{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 4353, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006893382352941176, "grad_norm": 408.0095355325432, "learning_rate": 2.064220183486239e-07, "loss": 1.899764633178711, "step": 10 }, { "epoch": 0.013786764705882353, "grad_norm": 92.61159411256806, "learning_rate": 4.357798165137615e-07, "loss": 1.4172555923461914, "step": 20 }, { "epoch": 0.02068014705882353, "grad_norm": 32.207767435815356, "learning_rate": 6.651376146788992e-07, "loss": 0.8929882049560547, "step": 30 }, { "epoch": 0.027573529411764705, "grad_norm": 32.755132366261854, "learning_rate": 8.944954128440368e-07, "loss": 0.6050376415252685, "step": 40 }, { "epoch": 0.034466911764705885, "grad_norm": 13.127638750604937, "learning_rate": 1.1238532110091744e-06, "loss": 0.40024476051330565, "step": 50 }, { "epoch": 0.04136029411764706, "grad_norm": 13.958674191161862, "learning_rate": 1.353211009174312e-06, "loss": 0.28873419761657715, "step": 60 }, { "epoch": 0.04825367647058824, "grad_norm": 9.475701802831885, "learning_rate": 1.5825688073394496e-06, "loss": 0.24238238334655762, "step": 70 }, { "epoch": 0.05514705882352941, "grad_norm": 7.021237440607234, "learning_rate": 1.8119266055045873e-06, "loss": 0.23558053970336915, "step": 80 }, { "epoch": 0.06204044117647059, "grad_norm": 13.964661987592764, "learning_rate": 2.041284403669725e-06, "loss": 0.20369558334350585, "step": 90 }, { "epoch": 0.06893382352941177, "grad_norm": 6.904745638393748, "learning_rate": 2.2706422018348624e-06, "loss": 0.2047752857208252, "step": 100 }, { "epoch": 0.07582720588235294, "grad_norm": 6.671775484183751, "learning_rate": 2.5e-06, "loss": 0.20352354049682617, "step": 110 }, { "epoch": 0.08272058823529412, "grad_norm": 6.222310915287519, "learning_rate": 2.7293577981651376e-06, "loss": 0.21354033946990966, "step": 120 }, { "epoch": 0.0896139705882353, "grad_norm": 4.849297586859702, "learning_rate": 2.9587155963302755e-06, "loss": 0.18913990259170532, "step": 130 }, { "epoch": 0.09650735294117647, "grad_norm": 3.970356137509761, "learning_rate": 3.188073394495413e-06, "loss": 0.18926186561584474, "step": 140 }, { "epoch": 0.10340073529411764, "grad_norm": 5.085440983605754, "learning_rate": 3.4174311926605508e-06, "loss": 0.17663187980651857, "step": 150 }, { "epoch": 0.11029411764705882, "grad_norm": 4.070361033499435, "learning_rate": 3.646788990825688e-06, "loss": 0.20000953674316407, "step": 160 }, { "epoch": 0.1171875, "grad_norm": 3.7938381340697718, "learning_rate": 3.876146788990826e-06, "loss": 0.1932319164276123, "step": 170 }, { "epoch": 0.12408088235294118, "grad_norm": 4.224904079524738, "learning_rate": 4.105504587155963e-06, "loss": 0.19782212972640992, "step": 180 }, { "epoch": 0.13097426470588236, "grad_norm": 4.24134231418686, "learning_rate": 4.334862385321102e-06, "loss": 0.16215966939926146, "step": 190 }, { "epoch": 0.13786764705882354, "grad_norm": 4.651074223514888, "learning_rate": 4.564220183486239e-06, "loss": 0.1765323281288147, "step": 200 }, { "epoch": 0.14476102941176472, "grad_norm": 3.8989243198161176, "learning_rate": 4.793577981651377e-06, "loss": 0.1944495677947998, "step": 210 }, { "epoch": 0.15165441176470587, "grad_norm": 4.23498818757111, "learning_rate": 5.0229357798165144e-06, "loss": 0.1924619197845459, "step": 220 }, { "epoch": 0.15854779411764705, "grad_norm": 6.00696293600751, "learning_rate": 5.252293577981652e-06, "loss": 0.19220852851867676, "step": 230 }, { "epoch": 0.16544117647058823, "grad_norm": 2.988377478624419, "learning_rate": 5.481651376146789e-06, "loss": 0.20981230735778808, "step": 240 }, { "epoch": 0.1723345588235294, "grad_norm": 3.53288683385863, "learning_rate": 5.711009174311926e-06, "loss": 0.19124144315719604, "step": 250 }, { "epoch": 0.1792279411764706, "grad_norm": 9.121392576219252, "learning_rate": 5.940366972477065e-06, "loss": 0.18142223358154297, "step": 260 }, { "epoch": 0.18612132352941177, "grad_norm": 3.4843827538742667, "learning_rate": 6.169724770642203e-06, "loss": 0.1944233298301697, "step": 270 }, { "epoch": 0.19301470588235295, "grad_norm": 2.5474386014966055, "learning_rate": 6.39908256880734e-06, "loss": 0.1755244493484497, "step": 280 }, { "epoch": 0.19990808823529413, "grad_norm": 3.839649820728239, "learning_rate": 6.628440366972477e-06, "loss": 0.19340382814407348, "step": 290 }, { "epoch": 0.20680147058823528, "grad_norm": 2.886883512390973, "learning_rate": 6.8577981651376156e-06, "loss": 0.16824949979782106, "step": 300 }, { "epoch": 0.21369485294117646, "grad_norm": 4.2127209530067855, "learning_rate": 7.087155963302753e-06, "loss": 0.19202438592910767, "step": 310 }, { "epoch": 0.22058823529411764, "grad_norm": 3.062259022475788, "learning_rate": 7.31651376146789e-06, "loss": 0.17803602218627929, "step": 320 }, { "epoch": 0.22748161764705882, "grad_norm": 2.973124517202252, "learning_rate": 7.545871559633028e-06, "loss": 0.18407149314880372, "step": 330 }, { "epoch": 0.234375, "grad_norm": 3.080222861587291, "learning_rate": 7.775229357798164e-06, "loss": 0.16222720146179198, "step": 340 }, { "epoch": 0.24126838235294118, "grad_norm": 3.2202753581915182, "learning_rate": 8.004587155963303e-06, "loss": 0.18032631874084473, "step": 350 }, { "epoch": 0.24816176470588236, "grad_norm": 4.664501676539128, "learning_rate": 8.233944954128442e-06, "loss": 0.18896214962005614, "step": 360 }, { "epoch": 0.25505514705882354, "grad_norm": 5.209193117107188, "learning_rate": 8.463302752293579e-06, "loss": 0.195867657661438, "step": 370 }, { "epoch": 0.2619485294117647, "grad_norm": 4.0958531533725, "learning_rate": 8.692660550458716e-06, "loss": 0.18059426546096802, "step": 380 }, { "epoch": 0.2688419117647059, "grad_norm": 7.150822572916362, "learning_rate": 8.922018348623855e-06, "loss": 0.17681434154510497, "step": 390 }, { "epoch": 0.2757352941176471, "grad_norm": 2.920438647918486, "learning_rate": 9.151376146788992e-06, "loss": 0.18795492649078369, "step": 400 }, { "epoch": 0.28262867647058826, "grad_norm": 2.5081095655528745, "learning_rate": 9.380733944954129e-06, "loss": 0.1930767059326172, "step": 410 }, { "epoch": 0.28952205882352944, "grad_norm": 2.5913970488585814, "learning_rate": 9.610091743119267e-06, "loss": 0.1833290934562683, "step": 420 }, { "epoch": 0.29641544117647056, "grad_norm": 4.581750590951869, "learning_rate": 9.839449541284404e-06, "loss": 0.19203636646270753, "step": 430 }, { "epoch": 0.30330882352941174, "grad_norm": 3.806206792421457, "learning_rate": 9.999985526455163e-06, "loss": 0.1817917823791504, "step": 440 }, { "epoch": 0.3102022058823529, "grad_norm": 5.495198063895541, "learning_rate": 9.99972822132241e-06, "loss": 0.19012433290481567, "step": 450 }, { "epoch": 0.3170955882352941, "grad_norm": 1.999975785747172, "learning_rate": 9.999149300911473e-06, "loss": 0.1932447910308838, "step": 460 }, { "epoch": 0.3239889705882353, "grad_norm": 4.259835150245755, "learning_rate": 9.998248802462309e-06, "loss": 0.17884019613265992, "step": 470 }, { "epoch": 0.33088235294117646, "grad_norm": 1.9870921470917253, "learning_rate": 9.997026783900877e-06, "loss": 0.19179301261901854, "step": 480 }, { "epoch": 0.33777573529411764, "grad_norm": 3.149363390626566, "learning_rate": 9.995483323835415e-06, "loss": 0.16465436220169066, "step": 490 }, { "epoch": 0.3446691176470588, "grad_norm": 2.2913290521139547, "learning_rate": 9.993618521551392e-06, "loss": 0.18261477947235108, "step": 500 }, { "epoch": 0.3515625, "grad_norm": 2.6584422304956528, "learning_rate": 9.991432497005108e-06, "loss": 0.16887296438217164, "step": 510 }, { "epoch": 0.3584558823529412, "grad_norm": 2.3465797902420165, "learning_rate": 9.988925390815983e-06, "loss": 0.17460349798202515, "step": 520 }, { "epoch": 0.36534926470588236, "grad_norm": 2.3984953552948767, "learning_rate": 9.986097364257516e-06, "loss": 0.1771254301071167, "step": 530 }, { "epoch": 0.37224264705882354, "grad_norm": 2.1309951969550074, "learning_rate": 9.982948599246905e-06, "loss": 0.17704691886901855, "step": 540 }, { "epoch": 0.3791360294117647, "grad_norm": 2.7125303523799342, "learning_rate": 9.979479298333345e-06, "loss": 0.16429059505462645, "step": 550 }, { "epoch": 0.3860294117647059, "grad_norm": 2.5221873852843695, "learning_rate": 9.975689684685003e-06, "loss": 0.16307862997055053, "step": 560 }, { "epoch": 0.3929227941176471, "grad_norm": 2.4156518244400145, "learning_rate": 9.97158000207466e-06, "loss": 0.18063623905181886, "step": 570 }, { "epoch": 0.39981617647058826, "grad_norm": 1.7052013475184895, "learning_rate": 9.967150514864025e-06, "loss": 0.17896972894668578, "step": 580 }, { "epoch": 0.40670955882352944, "grad_norm": 3.9649815254577345, "learning_rate": 9.962401507986744e-06, "loss": 0.17231045961380004, "step": 590 }, { "epoch": 0.41360294117647056, "grad_norm": 2.0152421795545843, "learning_rate": 9.957333286930052e-06, "loss": 0.1710118055343628, "step": 600 }, { "epoch": 0.42049632352941174, "grad_norm": 2.2784545567461327, "learning_rate": 9.951946177715135e-06, "loss": 0.16978123188018798, "step": 610 }, { "epoch": 0.4273897058823529, "grad_norm": 2.485412274625397, "learning_rate": 9.946240526876156e-06, "loss": 0.1771092653274536, "step": 620 }, { "epoch": 0.4342830882352941, "grad_norm": 2.155278632580223, "learning_rate": 9.940216701437959e-06, "loss": 0.17805719375610352, "step": 630 }, { "epoch": 0.4411764705882353, "grad_norm": 2.634826396766847, "learning_rate": 9.933875088892469e-06, "loss": 0.1876924753189087, "step": 640 }, { "epoch": 0.44806985294117646, "grad_norm": 2.5253337051343343, "learning_rate": 9.927216097173753e-06, "loss": 0.16187468767166138, "step": 650 }, { "epoch": 0.45496323529411764, "grad_norm": 1.7880514692807836, "learning_rate": 9.92024015463179e-06, "loss": 0.15662612915039062, "step": 660 }, { "epoch": 0.4618566176470588, "grad_norm": 2.6211333298114403, "learning_rate": 9.912947710004914e-06, "loss": 0.16395634412765503, "step": 670 }, { "epoch": 0.46875, "grad_norm": 6.803510886519711, "learning_rate": 9.905339232390941e-06, "loss": 0.1961168885231018, "step": 680 }, { "epoch": 0.4756433823529412, "grad_norm": 2.2560745584712976, "learning_rate": 9.897415211217005e-06, "loss": 0.17447874546051026, "step": 690 }, { "epoch": 0.48253676470588236, "grad_norm": 2.308703518802818, "learning_rate": 9.889176156208067e-06, "loss": 0.15677268505096437, "step": 700 }, { "epoch": 0.48943014705882354, "grad_norm": 1.6557324265716848, "learning_rate": 9.880622597354128e-06, "loss": 0.16228680610656737, "step": 710 }, { "epoch": 0.4963235294117647, "grad_norm": 2.3357722885845935, "learning_rate": 9.871755084876138e-06, "loss": 0.18117380142211914, "step": 720 }, { "epoch": 0.5032169117647058, "grad_norm": 2.0219706055523763, "learning_rate": 9.862574189190602e-06, "loss": 0.16354126930236818, "step": 730 }, { "epoch": 0.5101102941176471, "grad_norm": 2.0421756504474557, "learning_rate": 9.853080500872885e-06, "loss": 0.17628874778747558, "step": 740 }, { "epoch": 0.5170036764705882, "grad_norm": 2.292579436194196, "learning_rate": 9.843274630619223e-06, "loss": 0.170723819732666, "step": 750 }, { "epoch": 0.5238970588235294, "grad_norm": 2.4042538922350154, "learning_rate": 9.83315720920744e-06, "loss": 0.16912319660186767, "step": 760 }, { "epoch": 0.5307904411764706, "grad_norm": 2.6657736414253272, "learning_rate": 9.822728887456371e-06, "loss": 0.17005774974822999, "step": 770 }, { "epoch": 0.5376838235294118, "grad_norm": 2.1871853204746974, "learning_rate": 9.811990336184002e-06, "loss": 0.15716840028762818, "step": 780 }, { "epoch": 0.5445772058823529, "grad_norm": 2.1039922622512695, "learning_rate": 9.80094224616431e-06, "loss": 0.1609179139137268, "step": 790 }, { "epoch": 0.5514705882352942, "grad_norm": 2.700897716338548, "learning_rate": 9.789585328082834e-06, "loss": 0.165602707862854, "step": 800 }, { "epoch": 0.5583639705882353, "grad_norm": 2.4045793157665734, "learning_rate": 9.777920312490956e-06, "loss": 0.165569269657135, "step": 810 }, { "epoch": 0.5652573529411765, "grad_norm": 3.4466475085106003, "learning_rate": 9.765947949758912e-06, "loss": 0.18095078468322753, "step": 820 }, { "epoch": 0.5721507352941176, "grad_norm": 1.9864981229287977, "learning_rate": 9.753669010027516e-06, "loss": 0.15277321338653566, "step": 830 }, { "epoch": 0.5790441176470589, "grad_norm": 2.008725930996786, "learning_rate": 9.741084283158625e-06, "loss": 0.16132116317749023, "step": 840 }, { "epoch": 0.5859375, "grad_norm": 2.2736349123593915, "learning_rate": 9.728194578684329e-06, "loss": 0.16320421695709228, "step": 850 }, { "epoch": 0.5928308823529411, "grad_norm": 1.6275630590940082, "learning_rate": 9.715000725754876e-06, "loss": 0.16025235652923583, "step": 860 }, { "epoch": 0.5997242647058824, "grad_norm": 2.2920671077137373, "learning_rate": 9.701503573085333e-06, "loss": 0.1543705105781555, "step": 870 }, { "epoch": 0.6066176470588235, "grad_norm": 2.270603371483843, "learning_rate": 9.687703988900997e-06, "loss": 0.16801002025604247, "step": 880 }, { "epoch": 0.6135110294117647, "grad_norm": 2.1946461234899126, "learning_rate": 9.673602860881537e-06, "loss": 0.1437917470932007, "step": 890 }, { "epoch": 0.6204044117647058, "grad_norm": 2.3507098335526435, "learning_rate": 9.6592010961039e-06, "loss": 0.17003096342086793, "step": 900 }, { "epoch": 0.6272977941176471, "grad_norm": 2.017492647818431, "learning_rate": 9.644499620983963e-06, "loss": 0.15792806148529054, "step": 910 }, { "epoch": 0.6341911764705882, "grad_norm": 2.0787254533352786, "learning_rate": 9.62949938121693e-06, "loss": 0.14900211095809937, "step": 920 }, { "epoch": 0.6410845588235294, "grad_norm": 2.40035447227194, "learning_rate": 9.614201341716504e-06, "loss": 0.1706167697906494, "step": 930 }, { "epoch": 0.6479779411764706, "grad_norm": 1.8538950485267431, "learning_rate": 9.598606486552824e-06, "loss": 0.15982599258422853, "step": 940 }, { "epoch": 0.6548713235294118, "grad_norm": 1.9043934071906214, "learning_rate": 9.582715818889153e-06, "loss": 0.17432740926742554, "step": 950 }, { "epoch": 0.6617647058823529, "grad_norm": 2.27587594496883, "learning_rate": 9.566530360917352e-06, "loss": 0.1577114224433899, "step": 960 }, { "epoch": 0.6686580882352942, "grad_norm": 2.105344773854573, "learning_rate": 9.55005115379213e-06, "loss": 0.16678417921066285, "step": 970 }, { "epoch": 0.6755514705882353, "grad_norm": 2.5167176992600693, "learning_rate": 9.53327925756406e-06, "loss": 0.17092509269714357, "step": 980 }, { "epoch": 0.6824448529411765, "grad_norm": 2.370482416583327, "learning_rate": 9.516215751111404e-06, "loss": 0.16372032165527345, "step": 990 }, { "epoch": 0.6893382352941176, "grad_norm": 2.028088178828449, "learning_rate": 9.498861732070696e-06, "loss": 0.161215341091156, "step": 1000 }, { "epoch": 0.6962316176470589, "grad_norm": 2.451825452141502, "learning_rate": 9.48121831676615e-06, "loss": 0.1647666573524475, "step": 1010 }, { "epoch": 0.703125, "grad_norm": 2.2527801259080906, "learning_rate": 9.463286640137836e-06, "loss": 0.15716235637664794, "step": 1020 }, { "epoch": 0.7100183823529411, "grad_norm": 2.097993910638137, "learning_rate": 9.445067855668692e-06, "loss": 0.16385359764099122, "step": 1030 }, { "epoch": 0.7169117647058824, "grad_norm": 3.0584172391268507, "learning_rate": 9.426563135310302e-06, "loss": 0.17193572521209716, "step": 1040 }, { "epoch": 0.7238051470588235, "grad_norm": 1.6318781928354185, "learning_rate": 9.407773669407529e-06, "loss": 0.1576675534248352, "step": 1050 }, { "epoch": 0.7306985294117647, "grad_norm": 1.3266401164663664, "learning_rate": 9.388700666621928e-06, "loss": 0.14984090328216554, "step": 1060 }, { "epoch": 0.7375919117647058, "grad_norm": 2.127107914334403, "learning_rate": 9.369345353854009e-06, "loss": 0.16828520298004152, "step": 1070 }, { "epoch": 0.7444852941176471, "grad_norm": 2.927318758975383, "learning_rate": 9.349708976164309e-06, "loss": 0.1415470600128174, "step": 1080 }, { "epoch": 0.7513786764705882, "grad_norm": 1.9163131807789373, "learning_rate": 9.329792796693303e-06, "loss": 0.14385123252868653, "step": 1090 }, { "epoch": 0.7582720588235294, "grad_norm": 1.7777424344257127, "learning_rate": 9.309598096580144e-06, "loss": 0.1374192714691162, "step": 1100 }, { "epoch": 0.7651654411764706, "grad_norm": 2.2574148851852174, "learning_rate": 9.289126174880264e-06, "loss": 0.16254189014434814, "step": 1110 }, { "epoch": 0.7720588235294118, "grad_norm": 1.8406257858680126, "learning_rate": 9.268378348481803e-06, "loss": 0.16165242195129395, "step": 1120 }, { "epoch": 0.7789522058823529, "grad_norm": 1.9984650789891443, "learning_rate": 9.247355952020896e-06, "loss": 0.15757261514663695, "step": 1130 }, { "epoch": 0.7858455882352942, "grad_norm": 1.807488800870132, "learning_rate": 9.226060337795828e-06, "loss": 0.1674361228942871, "step": 1140 }, { "epoch": 0.7927389705882353, "grad_norm": 2.8527206210520517, "learning_rate": 9.204492875680036e-06, "loss": 0.17353161573410034, "step": 1150 }, { "epoch": 0.7996323529411765, "grad_norm": 1.9864562225381739, "learning_rate": 9.182654953033998e-06, "loss": 0.1709738254547119, "step": 1160 }, { "epoch": 0.8065257352941176, "grad_norm": 1.81435176617034, "learning_rate": 9.160547974615984e-06, "loss": 0.14444026947021485, "step": 1170 }, { "epoch": 0.8134191176470589, "grad_norm": 2.387257767795693, "learning_rate": 9.138173362491691e-06, "loss": 0.16030573844909668, "step": 1180 }, { "epoch": 0.8203125, "grad_norm": 2.1939235046635783, "learning_rate": 9.115532555942775e-06, "loss": 0.16388990879058837, "step": 1190 }, { "epoch": 0.8272058823529411, "grad_norm": 2.222000975052618, "learning_rate": 9.092627011374262e-06, "loss": 0.16416647434234619, "step": 1200 }, { "epoch": 0.8340992647058824, "grad_norm": 1.7100514464919614, "learning_rate": 9.069458202220856e-06, "loss": 0.1494975209236145, "step": 1210 }, { "epoch": 0.8409926470588235, "grad_norm": 1.6705268223100351, "learning_rate": 9.046027618852166e-06, "loss": 0.1610775589942932, "step": 1220 }, { "epoch": 0.8478860294117647, "grad_norm": 1.5995452402151205, "learning_rate": 9.022336768476838e-06, "loss": 0.16996046304702758, "step": 1230 }, { "epoch": 0.8547794117647058, "grad_norm": 2.041549973190287, "learning_rate": 8.998387175045594e-06, "loss": 0.1636579990386963, "step": 1240 }, { "epoch": 0.8616727941176471, "grad_norm": 1.7037094609055712, "learning_rate": 8.974180379153204e-06, "loss": 0.1470111846923828, "step": 1250 }, { "epoch": 0.8685661764705882, "grad_norm": 12.65925244398326, "learning_rate": 8.949717937939386e-06, "loss": 0.1743556022644043, "step": 1260 }, { "epoch": 0.8754595588235294, "grad_norm": 1.5699028556152872, "learning_rate": 8.925001424988643e-06, "loss": 0.15395480394363403, "step": 1270 }, { "epoch": 0.8823529411764706, "grad_norm": 1.8226746929112438, "learning_rate": 8.90003243022903e-06, "loss": 0.14501887559890747, "step": 1280 }, { "epoch": 0.8892463235294118, "grad_norm": 1.6835055994056067, "learning_rate": 8.874812559829895e-06, "loss": 0.16053210496902465, "step": 1290 }, { "epoch": 0.8961397058823529, "grad_norm": 1.91322433569754, "learning_rate": 8.849343436098546e-06, "loss": 0.15655715465545655, "step": 1300 }, { "epoch": 0.9030330882352942, "grad_norm": 1.844931916160508, "learning_rate": 8.823626697375896e-06, "loss": 0.17419509887695311, "step": 1310 }, { "epoch": 0.9099264705882353, "grad_norm": 2.198528532750326, "learning_rate": 8.79766399793108e-06, "loss": 0.16050173044204713, "step": 1320 }, { "epoch": 0.9168198529411765, "grad_norm": 1.767688811197616, "learning_rate": 8.771457007855043e-06, "loss": 0.17059826850891113, "step": 1330 }, { "epoch": 0.9237132352941176, "grad_norm": 1.675386445109649, "learning_rate": 8.745007412953093e-06, "loss": 0.1467560887336731, "step": 1340 }, { "epoch": 0.9306066176470589, "grad_norm": 2.084810779676981, "learning_rate": 8.718316914636478e-06, "loss": 0.15948697328567504, "step": 1350 }, { "epoch": 0.9375, "grad_norm": 1.957514064781039, "learning_rate": 8.69138722981293e-06, "loss": 0.16934080123901368, "step": 1360 }, { "epoch": 0.9443933823529411, "grad_norm": 1.6377851644577517, "learning_rate": 8.664220090776225e-06, "loss": 0.16854534149169922, "step": 1370 }, { "epoch": 0.9512867647058824, "grad_norm": 1.8510588416477833, "learning_rate": 8.636817245094748e-06, "loss": 0.15824053287506104, "step": 1380 }, { "epoch": 0.9581801470588235, "grad_norm": 2.21286548122359, "learning_rate": 8.609180455499082e-06, "loss": 0.1537485122680664, "step": 1390 }, { "epoch": 0.9650735294117647, "grad_norm": 2.2136550539311246, "learning_rate": 8.581311499768613e-06, "loss": 0.1517881155014038, "step": 1400 }, { "epoch": 0.9719669117647058, "grad_norm": 2.2606781494619894, "learning_rate": 8.553212170617175e-06, "loss": 0.16092751026153565, "step": 1410 }, { "epoch": 0.9788602941176471, "grad_norm": 1.7674200123266897, "learning_rate": 8.524884275577734e-06, "loss": 0.15237100124359132, "step": 1420 }, { "epoch": 0.9857536764705882, "grad_norm": 2.0081256630907416, "learning_rate": 8.496329636886102e-06, "loss": 0.14266293048858641, "step": 1430 }, { "epoch": 0.9926470588235294, "grad_norm": 2.273672127947933, "learning_rate": 8.467550091363738e-06, "loss": 0.15185041427612306, "step": 1440 }, { "epoch": 0.9995404411764706, "grad_norm": 1.8190214263965316, "learning_rate": 8.438547490299576e-06, "loss": 0.16282849311828612, "step": 1450 }, { "epoch": 1.006204044117647, "grad_norm": 1.5988745095260293, "learning_rate": 8.409323699330947e-06, "loss": 0.1472927451133728, "step": 1460 }, { "epoch": 1.0130974264705883, "grad_norm": 1.6223397490497409, "learning_rate": 8.379880598323567e-06, "loss": 0.1473831295967102, "step": 1470 }, { "epoch": 1.0199908088235294, "grad_norm": 2.6672758933732466, "learning_rate": 8.350220081250604e-06, "loss": 0.17242648601531982, "step": 1480 }, { "epoch": 1.0268841911764706, "grad_norm": 1.4051229719062264, "learning_rate": 8.320344056070856e-06, "loss": 0.16210659742355346, "step": 1490 }, { "epoch": 1.0337775735294117, "grad_norm": 1.8082907890381676, "learning_rate": 8.29025444460602e-06, "loss": 0.1460418939590454, "step": 1500 }, { "epoch": 1.040670955882353, "grad_norm": 2.1707620899501356, "learning_rate": 8.259953182417055e-06, "loss": 0.14574445486068727, "step": 1510 }, { "epoch": 1.0475643382352942, "grad_norm": 1.9668153212469441, "learning_rate": 8.229442218679681e-06, "loss": 0.15444610118865967, "step": 1520 }, { "epoch": 1.0544577205882353, "grad_norm": 1.6828432460896554, "learning_rate": 8.198723516059004e-06, "loss": 0.14573996067047118, "step": 1530 }, { "epoch": 1.0613511029411764, "grad_norm": 2.3639646606880267, "learning_rate": 8.167799050583243e-06, "loss": 0.15691652297973632, "step": 1540 }, { "epoch": 1.0682444852941178, "grad_norm": 2.2055580864363713, "learning_rate": 8.136670811516643e-06, "loss": 0.15435473918914794, "step": 1550 }, { "epoch": 1.0751378676470589, "grad_norm": 1.8433229201656933, "learning_rate": 8.105340801231497e-06, "loss": 0.1509031295776367, "step": 1560 }, { "epoch": 1.08203125, "grad_norm": 1.5824119795770026, "learning_rate": 8.073811035079347e-06, "loss": 0.1492925763130188, "step": 1570 }, { "epoch": 1.0889246323529411, "grad_norm": 1.5830695765054288, "learning_rate": 8.042083541261338e-06, "loss": 0.15630196332931517, "step": 1580 }, { "epoch": 1.0958180147058822, "grad_norm": 1.6076644988931885, "learning_rate": 8.010160360697756e-06, "loss": 0.13141361474990845, "step": 1590 }, { "epoch": 1.1027113970588236, "grad_norm": 1.585222535618291, "learning_rate": 7.978043546896743e-06, "loss": 0.15333921909332277, "step": 1600 }, { "epoch": 1.1096047794117647, "grad_norm": 1.63768137856969, "learning_rate": 7.945735165822193e-06, "loss": 0.1440296769142151, "step": 1610 }, { "epoch": 1.1164981617647058, "grad_norm": 1.907337845859398, "learning_rate": 7.91323729576087e-06, "loss": 0.1427100419998169, "step": 1620 }, { "epoch": 1.123391544117647, "grad_norm": 2.115544584235045, "learning_rate": 7.880552027188703e-06, "loss": 0.14052720069885255, "step": 1630 }, { "epoch": 1.1302849264705883, "grad_norm": 1.9214615227942893, "learning_rate": 7.84768146263633e-06, "loss": 0.13519850969314576, "step": 1640 }, { "epoch": 1.1371783088235294, "grad_norm": 1.9454184289215273, "learning_rate": 7.814627716553832e-06, "loss": 0.15731390714645385, "step": 1650 }, { "epoch": 1.1440716911764706, "grad_norm": 2.289939209729343, "learning_rate": 7.781392915174733e-06, "loss": 0.14594757556915283, "step": 1660 }, { "epoch": 1.1509650735294117, "grad_norm": 2.0907599024191326, "learning_rate": 7.747979196379219e-06, "loss": 0.15411378145217897, "step": 1670 }, { "epoch": 1.157858455882353, "grad_norm": 1.7624952652395163, "learning_rate": 7.714388709556609e-06, "loss": 0.15513694286346436, "step": 1680 }, { "epoch": 1.1647518382352942, "grad_norm": 1.9680280085303146, "learning_rate": 7.68062361546711e-06, "loss": 0.14441139698028566, "step": 1690 }, { "epoch": 1.1716452205882353, "grad_norm": 1.7092966245886136, "learning_rate": 7.646686086102806e-06, "loss": 0.13383402824401855, "step": 1700 }, { "epoch": 1.1785386029411764, "grad_norm": 2.0157942232171124, "learning_rate": 7.61257830454795e-06, "loss": 0.14235570430755615, "step": 1710 }, { "epoch": 1.1854319852941178, "grad_norm": 1.801340431180514, "learning_rate": 7.578302464838532e-06, "loss": 0.14418511390686034, "step": 1720 }, { "epoch": 1.1923253676470589, "grad_norm": 2.014703855062623, "learning_rate": 7.543860771821141e-06, "loss": 0.15101964473724366, "step": 1730 }, { "epoch": 1.19921875, "grad_norm": 1.9210973609098658, "learning_rate": 7.509255441011141e-06, "loss": 0.1443597912788391, "step": 1740 }, { "epoch": 1.2061121323529411, "grad_norm": 1.4104800122560395, "learning_rate": 7.474488698450148e-06, "loss": 0.14291495084762573, "step": 1750 }, { "epoch": 1.2130055147058822, "grad_norm": 1.5258623028176626, "learning_rate": 7.439562780562839e-06, "loss": 0.1412590980529785, "step": 1760 }, { "epoch": 1.2198988970588236, "grad_norm": 2.6367674482757453, "learning_rate": 7.4044799340130946e-06, "loss": 0.14387788772583007, "step": 1770 }, { "epoch": 1.2267922794117647, "grad_norm": 1.7069860176463973, "learning_rate": 7.3692424155594745e-06, "loss": 0.14593122005462647, "step": 1780 }, { "epoch": 1.2336856617647058, "grad_norm": 1.5917622816859138, "learning_rate": 7.333852491910043e-06, "loss": 0.13555134534835817, "step": 1790 }, { "epoch": 1.240579044117647, "grad_norm": 1.9305033420502284, "learning_rate": 7.298312439576574e-06, "loss": 0.14243204593658448, "step": 1800 }, { "epoch": 1.2474724264705883, "grad_norm": 1.4958837788508892, "learning_rate": 7.262624544728094e-06, "loss": 0.15101094245910646, "step": 1810 }, { "epoch": 1.2543658088235294, "grad_norm": 1.6747899060756728, "learning_rate": 7.226791103043835e-06, "loss": 0.14668235778808594, "step": 1820 }, { "epoch": 1.2612591911764706, "grad_norm": 2.2518485128377312, "learning_rate": 7.19081441956555e-06, "loss": 0.14163424968719482, "step": 1830 }, { "epoch": 1.2681525735294117, "grad_norm": 1.728273951797738, "learning_rate": 7.154696808549246e-06, "loss": 0.13002049922943115, "step": 1840 }, { "epoch": 1.2750459558823528, "grad_norm": 1.7020053589071926, "learning_rate": 7.118440593316312e-06, "loss": 0.16444404125213624, "step": 1850 }, { "epoch": 1.2819393382352942, "grad_norm": 2.0330568773602344, "learning_rate": 7.082048106104068e-06, "loss": 0.14571700096130372, "step": 1860 }, { "epoch": 1.2888327205882353, "grad_norm": 1.5544759227267877, "learning_rate": 7.045521687915739e-06, "loss": 0.15139193534851075, "step": 1870 }, { "epoch": 1.2957261029411764, "grad_norm": 1.3707954890971656, "learning_rate": 7.008863688369873e-06, "loss": 0.1477123022079468, "step": 1880 }, { "epoch": 1.3026194852941178, "grad_norm": 1.5077479473963344, "learning_rate": 6.972076465549186e-06, "loss": 0.14567289352416993, "step": 1890 }, { "epoch": 1.3095128676470589, "grad_norm": 1.8621365716256821, "learning_rate": 6.935162385848888e-06, "loss": 0.15198432207107543, "step": 1900 }, { "epoch": 1.31640625, "grad_norm": 1.5713690215818659, "learning_rate": 6.898123823824452e-06, "loss": 0.15759592056274413, "step": 1910 }, { "epoch": 1.3232996323529411, "grad_norm": 1.891675471457382, "learning_rate": 6.860963162038866e-06, "loss": 0.13721535205841065, "step": 1920 }, { "epoch": 1.3301930147058822, "grad_norm": 1.6943184507678362, "learning_rate": 6.823682790909384e-06, "loss": 0.13009350299835204, "step": 1930 }, { "epoch": 1.3370863970588236, "grad_norm": 1.7774359175748022, "learning_rate": 6.786285108553739e-06, "loss": 0.1439496397972107, "step": 1940 }, { "epoch": 1.3439797794117647, "grad_norm": 1.8597414102572818, "learning_rate": 6.748772520635899e-06, "loss": 0.13554062843322753, "step": 1950 }, { "epoch": 1.3508731617647058, "grad_norm": 2.1852960570901785, "learning_rate": 6.711147440211304e-06, "loss": 0.14609992504119873, "step": 1960 }, { "epoch": 1.3577665441176472, "grad_norm": 1.9313283084309325, "learning_rate": 6.673412287571655e-06, "loss": 0.14392735958099365, "step": 1970 }, { "epoch": 1.3646599264705883, "grad_norm": 1.7421508143880167, "learning_rate": 6.635569490089215e-06, "loss": 0.13514573574066163, "step": 1980 }, { "epoch": 1.3715533088235294, "grad_norm": 1.5432541026623707, "learning_rate": 6.5976214820606695e-06, "loss": 0.14920060634613036, "step": 1990 }, { "epoch": 1.3784466911764706, "grad_norm": 1.7325648788299666, "learning_rate": 6.559570704550536e-06, "loss": 0.13802111148834229, "step": 2000 }, { "epoch": 1.3853400735294117, "grad_norm": 1.4180755814316135, "learning_rate": 6.521419605234141e-06, "loss": 0.14823660850524903, "step": 2010 }, { "epoch": 1.3922334558823528, "grad_norm": 1.6671150546352118, "learning_rate": 6.48317063824016e-06, "loss": 0.1522348165512085, "step": 2020 }, { "epoch": 1.3991268382352942, "grad_norm": 1.6560268949174834, "learning_rate": 6.444826263992767e-06, "loss": 0.1401064395904541, "step": 2030 }, { "epoch": 1.4060202205882353, "grad_norm": 1.949640947160851, "learning_rate": 6.40638894905335e-06, "loss": 0.13964433670043946, "step": 2040 }, { "epoch": 1.4129136029411764, "grad_norm": 1.6916477749048844, "learning_rate": 6.367861165961854e-06, "loss": 0.14463403224945068, "step": 2050 }, { "epoch": 1.4198069852941178, "grad_norm": 1.7534809687050923, "learning_rate": 6.329245393077727e-06, "loss": 0.1377117156982422, "step": 2060 }, { "epoch": 1.4267003676470589, "grad_norm": 2.4343486564199748, "learning_rate": 6.290544114420496e-06, "loss": 0.1427626609802246, "step": 2070 }, { "epoch": 1.43359375, "grad_norm": 1.6339522704199174, "learning_rate": 6.251759819509984e-06, "loss": 0.150077486038208, "step": 2080 }, { "epoch": 1.4404871323529411, "grad_norm": 1.4745669822133622, "learning_rate": 6.212895003206158e-06, "loss": 0.14722493886947632, "step": 2090 }, { "epoch": 1.4473805147058822, "grad_norm": 2.0466125953036935, "learning_rate": 6.173952165548651e-06, "loss": 0.13647210597991943, "step": 2100 }, { "epoch": 1.4542738970588236, "grad_norm": 1.4084165087359701, "learning_rate": 6.13493381159594e-06, "loss": 0.15385825634002687, "step": 2110 }, { "epoch": 1.4611672794117647, "grad_norm": 1.5987480886779193, "learning_rate": 6.095842451264207e-06, "loss": 0.13793781995773316, "step": 2120 }, { "epoch": 1.4680606617647058, "grad_norm": 2.2310062139904354, "learning_rate": 6.056680599165882e-06, "loss": 0.14825844764709473, "step": 2130 }, { "epoch": 1.4749540441176472, "grad_norm": 1.654927391132379, "learning_rate": 6.017450774447885e-06, "loss": 0.13707478046417237, "step": 2140 }, { "epoch": 1.4818474264705883, "grad_norm": 1.7240535638114054, "learning_rate": 5.97815550062958e-06, "loss": 0.152138090133667, "step": 2150 }, { "epoch": 1.4887408088235294, "grad_norm": 1.6993262585571232, "learning_rate": 5.938797305440452e-06, "loss": 0.1269232749938965, "step": 2160 }, { "epoch": 1.4956341911764706, "grad_norm": 2.305065486004532, "learning_rate": 5.899378720657491e-06, "loss": 0.14829449653625487, "step": 2170 }, { "epoch": 1.5025275735294117, "grad_norm": 1.812931865023039, "learning_rate": 5.859902281942353e-06, "loss": 0.12375198602676392, "step": 2180 }, { "epoch": 1.5094209558823528, "grad_norm": 1.917807473002464, "learning_rate": 5.820370528678226e-06, "loss": 0.1606054425239563, "step": 2190 }, { "epoch": 1.5163143382352942, "grad_norm": 1.7798610166196271, "learning_rate": 5.780786003806502e-06, "loss": 0.1301969289779663, "step": 2200 }, { "epoch": 1.5232077205882353, "grad_norm": 1.7316987198868292, "learning_rate": 5.741151253663183e-06, "loss": 0.12928574085235595, "step": 2210 }, { "epoch": 1.5301011029411766, "grad_norm": 1.5262360769836112, "learning_rate": 5.7014688278150906e-06, "loss": 0.1264800548553467, "step": 2220 }, { "epoch": 1.5369944852941178, "grad_norm": 1.4924643904629133, "learning_rate": 5.661741278895862e-06, "loss": 0.13658742904663085, "step": 2230 }, { "epoch": 1.5438878676470589, "grad_norm": 2.0917676181153664, "learning_rate": 5.621971162441746e-06, "loss": 0.13064200878143312, "step": 2240 }, { "epoch": 1.55078125, "grad_norm": 2.3981719986350605, "learning_rate": 5.582161036727209e-06, "loss": 0.14448009729385375, "step": 2250 }, { "epoch": 1.5576746323529411, "grad_norm": 2.0348320032998495, "learning_rate": 5.542313462600384e-06, "loss": 0.12393027544021606, "step": 2260 }, { "epoch": 1.5645680147058822, "grad_norm": 1.8193697546174674, "learning_rate": 5.502431003318322e-06, "loss": 0.1507801055908203, "step": 2270 }, { "epoch": 1.5714613970588234, "grad_norm": 2.4845580997807186, "learning_rate": 5.4625162243821205e-06, "loss": 0.16156342029571533, "step": 2280 }, { "epoch": 1.5783547794117647, "grad_norm": 1.184445176280688, "learning_rate": 5.422571693371891e-06, "loss": 0.12696654796600343, "step": 2290 }, { "epoch": 1.5852481617647058, "grad_norm": 1.6066615967639477, "learning_rate": 5.382599979781588e-06, "loss": 0.14744441509246825, "step": 2300 }, { "epoch": 1.5921415441176472, "grad_norm": 1.6022406930157385, "learning_rate": 5.3426036548537315e-06, "loss": 0.12689508199691774, "step": 2310 }, { "epoch": 1.5990349264705883, "grad_norm": 1.5670282783908427, "learning_rate": 5.302585291414004e-06, "loss": 0.14102492332458497, "step": 2320 }, { "epoch": 1.6059283088235294, "grad_norm": 1.6969524622265773, "learning_rate": 5.262547463705747e-06, "loss": 0.14767897129058838, "step": 2330 }, { "epoch": 1.6128216911764706, "grad_norm": 1.7071268612508324, "learning_rate": 5.222492747224373e-06, "loss": 0.14464342594146729, "step": 2340 }, { "epoch": 1.6197150735294117, "grad_norm": 1.82359074948181, "learning_rate": 5.182423718551692e-06, "loss": 0.14657317399978637, "step": 2350 }, { "epoch": 1.6266084558823528, "grad_norm": 1.9443082806773748, "learning_rate": 5.142342955190163e-06, "loss": 0.13043413162231446, "step": 2360 }, { "epoch": 1.6335018382352942, "grad_norm": 1.5573398014873407, "learning_rate": 5.102253035397105e-06, "loss": 0.1361347556114197, "step": 2370 }, { "epoch": 1.6403952205882353, "grad_norm": 1.4728957935010625, "learning_rate": 5.062156538018832e-06, "loss": 0.145288348197937, "step": 2380 }, { "epoch": 1.6472886029411766, "grad_norm": 1.4961237431450092, "learning_rate": 5.0220560423247755e-06, "loss": 0.14340994358062745, "step": 2390 }, { "epoch": 1.6541819852941178, "grad_norm": 1.6411953674167117, "learning_rate": 4.981954127841562e-06, "loss": 0.15326478481292724, "step": 2400 }, { "epoch": 1.6610753676470589, "grad_norm": 1.3741078444189752, "learning_rate": 4.941853374187083e-06, "loss": 0.1366991877555847, "step": 2410 }, { "epoch": 1.66796875, "grad_norm": 2.0978470854164675, "learning_rate": 4.901756360904565e-06, "loss": 0.15518345832824706, "step": 2420 }, { "epoch": 1.6748621323529411, "grad_norm": 1.5814673061583175, "learning_rate": 4.861665667296619e-06, "loss": 0.1281091809272766, "step": 2430 }, { "epoch": 1.6817555147058822, "grad_norm": 1.6260719642062298, "learning_rate": 4.821583872259341e-06, "loss": 0.12725906372070311, "step": 2440 }, { "epoch": 1.6886488970588234, "grad_norm": 1.7690763597862846, "learning_rate": 4.781513554116408e-06, "loss": 0.13620359897613527, "step": 2450 }, { "epoch": 1.6955422794117647, "grad_norm": 1.6594918804985923, "learning_rate": 4.741457290453233e-06, "loss": 0.145400071144104, "step": 2460 }, { "epoch": 1.7024356617647058, "grad_norm": 1.4709815736807386, "learning_rate": 4.7014176579511456e-06, "loss": 0.142938494682312, "step": 2470 }, { "epoch": 1.7093290441176472, "grad_norm": 1.8067264635148756, "learning_rate": 4.661397232221658e-06, "loss": 0.13525724411010742, "step": 2480 }, { "epoch": 1.7162224264705883, "grad_norm": 1.6742657569361763, "learning_rate": 4.621398587640769e-06, "loss": 0.1330089569091797, "step": 2490 }, { "epoch": 1.7231158088235294, "grad_norm": 1.6012543971591917, "learning_rate": 4.58142429718338e-06, "loss": 0.1341208577156067, "step": 2500 }, { "epoch": 1.7300091911764706, "grad_norm": 1.9205684863387458, "learning_rate": 4.541476932257766e-06, "loss": 0.14351036548614501, "step": 2510 }, { "epoch": 1.7369025735294117, "grad_norm": 1.762354374799991, "learning_rate": 4.501559062540184e-06, "loss": 0.13325161933898927, "step": 2520 }, { "epoch": 1.7437959558823528, "grad_norm": 2.0632179097039973, "learning_rate": 4.461673255809562e-06, "loss": 0.12966744899749755, "step": 2530 }, { "epoch": 1.7506893382352942, "grad_norm": 2.1283125222582537, "learning_rate": 4.421822077782323e-06, "loss": 0.13448989391326904, "step": 2540 }, { "epoch": 1.7575827205882353, "grad_norm": 1.4134072111967055, "learning_rate": 4.382008091947355e-06, "loss": 0.1310030460357666, "step": 2550 }, { "epoch": 1.7644761029411766, "grad_norm": 2.298403913407891, "learning_rate": 4.3422338594010885e-06, "loss": 0.14739159345626832, "step": 2560 }, { "epoch": 1.7713694852941178, "grad_norm": 1.7763077758774186, "learning_rate": 4.302501938682771e-06, "loss": 0.1399444580078125, "step": 2570 }, { "epoch": 1.7782628676470589, "grad_norm": 1.653606623491891, "learning_rate": 4.262814885609872e-06, "loss": 0.1351703405380249, "step": 2580 }, { "epoch": 1.78515625, "grad_norm": 2.6738819877618853, "learning_rate": 4.223175253113681e-06, "loss": 0.1410216808319092, "step": 2590 }, { "epoch": 1.7920496323529411, "grad_norm": 1.6971057699000849, "learning_rate": 4.1835855910750835e-06, "loss": 0.13644049167633057, "step": 2600 }, { "epoch": 1.7989430147058822, "grad_norm": 1.6326460704526091, "learning_rate": 4.144048446160541e-06, "loss": 0.13414173126220702, "step": 2610 }, { "epoch": 1.8058363970588234, "grad_norm": 1.7336577381080374, "learning_rate": 4.104566361658267e-06, "loss": 0.13017280101776124, "step": 2620 }, { "epoch": 1.8127297794117647, "grad_norm": 1.9262868180041908, "learning_rate": 4.065141877314631e-06, "loss": 0.1337353229522705, "step": 2630 }, { "epoch": 1.8196231617647058, "grad_norm": 1.3835519377438648, "learning_rate": 4.02577752917078e-06, "loss": 0.13349078893661498, "step": 2640 }, { "epoch": 1.8265165441176472, "grad_norm": 1.9611288995915224, "learning_rate": 3.986475849399507e-06, "loss": 0.13329349756240844, "step": 2650 }, { "epoch": 1.8334099264705883, "grad_norm": 1.8948393474300083, "learning_rate": 3.947239366142369e-06, "loss": 0.1371665596961975, "step": 2660 }, { "epoch": 1.8403033088235294, "grad_norm": 1.7416005426621846, "learning_rate": 3.9080706033470464e-06, "loss": 0.1397342562675476, "step": 2670 }, { "epoch": 1.8471966911764706, "grad_norm": 1.2646051845672215, "learning_rate": 3.8689720806050095e-06, "loss": 0.11453455686569214, "step": 2680 }, { "epoch": 1.8540900735294117, "grad_norm": 2.001472916370873, "learning_rate": 3.829946312989414e-06, "loss": 0.13941944837570192, "step": 2690 }, { "epoch": 1.8609834558823528, "grad_norm": 1.9800679774471892, "learning_rate": 3.79099581089334e-06, "loss": 0.15124634504318238, "step": 2700 }, { "epoch": 1.8678768382352942, "grad_norm": 1.6867655002024835, "learning_rate": 3.7521230798682884e-06, "loss": 0.14064371585845947, "step": 2710 }, { "epoch": 1.8747702205882353, "grad_norm": 1.8976530277714836, "learning_rate": 3.7133306204630227e-06, "loss": 0.1397136926651001, "step": 2720 }, { "epoch": 1.8816636029411766, "grad_norm": 2.14151373187302, "learning_rate": 3.6746209280627034e-06, "loss": 0.14189364910125732, "step": 2730 }, { "epoch": 1.8885569852941178, "grad_norm": 1.9672105753560098, "learning_rate": 3.6359964927283776e-06, "loss": 0.1172229528427124, "step": 2740 }, { "epoch": 1.8954503676470589, "grad_norm": 1.993330453741204, "learning_rate": 3.597459799036802e-06, "loss": 0.13286043405532838, "step": 2750 }, { "epoch": 1.90234375, "grad_norm": 1.5302298187029924, "learning_rate": 3.5590133259206093e-06, "loss": 0.14128028154373168, "step": 2760 }, { "epoch": 1.9092371323529411, "grad_norm": 2.011950617156456, "learning_rate": 3.5206595465088606e-06, "loss": 0.13666582107543945, "step": 2770 }, { "epoch": 1.9161305147058822, "grad_norm": 1.7288358974818068, "learning_rate": 3.4824009279679456e-06, "loss": 0.13020799160003663, "step": 2780 }, { "epoch": 1.9230238970588234, "grad_norm": 1.5190704485403526, "learning_rate": 3.4442399313428875e-06, "loss": 0.13748562335968018, "step": 2790 }, { "epoch": 1.9299172794117647, "grad_norm": 1.832103272072538, "learning_rate": 3.406179011399021e-06, "loss": 0.1284859299659729, "step": 2800 }, { "epoch": 1.9368106617647058, "grad_norm": 1.4546021900693107, "learning_rate": 3.368220616464105e-06, "loss": 0.11885954141616821, "step": 2810 }, { "epoch": 1.9437040441176472, "grad_norm": 1.8271489966041947, "learning_rate": 3.330367188270805e-06, "loss": 0.12866705656051636, "step": 2820 }, { "epoch": 1.9505974264705883, "grad_norm": 1.8068298861667877, "learning_rate": 3.2926211617996474e-06, "loss": 0.14845612049102783, "step": 2830 }, { "epoch": 1.9574908088235294, "grad_norm": 1.5573554184944385, "learning_rate": 3.2549849651223693e-06, "loss": 0.13820537328720092, "step": 2840 }, { "epoch": 1.9643841911764706, "grad_norm": 1.9779923865800493, "learning_rate": 3.217461019245741e-06, "loss": 0.12901639938354492, "step": 2850 }, { "epoch": 1.9712775735294117, "grad_norm": 1.4256869281739777, "learning_rate": 3.180051737955826e-06, "loss": 0.13740575313568115, "step": 2860 }, { "epoch": 1.9781709558823528, "grad_norm": 1.4109838187842052, "learning_rate": 3.1427595276627042e-06, "loss": 0.13781973123550414, "step": 2870 }, { "epoch": 1.9850643382352942, "grad_norm": 1.6978632689805804, "learning_rate": 3.105586787245689e-06, "loss": 0.1352555513381958, "step": 2880 }, { "epoch": 1.9919577205882353, "grad_norm": 1.8073855403990506, "learning_rate": 3.068535907899004e-06, "loss": 0.13522062301635743, "step": 2890 }, { "epoch": 1.9988511029411766, "grad_norm": 1.704630610572276, "learning_rate": 3.0316092729779733e-06, "loss": 0.14497931003570558, "step": 2900 }, { "epoch": 2.005514705882353, "grad_norm": 1.356328172600568, "learning_rate": 2.9948092578457015e-06, "loss": 0.1228764533996582, "step": 2910 }, { "epoch": 2.012408088235294, "grad_norm": 2.407536667228917, "learning_rate": 2.9581382297202852e-06, "loss": 0.11468364000320434, "step": 2920 }, { "epoch": 2.0193014705882355, "grad_norm": 1.410250558397681, "learning_rate": 2.9215985475225224e-06, "loss": 0.11977126598358154, "step": 2930 }, { "epoch": 2.0261948529411766, "grad_norm": 1.5553196634912534, "learning_rate": 2.885192561724191e-06, "loss": 0.12928369045257568, "step": 2940 }, { "epoch": 2.0330882352941178, "grad_norm": 1.5120256544331756, "learning_rate": 2.8489226141968297e-06, "loss": 0.1211053967475891, "step": 2950 }, { "epoch": 2.039981617647059, "grad_norm": 1.510327380144663, "learning_rate": 2.8127910380611146e-06, "loss": 0.11670500040054321, "step": 2960 }, { "epoch": 2.046875, "grad_norm": 1.3126974404969163, "learning_rate": 2.776800157536761e-06, "loss": 0.13219075202941893, "step": 2970 }, { "epoch": 2.053768382352941, "grad_norm": 1.872423900612551, "learning_rate": 2.7409522877930184e-06, "loss": 0.12856197357177734, "step": 2980 }, { "epoch": 2.0606617647058822, "grad_norm": 1.715367764063543, "learning_rate": 2.7052497347997577e-06, "loss": 0.1153645634651184, "step": 2990 }, { "epoch": 2.0675551470588234, "grad_norm": 1.9674087281129433, "learning_rate": 2.669694795179106e-06, "loss": 0.12575641870498658, "step": 3000 }, { "epoch": 2.0744485294117645, "grad_norm": 2.184395219605904, "learning_rate": 2.6342897560577478e-06, "loss": 0.11486480236053467, "step": 3010 }, { "epoch": 2.081341911764706, "grad_norm": 1.9560867025510356, "learning_rate": 2.5990368949197776e-06, "loss": 0.12360923290252686, "step": 3020 }, { "epoch": 2.088235294117647, "grad_norm": 1.4957547139600433, "learning_rate": 2.5639384794602045e-06, "loss": 0.12444189786911011, "step": 3030 }, { "epoch": 2.0951286764705883, "grad_norm": 1.958571347724113, "learning_rate": 2.5289967674390804e-06, "loss": 0.12822755575180053, "step": 3040 }, { "epoch": 2.1020220588235294, "grad_norm": 1.6027469500661649, "learning_rate": 2.4942140065362684e-06, "loss": 0.13448936939239503, "step": 3050 }, { "epoch": 2.1089154411764706, "grad_norm": 1.6765411649394228, "learning_rate": 2.459592434206851e-06, "loss": 0.12157846689224243, "step": 3060 }, { "epoch": 2.1158088235294117, "grad_norm": 1.629101262437938, "learning_rate": 2.4251342775372044e-06, "loss": 0.13914096355438232, "step": 3070 }, { "epoch": 2.122702205882353, "grad_norm": 1.5912622976226074, "learning_rate": 2.3908417531017437e-06, "loss": 0.12324203252792358, "step": 3080 }, { "epoch": 2.129595588235294, "grad_norm": 2.210174202861284, "learning_rate": 2.3567170668203295e-06, "loss": 0.11572927236557007, "step": 3090 }, { "epoch": 2.1364889705882355, "grad_norm": 1.4923410743938628, "learning_rate": 2.322762413816373e-06, "loss": 0.12262394428253173, "step": 3100 }, { "epoch": 2.1433823529411766, "grad_norm": 1.7949914671907106, "learning_rate": 2.2889799782756296e-06, "loss": 0.10686519145965576, "step": 3110 }, { "epoch": 2.1502757352941178, "grad_norm": 2.1257598100960053, "learning_rate": 2.255371933305705e-06, "loss": 0.11408430337905884, "step": 3120 }, { "epoch": 2.157169117647059, "grad_norm": 2.53927856986225, "learning_rate": 2.2219404407962546e-06, "loss": 0.1226811408996582, "step": 3130 }, { "epoch": 2.1640625, "grad_norm": 1.7030436901690522, "learning_rate": 2.1886876512799254e-06, "loss": 0.11708424091339112, "step": 3140 }, { "epoch": 2.170955882352941, "grad_norm": 1.6614634238791786, "learning_rate": 2.155615703794014e-06, "loss": 0.12207735776901245, "step": 3150 }, { "epoch": 2.1778492647058822, "grad_norm": 1.1739219439939677, "learning_rate": 2.1227267257428812e-06, "loss": 0.12072246074676514, "step": 3160 }, { "epoch": 2.1847426470588234, "grad_norm": 1.623098330425371, "learning_rate": 2.0900228327610813e-06, "loss": 0.1309061050415039, "step": 3170 }, { "epoch": 2.1916360294117645, "grad_norm": 2.456163474600315, "learning_rate": 2.0575061285772974e-06, "loss": 0.12170616388320923, "step": 3180 }, { "epoch": 2.198529411764706, "grad_norm": 1.7439506066029569, "learning_rate": 2.0251787048789952e-06, "loss": 0.12398629188537598, "step": 3190 }, { "epoch": 2.205422794117647, "grad_norm": 1.618423785542649, "learning_rate": 1.9930426411778793e-06, "loss": 0.12292356491088867, "step": 3200 }, { "epoch": 2.2123161764705883, "grad_norm": 1.5653768754449628, "learning_rate": 1.9611000046761307e-06, "loss": 0.12482486963272095, "step": 3210 }, { "epoch": 2.2192095588235294, "grad_norm": 1.6970159191224437, "learning_rate": 1.929352850133421e-06, "loss": 0.12064193487167359, "step": 3220 }, { "epoch": 2.2261029411764706, "grad_norm": 1.4093474902826688, "learning_rate": 1.8978032197347428e-06, "loss": 0.11071947813034058, "step": 3230 }, { "epoch": 2.2329963235294117, "grad_norm": 1.6659035365221513, "learning_rate": 1.8664531429590388e-06, "loss": 0.1171844482421875, "step": 3240 }, { "epoch": 2.239889705882353, "grad_norm": 1.4585861475663948, "learning_rate": 1.835304636448662e-06, "loss": 0.12667326927185057, "step": 3250 }, { "epoch": 2.246783088235294, "grad_norm": 1.7852807628759235, "learning_rate": 1.8043597038796385e-06, "loss": 0.12232849597930909, "step": 3260 }, { "epoch": 2.2536764705882355, "grad_norm": 1.5846324738297328, "learning_rate": 1.773620335832788e-06, "loss": 0.12169291973114013, "step": 3270 }, { "epoch": 2.2605698529411766, "grad_norm": 1.3941886655728606, "learning_rate": 1.7430885096656697e-06, "loss": 0.12119593620300292, "step": 3280 }, { "epoch": 2.2674632352941178, "grad_norm": 1.7479226517961066, "learning_rate": 1.7127661893853974e-06, "loss": 0.13094499111175537, "step": 3290 }, { "epoch": 2.274356617647059, "grad_norm": 1.8497602209824469, "learning_rate": 1.682655325522281e-06, "loss": 0.12754638195037843, "step": 3300 }, { "epoch": 2.28125, "grad_norm": 1.8300480124155798, "learning_rate": 1.6527578550043794e-06, "loss": 0.12330667972564698, "step": 3310 }, { "epoch": 2.288143382352941, "grad_norm": 1.8351350793873797, "learning_rate": 1.6230757010328912e-06, "loss": 0.1271721363067627, "step": 3320 }, { "epoch": 2.2950367647058822, "grad_norm": 1.343942724740844, "learning_rate": 1.5936107729584366e-06, "loss": 0.1242860198020935, "step": 3330 }, { "epoch": 2.3019301470588234, "grad_norm": 2.0609844162533277, "learning_rate": 1.5643649661582516e-06, "loss": 0.12298851013183594, "step": 3340 }, { "epoch": 2.3088235294117645, "grad_norm": 1.7072391975471128, "learning_rate": 1.5353401619142522e-06, "loss": 0.11442519426345825, "step": 3350 }, { "epoch": 2.315716911764706, "grad_norm": 11.43260460138998, "learning_rate": 1.5065382272920216e-06, "loss": 0.1262655019760132, "step": 3360 }, { "epoch": 2.322610294117647, "grad_norm": 1.8237230391467154, "learning_rate": 1.477961015020708e-06, "loss": 0.13734149932861328, "step": 3370 }, { "epoch": 2.3295036764705883, "grad_norm": 2.2877695118445827, "learning_rate": 1.4496103633738501e-06, "loss": 0.13214576244354248, "step": 3380 }, { "epoch": 2.3363970588235294, "grad_norm": 1.5917342803973868, "learning_rate": 1.4214880960511185e-06, "loss": 0.13003909587860107, "step": 3390 }, { "epoch": 2.3432904411764706, "grad_norm": 1.7245932014266123, "learning_rate": 1.3935960220610085e-06, "loss": 0.12499830722808838, "step": 3400 }, { "epoch": 2.3501838235294117, "grad_norm": 1.9571976645528342, "learning_rate": 1.3659359356044704e-06, "loss": 0.10829086303710937, "step": 3410 }, { "epoch": 2.357077205882353, "grad_norm": 1.4718641738407137, "learning_rate": 1.3385096159595018e-06, "loss": 0.12705686092376708, "step": 3420 }, { "epoch": 2.363970588235294, "grad_norm": 1.401988786297165, "learning_rate": 1.3113188273666817e-06, "loss": 0.1253787398338318, "step": 3430 }, { "epoch": 2.3708639705882355, "grad_norm": 1.464538112801459, "learning_rate": 1.2843653189156895e-06, "loss": 0.12692570686340332, "step": 3440 }, { "epoch": 2.3777573529411766, "grad_norm": 1.587203541690375, "learning_rate": 1.2576508244327974e-06, "loss": 0.11601523160934449, "step": 3450 }, { "epoch": 2.3846507352941178, "grad_norm": 1.5265589774767858, "learning_rate": 1.2311770623693203e-06, "loss": 0.12817733287811278, "step": 3460 }, { "epoch": 2.391544117647059, "grad_norm": 2.5795723967867916, "learning_rate": 1.2049457356911004e-06, "loss": 0.1324072003364563, "step": 3470 }, { "epoch": 2.3984375, "grad_norm": 1.5185889507472856, "learning_rate": 1.1789585317689396e-06, "loss": 0.12961714267730712, "step": 3480 }, { "epoch": 2.405330882352941, "grad_norm": 1.355489655361134, "learning_rate": 1.153217122270065e-06, "loss": 0.12598588466644287, "step": 3490 }, { "epoch": 2.4122242647058822, "grad_norm": 1.7039180382759966, "learning_rate": 1.1277231630505974e-06, "loss": 0.11995019912719726, "step": 3500 }, { "epoch": 2.4191176470588234, "grad_norm": 1.3378222465611385, "learning_rate": 1.1024782940490359e-06, "loss": 0.12128536701202393, "step": 3510 }, { "epoch": 2.4260110294117645, "grad_norm": 2.5433540934359367, "learning_rate": 1.0774841391807621e-06, "loss": 0.1285119652748108, "step": 3520 }, { "epoch": 2.432904411764706, "grad_norm": 2.024696419036, "learning_rate": 1.0527423062335817e-06, "loss": 0.13637562990188598, "step": 3530 }, { "epoch": 2.439797794117647, "grad_norm": 1.6381170358240307, "learning_rate": 1.0282543867643035e-06, "loss": 0.11671664714813232, "step": 3540 }, { "epoch": 2.4466911764705883, "grad_norm": 1.3734365626645477, "learning_rate": 1.0040219559963566e-06, "loss": 0.11699503660202026, "step": 3550 }, { "epoch": 2.4535845588235294, "grad_norm": 1.774646527543002, "learning_rate": 9.800465727184615e-07, "loss": 0.13001445531845093, "step": 3560 }, { "epoch": 2.4604779411764706, "grad_norm": 1.3487004239076588, "learning_rate": 9.5632977918436e-07, "loss": 0.11101350784301758, "step": 3570 }, { "epoch": 2.4673713235294117, "grad_norm": 2.5371711664913716, "learning_rate": 9.328731010136127e-07, "loss": 0.11515891551971436, "step": 3580 }, { "epoch": 2.474264705882353, "grad_norm": 1.6498866705810662, "learning_rate": 9.096780470934452e-07, "loss": 0.12387334108352661, "step": 3590 }, { "epoch": 2.481158088235294, "grad_norm": 2.0340008261358844, "learning_rate": 8.867461094817076e-07, "loss": 0.11307168006896973, "step": 3600 }, { "epoch": 2.4880514705882355, "grad_norm": 2.0663184005008723, "learning_rate": 8.640787633108794e-07, "loss": 0.11421011686325074, "step": 3610 }, { "epoch": 2.4949448529411766, "grad_norm": 2.9574688497452257, "learning_rate": 8.416774666931865e-07, "loss": 0.1383601188659668, "step": 3620 }, { "epoch": 2.5018382352941178, "grad_norm": 1.3992496133775376, "learning_rate": 8.19543660626802e-07, "loss": 0.11277010440826415, "step": 3630 }, { "epoch": 2.508731617647059, "grad_norm": 2.013275617557738, "learning_rate": 7.976787689031595e-07, "loss": 0.12040656805038452, "step": 3640 }, { "epoch": 2.515625, "grad_norm": 1.688288679938074, "learning_rate": 7.760841980153549e-07, "loss": 0.11580615043640137, "step": 3650 }, { "epoch": 2.522518382352941, "grad_norm": 1.7801536781898577, "learning_rate": 7.547613370676781e-07, "loss": 0.11590677499771118, "step": 3660 }, { "epoch": 2.5294117647058822, "grad_norm": 1.5427348330312067, "learning_rate": 7.33711557686258e-07, "loss": 0.12278809547424316, "step": 3670 }, { "epoch": 2.5363051470588234, "grad_norm": 1.8284382603574516, "learning_rate": 7.129362139308244e-07, "loss": 0.12422704696655273, "step": 3680 }, { "epoch": 2.5431985294117645, "grad_norm": 1.5965588977584688, "learning_rate": 6.924366422076112e-07, "loss": 0.11048816442489624, "step": 3690 }, { "epoch": 2.5500919117647056, "grad_norm": 1.5253302854347293, "learning_rate": 6.722141611833871e-07, "loss": 0.12218728065490722, "step": 3700 }, { "epoch": 2.556985294117647, "grad_norm": 1.201475281413098, "learning_rate": 6.522700717006347e-07, "loss": 0.10220586061477661, "step": 3710 }, { "epoch": 2.5638786764705883, "grad_norm": 3.081778902240648, "learning_rate": 6.326056566938632e-07, "loss": 0.1138386845588684, "step": 3720 }, { "epoch": 2.5707720588235294, "grad_norm": 1.6512925830327463, "learning_rate": 6.132221811070921e-07, "loss": 0.12896506786346434, "step": 3730 }, { "epoch": 2.5776654411764706, "grad_norm": 1.5166413284955438, "learning_rate": 5.941208918124747e-07, "loss": 0.10645806789398193, "step": 3740 }, { "epoch": 2.5845588235294117, "grad_norm": 1.8186297717660707, "learning_rate": 5.753030175300911e-07, "loss": 0.11889870166778564, "step": 3750 }, { "epoch": 2.591452205882353, "grad_norm": 1.5580989576068087, "learning_rate": 5.567697687489154e-07, "loss": 0.12735145092010497, "step": 3760 }, { "epoch": 2.5983455882352944, "grad_norm": 1.4518378617234164, "learning_rate": 5.385223376489407e-07, "loss": 0.11554868221282959, "step": 3770 }, { "epoch": 2.6052389705882355, "grad_norm": 1.5547790547007871, "learning_rate": 5.205618980244947e-07, "loss": 0.13258237838745118, "step": 3780 }, { "epoch": 2.6121323529411766, "grad_norm": 1.572429077130676, "learning_rate": 5.028896052087335e-07, "loss": 0.12007336616516114, "step": 3790 }, { "epoch": 2.6190257352941178, "grad_norm": 1.7166206497939747, "learning_rate": 4.855065959993243e-07, "loss": 0.11507387161254883, "step": 3800 }, { "epoch": 2.625919117647059, "grad_norm": 1.6193340802293354, "learning_rate": 4.684139885853145e-07, "loss": 0.11864235401153564, "step": 3810 }, { "epoch": 2.6328125, "grad_norm": 1.7393702753965983, "learning_rate": 4.516128824752064e-07, "loss": 0.11445059776306152, "step": 3820 }, { "epoch": 2.639705882352941, "grad_norm": 1.6072292653652183, "learning_rate": 4.3510435842622767e-07, "loss": 0.11035342216491699, "step": 3830 }, { "epoch": 2.6465992647058822, "grad_norm": 1.606064949077685, "learning_rate": 4.1888947837481375e-07, "loss": 0.12097694873809814, "step": 3840 }, { "epoch": 2.6534926470588234, "grad_norm": 1.512296765366981, "learning_rate": 4.029692853682887e-07, "loss": 0.11435999870300292, "step": 3850 }, { "epoch": 2.6603860294117645, "grad_norm": 1.7403794577248, "learning_rate": 3.8734480349778e-07, "loss": 0.12074418067932129, "step": 3860 }, { "epoch": 2.6672794117647056, "grad_norm": 1.949724737199273, "learning_rate": 3.720170378323379e-07, "loss": 0.10687488317489624, "step": 3870 }, { "epoch": 2.674172794117647, "grad_norm": 1.9877400833773105, "learning_rate": 3.569869743542753e-07, "loss": 0.11448534727096557, "step": 3880 }, { "epoch": 2.6810661764705883, "grad_norm": 1.5259255754213394, "learning_rate": 3.422555798957572e-07, "loss": 0.11829607486724854, "step": 3890 }, { "epoch": 2.6879595588235294, "grad_norm": 1.626690639216131, "learning_rate": 3.2782380207659783e-07, "loss": 0.1268585205078125, "step": 3900 }, { "epoch": 2.6948529411764706, "grad_norm": 1.94094278614922, "learning_rate": 3.13692569243304e-07, "loss": 0.1243630290031433, "step": 3910 }, { "epoch": 2.7017463235294117, "grad_norm": 1.7245219991844833, "learning_rate": 2.9986279040936207e-07, "loss": 0.12488038539886474, "step": 3920 }, { "epoch": 2.708639705882353, "grad_norm": 1.8142262502061772, "learning_rate": 2.8633535519676294e-07, "loss": 0.11174612045288086, "step": 3930 }, { "epoch": 2.7155330882352944, "grad_norm": 1.6556190362956986, "learning_rate": 2.7311113377877175e-07, "loss": 0.11386919021606445, "step": 3940 }, { "epoch": 2.7224264705882355, "grad_norm": 1.5447919172735272, "learning_rate": 2.6019097682395744e-07, "loss": 0.12517250776290895, "step": 3950 }, { "epoch": 2.7293198529411766, "grad_norm": 1.7110649545377792, "learning_rate": 2.475757154414704e-07, "loss": 0.12617422342300416, "step": 3960 }, { "epoch": 2.7362132352941178, "grad_norm": 1.659104354503707, "learning_rate": 2.3526616112758139e-07, "loss": 0.12844340801239013, "step": 3970 }, { "epoch": 2.743106617647059, "grad_norm": 1.8015265455810567, "learning_rate": 2.2326310571347432e-07, "loss": 0.12189750671386719, "step": 3980 }, { "epoch": 2.75, "grad_norm": 2.3648605366638678, "learning_rate": 2.1156732131432213e-07, "loss": 0.11262389421463012, "step": 3990 }, { "epoch": 2.756893382352941, "grad_norm": 1.2501832028253748, "learning_rate": 2.0017956027961082e-07, "loss": 0.12388832569122314, "step": 4000 }, { "epoch": 2.7637867647058822, "grad_norm": 1.2851557190203722, "learning_rate": 1.8910055514474112e-07, "loss": 0.10303380489349365, "step": 4010 }, { "epoch": 2.7706801470588234, "grad_norm": 1.9204470859198808, "learning_rate": 1.7833101858391767e-07, "loss": 0.11358997821807862, "step": 4020 }, { "epoch": 2.7775735294117645, "grad_norm": 1.7080227045479466, "learning_rate": 1.6787164336429461e-07, "loss": 0.11228070259094239, "step": 4030 }, { "epoch": 2.7844669117647056, "grad_norm": 1.3775416790359925, "learning_rate": 1.5772310230141695e-07, "loss": 0.117854642868042, "step": 4040 }, { "epoch": 2.791360294117647, "grad_norm": 1.8791584442399056, "learning_rate": 1.478860482159411e-07, "loss": 0.112187659740448, "step": 4050 }, { "epoch": 2.7982536764705883, "grad_norm": 1.9987917177922738, "learning_rate": 1.3836111389163965e-07, "loss": 0.11832698583602905, "step": 4060 }, { "epoch": 2.8051470588235294, "grad_norm": 1.423866172565035, "learning_rate": 1.2914891203469782e-07, "loss": 0.1236728310585022, "step": 4070 }, { "epoch": 2.8120404411764706, "grad_norm": 1.6404941553348855, "learning_rate": 1.2025003523429834e-07, "loss": 0.11068458557128906, "step": 4080 }, { "epoch": 2.8189338235294117, "grad_norm": 1.56385801030188, "learning_rate": 1.1166505592450305e-07, "loss": 0.11898646354675294, "step": 4090 }, { "epoch": 2.825827205882353, "grad_norm": 1.1743785101898536, "learning_rate": 1.0339452634743286e-07, "loss": 0.11896709203720093, "step": 4100 }, { "epoch": 2.8327205882352944, "grad_norm": 1.3903690395275774, "learning_rate": 9.543897851773897e-08, "loss": 0.11602020263671875, "step": 4110 }, { "epoch": 2.8396139705882355, "grad_norm": 1.6220280778411569, "learning_rate": 8.77989241883831e-08, "loss": 0.12697683572769164, "step": 4120 }, { "epoch": 2.8465073529411766, "grad_norm": 1.1783819120179762, "learning_rate": 8.047485481772032e-08, "loss": 0.10793635845184327, "step": 4130 }, { "epoch": 2.8534007352941178, "grad_norm": 1.51950265310692, "learning_rate": 7.346724153787955e-08, "loss": 0.11777899265289307, "step": 4140 }, { "epoch": 2.860294117647059, "grad_norm": 1.6288327212397373, "learning_rate": 6.677653512446203e-08, "loss": 0.11815171241760254, "step": 4150 }, { "epoch": 2.8671875, "grad_norm": 1.9866334489353243, "learning_rate": 6.040316596754359e-08, "loss": 0.1235661268234253, "step": 4160 }, { "epoch": 2.874080882352941, "grad_norm": 1.9577164147990023, "learning_rate": 5.434754404398668e-08, "loss": 0.13137286901474, "step": 4170 }, { "epoch": 2.8809742647058822, "grad_norm": 1.9088848039878026, "learning_rate": 4.861005889107151e-08, "loss": 0.12607433795928955, "step": 4180 }, { "epoch": 2.8878676470588234, "grad_norm": 1.6351225910652742, "learning_rate": 4.319107958143554e-08, "loss": 0.11220908164978027, "step": 4190 }, { "epoch": 2.8947610294117645, "grad_norm": 2.4269218269069577, "learning_rate": 3.809095469933466e-08, "loss": 0.13201329708099366, "step": 4200 }, { "epoch": 2.9016544117647056, "grad_norm": 1.307879015339929, "learning_rate": 3.331001231821729e-08, "loss": 0.12485461235046387, "step": 4210 }, { "epoch": 2.908547794117647, "grad_norm": 1.9333207410600393, "learning_rate": 2.8848559979623436e-08, "loss": 0.11161249876022339, "step": 4220 }, { "epoch": 2.9154411764705883, "grad_norm": 1.5659557927019145, "learning_rate": 2.470688467339888e-08, "loss": 0.11746110916137695, "step": 4230 }, { "epoch": 2.9223345588235294, "grad_norm": 1.5186439196369166, "learning_rate": 2.0885252819237147e-08, "loss": 0.12025998830795288, "step": 4240 }, { "epoch": 2.9292279411764706, "grad_norm": 2.075056165300313, "learning_rate": 1.738391024953878e-08, "loss": 0.1375720977783203, "step": 4250 }, { "epoch": 2.9361213235294117, "grad_norm": 1.656928406562593, "learning_rate": 1.4203082193599005e-08, "loss": 0.12192656993865966, "step": 4260 }, { "epoch": 2.943014705882353, "grad_norm": 1.9732461153180607, "learning_rate": 1.1342973263119283e-08, "loss": 0.11261507272720336, "step": 4270 }, { "epoch": 2.9499080882352944, "grad_norm": 1.8675859339914511, "learning_rate": 8.803767439046206e-09, "loss": 0.11683320999145508, "step": 4280 }, { "epoch": 2.9568014705882355, "grad_norm": 1.6534479598597356, "learning_rate": 6.585628059735949e-09, "loss": 0.12072156667709351, "step": 4290 }, { "epoch": 2.9636948529411766, "grad_norm": 1.6128943708956411, "learning_rate": 4.688697810446563e-09, "loss": 0.11794602870941162, "step": 4300 }, { "epoch": 2.9705882352941178, "grad_norm": 1.6185222266398032, "learning_rate": 3.1130987141608783e-09, "loss": 0.10645477771759033, "step": 4310 }, { "epoch": 2.977481617647059, "grad_norm": 1.4801680409041869, "learning_rate": 1.8589321237366675e-09, "loss": 0.11435923576354981, "step": 4320 }, { "epoch": 2.984375, "grad_norm": 1.3859162146614572, "learning_rate": 9.262787153857533e-10, "loss": 0.12736527919769286, "step": 4330 }, { "epoch": 2.991268382352941, "grad_norm": 1.7791868203390604, "learning_rate": 3.151984834864896e-10, "loss": 0.10816608667373658, "step": 4340 }, { "epoch": 2.9981617647058822, "grad_norm": 1.4745807290302329, "learning_rate": 2.5730736723517113e-11, "loss": 0.12245618104934693, "step": 4350 }, { "epoch": 3.0, "step": 4353, "total_flos": 162751958106112.0, "train_loss": 0.1549751561536423, "train_runtime": 27473.2342, "train_samples_per_second": 7.603, "train_steps_per_second": 0.158 } ], "logging_steps": 10, "max_steps": 4353, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 162751958106112.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }