667, "learning_rate": 7.1228113740220895e-06, "loss": 0.5768, "step": 23374 }, { "epoch": 0.36094596991217315, "grad_norm": 0.6171791553497314, "learning_rate": 7.064205712766226e-06, "loss": 0.5769, "step": 23405 }, { "epoch": 0.3614240440445072, "grad_norm": 0.5774204730987549, "learning_rate": 7.005802454511129e-06, "loss": 0.5712, "step": 23436 }, { "epoch": 0.36190211817684115, "grad_norm": 0.5799962878227234, "learning_rate": 6.947602258329639e-06, "loss": 0.5762, "step": 23467 }, { "epoch": 0.3623801923091752, "grad_norm": 0.5970575213432312, "learning_rate": 6.889605781003078e-06, "loss": 0.5713, "step": 23498 }, { "epoch": 0.36285826644150915, "grad_norm": 0.5728057026863098, "learning_rate": 6.831813677013776e-06, "loss": 0.5691, "step": 23529 }, { "epoch": 0.3633363405738432, "grad_norm": 0.6017605066299438, "learning_rate": 6.774226598537792e-06, "loss": 0.5701, "step": 23560 }, { "epoch": 0.3638144147061772, "grad_norm": 0.5233104825019836, "learning_rate": 6.716845195437482e-06, "loss": 0.5688, "step": 23591 }, { "epoch": 0.3642924888385112, "grad_norm": 0.5983685851097107, "learning_rate": 6.659670115254168e-06, "loss": 0.5679, "step": 23622 }, { "epoch": 0.3647705629708452, "grad_norm": 0.5858353972434998, "learning_rate": 6.602702003200872e-06, "loss": 0.5761, "step": 23653 }, { "epoch": 0.3652486371031792, "grad_norm": 0.5972424149513245, "learning_rate": 6.545941502154992e-06, "loss": 0.5802, "step": 23684 }, { "epoch": 0.3657267112355132, "grad_norm": 0.6174728870391846, "learning_rate": 6.489389252651057e-06, "loss": 0.5829, "step": 23715 }, { "epoch": 0.3662047853678472, "grad_norm": 0.5846561789512634, "learning_rate": 6.4330458928735325e-06, "loss": 0.5762, "step": 23746 }, { "epoch": 0.3666828595001812, "grad_norm": 0.5355708599090576, "learning_rate": 6.376912058649559e-06, "loss": 0.572, "step": 23777 }, { "epoch": 0.36716093363251523, "grad_norm": 0.5898821353912354, "learning_rate": 6.320988383441845e-06, "loss": 0.5747, "step": 23808 }, { "epoch": 0.3676390077648492, "grad_norm": 0.5782723426818848, "learning_rate": 6.265275498341452e-06, "loss": 0.5671, "step": 23839 }, { "epoch": 0.36811708189718323, "grad_norm": 0.5315823554992676, "learning_rate": 6.209774032060714e-06, "loss": 0.5771, "step": 23870 }, { "epoch": 0.3685951560295172, "grad_norm": 0.5441523194313049, "learning_rate": 6.1544846109261365e-06, "loss": 0.5775, "step": 23901 }, { "epoch": 0.36907323016185123, "grad_norm": 0.5592854619026184, "learning_rate": 6.099407858871342e-06, "loss": 0.5743, "step": 23932 }, { "epoch": 0.36955130429418526, "grad_norm": 0.5144609212875366, "learning_rate": 6.044544397429958e-06, "loss": 0.5796, "step": 23963 }, { "epoch": 0.37002937842651923, "grad_norm": 0.5619729161262512, "learning_rate": 5.989894845728708e-06, "loss": 0.5703, "step": 23994 }, { "epoch": 0.37050745255885326, "grad_norm": 0.5606945157051086, "learning_rate": 5.9354598204803605e-06, "loss": 0.5799, "step": 24025 }, { "epoch": 0.37098552669118723, "grad_norm": 0.6192461848258972, "learning_rate": 5.881239935976762e-06, "loss": 0.5785, "step": 24056 }, { "epoch": 0.37146360082352126, "grad_norm": 0.5790452361106873, "learning_rate": 5.827235804081954e-06, "loss": 0.5719, "step": 24087 }, { "epoch": 0.37194167495585523, "grad_norm": 0.5728137493133545, "learning_rate": 5.773448034225221e-06, "loss": 0.5703, "step": 24118 }, { "epoch": 0.37241974908818926, "grad_norm": 0.5850538015365601, "learning_rate": 5.719877233394228e-06, "loss": 0.5635, "step": 24149 }, { "epoch": 0.3728978232205233, "grad_norm": 0.6578365564346313, "learning_rate": 5.666524006128191e-06, "loss": 0.5727, "step": 24180 }, { "epoch": 0.37337589735285726, "grad_norm": 0.6143426299095154, "learning_rate": 5.613388954511015e-06, "loss": 0.574, "step": 24211 }, { "epoch": 0.3738539714851913, "grad_norm": 0.62923663854599, "learning_rate": 5.560472678164552e-06, "loss": 0.5704, "step": 24242 }, { "epoch": 0.37433204561752526, "grad_norm": 0.5755168199539185, "learning_rate": 5.507775774241775e-06, "loss": 0.5688, "step": 24273 }, { "epoch": 0.3748101197498593, "grad_norm": 0.5668964385986328, "learning_rate": 5.4552988374200945e-06, "loss": 0.5692, "step": 24304 }, { "epoch": 0.37528819388219326, "grad_norm": 0.5009447336196899, "learning_rate": 5.403042459894597e-06, "loss": 0.5702, "step": 24335 }, { "epoch": 0.3757662680145273, "grad_norm": 0.5665227174758911, "learning_rate": 5.3510072313714135e-06, "loss": 0.5711, "step": 24366 }, { "epoch": 0.3762443421468613, "grad_norm": 0.5384367108345032, "learning_rate": 5.2991937390610205e-06, "loss": 0.5683, "step": 24397 }, { "epoch": 0.3767224162791953, "grad_norm": 0.5419508814811707, "learning_rate": 5.247602567671625e-06, "loss": 0.571, "step": 24428 }, { "epoch": 0.3772004904115293, "grad_norm": 0.5364875793457031, "learning_rate": 5.196234299402603e-06, "loss": 0.563, "step": 24459 }, { "epoch": 0.3776785645438633, "grad_norm": 0.5826189517974854, "learning_rate": 5.145089513937865e-06, "loss": 0.5691, "step": 24490 }, { "epoch": 0.3781566386761973, "grad_norm": 0.5769446492195129, "learning_rate": 5.094168788439369e-06, "loss": 0.5762, "step": 24521 }, { "epoch": 0.37863471280853134, "grad_norm": 0.5343894958496094, "learning_rate": 5.043472697540594e-06, "loss": 0.571, "step": 24552 }, { "epoch": 0.3791127869408653, "grad_norm": 0.5326864719390869, "learning_rate": 4.993001813340012e-06, "loss": 0.5733, "step": 24583 }, { "epoch": 0.37959086107319934, "grad_norm": 0.5287531614303589, "learning_rate": 4.942756705394702e-06, "loss": 0.5747, "step": 24614 }, { "epoch": 0.3800689352055333, "grad_norm": 0.5341933965682983, "learning_rate": 4.892737940713884e-06, "loss": 0.5663, "step": 24645 }, { "epoch": 0.38054700933786734, "grad_norm": 0.5358434915542603, "learning_rate": 4.842946083752511e-06, "loss": 0.5684, "step": 24676 }, { "epoch": 0.3810250834702013, "grad_norm": 0.5361096262931824, "learning_rate": 4.79338169640493e-06, "loss": 0.5678, "step": 24707 }, { "epoch": 0.38150315760253534, "grad_norm": 0.5188061594963074, "learning_rate": 4.74404533799851e-06, "loss": 0.5719, "step": 24738 }, { "epoch": 0.38198123173486936, "grad_norm": 0.5487860441207886, "learning_rate": 4.694937565287344e-06, "loss": 0.5773, "step": 24769 }, { "epoch": 0.38245930586720334, "grad_norm": 0.5515732169151306, "learning_rate": 4.646058932445985e-06, "loss": 0.5686, "step": 24800 }, { "epoch": 0.38293737999953736, "grad_norm": 0.5656226277351379, "learning_rate": 4.597409991063148e-06, "loss": 0.5672, "step": 24831 }, { "epoch": 0.38341545413187134, "grad_norm": 0.49390023946762085, "learning_rate": 4.5489912901355375e-06, "loss": 0.5714, "step": 24862 }, { "epoch": 0.38389352826420536, "grad_norm": 0.5774050354957581, "learning_rate": 4.500803376061608e-06, "loss": 0.5685, "step": 24893 }, { "epoch": 0.38437160239653934, "grad_norm": 0.5529614090919495, "learning_rate": 4.45284679263541e-06, "loss": 0.5751, "step": 24924 }, { "epoch": 0.38484967652887336, "grad_norm": 0.5055797696113586, "learning_rate": 4.4051220810404775e-06, "loss": 0.5712, "step": 24955 }, { "epoch": 0.3853277506612074, "grad_norm": 0.5665472149848938, "learning_rate": 4.3576297798437025e-06, "loss": 0.5707, "step": 24986 }, { "epoch": 0.38580582479354136, "grad_norm": 0.5053175091743469, "learning_rate": 4.3103704249892436e-06, "loss": 0.5698, "step": 25017 }, { "epoch": 0.3862838989258754, "grad_norm": 0.5849627256393433, "learning_rate": 4.263344549792487e-06, "loss": 0.5662, "step": 25048 }, { "epoch": 0.38676197305820936, "grad_norm": 0.6158141493797302, "learning_rate": 4.216552684934056e-06, "loss": 0.5741, "step": 25079 }, { "epoch": 0.3872400471905434, "grad_norm": 0.5662816166877747, "learning_rate": 4.169995358453777e-06, "loss": 0.5695, "step": 25110 }, { "epoch": 0.38771812132287736, "grad_norm": 0.5143694281578064, "learning_rate": 4.123673095744757e-06, "loss": 0.5724, "step": 25141 }, { "epoch": 0.3881961954552114, "grad_norm": 0.5500748157501221, "learning_rate": 4.077586419547435e-06, "loss": 0.5706, "step": 25172 }, { "epoch": 0.3886742695875454, "grad_norm": 0.5526003837585449, "learning_rate": 4.03173584994368e-06, "loss": 0.5723, "step": 25203 }, { "epoch": 0.3891523437198794, "grad_norm": 0.6642509698867798, "learning_rate": 3.986121904350948e-06, "loss": 0.5595, "step": 25234 }, { "epoch": 0.3896304178522134, "grad_norm": 0.593861997127533, "learning_rate": 3.940745097516407e-06, "loss": 0.5705, "step": 25265 }, { "epoch": 0.3901084919845474, "grad_norm": 0.5373812913894653, "learning_rate": 3.89560594151116e-06, "loss": 0.5708, "step": 25296 }, { "epoch": 0.3905865661168814, "grad_norm": 0.5997393131256104, "learning_rate": 3.850704945724456e-06, "loss": 0.573, "step": 25327 }, { "epoch": 0.39106464024921544, "grad_norm": 0.5451370477676392, "learning_rate": 3.8060426168579077e-06, "loss": 0.5606, "step": 25358 }, { "epoch": 0.3915427143815494, "grad_norm": 0.6029524207115173, "learning_rate": 3.7616194589198407e-06, "loss": 0.5654, "step": 25389 }, { "epoch": 0.39202078851388344, "grad_norm": 0.6756661534309387, "learning_rate": 3.7174359732195574e-06, "loss": 0.5634, "step": 25420 }, { "epoch": 0.3924988626462174, "grad_norm": 0.5419114232063293, "learning_rate": 3.673492658361677e-06, "loss": 0.5686, "step": 25451 }, { "epoch": 0.39297693677855144, "grad_norm": 0.6168972849845886, "learning_rate": 3.6297900102405467e-06, "loss": 0.5788, "step": 25482 }, { "epoch": 0.3934550109108854, "grad_norm": 0.5589380860328674, "learning_rate": 3.586328522034607e-06, "loss": 0.5766, "step": 25513 }, { "epoch": 0.39393308504321944, "grad_norm": 0.5675833225250244, "learning_rate": 3.543108684200838e-06, "loss": 0.5673, "step": 25544 }, { "epoch": 0.39441115917555347, "grad_norm": 0.5859025120735168, "learning_rate": 3.5001309844692464e-06, "loss": 0.5742, "step": 25575 }, { "epoch": 0.39488923330788744, "grad_norm": 0.6126372814178467, "learning_rate": 3.4573959078373215e-06, "loss": 0.5684, "step": 25606 }, { "epoch": 0.39536730744022147, "grad_norm": 0.5508156418800354, "learning_rate": 3.4149039365646063e-06, "loss": 0.5665, "step": 25637 }, { "epoch": 0.39584538157255544, "grad_norm": 0.5331482887268066, "learning_rate": 3.3726555501672143e-06, "loss": 0.5613, "step": 25668 }, { "epoch": 0.39632345570488947, "grad_norm": 0.5536491870880127, "learning_rate": 3.33065122541244e-06, "loss": 0.5685, "step": 25699 }, { "epoch": 0.39680152983722344, "grad_norm": 0.5023953318595886, "learning_rate": 3.288891436313385e-06, "loss": 0.568, "step": 25730 }, { "epoch": 0.39727960396955747, "grad_norm": 0.5827000737190247, "learning_rate": 3.2473766541235963e-06, "loss": 0.5649, "step": 25761 }, { "epoch": 0.3977576781018915, "grad_norm": 0.6178136467933655, "learning_rate": 3.2061073473317466e-06, "loss": 0.5742, "step": 25792 }, { "epoch": 0.39823575223422547, "grad_norm": 0.49690869450569153, "learning_rate": 3.1650839816563444e-06, "loss": 0.5655, "step": 25823 }, { "epoch": 0.3987138263665595, "grad_norm": 0.5496050119400024, "learning_rate": 3.1243070200405093e-06, "loss": 0.5686, "step": 25854 }, { "epoch": 0.39919190049889347, "grad_norm": 0.55158531665802, "learning_rate": 3.0837769226467e-06, "loss": 0.571, "step": 25885 }, { "epoch": 0.3996699746312275, "grad_norm": 0.5945053696632385, "learning_rate": 3.0434941468515666e-06, "loss": 0.5732, "step": 25916 }, { "epoch": 0.4001480487635615, "grad_norm": 0.5174633860588074, "learning_rate": 3.003459147240753e-06, "loss": 0.5704, "step": 25947 }, { "epoch": 0.4006261228958955, "grad_norm": 0.588633120059967, "learning_rate": 2.9636723756037875e-06, "loss": 0.5677, "step": 25978 }, { "epoch": 0.4011041970282295, "grad_norm": 0.5764910578727722, "learning_rate": 2.9241342809289833e-06, "loss": 0.5718, "step": 26009 }, { "epoch": 0.4015822711605635, "grad_norm": 0.5911231637001038, "learning_rate": 2.8848453093983594e-06, "loss": 0.576, "step": 26040 }, { "epoch": 0.4020603452928975, "grad_norm": 0.5014284253120422, "learning_rate": 2.8458059043826257e-06, "loss": 0.5699, "step": 26071 }, { "epoch": 0.4025384194252315, "grad_norm": 0.5628160834312439, "learning_rate": 2.807016506436172e-06, "loss": 0.5712, "step": 26102 }, { "epoch": 0.4030164935575655, "grad_norm": 0.536497950553894, "learning_rate": 2.7684775532920566e-06, "loss": 0.565, "step": 26133 }, { "epoch": 0.40349456768989955, "grad_norm": 0.5986963510513306, "learning_rate": 2.7301894798571425e-06, "loss": 0.5741, "step": 26164 }, { "epoch": 0.4039726418222335, "grad_norm": 0.5085678100585938, "learning_rate": 2.6921527182071386e-06, "loss": 0.5645, "step": 26195 }, { "epoch": 0.40445071595456755, "grad_norm": 0.5823872685432434, "learning_rate": 2.654367697581725e-06, "loss": 0.5578, "step": 26226 }, { "epoch": 0.4049287900869015, "grad_norm": 0.5357898473739624, "learning_rate": 2.6168348443797175e-06, "loss": 0.5715, "step": 26257 }, { "epoch": 0.40540686421923555, "grad_norm": 0.6874336004257202, "learning_rate": 2.5795545821542757e-06, "loss": 0.5723, "step": 26288 }, { "epoch": 0.4058849383515695, "grad_norm": 0.5069230198860168, "learning_rate": 2.54252733160808e-06, "loss": 0.5739, "step": 26319 }, { "epoch": 0.40636301248390355, "grad_norm": 0.5667560696601868, "learning_rate": 2.5057535105886294e-06, "loss": 0.5638, "step": 26350 }, { "epoch": 0.4068410866162376, "grad_norm": 0.5513550639152527, "learning_rate": 2.4692335340834953e-06, "loss": 0.5706, "step": 26381 }, { "epoch": 0.40731916074857155, "grad_norm": 0.583328366279602, "learning_rate": 2.432967814215639e-06, "loss": 0.5635, "step": 26412 }, { "epoch": 0.4077972348809056, "grad_norm": 0.5765253305435181, "learning_rate": 2.396956760238794e-06, "loss": 0.5715, "step": 26443 }, { "epoch": 0.40827530901323955, "grad_norm": 0.5591960549354553, "learning_rate": 2.361200778532796e-06, "loss": 0.5637, "step": 26474 }, { "epoch": 0.4087533831455736, "grad_norm": 0.5683372616767883, "learning_rate": 2.325700272599049e-06, "loss": 0.5667, "step": 26505 }, { "epoch": 0.40923145727790755, "grad_norm": 0.7753663063049316, "learning_rate": 2.2904556430559415e-06, "loss": 0.5684, "step": 26536 }, { "epoch": 0.4097095314102416, "grad_norm": 0.5882099866867065, "learning_rate": 2.2554672876343106e-06, "loss": 0.5644, "step": 26567 }, { "epoch": 0.4101876055425756, "grad_norm": 0.5205914378166199, "learning_rate": 2.220735601173002e-06, "loss": 0.5722, "step": 26598 }, { "epoch": 0.4106656796749096, "grad_norm": 0.5754354000091553, "learning_rate": 2.186260975614382e-06, "loss": 0.5811, "step": 26629 }, { "epoch": 0.4111437538072436, "grad_norm": 0.5526401996612549, "learning_rate": 2.1520437999999034e-06, "loss": 0.5656, "step": 26660 }, { "epoch": 0.4116218279395776, "grad_norm": 0.5454549789428711, "learning_rate": 2.1180844604657526e-06, "loss": 0.5753, "step": 26691 }, { "epoch": 0.4120999020719116, "grad_norm": 0.6748654246330261, "learning_rate": 2.084383340238455e-06, "loss": 0.5736, "step": 26722 }, { "epoch": 0.41257797620424563, "grad_norm": 0.506722092628479, "learning_rate": 2.0509408196305704e-06, "loss": 0.5766, "step": 26753 }, { "epoch": 0.4130560503365796, "grad_norm": 0.6061763763427734, "learning_rate": 2.017757276036403e-06, "loss": 0.5707, "step": 26784 }, { "epoch": 0.41353412446891363, "grad_norm": 0.5422362685203552, "learning_rate": 1.984833083927726e-06, "loss": 0.5741, "step": 26815 }, { "epoch": 0.4140121986012476, "grad_norm": 0.5236985683441162, "learning_rate": 1.952168614849581e-06, "loss": 0.5618, "step": 26846 }, { "epoch": 0.41449027273358163, "grad_norm": 0.48521238565444946, "learning_rate": 1.919764237416058e-06, "loss": 0.5642, "step": 26877 }, { "epoch": 0.4149683468659156, "grad_norm": 0.4921460449695587, "learning_rate": 1.8876203173061463e-06, "loss": 0.5643, "step": 26908 }, { "epoch": 0.41544642099824963, "grad_norm": 0.5896371006965637, "learning_rate": 1.8557372172596206e-06, "loss": 0.5711, "step": 26939 }, { "epoch": 0.41592449513058366, "grad_norm": 0.5045610666275024, "learning_rate": 1.8241152970729341e-06, "loss": 0.5803, "step": 26970 }, { "epoch": 0.41640256926291763, "grad_norm": 0.6058014035224915, "learning_rate": 1.7927549135951572e-06, "loss": 0.5676, "step": 27001 }, { "epoch": 0.41688064339525166, "grad_norm": 0.4907824397087097, "learning_rate": 1.7616564207239477e-06, "loss": 0.5643, "step": 27032 }, { "epoch": 0.41735871752758563, "grad_norm": 0.5123028755187988, "learning_rate": 1.730820169401584e-06, "loss": 0.5696, "step": 27063 }, { "epoch": 0.41783679165991966, "grad_norm": 0.646056592464447, "learning_rate": 1.7002465076109558e-06, "loss": 0.5692, "step": 27094 }, { "epoch": 0.41831486579225363, "grad_norm": 0.5923252701759338, "learning_rate": 1.6699357803716898e-06, "loss": 0.5614, "step": 27125 }, { "epoch": 0.41879293992458766, "grad_norm": 0.6700661778450012, "learning_rate": 1.6398883297362305e-06, "loss": 0.5685, "step": 27156 }, { "epoch": 0.4192710140569217, "grad_norm": 0.6059920787811279, "learning_rate": 1.6101044947859606e-06, "loss": 0.5664, "step": 27187 }, { "epoch": 0.41974908818925566, "grad_norm": 0.5154827833175659, "learning_rate": 1.5805846116274114e-06, "loss": 0.569, "step": 27218 }, { "epoch": 0.4202271623215897, "grad_norm": 0.48046451807022095, "learning_rate": 1.5513290133884611e-06, "loss": 0.5744, "step": 27249 }, { "epoch": 0.42070523645392366, "grad_norm": 0.5736571550369263, "learning_rate": 1.5223380302145512e-06, "loss": 0.5661, "step": 27280 }, { "epoch": 0.4211833105862577, "grad_norm": 0.4849691092967987, "learning_rate": 1.4936119892649925e-06, "loss": 0.5602, "step": 27311 }, { "epoch": 0.42166138471859166, "grad_norm": 0.45344623923301697, "learning_rate": 1.4651512147092482e-06, "loss": 0.5731, "step": 27342 }, { "epoch": 0.4221394588509257, "grad_norm": 0.5611448287963867, "learning_rate": 1.4369560277232908e-06, "loss": 0.5758, "step": 27373 }, { "epoch": 0.4226175329832597, "grad_norm": 0.5461937189102173, "learning_rate": 1.409026746485978e-06, "loss": 0.5768, "step": 27404 }, { "epoch": 0.4230956071155937, "grad_norm": 0.6484282612800598, "learning_rate": 1.3813636861754464e-06, "loss": 0.5611, "step": 27435 }, { "epoch": 0.4235736812479277, "grad_norm": 0.5170944929122925, "learning_rate": 1.3539671589655773e-06, "loss": 0.5661, "step": 27466 }, { "epoch": 0.4240517553802617, "grad_norm": 0.5337830185890198, "learning_rate": 1.3268374740224548e-06, "loss": 0.5683, "step": 27497 }, { "epoch": 0.4245298295125957, "grad_norm": 0.5495180487632751, "learning_rate": 1.2999749375008807e-06, "loss": 0.564, "step": 27528 }, { "epoch": 0.42500790364492974, "grad_norm": 0.5563623309135437, "learning_rate": 1.2733798525409346e-06, "loss": 0.5675, "step": 27559 }, { "epoch": 0.4254859777772637, "grad_norm": 0.5303583145141602, "learning_rate": 1.2470525192645383e-06, "loss": 0.561, "step": 27590 }, { "epoch": 0.42596405190959774, "grad_norm": 0.6232916116714478, "learning_rate": 1.2209932347720666e-06, "loss": 0.5804, "step": 27621 }, { "epoch": 0.4264421260419317, "grad_norm": 0.5853449106216431, "learning_rate": 1.1952022931389972e-06, "loss": 0.5689, "step": 27652 }, { "epoch": 0.42692020017426574, "grad_norm": 0.6670809984207153, "learning_rate": 1.1696799854126083e-06, "loss": 0.564, "step": 27683 }, { "epoch": 0.4273982743065997, "grad_norm": 0.5922245979309082, "learning_rate": 1.1444265996086694e-06, "loss": 0.5688, "step": 27714 }, { "epoch": 0.42787634843893374, "grad_norm": 0.5603543519973755, "learning_rate": 1.119442420708211e-06, "loss": 0.5726, "step": 27745 }, { "epoch": 0.42835442257126777, "grad_norm": 0.552730917930603, "learning_rate": 1.0947277306542964e-06, "loss": 0.5666, "step": 27776 }, { "epoch": 0.42883249670360174, "grad_norm": 0.5957998633384705, "learning_rate": 1.0702828083488353e-06, "loss": 0.567, "step": 27807 }, { "epoch": 0.42931057083593577, "grad_norm": 0.5674703121185303, "learning_rate": 1.0461079296494647e-06, "loss": 0.5677, "step": 27838 }, { "epoch": 0.42978864496826974, "grad_norm": 0.5395528674125671, "learning_rate": 1.0222033673663978e-06, "loss": 0.5614, "step": 27869 }, { "epoch": 0.43026671910060377, "grad_norm": 0.5590517520904541, "learning_rate": 9.985693912593713e-07, "loss": 0.5702, "step": 27900 }, { "epoch": 0.43074479323293774, "grad_norm": 0.4705580770969391, "learning_rate": 9.752062680346035e-07, "loss": 0.5703, "step": 27931 }, { "epoch": 0.43122286736527177, "grad_norm": 0.6177532076835632, "learning_rate": 9.521142613417494e-07, "loss": 0.5704, "step": 27962 }, { "epoch": 0.4317009414976058, "grad_norm": 0.5978263020515442, "learning_rate": 9.292936317709722e-07, "loss": 0.573, "step": 27993 }, { "epoch": 0.43217901562993977, "grad_norm": 0.6239224076271057, "learning_rate": 9.067446368499793e-07, "loss": 0.5685, "step": 28024 }, { "epoch": 0.4326570897622738, "grad_norm": 0.5486834645271301, "learning_rate": 8.844675310411055e-07, "loss": 0.5737, "step": 28055 }, { "epoch": 0.43313516389460777, "grad_norm": 0.546748697757721, "learning_rate": 8.6246256573847e-07, "loss": 0.5652, "step": 28086 }, { "epoch": 0.4336132380269418, "grad_norm": 0.5774748921394348, "learning_rate": 8.407299892651127e-07, "loss": 0.5738, "step": 28117 }, { "epoch": 0.4340913121592758, "grad_norm": 0.5749956965446472, "learning_rate": 8.19270046870202e-07, "loss": 0.569, "step": 28148 }, { "epoch": 0.4345693862916098, "grad_norm": 0.550385594367981, "learning_rate": 7.980829807262752e-07, "loss": 0.5743, "step": 28179 }, { "epoch": 0.4350474604239438, "grad_norm": 0.546572208404541, "learning_rate": 7.771690299264889e-07, "loss": 0.563, "step": 28210 }, { "epoch": 0.4355255345562778, "grad_norm": 0.5156393647193909, "learning_rate": 7.565284304819426e-07, "loss": 0.5712, "step": 28241 }, { "epoch": 0.4360036086886118, "grad_norm": 0.5540571212768555, "learning_rate": 7.361614153189922e-07, "loss": 0.5677, "step": 28272 }, { "epoch": 0.4364816828209458, "grad_norm": 0.4842173159122467, "learning_rate": 7.160682142766328e-07, "loss": 0.5677, "step": 28303 }, { "epoch": 0.4369597569532798, "grad_norm": 0.5632885694503784, "learning_rate": 6.962490541039091e-07, "loss": 0.5725, "step": 28334 }, { "epoch": 0.43743783108561385, "grad_norm": 0.532958447933197, "learning_rate": 6.767041584573531e-07, "loss": 0.5646, "step": 28365 }, { "epoch": 0.4379159052179478, "grad_norm": 0.5175893306732178, "learning_rate": 6.574337478984532e-07, "loss": 0.5621, "step": 28396 }, { "epoch": 0.43839397935028185, "grad_norm": 0.5376450419425964, "learning_rate": 6.384380398911732e-07, "loss": 0.5691, "step": 28427 }, { "epoch": 0.4388720534826158, "grad_norm": 0.5386781692504883, "learning_rate": 6.197172487994951e-07, "loss": 0.5739, "step": 28458 }, { "epoch": 0.43935012761494985, "grad_norm": 0.5802245736122131, "learning_rate": 6.012715858850021e-07, "loss": 0.5694, "step": 28489 }, { "epoch": 0.4398282017472838, "grad_norm": 0.6069300770759583, "learning_rate": 5.831012593044971e-07, "loss": 0.5654, "step": 28520 }, { "epoch": 0.44030627587961785, "grad_norm": 0.5251255631446838, "learning_rate": 5.652064741076435e-07, "loss": 0.5742, "step": 28551 }, { "epoch": 0.4407843500119519, "grad_norm": 0.857638418674469, "learning_rate": 5.475874322346558e-07, "loss": 0.5633, "step": 28582 }, { "epoch": 0.44126242414428585, "grad_norm": 0.5898762345314026, "learning_rate": 5.30244332514035e-07, "loss": 0.5792, "step": 28613 }, { "epoch": 0.4417404982766199, "grad_norm": 0.5745364427566528, "learning_rate": 5.131773706602977e-07, "loss": 0.5692, "step": 28644 }, { "epoch": 0.44221857240895385, "grad_norm": 0.5742127895355225, "learning_rate": 4.963867392717897e-07, "loss": 0.5816, "step": 28675 }, { "epoch": 0.4426966465412879, "grad_norm": 0.5671530961990356, "learning_rate": 4.798726278285093e-07, "loss": 0.5715, "step": 28706 }, { "epoch": 0.44317472067362185, "grad_norm": 0.5267143845558167, "learning_rate": 4.6363522268995097e-07, "loss": 0.564, "step": 28737 }, { "epoch": 0.4436527948059559, "grad_norm": 0.4694323241710663, "learning_rate": 4.4767470709302927e-07, "loss": 0.5676, "step": 28768 }, { "epoch": 0.4441308689382899, "grad_norm": 0.5049657821655273, "learning_rate": 4.319912611499971e-07, "loss": 0.5686, "step": 28799 }, { "epoch": 0.4446089430706239, "grad_norm": 0.5846327543258667, "learning_rate": 4.1658506184640564e-07, "loss": 0.5638, "step": 28830 }, { "epoch": 0.4450870172029579, "grad_norm": 0.6463845372200012, "learning_rate": 4.0145628303911996e-07, "loss": 0.5715, "step": 28861 }, { "epoch": 0.4455650913352919, "grad_norm": 0.5498476624488831, "learning_rate": 3.866050954543565e-07, "loss": 0.5692, "step": 28892 }, { "epoch": 0.4460431654676259, "grad_norm": 0.6105197072029114, "learning_rate": 3.720316666857432e-07, "loss": 0.5587, "step": 28923 }, { "epoch": 0.44652123959995993, "grad_norm": 0.5666882395744324, "learning_rate": 3.5773616119244845e-07, "loss": 0.5688, "step": 28954 }, { "epoch": 0.4469993137322939, "grad_norm": 0.5763387680053711, "learning_rate": 3.437187402973052e-07, "loss": 0.5647, "step": 28985 }, { "epoch": 0.44747738786462793, "grad_norm": 0.5094069838523865, "learning_rate": 3.2997956218500104e-07, "loss": 0.5742, "step": 29016 }, { "epoch": 0.4479554619969619, "grad_norm": 0.5137080550193787, "learning_rate": 3.165187819003018e-07, "loss": 0.5659, "step": 29047 }, { "epoch": 0.44843353612929593, "grad_norm": 0.47000959515571594, "learning_rate": 3.033365513462755e-07, "loss": 0.555, "step": 29078 }, { "epoch": 0.4489116102616299, "grad_norm": 0.49969279766082764, "learning_rate": 2.9043301928260437e-07, "loss": 0.5719, "step": 29109 }, { "epoch": 0.44938968439396393, "grad_norm": 0.5961170792579651, "learning_rate": 2.7780833132389773e-07, "loss": 0.5716, "step": 29140 }, { "epoch": 0.44986775852629796, "grad_norm": 0.45310088992118835, "learning_rate": 2.6546262993803473e-07, "loss": 0.5664, "step": 29171 }, { "epoch": 0.45034583265863193, "grad_norm": 0.5196030735969543, "learning_rate": 2.533960544445879e-07, "loss": 0.5651, "step": 29202 }, { "epoch": 0.45082390679096596, "grad_norm": 0.5428928732872009, "learning_rate": 2.416087410132134e-07, "loss": 0.5725, "step": 29233 }, { "epoch": 0.45130198092329993, "grad_norm": 0.5611571073532104, "learning_rate": 2.301008226621465e-07, "loss": 0.5654, "step": 29264 }, { "epoch": 0.45178005505563396, "grad_norm": 0.5128880143165588, "learning_rate": 2.1887242925668073e-07, "loss": 0.567, "step": 29295 }, { "epoch": 0.4522581291879679, "grad_norm": 0.5531268119812012, "learning_rate": 2.0792368750770785e-07, "loss": 0.5609, "step": 29326 }, { "epoch": 0.45273620332030196, "grad_norm": 0.5210745930671692, "learning_rate": 1.9725472097028851e-07, "loss": 0.566, "step": 29357 }, { "epoch": 0.453214277452636, "grad_norm": 0.5298446416854858, "learning_rate": 1.8686565004226718e-07, "loss": 0.5635, "step": 29388 }, { "epoch": 0.45369235158496996, "grad_norm": 0.5491095185279846, "learning_rate": 1.7675659196288995e-07, "loss": 0.558, "step": 29419 }, { "epoch": 0.454170425717304, "grad_norm": 0.5643526911735535, "learning_rate": 1.6692766081150556e-07, "loss": 0.5572, "step": 29450 }, { "epoch": 0.45464849984963795, "grad_norm": 0.5595051646232605, "learning_rate": 1.5737896750626647e-07, "loss": 0.5727, "step": 29481 }, { "epoch": 0.455126573981972, "grad_norm": 0.5803290605545044, "learning_rate": 1.4811061980287976e-07, "loss": 0.5677, "step": 29512 }, { "epoch": 0.455604648114306, "grad_norm": 0.6208820343017578, "learning_rate": 1.3912272229338886e-07, "loss": 0.5693, "step": 29543 }, { "epoch": 0.45608272224664, "grad_norm": 0.6184868216514587, "learning_rate": 1.3041537640499645e-07, "loss": 0.5594, "step": 29574 }, { "epoch": 0.456560796378974, "grad_norm": 0.6103149652481079, "learning_rate": 1.2198868039891564e-07, "loss": 0.5682, "step": 29605 }, { "epoch": 0.457038870511308, "grad_norm": 0.5478423237800598, "learning_rate": 1.138427293692651e-07, "loss": 0.5639, "step": 29636 }, { "epoch": 0.457516944643642, "grad_norm": 0.619123637676239, "learning_rate": 1.0597761524199778e-07, "loss": 0.5621, "step": 29667 }, { "epoch": 0.457995018775976, "grad_norm": 0.5106766819953918, "learning_rate": 9.839342677385455e-08, "loss": 0.5645, "step": 29698 }, { "epoch": 0.45847309290831, "grad_norm": 0.5249870419502258, "learning_rate": 9.109024955137325e-08, "loss": 0.5791, "step": 29729 }, { "epoch": 0.45895116704064404, "grad_norm": 0.5704385042190552, "learning_rate": 8.406816598991729e-08, "loss": 0.5671, "step": 29760 }, { "epoch": 0.459429241172978, "grad_norm": 0.5292198061943054, "learning_rate": 7.73272553327431e-08, "loss": 0.5754, "step": 29791 }, { "epoch": 0.45990731530531204, "grad_norm": 0.4351247251033783, "learning_rate": 7.086759365011186e-08, "loss": 0.5677, "step": 29822 }, { "epoch": 0.460385389437646, "grad_norm": 0.5705137252807617, "learning_rate": 6.468925383842639e-08, "loss": 0.5695, "step": 29853 }, { "epoch": 0.46086346356998004, "grad_norm": 0.5587801337242126, "learning_rate": 5.8792305619415067e-08, "loss": 0.5672, "step": 29884 }, { "epoch": 0.461341537702314, "grad_norm": 0.5599956512451172, "learning_rate": 5.317681553933529e-08, "loss": 0.5655, "step": 29915 }, { "epoch": 0.46181961183464804, "grad_norm": 0.5381226539611816, "learning_rate": 4.78428469682296e-08, "loss": 0.5555, "step": 29946 }, { "epoch": 0.46229768596698206, "grad_norm": 0.518403947353363, "learning_rate": 4.2790460099206844e-08, "loss": 0.5628, "step": 29977 }, { "epoch": 0.46277576009931604, "grad_norm": 0.5325192213058472, "learning_rate": 3.801971194777043e-08, "loss": 0.5673, "step": 30008 }, { "epoch": 0.46325383423165006, "grad_norm": 0.5758033990859985, "learning_rate": 3.353065635115782e-08, "loss": 0.5626, "step": 30039 }, { "epoch": 0.46373190836398404, "grad_norm": 0.5737308263778687, "learning_rate": 2.93233439677576e-08, "loss": 0.5745, "step": 30070 }, { "epoch": 0.46420998249631806, "grad_norm": 0.5368719100952148, "learning_rate": 2.539782227651555e-08, "loss": 0.5631, "step": 30101 }, { "epoch": 0.46468805662865204, "grad_norm": 0.5507616996765137, "learning_rate": 2.175413557641004e-08, "loss": 0.5614, "step": 30132 }, { "epoch": 0.46516613076098606, "grad_norm": 0.4974292516708374, "learning_rate": 1.839232498594967e-08, "loss": 0.5682, "step": 30163 }, { "epoch": 0.4656442048933201, "grad_norm": 0.5380896925926208, "learning_rate": 1.5312428442712522e-08, "loss": 0.5705, "step": 30194 }, { "epoch": 0.46612227902565406, "grad_norm": 0.5986722111701965, "learning_rate": 1.2514480702913168e-08, "loss": 0.5636, "step": 30225 }, { "epoch": 0.4666003531579881, "grad_norm": 0.5088329315185547, "learning_rate": 9.998513341005766e-09, "loss": 0.568, "step": 30256 }, { "epoch": 0.46707842729032206, "grad_norm": 0.5092610120773315, "learning_rate": 7.764554749345454e-09, "loss": 0.5656, "step": 30287 }, { "epoch": 0.4675565014226561, "grad_norm": 0.5487105846405029, "learning_rate": 5.812630137849717e-09, "loss": 0.5726, "step": 30318 }, { "epoch": 0.4680345755549901, "grad_norm": 0.5827004313468933, "learning_rate": 4.142761533723616e-09, "loss": 0.5625, "step": 30349 }, { "epoch": 0.4685126496873241, "grad_norm": 0.5354323983192444, "learning_rate": 2.7549677812044317e-09, "loss": 0.5718, "step": 30380 }, { "epoch": 0.4689907238196581, "grad_norm": 0.5537958145141602, "learning_rate": 1.6492645413590525e-09, "loss": 0.5727, "step": 30411 }, { "epoch": 0.4694687979519921, "grad_norm": 0.5670791864395142, "learning_rate": 8.256642918980096e-10, "loss": 0.5693, "step": 30442 }, { "epoch": 0.4699468720843261, "grad_norm": 0.4846827983856201, "learning_rate": 2.841763270367004e-10, "loss": 0.5669, "step": 30473 }, { "epoch": 0.4704249462166601, "grad_norm": 0.6159082055091858, "learning_rate": 2.480675739269245e-11, "loss": 0.5641, "step": 30504 } ], "logging_steps": 31, "max_steps": 30517, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3052, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.1211455570573263e+19, "train_batch_size": 16, "trial_name": null, "trial_params": null }