{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 2275, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02201430930104568, "grad_norm": 149.0924530029297, "learning_rate": 3.9473684210526315e-07, "loss": 2.8313, "step": 10 }, { "epoch": 0.04402861860209136, "grad_norm": 113.37779998779297, "learning_rate": 8.333333333333333e-07, "loss": 2.6084, "step": 20 }, { "epoch": 0.06604292790313704, "grad_norm": 50.01759338378906, "learning_rate": 1.2719298245614037e-06, "loss": 1.9398, "step": 30 }, { "epoch": 0.08805723720418272, "grad_norm": 34.920753479003906, "learning_rate": 1.710526315789474e-06, "loss": 0.9434, "step": 40 }, { "epoch": 0.1100715465052284, "grad_norm": 39.18187713623047, "learning_rate": 2.149122807017544e-06, "loss": 0.6265, "step": 50 }, { "epoch": 0.13208585580627408, "grad_norm": 24.341272354125977, "learning_rate": 2.5877192982456147e-06, "loss": 0.5175, "step": 60 }, { "epoch": 0.15410016510731975, "grad_norm": 28.49750518798828, "learning_rate": 3.0263157894736843e-06, "loss": 0.3675, "step": 70 }, { "epoch": 0.17611447440836545, "grad_norm": 19.006736755371094, "learning_rate": 3.464912280701755e-06, "loss": 0.3837, "step": 80 }, { "epoch": 0.19812878370941112, "grad_norm": 17.02811622619629, "learning_rate": 3.903508771929825e-06, "loss": 0.3962, "step": 90 }, { "epoch": 0.2201430930104568, "grad_norm": 21.771198272705078, "learning_rate": 4.342105263157895e-06, "loss": 0.4951, "step": 100 }, { "epoch": 0.24215740231150248, "grad_norm": 21.4830379486084, "learning_rate": 4.780701754385965e-06, "loss": 0.3893, "step": 110 }, { "epoch": 0.26417171161254815, "grad_norm": 18.051719665527344, "learning_rate": 5.219298245614035e-06, "loss": 0.3426, "step": 120 }, { "epoch": 0.28618602091359385, "grad_norm": 19.548246383666992, "learning_rate": 5.657894736842106e-06, "loss": 0.3329, "step": 130 }, { "epoch": 0.3082003302146395, "grad_norm": 18.77153778076172, "learning_rate": 6.096491228070176e-06, "loss": 0.2798, "step": 140 }, { "epoch": 0.3302146395156852, "grad_norm": 13.931683540344238, "learning_rate": 6.535087719298247e-06, "loss": 0.3467, "step": 150 }, { "epoch": 0.3522289488167309, "grad_norm": 19.239925384521484, "learning_rate": 6.973684210526316e-06, "loss": 0.338, "step": 160 }, { "epoch": 0.37424325811777653, "grad_norm": 20.201244354248047, "learning_rate": 7.4122807017543865e-06, "loss": 0.3851, "step": 170 }, { "epoch": 0.39625756741882223, "grad_norm": 11.52122688293457, "learning_rate": 7.850877192982457e-06, "loss": 0.3066, "step": 180 }, { "epoch": 0.41827187671986793, "grad_norm": 18.884485244750977, "learning_rate": 8.289473684210526e-06, "loss": 0.4208, "step": 190 }, { "epoch": 0.4402861860209136, "grad_norm": 20.8024959564209, "learning_rate": 8.728070175438597e-06, "loss": 0.3226, "step": 200 }, { "epoch": 0.46230049532195927, "grad_norm": 17.418704986572266, "learning_rate": 9.166666666666666e-06, "loss": 0.4163, "step": 210 }, { "epoch": 0.48431480462300497, "grad_norm": 31.44495391845703, "learning_rate": 9.605263157894737e-06, "loss": 0.508, "step": 220 }, { "epoch": 0.5063291139240507, "grad_norm": 17.460351943969727, "learning_rate": 9.999994111509437e-06, "loss": 0.4911, "step": 230 }, { "epoch": 0.5283434232250963, "grad_norm": 15.517730712890625, "learning_rate": 9.999287509423918e-06, "loss": 0.3857, "step": 240 }, { "epoch": 0.550357732526142, "grad_norm": 10.413957595825195, "learning_rate": 9.997403399926886e-06, "loss": 0.3728, "step": 250 }, { "epoch": 0.5723720418271877, "grad_norm": 13.081694602966309, "learning_rate": 9.994342226792157e-06, "loss": 0.4749, "step": 260 }, { "epoch": 0.5943863511282333, "grad_norm": 5.745361804962158, "learning_rate": 9.990104711033287e-06, "loss": 0.2843, "step": 270 }, { "epoch": 0.616400660429279, "grad_norm": 7.066932678222656, "learning_rate": 9.98469185073374e-06, "loss": 0.3108, "step": 280 }, { "epoch": 0.6384149697303247, "grad_norm": 16.691713333129883, "learning_rate": 9.978104920811815e-06, "loss": 0.4083, "step": 290 }, { "epoch": 0.6604292790313704, "grad_norm": 7.5896100997924805, "learning_rate": 9.970345472720353e-06, "loss": 0.3932, "step": 300 }, { "epoch": 0.682443588332416, "grad_norm": 15.394400596618652, "learning_rate": 9.961415334081313e-06, "loss": 0.3618, "step": 310 }, { "epoch": 0.7044578976334618, "grad_norm": 19.94350242614746, "learning_rate": 9.951316608255304e-06, "loss": 0.3621, "step": 320 }, { "epoch": 0.7264722069345074, "grad_norm": 13.709397315979004, "learning_rate": 9.940051673846178e-06, "loss": 0.419, "step": 330 }, { "epoch": 0.7484865162355531, "grad_norm": 12.47382640838623, "learning_rate": 9.927623184140772e-06, "loss": 0.3059, "step": 340 }, { "epoch": 0.7705008255365988, "grad_norm": 19.130361557006836, "learning_rate": 9.914034066483977e-06, "loss": 0.4022, "step": 350 }, { "epoch": 0.7925151348376445, "grad_norm": 16.35902214050293, "learning_rate": 9.89928752158924e-06, "loss": 0.2986, "step": 360 }, { "epoch": 0.8145294441386901, "grad_norm": 14.079461097717285, "learning_rate": 9.883387022784685e-06, "loss": 0.288, "step": 370 }, { "epoch": 0.8365437534397359, "grad_norm": 13.393936157226562, "learning_rate": 9.866336315195021e-06, "loss": 0.4418, "step": 380 }, { "epoch": 0.8585580627407815, "grad_norm": 10.819969177246094, "learning_rate": 9.848139414859441e-06, "loss": 0.3744, "step": 390 }, { "epoch": 0.8805723720418271, "grad_norm": 11.345392227172852, "learning_rate": 9.828800607785694e-06, "loss": 0.2786, "step": 400 }, { "epoch": 0.9025866813428729, "grad_norm": 10.613056182861328, "learning_rate": 9.808324448940587e-06, "loss": 0.3415, "step": 410 }, { "epoch": 0.9246009906439185, "grad_norm": 16.627853393554688, "learning_rate": 9.786715761177125e-06, "loss": 0.3052, "step": 420 }, { "epoch": 0.9466152999449642, "grad_norm": 12.382245063781738, "learning_rate": 9.763979634098565e-06, "loss": 0.3485, "step": 430 }, { "epoch": 0.9686296092460099, "grad_norm": 11.370132446289062, "learning_rate": 9.740121422859641e-06, "loss": 0.3978, "step": 440 }, { "epoch": 0.9906439185470556, "grad_norm": 11.875682830810547, "learning_rate": 9.71514674690522e-06, "loss": 0.3367, "step": 450 }, { "epoch": 1.0110071546505228, "grad_norm": 5.493345260620117, "learning_rate": 9.689061488646743e-06, "loss": 0.226, "step": 460 }, { "epoch": 1.0330214639515685, "grad_norm": 8.90275764465332, "learning_rate": 9.661871792076705e-06, "loss": 0.1707, "step": 470 }, { "epoch": 1.055035773252614, "grad_norm": 16.285871505737305, "learning_rate": 9.633584061321524e-06, "loss": 0.2521, "step": 480 }, { "epoch": 1.07705008255366, "grad_norm": 15.022496223449707, "learning_rate": 9.604204959133158e-06, "loss": 0.1966, "step": 490 }, { "epoch": 1.0990643918547056, "grad_norm": 9.199139595031738, "learning_rate": 9.573741405319778e-06, "loss": 0.15, "step": 500 }, { "epoch": 1.1210787011557513, "grad_norm": 15.009807586669922, "learning_rate": 9.542200575115921e-06, "loss": 0.1361, "step": 510 }, { "epoch": 1.143093010456797, "grad_norm": 8.542426109313965, "learning_rate": 9.509589897492468e-06, "loss": 0.1845, "step": 520 }, { "epoch": 1.1651073197578425, "grad_norm": 12.44705581665039, "learning_rate": 9.475917053406857e-06, "loss": 0.1707, "step": 530 }, { "epoch": 1.1871216290588882, "grad_norm": 12.752492904663086, "learning_rate": 9.441189973993962e-06, "loss": 0.1836, "step": 540 }, { "epoch": 1.209135938359934, "grad_norm": 12.074056625366211, "learning_rate": 9.40541683869801e-06, "loss": 0.1419, "step": 550 }, { "epoch": 1.2311502476609797, "grad_norm": 30.33481216430664, "learning_rate": 9.368606073346055e-06, "loss": 0.2167, "step": 560 }, { "epoch": 1.2531645569620253, "grad_norm": 7.651270389556885, "learning_rate": 9.330766348163399e-06, "loss": 0.1721, "step": 570 }, { "epoch": 1.275178866263071, "grad_norm": 11.890057563781738, "learning_rate": 9.29190657573143e-06, "loss": 0.2105, "step": 580 }, { "epoch": 1.2971931755641166, "grad_norm": 10.304011344909668, "learning_rate": 9.252035908888424e-06, "loss": 0.1419, "step": 590 }, { "epoch": 1.3192074848651623, "grad_norm": 15.464428901672363, "learning_rate": 9.211163738573714e-06, "loss": 0.175, "step": 600 }, { "epoch": 1.341221794166208, "grad_norm": 10.08139419555664, "learning_rate": 9.1692996916158e-06, "loss": 0.1194, "step": 610 }, { "epoch": 1.3632361034672538, "grad_norm": 31.760950088500977, "learning_rate": 9.126453628464889e-06, "loss": 0.1803, "step": 620 }, { "epoch": 1.3852504127682994, "grad_norm": 12.612894058227539, "learning_rate": 9.08263564087042e-06, "loss": 0.223, "step": 630 }, { "epoch": 1.407264722069345, "grad_norm": 14.56605052947998, "learning_rate": 9.037856049504099e-06, "loss": 0.1577, "step": 640 }, { "epoch": 1.4292790313703907, "grad_norm": 12.891292572021484, "learning_rate": 8.992125401529021e-06, "loss": 0.2345, "step": 650 }, { "epoch": 1.4512933406714366, "grad_norm": 7.856708526611328, "learning_rate": 8.945454468115442e-06, "loss": 0.1693, "step": 660 }, { "epoch": 1.4733076499724822, "grad_norm": 13.625117301940918, "learning_rate": 8.897854241903795e-06, "loss": 0.2113, "step": 670 }, { "epoch": 1.4953219592735278, "grad_norm": 15.025895118713379, "learning_rate": 8.849335934415525e-06, "loss": 0.2201, "step": 680 }, { "epoch": 1.5173362685745735, "grad_norm": 10.24340534210205, "learning_rate": 8.799910973412405e-06, "loss": 0.219, "step": 690 }, { "epoch": 1.5393505778756191, "grad_norm": 4.124502182006836, "learning_rate": 8.749591000204874e-06, "loss": 0.1391, "step": 700 }, { "epoch": 1.5613648871766648, "grad_norm": 9.478644371032715, "learning_rate": 8.698387866910118e-06, "loss": 0.1765, "step": 710 }, { "epoch": 1.5833791964777104, "grad_norm": 14.1632080078125, "learning_rate": 8.646313633660475e-06, "loss": 0.1982, "step": 720 }, { "epoch": 1.605393505778756, "grad_norm": 11.754325866699219, "learning_rate": 8.593380565762845e-06, "loss": 0.1667, "step": 730 }, { "epoch": 1.627407815079802, "grad_norm": 9.502894401550293, "learning_rate": 8.539601130809791e-06, "loss": 0.1364, "step": 740 }, { "epoch": 1.6494221243808476, "grad_norm": 11.475814819335938, "learning_rate": 8.484987995742976e-06, "loss": 0.1836, "step": 750 }, { "epoch": 1.6714364336818932, "grad_norm": 9.57651138305664, "learning_rate": 8.42955402386966e-06, "loss": 0.1789, "step": 760 }, { "epoch": 1.693450742982939, "grad_norm": 1.815674901008606, "learning_rate": 8.373312271832933e-06, "loss": 0.1454, "step": 770 }, { "epoch": 1.7154650522839847, "grad_norm": 11.558368682861328, "learning_rate": 8.316275986536428e-06, "loss": 0.1539, "step": 780 }, { "epoch": 1.7374793615850304, "grad_norm": 10.416860580444336, "learning_rate": 8.258458602024204e-06, "loss": 0.1487, "step": 790 }, { "epoch": 1.759493670886076, "grad_norm": 6.910308837890625, "learning_rate": 8.199873736316558e-06, "loss": 0.1803, "step": 800 }, { "epoch": 1.7815079801871216, "grad_norm": 4.146355152130127, "learning_rate": 8.140535188202505e-06, "loss": 0.1385, "step": 810 }, { "epoch": 1.8035222894881673, "grad_norm": 5.6611552238464355, "learning_rate": 8.080456933989683e-06, "loss": 0.2152, "step": 820 }, { "epoch": 1.825536598789213, "grad_norm": 23.37342071533203, "learning_rate": 8.019653124212435e-06, "loss": 0.1536, "step": 830 }, { "epoch": 1.8475509080902586, "grad_norm": 4.826507568359375, "learning_rate": 7.958138080298872e-06, "loss": 0.1699, "step": 840 }, { "epoch": 1.8695652173913042, "grad_norm": 9.595096588134766, "learning_rate": 7.895926291197667e-06, "loss": 0.216, "step": 850 }, { "epoch": 1.89157952669235, "grad_norm": 9.86635684967041, "learning_rate": 7.833032409965404e-06, "loss": 0.1626, "step": 860 }, { "epoch": 1.9135938359933957, "grad_norm": 31.581125259399414, "learning_rate": 7.769471250315264e-06, "loss": 0.2297, "step": 870 }, { "epoch": 1.9356081452944414, "grad_norm": 16.1098575592041, "learning_rate": 7.705257783127885e-06, "loss": 0.1498, "step": 880 }, { "epoch": 1.9576224545954872, "grad_norm": 0.9061281681060791, "learning_rate": 7.640407132925194e-06, "loss": 0.1173, "step": 890 }, { "epoch": 1.9796367638965329, "grad_norm": 16.087814331054688, "learning_rate": 7.574934574308036e-06, "loss": 0.2283, "step": 900 }, { "epoch": 2.0, "grad_norm": 0.026864640414714813, "learning_rate": 7.5088555283584955e-06, "loss": 0.1135, "step": 910 }, { "epoch": 2.0220143093010456, "grad_norm": 5.347623348236084, "learning_rate": 7.442185559007673e-06, "loss": 0.0859, "step": 920 }, { "epoch": 2.0440286186020913, "grad_norm": 3.5978448390960693, "learning_rate": 7.374940369369839e-06, "loss": 0.0429, "step": 930 }, { "epoch": 2.066042927903137, "grad_norm": 0.6228177547454834, "learning_rate": 7.307135798043802e-06, "loss": 0.0668, "step": 940 }, { "epoch": 2.0880572372041826, "grad_norm": 5.9448933601379395, "learning_rate": 7.2387878153823596e-06, "loss": 0.0667, "step": 950 }, { "epoch": 2.110071546505228, "grad_norm": 2.500957727432251, "learning_rate": 7.169912519730729e-06, "loss": 0.0608, "step": 960 }, { "epoch": 2.132085855806274, "grad_norm": 3.9965829849243164, "learning_rate": 7.100526133634809e-06, "loss": 0.0592, "step": 970 }, { "epoch": 2.15410016510732, "grad_norm": 5.488401889801025, "learning_rate": 7.0306450000202134e-06, "loss": 0.0849, "step": 980 }, { "epoch": 2.1761144744083656, "grad_norm": 2.707719087600708, "learning_rate": 6.960285578342935e-06, "loss": 0.0558, "step": 990 }, { "epoch": 2.1981287837094112, "grad_norm": 5.113603115081787, "learning_rate": 6.889464440712568e-06, "loss": 0.0945, "step": 1000 }, { "epoch": 2.220143093010457, "grad_norm": 12.504261016845703, "learning_rate": 6.818198267988991e-06, "loss": 0.0602, "step": 1010 }, { "epoch": 2.2421574023115025, "grad_norm": 4.4827446937561035, "learning_rate": 6.74650384585345e-06, "loss": 0.079, "step": 1020 }, { "epoch": 2.264171711612548, "grad_norm": 8.459637641906738, "learning_rate": 6.674398060854931e-06, "loss": 0.0648, "step": 1030 }, { "epoch": 2.286186020913594, "grad_norm": 3.4400408267974854, "learning_rate": 6.601897896432792e-06, "loss": 0.0719, "step": 1040 }, { "epoch": 2.3082003302146394, "grad_norm": 0.06874310225248337, "learning_rate": 6.529020428916565e-06, "loss": 0.049, "step": 1050 }, { "epoch": 2.330214639515685, "grad_norm": 4.816253185272217, "learning_rate": 6.455782823503885e-06, "loss": 0.0926, "step": 1060 }, { "epoch": 2.3522289488167307, "grad_norm": 2.374338150024414, "learning_rate": 6.3822023302174844e-06, "loss": 0.0904, "step": 1070 }, { "epoch": 2.3742432581177764, "grad_norm": 8.643360137939453, "learning_rate": 6.308296279842204e-06, "loss": 0.0629, "step": 1080 }, { "epoch": 2.3962575674188225, "grad_norm": 13.684159278869629, "learning_rate": 6.234082079842989e-06, "loss": 0.0863, "step": 1090 }, { "epoch": 2.418271876719868, "grad_norm": 16.594545364379883, "learning_rate": 6.15957721026482e-06, "loss": 0.0651, "step": 1100 }, { "epoch": 2.4402861860209137, "grad_norm": 8.79535961151123, "learning_rate": 6.084799219615553e-06, "loss": 0.0637, "step": 1110 }, { "epoch": 2.4623004953219594, "grad_norm": 5.216023921966553, "learning_rate": 6.009765720732622e-06, "loss": 0.0475, "step": 1120 }, { "epoch": 2.484314804623005, "grad_norm": 9.686095237731934, "learning_rate": 5.934494386634612e-06, "loss": 0.0813, "step": 1130 }, { "epoch": 2.5063291139240507, "grad_norm": 4.476397514343262, "learning_rate": 5.859002946358628e-06, "loss": 0.0816, "step": 1140 }, { "epoch": 2.5283434232250963, "grad_norm": 4.840889930725098, "learning_rate": 5.783309180784504e-06, "loss": 0.0697, "step": 1150 }, { "epoch": 2.550357732526142, "grad_norm": 10.199071884155273, "learning_rate": 5.707430918446761e-06, "loss": 0.1216, "step": 1160 }, { "epoch": 2.5723720418271876, "grad_norm": 4.8565497398376465, "learning_rate": 5.631386031335381e-06, "loss": 0.0485, "step": 1170 }, { "epoch": 2.5943863511282332, "grad_norm": 18.065574645996094, "learning_rate": 5.555192430686318e-06, "loss": 0.0628, "step": 1180 }, { "epoch": 2.616400660429279, "grad_norm": 7.5452351570129395, "learning_rate": 5.478868062762776e-06, "loss": 0.0472, "step": 1190 }, { "epoch": 2.6384149697303245, "grad_norm": 7.040380001068115, "learning_rate": 5.402430904628231e-06, "loss": 0.0655, "step": 1200 }, { "epoch": 2.66042927903137, "grad_norm": 15.333260536193848, "learning_rate": 5.325898959912213e-06, "loss": 0.043, "step": 1210 }, { "epoch": 2.682443588332416, "grad_norm": 8.55695915222168, "learning_rate": 5.249290254569811e-06, "loss": 0.0979, "step": 1220 }, { "epoch": 2.704457897633462, "grad_norm": 5.6836371421813965, "learning_rate": 5.172622832635932e-06, "loss": 0.1255, "step": 1230 }, { "epoch": 2.7264722069345075, "grad_norm": 1.0160411596298218, "learning_rate": 5.095914751975294e-06, "loss": 0.0367, "step": 1240 }, { "epoch": 2.748486516235553, "grad_norm": 9.370463371276855, "learning_rate": 5.019184080029176e-06, "loss": 0.0666, "step": 1250 }, { "epoch": 2.770500825536599, "grad_norm": 4.173619747161865, "learning_rate": 4.942448889559894e-06, "loss": 0.0661, "step": 1260 }, { "epoch": 2.7925151348376445, "grad_norm": 3.82051420211792, "learning_rate": 4.8657272543940345e-06, "loss": 0.0436, "step": 1270 }, { "epoch": 2.81452944413869, "grad_norm": 8.042530059814453, "learning_rate": 4.789037245165433e-06, "loss": 0.0582, "step": 1280 }, { "epoch": 2.8365437534397357, "grad_norm": 7.33740234375, "learning_rate": 4.712396925058913e-06, "loss": 0.0666, "step": 1290 }, { "epoch": 2.8585580627407814, "grad_norm": 2.088062286376953, "learning_rate": 4.635824345555764e-06, "loss": 0.0633, "step": 1300 }, { "epoch": 2.880572372041827, "grad_norm": 2.6091432571411133, "learning_rate": 4.559337542181993e-06, "loss": 0.0467, "step": 1310 }, { "epoch": 2.902586681342873, "grad_norm": 5.055851459503174, "learning_rate": 4.482954530260317e-06, "loss": 0.0286, "step": 1320 }, { "epoch": 2.9246009906439188, "grad_norm": 2.7082486152648926, "learning_rate": 4.406693300666938e-06, "loss": 0.046, "step": 1330 }, { "epoch": 2.9466152999449644, "grad_norm": 0.3161621689796448, "learning_rate": 4.330571815594041e-06, "loss": 0.0532, "step": 1340 }, { "epoch": 2.96862960924601, "grad_norm": 13.934333801269531, "learning_rate": 4.254608004319086e-06, "loss": 0.0712, "step": 1350 }, { "epoch": 2.9906439185470557, "grad_norm": 0.16270780563354492, "learning_rate": 4.178819758981824e-06, "loss": 0.0262, "step": 1360 }, { "epoch": 3.011007154650523, "grad_norm": 0.28307250142097473, "learning_rate": 4.103224930370082e-06, "loss": 0.0513, "step": 1370 }, { "epoch": 3.0330214639515685, "grad_norm": 3.5897815227508545, "learning_rate": 4.027841323715258e-06, "loss": 0.0126, "step": 1380 }, { "epoch": 3.055035773252614, "grad_norm": 1.7566109895706177, "learning_rate": 3.952686694498587e-06, "loss": 0.0306, "step": 1390 }, { "epoch": 3.0770500825536597, "grad_norm": 30.840288162231445, "learning_rate": 3.877778744269086e-06, "loss": 0.0245, "step": 1400 }, { "epoch": 3.0990643918547054, "grad_norm": 2.281254529953003, "learning_rate": 3.8031351164742313e-06, "loss": 0.018, "step": 1410 }, { "epoch": 3.121078701155751, "grad_norm": 1.2128616571426392, "learning_rate": 3.728773392304297e-06, "loss": 0.0197, "step": 1420 }, { "epoch": 3.143093010456797, "grad_norm": 3.7622814178466797, "learning_rate": 3.654711086551379e-06, "loss": 0.0192, "step": 1430 }, { "epoch": 3.1651073197578428, "grad_norm": 2.670830726623535, "learning_rate": 3.5809656434840366e-06, "loss": 0.024, "step": 1440 }, { "epoch": 3.1871216290588884, "grad_norm": 0.5346924662590027, "learning_rate": 3.5075544327385703e-06, "loss": 0.0138, "step": 1450 }, { "epoch": 3.209135938359934, "grad_norm": 0.17593185603618622, "learning_rate": 3.434494745227848e-06, "loss": 0.0203, "step": 1460 }, { "epoch": 3.2311502476609797, "grad_norm": 4.213673114776611, "learning_rate": 3.3618037890686993e-06, "loss": 0.0131, "step": 1470 }, { "epoch": 3.2531645569620253, "grad_norm": 0.484234094619751, "learning_rate": 3.2894986855287974e-06, "loss": 0.0105, "step": 1480 }, { "epoch": 3.275178866263071, "grad_norm": 14.269530296325684, "learning_rate": 3.2175964649940052e-06, "loss": 0.0291, "step": 1490 }, { "epoch": 3.2971931755641166, "grad_norm": 5.377061367034912, "learning_rate": 3.1461140629571106e-06, "loss": 0.0068, "step": 1500 }, { "epoch": 3.3192074848651623, "grad_norm": 0.9835841059684753, "learning_rate": 3.0750683160289417e-06, "loss": 0.0144, "step": 1510 }, { "epoch": 3.341221794166208, "grad_norm": 2.4685771465301514, "learning_rate": 3.0044759579727366e-06, "loss": 0.0267, "step": 1520 }, { "epoch": 3.3632361034672535, "grad_norm": 8.715569496154785, "learning_rate": 2.9343536157627737e-06, "loss": 0.0085, "step": 1530 }, { "epoch": 3.3852504127682996, "grad_norm": 0.8378893733024597, "learning_rate": 2.8647178056681197e-06, "loss": 0.0102, "step": 1540 }, { "epoch": 3.4072647220693453, "grad_norm": 1.1232154369354248, "learning_rate": 2.795584929362485e-06, "loss": 0.0094, "step": 1550 }, { "epoch": 3.429279031370391, "grad_norm": 0.3502279222011566, "learning_rate": 2.7269712700610373e-06, "loss": 0.0052, "step": 1560 }, { "epoch": 3.4512933406714366, "grad_norm": 12.604698181152344, "learning_rate": 2.658892988685153e-06, "loss": 0.0173, "step": 1570 }, { "epoch": 3.473307649972482, "grad_norm": 2.840749740600586, "learning_rate": 2.591366120055939e-06, "loss": 0.0189, "step": 1580 }, { "epoch": 3.495321959273528, "grad_norm": 4.326692581176758, "learning_rate": 2.52440656911748e-06, "loss": 0.0178, "step": 1590 }, { "epoch": 3.5173362685745735, "grad_norm": 21.543970108032227, "learning_rate": 2.4580301071906536e-06, "loss": 0.0202, "step": 1600 }, { "epoch": 3.539350577875619, "grad_norm": 0.6337364315986633, "learning_rate": 2.3922523682584547e-06, "loss": 0.0291, "step": 1610 }, { "epoch": 3.5613648871766648, "grad_norm": 12.031381607055664, "learning_rate": 2.327088845283616e-06, "loss": 0.0235, "step": 1620 }, { "epoch": 3.5833791964777104, "grad_norm": 0.06522835791110992, "learning_rate": 2.262554886559496e-06, "loss": 0.0045, "step": 1630 }, { "epoch": 3.605393505778756, "grad_norm": 0.1720537543296814, "learning_rate": 2.1986656920950044e-06, "loss": 0.0111, "step": 1640 }, { "epoch": 3.6274078150798017, "grad_norm": 5.680692672729492, "learning_rate": 2.135436310034474e-06, "loss": 0.0255, "step": 1650 }, { "epoch": 3.6494221243808473, "grad_norm": 0.9320427775382996, "learning_rate": 2.0728816331132914e-06, "loss": 0.0241, "step": 1660 }, { "epoch": 3.671436433681893, "grad_norm": 0.8085120916366577, "learning_rate": 2.0110163951501393e-06, "loss": 0.0085, "step": 1670 }, { "epoch": 3.693450742982939, "grad_norm": 58.013187408447266, "learning_rate": 1.9498551675766573e-06, "loss": 0.0402, "step": 1680 }, { "epoch": 3.7154650522839847, "grad_norm": 1.5258984565734863, "learning_rate": 1.8894123560053795e-06, "loss": 0.0228, "step": 1690 }, { "epoch": 3.7374793615850304, "grad_norm": 14.010522842407227, "learning_rate": 1.8297021968366786e-06, "loss": 0.0386, "step": 1700 }, { "epoch": 3.759493670886076, "grad_norm": 0.06895825266838074, "learning_rate": 1.7707387539056204e-06, "loss": 0.0034, "step": 1710 }, { "epoch": 3.7815079801871216, "grad_norm": 1.549134612083435, "learning_rate": 1.7125359151694238e-06, "loss": 0.0147, "step": 1720 }, { "epoch": 3.8035222894881673, "grad_norm": 0.04055091366171837, "learning_rate": 1.6551073894363645e-06, "loss": 0.0062, "step": 1730 }, { "epoch": 3.825536598789213, "grad_norm": 8.519526481628418, "learning_rate": 1.598466703136871e-06, "loss": 0.0169, "step": 1740 }, { "epoch": 3.8475509080902586, "grad_norm": 3.947218418121338, "learning_rate": 1.5426271971375744e-06, "loss": 0.0276, "step": 1750 }, { "epoch": 3.869565217391304, "grad_norm": 9.43228530883789, "learning_rate": 1.4876020235990623e-06, "loss": 0.0131, "step": 1760 }, { "epoch": 3.8915795266923503, "grad_norm": 1.181233286857605, "learning_rate": 1.4334041428781003e-06, "loss": 0.0108, "step": 1770 }, { "epoch": 3.913593835993396, "grad_norm": 0.33791837096214294, "learning_rate": 1.3800463204749898e-06, "loss": 0.0174, "step": 1780 }, { "epoch": 3.9356081452944416, "grad_norm": 8.082744598388672, "learning_rate": 1.327541124026866e-06, "loss": 0.0103, "step": 1790 }, { "epoch": 3.9576224545954872, "grad_norm": 0.30588212609291077, "learning_rate": 1.275900920347568e-06, "loss": 0.0074, "step": 1800 }, { "epoch": 3.979636763896533, "grad_norm": 0.2535891830921173, "learning_rate": 1.2251378725148254e-06, "loss": 0.0113, "step": 1810 }, { "epoch": 4.0, "grad_norm": 6.247642993927002, "learning_rate": 1.1752639370054237e-06, "loss": 0.0133, "step": 1820 }, { "epoch": 4.022014309301046, "grad_norm": 0.04303128644824028, "learning_rate": 1.1262908608790392e-06, "loss": 0.0036, "step": 1830 }, { "epoch": 4.044028618602091, "grad_norm": 0.8283238410949707, "learning_rate": 1.0782301790113858e-06, "loss": 0.0038, "step": 1840 }, { "epoch": 4.066042927903137, "grad_norm": 64.74305725097656, "learning_rate": 1.0310932113773653e-06, "loss": 0.0089, "step": 1850 }, { "epoch": 4.088057237204183, "grad_norm": 0.007313679903745651, "learning_rate": 9.848910603847944e-07, "loss": 0.0058, "step": 1860 }, { "epoch": 4.110071546505228, "grad_norm": 0.4082852900028229, "learning_rate": 9.39634608259416e-07, "loss": 0.0008, "step": 1870 }, { "epoch": 4.132085855806274, "grad_norm": 12.495570182800293, "learning_rate": 8.953345144817438e-07, "loss": 0.0087, "step": 1880 }, { "epoch": 4.1541001651073195, "grad_norm": 0.09043201804161072, "learning_rate": 8.520012132763877e-07, "loss": 0.0007, "step": 1890 }, { "epoch": 4.176114474408365, "grad_norm": 0.5336318016052246, "learning_rate": 8.096449111544219e-07, "loss": 0.0008, "step": 1900 }, { "epoch": 4.198128783709411, "grad_norm": 0.23744870722293854, "learning_rate": 7.682755845094003e-07, "loss": 0.0052, "step": 1910 }, { "epoch": 4.220143093010456, "grad_norm": 0.08849978446960449, "learning_rate": 7.279029772675572e-07, "loss": 0.0011, "step": 1920 }, { "epoch": 4.242157402311502, "grad_norm": 1.0609139204025269, "learning_rate": 6.885365985927839e-07, "loss": 0.0015, "step": 1930 }, { "epoch": 4.264171711612548, "grad_norm": 1.0154221057891846, "learning_rate": 6.501857206468748e-07, "loss": 0.0078, "step": 1940 }, { "epoch": 4.286186020913594, "grad_norm": 0.10400975495576859, "learning_rate": 6.128593764056162e-07, "loss": 0.0069, "step": 1950 }, { "epoch": 4.30820033021464, "grad_norm": 0.2593502104282379, "learning_rate": 5.765663575312014e-07, "loss": 0.0007, "step": 1960 }, { "epoch": 4.3302146395156855, "grad_norm": 0.001763040549121797, "learning_rate": 5.41315212301487e-07, "loss": 0.0022, "step": 1970 }, { "epoch": 4.352228948816731, "grad_norm": 0.023561056703329086, "learning_rate": 5.071142435965687e-07, "loss": 0.0061, "step": 1980 }, { "epoch": 4.374243258117777, "grad_norm": 0.32266297936439514, "learning_rate": 4.7397150694317496e-07, "loss": 0.0004, "step": 1990 }, { "epoch": 4.3962575674188225, "grad_norm": 0.07821591198444366, "learning_rate": 4.4189480861729137e-07, "loss": 0.0019, "step": 2000 }, { "epoch": 4.418271876719868, "grad_norm": 0.05453071370720863, "learning_rate": 4.108917038055216e-07, "loss": 0.0006, "step": 2010 }, { "epoch": 4.440286186020914, "grad_norm": 0.03200654685497284, "learning_rate": 3.809694948255721e-07, "loss": 0.0008, "step": 2020 }, { "epoch": 4.462300495321959, "grad_norm": 0.030320223420858383, "learning_rate": 3.521352294062985e-07, "loss": 0.016, "step": 2030 }, { "epoch": 4.484314804623005, "grad_norm": 2.3451313972473145, "learning_rate": 3.243956990277225e-07, "loss": 0.0023, "step": 2040 }, { "epoch": 4.506329113924051, "grad_norm": 0.0758775919675827, "learning_rate": 2.977574373213965e-07, "loss": 0.0006, "step": 2050 }, { "epoch": 4.528343423225096, "grad_norm": 0.15191303193569183, "learning_rate": 2.722267185315042e-07, "loss": 0.0039, "step": 2060 }, { "epoch": 4.550357732526142, "grad_norm": 0.22195246815681458, "learning_rate": 2.478095560370636e-07, "loss": 0.0034, "step": 2070 }, { "epoch": 4.572372041827188, "grad_norm": 0.3280889391899109, "learning_rate": 2.2451170093555296e-07, "loss": 0.001, "step": 2080 }, { "epoch": 4.594386351128233, "grad_norm": 0.9802552461624146, "learning_rate": 2.023386406883382e-07, "loss": 0.0051, "step": 2090 }, { "epoch": 4.616400660429279, "grad_norm": 1.5630686283111572, "learning_rate": 1.8129559782817495e-07, "loss": 0.0024, "step": 2100 }, { "epoch": 4.6384149697303245, "grad_norm": 3.1729488372802734, "learning_rate": 1.6138752872912334e-07, "loss": 0.0019, "step": 2110 }, { "epoch": 4.66042927903137, "grad_norm": 3.412952423095703, "learning_rate": 1.4261912243914599e-07, "loss": 0.0016, "step": 2120 }, { "epoch": 4.682443588332416, "grad_norm": 0.34012192487716675, "learning_rate": 1.2499479957567506e-07, "loss": 0.002, "step": 2130 }, { "epoch": 4.7044578976334614, "grad_norm": 0.17032365500926971, "learning_rate": 1.0851871128439828e-07, "loss": 0.0006, "step": 2140 }, { "epoch": 4.726472206934507, "grad_norm": 0.24360665678977966, "learning_rate": 9.319473826152503e-08, "loss": 0.0019, "step": 2150 }, { "epoch": 4.748486516235553, "grad_norm": 0.6027243733406067, "learning_rate": 7.902648983973804e-08, "loss": 0.0059, "step": 2160 }, { "epoch": 4.770500825536599, "grad_norm": 0.11540832370519638, "learning_rate": 6.601730313807675e-08, "loss": 0.0042, "step": 2170 }, { "epoch": 4.792515134837645, "grad_norm": 0.04149246588349342, "learning_rate": 5.417024227592327e-08, "loss": 0.0066, "step": 2180 }, { "epoch": 4.8145294441386906, "grad_norm": 0.05241992324590683, "learning_rate": 4.3488097651298575e-08, "loss": 0.007, "step": 2190 }, { "epoch": 4.836543753439736, "grad_norm": 0.37909314036369324, "learning_rate": 3.397338528362326e-08, "loss": 0.0012, "step": 2200 }, { "epoch": 4.858558062740782, "grad_norm": 0.044624462723731995, "learning_rate": 2.5628346221110434e-08, "loss": 0.0039, "step": 2210 }, { "epoch": 4.8805723720418275, "grad_norm": 0.40174078941345215, "learning_rate": 1.8454946012914087e-08, "loss": 0.0052, "step": 2220 }, { "epoch": 4.902586681342873, "grad_norm": 0.08541546761989594, "learning_rate": 1.2454874246181081e-08, "loss": 0.0008, "step": 2230 }, { "epoch": 4.924600990643919, "grad_norm": 0.1372637152671814, "learning_rate": 7.629544148087809e-09, "loss": 0.0005, "step": 2240 }, { "epoch": 4.946615299944964, "grad_norm": 0.050306595861911774, "learning_rate": 3.980092252978684e-09, "loss": 0.0006, "step": 2250 }, { "epoch": 4.96862960924601, "grad_norm": 0.024762878194451332, "learning_rate": 1.5073781346730543e-09, "loss": 0.0015, "step": 2260 }, { "epoch": 4.990643918547056, "grad_norm": 3.225762128829956, "learning_rate": 2.1198420400270204e-10, "loss": 0.0028, "step": 2270 } ], "logging_steps": 10, "max_steps": 2275, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.269169975197696e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }