{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 2856, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0070028011204481795, "grad_norm": 54.822365459213835, "learning_rate": 3.1468531468531473e-07, "loss": 2.9142, "step": 10 }, { "epoch": 0.014005602240896359, "grad_norm": 43.140784575015786, "learning_rate": 6.643356643356644e-07, "loss": 2.6364, "step": 20 }, { "epoch": 0.02100840336134454, "grad_norm": 20.52836873662029, "learning_rate": 1.013986013986014e-06, "loss": 2.0887, "step": 30 }, { "epoch": 0.028011204481792718, "grad_norm": 7.296293308558612, "learning_rate": 1.3636363636363636e-06, "loss": 1.593, "step": 40 }, { "epoch": 0.0350140056022409, "grad_norm": 5.69690111508328, "learning_rate": 1.7132867132867134e-06, "loss": 1.4625, "step": 50 }, { "epoch": 0.04201680672268908, "grad_norm": 4.407284596083797, "learning_rate": 2.0629370629370634e-06, "loss": 1.231, "step": 60 }, { "epoch": 0.049019607843137254, "grad_norm": 4.514294110845002, "learning_rate": 2.4125874125874128e-06, "loss": 1.1051, "step": 70 }, { "epoch": 0.056022408963585436, "grad_norm": 4.664107810659101, "learning_rate": 2.762237762237762e-06, "loss": 0.9814, "step": 80 }, { "epoch": 0.06302521008403361, "grad_norm": 3.983542706015, "learning_rate": 3.1118881118881123e-06, "loss": 0.9429, "step": 90 }, { "epoch": 0.0700280112044818, "grad_norm": 3.763711194865439, "learning_rate": 3.4615384615384617e-06, "loss": 0.8549, "step": 100 }, { "epoch": 0.07703081232492998, "grad_norm": 5.299639736915794, "learning_rate": 3.811188811188811e-06, "loss": 0.9123, "step": 110 }, { "epoch": 0.08403361344537816, "grad_norm": 5.376552790853205, "learning_rate": 4.160839160839161e-06, "loss": 0.7164, "step": 120 }, { "epoch": 0.09103641456582633, "grad_norm": 3.979790265000713, "learning_rate": 4.510489510489511e-06, "loss": 0.8358, "step": 130 }, { "epoch": 0.09803921568627451, "grad_norm": 3.2180158802612904, "learning_rate": 4.86013986013986e-06, "loss": 0.7863, "step": 140 }, { "epoch": 0.10504201680672269, "grad_norm": 3.653854239138897, "learning_rate": 5.20979020979021e-06, "loss": 0.7784, "step": 150 }, { "epoch": 0.11204481792717087, "grad_norm": 3.731091024980675, "learning_rate": 5.5594405594405596e-06, "loss": 0.696, "step": 160 }, { "epoch": 0.11904761904761904, "grad_norm": 3.371981147503621, "learning_rate": 5.90909090909091e-06, "loss": 0.7731, "step": 170 }, { "epoch": 0.12605042016806722, "grad_norm": 3.4539776878177544, "learning_rate": 6.258741258741259e-06, "loss": 0.7214, "step": 180 }, { "epoch": 0.1330532212885154, "grad_norm": 4.764005243860567, "learning_rate": 6.608391608391609e-06, "loss": 0.7684, "step": 190 }, { "epoch": 0.1400560224089636, "grad_norm": 3.4106980736508237, "learning_rate": 6.958041958041959e-06, "loss": 0.7845, "step": 200 }, { "epoch": 0.14705882352941177, "grad_norm": 3.5675277403879213, "learning_rate": 7.307692307692308e-06, "loss": 0.6937, "step": 210 }, { "epoch": 0.15406162464985995, "grad_norm": 3.6190398138061615, "learning_rate": 7.657342657342658e-06, "loss": 0.8302, "step": 220 }, { "epoch": 0.16106442577030813, "grad_norm": 3.5569990424945925, "learning_rate": 8.006993006993008e-06, "loss": 0.7539, "step": 230 }, { "epoch": 0.16806722689075632, "grad_norm": 2.957808482275135, "learning_rate": 8.356643356643356e-06, "loss": 0.7641, "step": 240 }, { "epoch": 0.17507002801120447, "grad_norm": 2.701665888444842, "learning_rate": 8.706293706293708e-06, "loss": 0.7131, "step": 250 }, { "epoch": 0.18207282913165265, "grad_norm": 3.582843229917075, "learning_rate": 9.055944055944057e-06, "loss": 0.595, "step": 260 }, { "epoch": 0.18907563025210083, "grad_norm": 3.453144473645395, "learning_rate": 9.405594405594406e-06, "loss": 0.7676, "step": 270 }, { "epoch": 0.19607843137254902, "grad_norm": 3.3312933939710114, "learning_rate": 9.755244755244755e-06, "loss": 0.7019, "step": 280 }, { "epoch": 0.2030812324929972, "grad_norm": 3.7248118142373494, "learning_rate": 9.999966378620396e-06, "loss": 0.6575, "step": 290 }, { "epoch": 0.21008403361344538, "grad_norm": 3.8896895986556688, "learning_rate": 9.999368677783691e-06, "loss": 0.6984, "step": 300 }, { "epoch": 0.21708683473389356, "grad_norm": 3.182135009379796, "learning_rate": 9.998023937980683e-06, "loss": 0.8306, "step": 310 }, { "epoch": 0.22408963585434175, "grad_norm": 2.8416958229620395, "learning_rate": 9.995932360151348e-06, "loss": 0.784, "step": 320 }, { "epoch": 0.23109243697478993, "grad_norm": 3.150294362261809, "learning_rate": 9.993094256833178e-06, "loss": 0.7085, "step": 330 }, { "epoch": 0.23809523809523808, "grad_norm": 3.0028637962745806, "learning_rate": 9.989510052114473e-06, "loss": 0.6222, "step": 340 }, { "epoch": 0.24509803921568626, "grad_norm": 2.845426871309238, "learning_rate": 9.985180281570976e-06, "loss": 0.7224, "step": 350 }, { "epoch": 0.25210084033613445, "grad_norm": 3.050098939646489, "learning_rate": 9.980105592185838e-06, "loss": 0.7097, "step": 360 }, { "epoch": 0.25910364145658266, "grad_norm": 2.6020917053511763, "learning_rate": 9.97428674225295e-06, "loss": 0.7017, "step": 370 }, { "epoch": 0.2661064425770308, "grad_norm": 3.6019215435633014, "learning_rate": 9.967724601263624e-06, "loss": 0.7097, "step": 380 }, { "epoch": 0.27310924369747897, "grad_norm": 4.104445886424035, "learning_rate": 9.960420149776674e-06, "loss": 0.7022, "step": 390 }, { "epoch": 0.2801120448179272, "grad_norm": 2.7297806144746204, "learning_rate": 9.952374479271894e-06, "loss": 0.7519, "step": 400 }, { "epoch": 0.28711484593837533, "grad_norm": 3.4868126922293694, "learning_rate": 9.943588791986956e-06, "loss": 0.6911, "step": 410 }, { "epoch": 0.29411764705882354, "grad_norm": 2.777255111697869, "learning_rate": 9.934064400737776e-06, "loss": 0.7083, "step": 420 }, { "epoch": 0.3011204481792717, "grad_norm": 2.667581928295271, "learning_rate": 9.923802728722326e-06, "loss": 0.7803, "step": 430 }, { "epoch": 0.3081232492997199, "grad_norm": 2.974529058609242, "learning_rate": 9.912805309307994e-06, "loss": 0.7277, "step": 440 }, { "epoch": 0.31512605042016806, "grad_norm": 2.8420842979615855, "learning_rate": 9.901073785802433e-06, "loss": 0.6997, "step": 450 }, { "epoch": 0.32212885154061627, "grad_norm": 2.9643793871710926, "learning_rate": 9.888609911208024e-06, "loss": 0.6917, "step": 460 }, { "epoch": 0.3291316526610644, "grad_norm": 2.6029717609338254, "learning_rate": 9.875415547959926e-06, "loss": 0.7042, "step": 470 }, { "epoch": 0.33613445378151263, "grad_norm": 2.6417095655684886, "learning_rate": 9.861492667647776e-06, "loss": 0.6818, "step": 480 }, { "epoch": 0.3431372549019608, "grad_norm": 2.912733389632055, "learning_rate": 9.846843350721084e-06, "loss": 0.7252, "step": 490 }, { "epoch": 0.35014005602240894, "grad_norm": 2.4477536058478804, "learning_rate": 9.831469786178359e-06, "loss": 0.7347, "step": 500 }, { "epoch": 0.35714285714285715, "grad_norm": 2.6814440911113353, "learning_rate": 9.81537427124001e-06, "loss": 0.6773, "step": 510 }, { "epoch": 0.3641456582633053, "grad_norm": 2.6474828003551125, "learning_rate": 9.798559211005083e-06, "loss": 0.6925, "step": 520 }, { "epoch": 0.3711484593837535, "grad_norm": 2.96009182699851, "learning_rate": 9.781027118091879e-06, "loss": 0.6953, "step": 530 }, { "epoch": 0.37815126050420167, "grad_norm": 3.047523864473747, "learning_rate": 9.76278061226249e-06, "loss": 0.7292, "step": 540 }, { "epoch": 0.3851540616246499, "grad_norm": 2.991785788396449, "learning_rate": 9.74382242003135e-06, "loss": 0.7072, "step": 550 }, { "epoch": 0.39215686274509803, "grad_norm": 2.369241516996275, "learning_rate": 9.724155374257816e-06, "loss": 0.6132, "step": 560 }, { "epoch": 0.39915966386554624, "grad_norm": 2.8220170208873023, "learning_rate": 9.703782413722856e-06, "loss": 0.7118, "step": 570 }, { "epoch": 0.4061624649859944, "grad_norm": 3.037044208560417, "learning_rate": 9.682706582689932e-06, "loss": 0.6837, "step": 580 }, { "epoch": 0.41316526610644255, "grad_norm": 2.820941643724944, "learning_rate": 9.660931030450092e-06, "loss": 0.7782, "step": 590 }, { "epoch": 0.42016806722689076, "grad_norm": 2.5666349293329107, "learning_rate": 9.638459010851389e-06, "loss": 0.6569, "step": 600 }, { "epoch": 0.4271708683473389, "grad_norm": 2.903374170685687, "learning_rate": 9.615293881812666e-06, "loss": 0.6597, "step": 610 }, { "epoch": 0.4341736694677871, "grad_norm": 2.4510273143556467, "learning_rate": 9.591439104821795e-06, "loss": 0.7102, "step": 620 }, { "epoch": 0.4411764705882353, "grad_norm": 2.724792508265338, "learning_rate": 9.566898244418443e-06, "loss": 0.7036, "step": 630 }, { "epoch": 0.4481792717086835, "grad_norm": 2.1578153197233183, "learning_rate": 9.541674967661424e-06, "loss": 0.6853, "step": 640 }, { "epoch": 0.45518207282913165, "grad_norm": 2.2982556480501977, "learning_rate": 9.515773043580754e-06, "loss": 0.6587, "step": 650 }, { "epoch": 0.46218487394957986, "grad_norm": 2.482971468008142, "learning_rate": 9.489196342614447e-06, "loss": 0.6941, "step": 660 }, { "epoch": 0.469187675070028, "grad_norm": 2.792625017068267, "learning_rate": 9.461948836030179e-06, "loss": 0.6527, "step": 670 }, { "epoch": 0.47619047619047616, "grad_norm": 2.8095289499726586, "learning_rate": 9.434034595331863e-06, "loss": 0.5537, "step": 680 }, { "epoch": 0.4831932773109244, "grad_norm": 2.6013084541081577, "learning_rate": 9.405457791651272e-06, "loss": 0.7455, "step": 690 }, { "epoch": 0.49019607843137253, "grad_norm": 2.323733631506617, "learning_rate": 9.376222695124748e-06, "loss": 0.6781, "step": 700 }, { "epoch": 0.49719887955182074, "grad_norm": 2.533641065336669, "learning_rate": 9.346333674255132e-06, "loss": 0.6807, "step": 710 }, { "epoch": 0.5042016806722689, "grad_norm": 2.310754494783324, "learning_rate": 9.315795195259003e-06, "loss": 0.7009, "step": 720 }, { "epoch": 0.511204481792717, "grad_norm": 2.247769256472491, "learning_rate": 9.284611821399295e-06, "loss": 0.6949, "step": 730 }, { "epoch": 0.5182072829131653, "grad_norm": 2.855866205125908, "learning_rate": 9.252788212303426e-06, "loss": 0.695, "step": 740 }, { "epoch": 0.5252100840336135, "grad_norm": 2.2123260966081144, "learning_rate": 9.220329123267031e-06, "loss": 0.6498, "step": 750 }, { "epoch": 0.5322128851540616, "grad_norm": 3.2793392899369955, "learning_rate": 9.187239404543387e-06, "loss": 0.6761, "step": 760 }, { "epoch": 0.5392156862745098, "grad_norm": 2.9849801807546132, "learning_rate": 9.153524000618663e-06, "loss": 0.6895, "step": 770 }, { "epoch": 0.5462184873949579, "grad_norm": 2.229602688156502, "learning_rate": 9.119187949473075e-06, "loss": 0.6221, "step": 780 }, { "epoch": 0.5532212885154062, "grad_norm": 2.1724377907001164, "learning_rate": 9.08423638182808e-06, "loss": 0.6749, "step": 790 }, { "epoch": 0.5602240896358543, "grad_norm": 2.4988277913931216, "learning_rate": 9.048674520379715e-06, "loss": 0.7179, "step": 800 }, { "epoch": 0.5672268907563025, "grad_norm": 2.4743732152259117, "learning_rate": 9.012507679018177e-06, "loss": 0.6926, "step": 810 }, { "epoch": 0.5742296918767507, "grad_norm": 2.3405306027107775, "learning_rate": 8.975741262033793e-06, "loss": 0.7389, "step": 820 }, { "epoch": 0.5812324929971989, "grad_norm": 2.272548602465369, "learning_rate": 8.93838076330947e-06, "loss": 0.6424, "step": 830 }, { "epoch": 0.5882352941176471, "grad_norm": 2.0400401153554935, "learning_rate": 8.900431765499773e-06, "loss": 0.6971, "step": 840 }, { "epoch": 0.5952380952380952, "grad_norm": 2.084177383415346, "learning_rate": 8.861899939196713e-06, "loss": 0.6155, "step": 850 }, { "epoch": 0.6022408963585434, "grad_norm": 3.794945397573399, "learning_rate": 8.82279104208242e-06, "loss": 0.6244, "step": 860 }, { "epoch": 0.6092436974789915, "grad_norm": 3.49165664633522, "learning_rate": 8.783110918068784e-06, "loss": 0.7264, "step": 870 }, { "epoch": 0.6162464985994398, "grad_norm": 2.039969801192167, "learning_rate": 8.742865496424228e-06, "loss": 0.6768, "step": 880 }, { "epoch": 0.623249299719888, "grad_norm": 2.335677247223129, "learning_rate": 8.70206079088771e-06, "loss": 0.5889, "step": 890 }, { "epoch": 0.6302521008403361, "grad_norm": 2.060225160885774, "learning_rate": 8.660702898770113e-06, "loss": 0.6492, "step": 900 }, { "epoch": 0.6372549019607843, "grad_norm": 2.798146335622228, "learning_rate": 8.618798000043142e-06, "loss": 0.6209, "step": 910 }, { "epoch": 0.6442577030812325, "grad_norm": 2.8734777136564493, "learning_rate": 8.576352356415876e-06, "loss": 0.6407, "step": 920 }, { "epoch": 0.6512605042016807, "grad_norm": 2.6762821835109154, "learning_rate": 8.533372310399093e-06, "loss": 0.6735, "step": 930 }, { "epoch": 0.6582633053221288, "grad_norm": 2.0693419886641125, "learning_rate": 8.48986428435754e-06, "loss": 0.6023, "step": 940 }, { "epoch": 0.665266106442577, "grad_norm": 2.5455745068080304, "learning_rate": 8.445834779550257e-06, "loss": 0.5726, "step": 950 }, { "epoch": 0.6722689075630253, "grad_norm": 2.8427810866745427, "learning_rate": 8.40129037515911e-06, "loss": 0.6442, "step": 960 }, { "epoch": 0.6792717086834734, "grad_norm": 2.338498753658426, "learning_rate": 8.356237727305695e-06, "loss": 0.6775, "step": 970 }, { "epoch": 0.6862745098039216, "grad_norm": 2.035099542215418, "learning_rate": 8.310683568056725e-06, "loss": 0.6076, "step": 980 }, { "epoch": 0.6932773109243697, "grad_norm": 2.2530856849283394, "learning_rate": 8.264634704418095e-06, "loss": 0.6701, "step": 990 }, { "epoch": 0.7002801120448179, "grad_norm": 2.124044857812194, "learning_rate": 8.218098017317715e-06, "loss": 0.6211, "step": 1000 }, { "epoch": 0.7072829131652661, "grad_norm": 2.3812764227997265, "learning_rate": 8.171080460577337e-06, "loss": 0.6853, "step": 1010 }, { "epoch": 0.7142857142857143, "grad_norm": 2.125710699424273, "learning_rate": 8.123589059873445e-06, "loss": 0.6516, "step": 1020 }, { "epoch": 0.7212885154061625, "grad_norm": 2.0639925369405163, "learning_rate": 8.075630911687451e-06, "loss": 0.5853, "step": 1030 }, { "epoch": 0.7282913165266106, "grad_norm": 2.4862110603900676, "learning_rate": 8.027213182245289e-06, "loss": 0.6107, "step": 1040 }, { "epoch": 0.7352941176470589, "grad_norm": 1.601475291312852, "learning_rate": 7.978343106446575e-06, "loss": 0.7112, "step": 1050 }, { "epoch": 0.742296918767507, "grad_norm": 2.871165956851756, "learning_rate": 7.929027986783538e-06, "loss": 0.6573, "step": 1060 }, { "epoch": 0.7492997198879552, "grad_norm": 2.502491985241327, "learning_rate": 7.879275192249822e-06, "loss": 0.6383, "step": 1070 }, { "epoch": 0.7563025210084033, "grad_norm": 2.3534352305326656, "learning_rate": 7.829092157239369e-06, "loss": 0.6707, "step": 1080 }, { "epoch": 0.7633053221288515, "grad_norm": 2.346735216001232, "learning_rate": 7.778486380435512e-06, "loss": 0.5754, "step": 1090 }, { "epoch": 0.7703081232492998, "grad_norm": 1.7069335554420118, "learning_rate": 7.727465423690487e-06, "loss": 0.6674, "step": 1100 }, { "epoch": 0.7773109243697479, "grad_norm": 2.857304704073804, "learning_rate": 7.676036910895475e-06, "loss": 0.6436, "step": 1110 }, { "epoch": 0.7843137254901961, "grad_norm": 2.704621305833269, "learning_rate": 7.624208526841399e-06, "loss": 0.5633, "step": 1120 }, { "epoch": 0.7913165266106442, "grad_norm": 2.3446023311507243, "learning_rate": 7.571988016070611e-06, "loss": 0.6534, "step": 1130 }, { "epoch": 0.7983193277310925, "grad_norm": 2.655699735724774, "learning_rate": 7.519383181719644e-06, "loss": 0.6152, "step": 1140 }, { "epoch": 0.8053221288515406, "grad_norm": 2.5608889463976983, "learning_rate": 7.466401884353227e-06, "loss": 0.6775, "step": 1150 }, { "epoch": 0.8123249299719888, "grad_norm": 2.3142838348541965, "learning_rate": 7.413052040789692e-06, "loss": 0.6514, "step": 1160 }, { "epoch": 0.819327731092437, "grad_norm": 2.134983409939985, "learning_rate": 7.359341622918006e-06, "loss": 0.6194, "step": 1170 }, { "epoch": 0.8263305322128851, "grad_norm": 2.4655749339506086, "learning_rate": 7.305278656506547e-06, "loss": 0.6381, "step": 1180 }, { "epoch": 0.8333333333333334, "grad_norm": 1.90146176033135, "learning_rate": 7.2508712200038435e-06, "loss": 0.6059, "step": 1190 }, { "epoch": 0.8403361344537815, "grad_norm": 2.7581098466146834, "learning_rate": 7.19612744333144e-06, "loss": 0.7107, "step": 1200 }, { "epoch": 0.8473389355742297, "grad_norm": 2.013181558142786, "learning_rate": 7.141055506669072e-06, "loss": 0.6062, "step": 1210 }, { "epoch": 0.8543417366946778, "grad_norm": 2.153881730897074, "learning_rate": 7.0856636392323205e-06, "loss": 0.5956, "step": 1220 }, { "epoch": 0.8613445378151261, "grad_norm": 2.527280124270099, "learning_rate": 7.0299601180429615e-06, "loss": 0.5936, "step": 1230 }, { "epoch": 0.8683473389355743, "grad_norm": 1.858330034501666, "learning_rate": 6.973953266692143e-06, "loss": 0.6314, "step": 1240 }, { "epoch": 0.8753501400560224, "grad_norm": 2.3746989063300186, "learning_rate": 6.91765145409663e-06, "loss": 0.6908, "step": 1250 }, { "epoch": 0.8823529411764706, "grad_norm": 2.2513458203129963, "learning_rate": 6.861063093248264e-06, "loss": 0.5709, "step": 1260 }, { "epoch": 0.8893557422969187, "grad_norm": 2.5609479562736106, "learning_rate": 6.804196639956828e-06, "loss": 0.627, "step": 1270 }, { "epoch": 0.896358543417367, "grad_norm": 2.4301069707639233, "learning_rate": 6.747060591586533e-06, "loss": 0.5996, "step": 1280 }, { "epoch": 0.9033613445378151, "grad_norm": 2.610417413605633, "learning_rate": 6.689663485786287e-06, "loss": 0.6943, "step": 1290 }, { "epoch": 0.9103641456582633, "grad_norm": 2.240908654296222, "learning_rate": 6.632013899213934e-06, "loss": 0.6311, "step": 1300 }, { "epoch": 0.9173669467787114, "grad_norm": 2.3215803208239394, "learning_rate": 6.574120446254672e-06, "loss": 0.6081, "step": 1310 }, { "epoch": 0.9243697478991597, "grad_norm": 1.7958005235142336, "learning_rate": 6.5159917777338466e-06, "loss": 0.6685, "step": 1320 }, { "epoch": 0.9313725490196079, "grad_norm": 2.042136754036796, "learning_rate": 6.457636579624278e-06, "loss": 0.5457, "step": 1330 }, { "epoch": 0.938375350140056, "grad_norm": 2.0200483342599367, "learning_rate": 6.3990635717483404e-06, "loss": 0.6981, "step": 1340 }, { "epoch": 0.9453781512605042, "grad_norm": 2.3485088870526827, "learning_rate": 6.340281506475003e-06, "loss": 0.6165, "step": 1350 }, { "epoch": 0.9523809523809523, "grad_norm": 2.0775112823384383, "learning_rate": 6.281299167411975e-06, "loss": 0.5656, "step": 1360 }, { "epoch": 0.9593837535014006, "grad_norm": 2.115129503123767, "learning_rate": 6.222125368093213e-06, "loss": 0.6473, "step": 1370 }, { "epoch": 0.9663865546218487, "grad_norm": 2.203147650702632, "learning_rate": 6.162768950661945e-06, "loss": 0.6279, "step": 1380 }, { "epoch": 0.9733893557422969, "grad_norm": 2.617800940269768, "learning_rate": 6.103238784549404e-06, "loss": 0.5426, "step": 1390 }, { "epoch": 0.9803921568627451, "grad_norm": 2.1058865000385754, "learning_rate": 6.043543765149514e-06, "loss": 0.6551, "step": 1400 }, { "epoch": 0.9873949579831933, "grad_norm": 2.262404955697173, "learning_rate": 5.983692812489679e-06, "loss": 0.6524, "step": 1410 }, { "epoch": 0.9943977591036415, "grad_norm": 2.1193412453943803, "learning_rate": 5.923694869897879e-06, "loss": 0.5787, "step": 1420 }, { "epoch": 1.0014005602240896, "grad_norm": 2.0659116339074166, "learning_rate": 5.863558902666318e-06, "loss": 0.6191, "step": 1430 }, { "epoch": 1.0084033613445378, "grad_norm": 2.13662088721353, "learning_rate": 5.803293896711756e-06, "loss": 0.4869, "step": 1440 }, { "epoch": 1.015406162464986, "grad_norm": 2.132520413876192, "learning_rate": 5.74290885723278e-06, "loss": 0.4959, "step": 1450 }, { "epoch": 1.022408963585434, "grad_norm": 1.862348432644305, "learning_rate": 5.682412807364187e-06, "loss": 0.4611, "step": 1460 }, { "epoch": 1.0294117647058822, "grad_norm": 2.1396458126762825, "learning_rate": 5.621814786828683e-06, "loss": 0.4828, "step": 1470 }, { "epoch": 1.0364145658263306, "grad_norm": 2.23299330212776, "learning_rate": 5.5611238505861094e-06, "loss": 0.4362, "step": 1480 }, { "epoch": 1.0434173669467788, "grad_norm": 2.336766894179504, "learning_rate": 5.5003490674804e-06, "loss": 0.4811, "step": 1490 }, { "epoch": 1.050420168067227, "grad_norm": 2.2053948018429126, "learning_rate": 5.439499518884433e-06, "loss": 0.4525, "step": 1500 }, { "epoch": 1.057422969187675, "grad_norm": 2.0455239012711806, "learning_rate": 5.378584297343053e-06, "loss": 0.4573, "step": 1510 }, { "epoch": 1.0644257703081232, "grad_norm": 2.799894111126595, "learning_rate": 5.3176125052143905e-06, "loss": 0.4475, "step": 1520 }, { "epoch": 1.0714285714285714, "grad_norm": 2.3537914083107743, "learning_rate": 5.256593253309728e-06, "loss": 0.4679, "step": 1530 }, { "epoch": 1.0784313725490196, "grad_norm": 2.3121216793787283, "learning_rate": 5.195535659532111e-06, "loss": 0.4982, "step": 1540 }, { "epoch": 1.0854341736694677, "grad_norm": 1.8801771013194575, "learning_rate": 5.134448847513873e-06, "loss": 0.4881, "step": 1550 }, { "epoch": 1.092436974789916, "grad_norm": 2.117146997784492, "learning_rate": 5.073341945253336e-06, "loss": 0.4518, "step": 1560 }, { "epoch": 1.0994397759103642, "grad_norm": 2.4512284660613592, "learning_rate": 5.012224083750845e-06, "loss": 0.4618, "step": 1570 }, { "epoch": 1.1064425770308124, "grad_norm": 2.3001015988026747, "learning_rate": 4.951104395644342e-06, "loss": 0.4647, "step": 1580 }, { "epoch": 1.1134453781512605, "grad_norm": 2.733492067730666, "learning_rate": 4.889992013844711e-06, "loss": 0.497, "step": 1590 }, { "epoch": 1.1204481792717087, "grad_norm": 2.624090029655425, "learning_rate": 4.828896070171084e-06, "loss": 0.5142, "step": 1600 }, { "epoch": 1.1274509803921569, "grad_norm": 2.3184684372082405, "learning_rate": 4.767825693986295e-06, "loss": 0.449, "step": 1610 }, { "epoch": 1.134453781512605, "grad_norm": 2.5173043040744836, "learning_rate": 4.706790010832714e-06, "loss": 0.5264, "step": 1620 }, { "epoch": 1.1414565826330532, "grad_norm": 2.088682951418163, "learning_rate": 4.6457981410686524e-06, "loss": 0.4551, "step": 1630 }, { "epoch": 1.1484593837535013, "grad_norm": 1.9999194791787656, "learning_rate": 4.584859198505526e-06, "loss": 0.5141, "step": 1640 }, { "epoch": 1.1554621848739495, "grad_norm": 2.0283863135066293, "learning_rate": 4.5239822890460174e-06, "loss": 0.4254, "step": 1650 }, { "epoch": 1.1624649859943978, "grad_norm": 2.4761929786113246, "learning_rate": 4.463176509323413e-06, "loss": 0.4986, "step": 1660 }, { "epoch": 1.169467787114846, "grad_norm": 1.6823258146384572, "learning_rate": 4.402450945342317e-06, "loss": 0.3929, "step": 1670 }, { "epoch": 1.1764705882352942, "grad_norm": 2.3712484150543065, "learning_rate": 4.341814671120965e-06, "loss": 0.5022, "step": 1680 }, { "epoch": 1.1834733893557423, "grad_norm": 2.1223027287039136, "learning_rate": 4.2812767473353205e-06, "loss": 0.5201, "step": 1690 }, { "epoch": 1.1904761904761905, "grad_norm": 2.280910320108766, "learning_rate": 4.220846219965168e-06, "loss": 0.4627, "step": 1700 }, { "epoch": 1.1974789915966386, "grad_norm": 1.850154690325662, "learning_rate": 4.160532118942411e-06, "loss": 0.4312, "step": 1710 }, { "epoch": 1.2044817927170868, "grad_norm": 2.339402359759638, "learning_rate": 4.100343456801747e-06, "loss": 0.4317, "step": 1720 }, { "epoch": 1.211484593837535, "grad_norm": 2.2500882330234604, "learning_rate": 4.040289227333961e-06, "loss": 0.4521, "step": 1730 }, { "epoch": 1.2184873949579833, "grad_norm": 2.8132677454268857, "learning_rate": 3.980378404242014e-06, "loss": 0.4432, "step": 1740 }, { "epoch": 1.2254901960784315, "grad_norm": 2.67999303980593, "learning_rate": 3.920619939800131e-06, "loss": 0.4613, "step": 1750 }, { "epoch": 1.2324929971988796, "grad_norm": 1.8885239257708604, "learning_rate": 3.861022763516091e-06, "loss": 0.4774, "step": 1760 }, { "epoch": 1.2394957983193278, "grad_norm": 2.815116777237025, "learning_rate": 3.8015957807969247e-06, "loss": 0.4879, "step": 1770 }, { "epoch": 1.246498599439776, "grad_norm": 2.174587271539217, "learning_rate": 3.7423478716182026e-06, "loss": 0.456, "step": 1780 }, { "epoch": 1.253501400560224, "grad_norm": 2.7567028224464183, "learning_rate": 3.68328788919714e-06, "loss": 0.4644, "step": 1790 }, { "epoch": 1.2605042016806722, "grad_norm": 2.1568363923043266, "learning_rate": 3.624424658669682e-06, "loss": 0.5225, "step": 1800 }, { "epoch": 1.2675070028011204, "grad_norm": 2.721189011538071, "learning_rate": 3.5657669757717927e-06, "loss": 0.3921, "step": 1810 }, { "epoch": 1.2745098039215685, "grad_norm": 2.120385676401417, "learning_rate": 3.5073236055251425e-06, "loss": 0.4793, "step": 1820 }, { "epoch": 1.2815126050420167, "grad_norm": 2.302768261718875, "learning_rate": 3.4491032809273784e-06, "loss": 0.4526, "step": 1830 }, { "epoch": 1.2885154061624648, "grad_norm": 2.334008008597067, "learning_rate": 3.3911147016471784e-06, "loss": 0.4855, "step": 1840 }, { "epoch": 1.2955182072829132, "grad_norm": 2.6089068847882744, "learning_rate": 3.3333665327242965e-06, "loss": 0.4522, "step": 1850 }, { "epoch": 1.3025210084033614, "grad_norm": 2.8426511093929556, "learning_rate": 3.275867403274763e-06, "loss": 0.4965, "step": 1860 }, { "epoch": 1.3095238095238095, "grad_norm": 2.515991574117609, "learning_rate": 3.2186259052014797e-06, "loss": 0.4635, "step": 1870 }, { "epoch": 1.3165266106442577, "grad_norm": 2.410804360632545, "learning_rate": 3.1616505919103446e-06, "loss": 0.44, "step": 1880 }, { "epoch": 1.3235294117647058, "grad_norm": 2.1144368698980234, "learning_rate": 3.1049499770321572e-06, "loss": 0.511, "step": 1890 }, { "epoch": 1.330532212885154, "grad_norm": 2.3764720452535113, "learning_rate": 3.0485325331504477e-06, "loss": 0.4298, "step": 1900 }, { "epoch": 1.3375350140056024, "grad_norm": 2.008815745845685, "learning_rate": 2.992406690535453e-06, "loss": 0.4353, "step": 1910 }, { "epoch": 1.3445378151260505, "grad_norm": 2.5495322694247404, "learning_rate": 2.936580835884404e-06, "loss": 0.5351, "step": 1920 }, { "epoch": 1.3515406162464987, "grad_norm": 2.6170532242550424, "learning_rate": 2.8810633110683312e-06, "loss": 0.4736, "step": 1930 }, { "epoch": 1.3585434173669468, "grad_norm": 2.304939061322721, "learning_rate": 2.8258624118855704e-06, "loss": 0.497, "step": 1940 }, { "epoch": 1.365546218487395, "grad_norm": 2.52028463522758, "learning_rate": 2.770986386822145e-06, "loss": 0.4561, "step": 1950 }, { "epoch": 1.3725490196078431, "grad_norm": 2.1554513929621653, "learning_rate": 2.7164434358192236e-06, "loss": 0.4771, "step": 1960 }, { "epoch": 1.3795518207282913, "grad_norm": 2.2864103571812247, "learning_rate": 2.6622417090478304e-06, "loss": 0.4244, "step": 1970 }, { "epoch": 1.3865546218487395, "grad_norm": 2.3291887139186604, "learning_rate": 2.6083893056909937e-06, "loss": 0.4818, "step": 1980 }, { "epoch": 1.3935574229691876, "grad_norm": 1.6186217281536261, "learning_rate": 2.5548942727335046e-06, "loss": 0.4473, "step": 1990 }, { "epoch": 1.4005602240896358, "grad_norm": 1.9490552509158812, "learning_rate": 2.5017646037594967e-06, "loss": 0.4653, "step": 2000 }, { "epoch": 1.407563025210084, "grad_norm": 2.4440857430217124, "learning_rate": 2.4490082377579805e-06, "loss": 0.4945, "step": 2010 }, { "epoch": 1.4145658263305323, "grad_norm": 2.9756203221062476, "learning_rate": 2.3966330579365436e-06, "loss": 0.4371, "step": 2020 }, { "epoch": 1.4215686274509804, "grad_norm": 2.202500602837109, "learning_rate": 2.3446468905434093e-06, "loss": 0.4495, "step": 2030 }, { "epoch": 1.4285714285714286, "grad_norm": 1.9506623499545588, "learning_rate": 2.2930575036979634e-06, "loss": 0.4552, "step": 2040 }, { "epoch": 1.4355742296918768, "grad_norm": 2.6310040966711776, "learning_rate": 2.241872606229998e-06, "loss": 0.4378, "step": 2050 }, { "epoch": 1.442577030812325, "grad_norm": 2.4781025094081706, "learning_rate": 2.191099846527813e-06, "loss": 0.5055, "step": 2060 }, { "epoch": 1.449579831932773, "grad_norm": 2.3262915560231217, "learning_rate": 2.14074681139534e-06, "loss": 0.4727, "step": 2070 }, { "epoch": 1.4565826330532212, "grad_norm": 2.001470623484971, "learning_rate": 2.090821024918462e-06, "loss": 0.4826, "step": 2080 }, { "epoch": 1.4635854341736696, "grad_norm": 2.8728529295622964, "learning_rate": 2.0413299473407285e-06, "loss": 0.4162, "step": 2090 }, { "epoch": 1.4705882352941178, "grad_norm": 2.54674433384974, "learning_rate": 1.9922809739485883e-06, "loss": 0.4516, "step": 2100 }, { "epoch": 1.477591036414566, "grad_norm": 1.7010786229876187, "learning_rate": 1.943681433966338e-06, "loss": 0.4727, "step": 2110 }, { "epoch": 1.484593837535014, "grad_norm": 2.7445575800859747, "learning_rate": 1.8955385894609414e-06, "loss": 0.4835, "step": 2120 }, { "epoch": 1.4915966386554622, "grad_norm": 2.5636924295564825, "learning_rate": 1.8478596342568827e-06, "loss": 0.5, "step": 2130 }, { "epoch": 1.4985994397759104, "grad_norm": 2.6320112816326806, "learning_rate": 1.8006516928612121e-06, "loss": 0.4783, "step": 2140 }, { "epoch": 1.5056022408963585, "grad_norm": 2.3130885237765653, "learning_rate": 1.753921819398966e-06, "loss": 0.4732, "step": 2150 }, { "epoch": 1.5126050420168067, "grad_norm": 2.4566766430867855, "learning_rate": 1.7076769965590834e-06, "loss": 0.4846, "step": 2160 }, { "epoch": 1.5196078431372548, "grad_norm": 2.1691439788909705, "learning_rate": 1.6619241345510057e-06, "loss": 0.5196, "step": 2170 }, { "epoch": 1.526610644257703, "grad_norm": 1.9388105151944164, "learning_rate": 1.6166700700721121e-06, "loss": 0.3903, "step": 2180 }, { "epoch": 1.5336134453781511, "grad_norm": 2.353752022853995, "learning_rate": 1.571921565286139e-06, "loss": 0.4923, "step": 2190 }, { "epoch": 1.5406162464985993, "grad_norm": 2.572914747835839, "learning_rate": 1.527685306812715e-06, "loss": 0.4166, "step": 2200 }, { "epoch": 1.5476190476190477, "grad_norm": 2.1724801712005792, "learning_rate": 1.4839679047282206e-06, "loss": 0.4504, "step": 2210 }, { "epoch": 1.5546218487394958, "grad_norm": 2.594065623296099, "learning_rate": 1.4407758915780578e-06, "loss": 0.477, "step": 2220 }, { "epoch": 1.561624649859944, "grad_norm": 2.208098426234172, "learning_rate": 1.3981157214005098e-06, "loss": 0.4586, "step": 2230 }, { "epoch": 1.5686274509803921, "grad_norm": 2.139581629149966, "learning_rate": 1.3559937687623458e-06, "loss": 0.4276, "step": 2240 }, { "epoch": 1.5756302521008403, "grad_norm": 2.538499089739133, "learning_rate": 1.3144163278062848e-06, "loss": 0.4206, "step": 2250 }, { "epoch": 1.5826330532212887, "grad_norm": 2.041136800394131, "learning_rate": 1.273389611310481e-06, "loss": 0.4034, "step": 2260 }, { "epoch": 1.5896358543417368, "grad_norm": 2.313241143682124, "learning_rate": 1.2329197497601742e-06, "loss": 0.4801, "step": 2270 }, { "epoch": 1.596638655462185, "grad_norm": 2.309500171812923, "learning_rate": 1.1930127904316286e-06, "loss": 0.5045, "step": 2280 }, { "epoch": 1.6036414565826331, "grad_norm": 2.485298750781323, "learning_rate": 1.1536746964885065e-06, "loss": 0.4301, "step": 2290 }, { "epoch": 1.6106442577030813, "grad_norm": 2.591481445677265, "learning_rate": 1.114911346090819e-06, "loss": 0.4554, "step": 2300 }, { "epoch": 1.6176470588235294, "grad_norm": 2.833792845787996, "learning_rate": 1.0767285315165675e-06, "loss": 0.4132, "step": 2310 }, { "epoch": 1.6246498599439776, "grad_norm": 2.388415928161688, "learning_rate": 1.0391319582962244e-06, "loss": 0.4707, "step": 2320 }, { "epoch": 1.6316526610644257, "grad_norm": 2.3441821249748798, "learning_rate": 1.002127244360171e-06, "loss": 0.422, "step": 2330 }, { "epoch": 1.638655462184874, "grad_norm": 1.9731306455288935, "learning_rate": 9.65719919199235e-07, "loss": 0.3684, "step": 2340 }, { "epoch": 1.645658263305322, "grad_norm": 3.7976656804390303, "learning_rate": 9.299154230384383e-07, "loss": 0.4887, "step": 2350 }, { "epoch": 1.6526610644257702, "grad_norm": 2.29269452111851, "learning_rate": 8.947191060240701e-07, "loss": 0.4054, "step": 2360 }, { "epoch": 1.6596638655462184, "grad_norm": 2.765208721785312, "learning_rate": 8.601362274242465e-07, "loss": 0.5191, "step": 2370 }, { "epoch": 1.6666666666666665, "grad_norm": 2.637952088090675, "learning_rate": 8.261719548430292e-07, "loss": 0.479, "step": 2380 }, { "epoch": 1.673669467787115, "grad_norm": 2.7259524316936496, "learning_rate": 7.928313634482454e-07, "loss": 0.4162, "step": 2390 }, { "epoch": 1.680672268907563, "grad_norm": 2.783618319304046, "learning_rate": 7.601194352131285e-07, "loss": 0.4662, "step": 2400 }, { "epoch": 1.6876750700280112, "grad_norm": 2.5896397818912957, "learning_rate": 7.280410581718761e-07, "loss": 0.466, "step": 2410 }, { "epoch": 1.6946778711484594, "grad_norm": 2.313925409486687, "learning_rate": 6.966010256892408e-07, "loss": 0.421, "step": 2420 }, { "epoch": 1.7016806722689075, "grad_norm": 2.2637352342234673, "learning_rate": 6.658040357442874e-07, "loss": 0.4384, "step": 2430 }, { "epoch": 1.708683473389356, "grad_norm": 2.2403407432076836, "learning_rate": 6.356546902283772e-07, "loss": 0.4423, "step": 2440 }, { "epoch": 1.715686274509804, "grad_norm": 2.7755062361806333, "learning_rate": 6.061574942575266e-07, "loss": 0.4507, "step": 2450 }, { "epoch": 1.7226890756302522, "grad_norm": 2.3259900192767713, "learning_rate": 5.773168554992248e-07, "loss": 0.426, "step": 2460 }, { "epoch": 1.7296918767507004, "grad_norm": 2.6341383732328456, "learning_rate": 5.491370835138116e-07, "loss": 0.4377, "step": 2470 }, { "epoch": 1.7366946778711485, "grad_norm": 2.3924610495134933, "learning_rate": 5.216223891105054e-07, "loss": 0.4585, "step": 2480 }, { "epoch": 1.7436974789915967, "grad_norm": 2.1758349972571507, "learning_rate": 4.947768837182093e-07, "loss": 0.4068, "step": 2490 }, { "epoch": 1.7507002801120448, "grad_norm": 2.0421217828565448, "learning_rate": 4.686045787711435e-07, "loss": 0.4066, "step": 2500 }, { "epoch": 1.757703081232493, "grad_norm": 2.115206308615413, "learning_rate": 4.4310938510943533e-07, "loss": 0.4522, "step": 2510 }, { "epoch": 1.7647058823529411, "grad_norm": 2.066405782929325, "learning_rate": 4.182951123947332e-07, "loss": 0.3312, "step": 2520 }, { "epoch": 1.7717086834733893, "grad_norm": 2.342484690456666, "learning_rate": 3.9416546854094294e-07, "loss": 0.4224, "step": 2530 }, { "epoch": 1.7787114845938374, "grad_norm": 2.512724647352599, "learning_rate": 3.7072405916016353e-07, "loss": 0.445, "step": 2540 }, { "epoch": 1.7857142857142856, "grad_norm": 2.470340765232829, "learning_rate": 3.479743870239188e-07, "loss": 0.4637, "step": 2550 }, { "epoch": 1.7927170868347337, "grad_norm": 2.130736248713378, "learning_rate": 3.2591985153974383e-07, "loss": 0.387, "step": 2560 }, { "epoch": 1.7997198879551821, "grad_norm": 2.1431789471135723, "learning_rate": 3.0456374824322674e-07, "loss": 0.4469, "step": 2570 }, { "epoch": 1.8067226890756303, "grad_norm": 2.099234007419937, "learning_rate": 2.839092683055622e-07, "loss": 0.4039, "step": 2580 }, { "epoch": 1.8137254901960784, "grad_norm": 2.459188631196229, "learning_rate": 2.639594980567162e-07, "loss": 0.3812, "step": 2590 }, { "epoch": 1.8207282913165266, "grad_norm": 2.555886554006267, "learning_rate": 2.447174185242324e-07, "loss": 0.4212, "step": 2600 }, { "epoch": 1.8277310924369747, "grad_norm": 2.2836207612772843, "learning_rate": 2.2618590498779847e-07, "loss": 0.4137, "step": 2610 }, { "epoch": 1.8347338935574231, "grad_norm": 2.1026781532549936, "learning_rate": 2.0836772654959647e-07, "loss": 0.4213, "step": 2620 }, { "epoch": 1.8417366946778713, "grad_norm": 2.4328664873281483, "learning_rate": 1.9126554572052813e-07, "loss": 0.4335, "step": 2630 }, { "epoch": 1.8487394957983194, "grad_norm": 2.3974367367984857, "learning_rate": 1.74881918022361e-07, "loss": 0.4056, "step": 2640 }, { "epoch": 1.8557422969187676, "grad_norm": 2.299811399188436, "learning_rate": 1.5921929160587045e-07, "loss": 0.4602, "step": 2650 }, { "epoch": 1.8627450980392157, "grad_norm": 1.9124769037343121, "learning_rate": 1.44280006885017e-07, "loss": 0.4231, "step": 2660 }, { "epoch": 1.8697478991596639, "grad_norm": 2.813578456729493, "learning_rate": 1.3006629618722733e-07, "loss": 0.4286, "step": 2670 }, { "epoch": 1.876750700280112, "grad_norm": 2.4806383435943613, "learning_rate": 1.1658028341982486e-07, "loss": 0.4368, "step": 2680 }, { "epoch": 1.8837535014005602, "grad_norm": 2.2681286986704534, "learning_rate": 1.0382398375266111e-07, "loss": 0.4691, "step": 2690 }, { "epoch": 1.8907563025210083, "grad_norm": 1.9128855914355993, "learning_rate": 9.179930331699615e-08, "loss": 0.4508, "step": 2700 }, { "epoch": 1.8977591036414565, "grad_norm": 2.1633704801409834, "learning_rate": 8.050803892067139e-08, "loss": 0.4422, "step": 2710 }, { "epoch": 1.9047619047619047, "grad_norm": 2.8200396806385, "learning_rate": 6.995187777961931e-08, "loss": 0.4254, "step": 2720 }, { "epoch": 1.9117647058823528, "grad_norm": 2.6445714035080887, "learning_rate": 6.013239726574694e-08, "loss": 0.4074, "step": 2730 }, { "epoch": 1.918767507002801, "grad_norm": 2.0546751872771627, "learning_rate": 5.105106467123477e-08, "loss": 0.4262, "step": 2740 }, { "epoch": 1.9257703081232493, "grad_norm": 2.7784776972549916, "learning_rate": 4.2709236989287305e-08, "loss": 0.4725, "step": 2750 }, { "epoch": 1.9327731092436975, "grad_norm": 2.272829343457401, "learning_rate": 3.510816071135681e-08, "loss": 0.4409, "step": 2760 }, { "epoch": 1.9397759103641457, "grad_norm": 2.4175361768734276, "learning_rate": 2.8248971640887913e-08, "loss": 0.393, "step": 2770 }, { "epoch": 1.9467787114845938, "grad_norm": 2.2153647657315347, "learning_rate": 2.213269472359836e-08, "loss": 0.474, "step": 2780 }, { "epoch": 1.9537815126050422, "grad_norm": 2.146439918476662, "learning_rate": 1.6760243894321513e-08, "loss": 0.4008, "step": 2790 }, { "epoch": 1.9607843137254903, "grad_norm": 2.0928270476543522, "learning_rate": 1.213242194044395e-08, "loss": 0.4111, "step": 2800 }, { "epoch": 1.9677871148459385, "grad_norm": 2.079556551258959, "learning_rate": 8.249920381946387e-09, "loss": 0.4999, "step": 2810 }, { "epoch": 1.9747899159663866, "grad_norm": 2.0113264107881164, "learning_rate": 5.113319368070801e-09, "loss": 0.4397, "step": 2820 }, { "epoch": 1.9817927170868348, "grad_norm": 2.3335982318192827, "learning_rate": 2.723087590632556e-09, "loss": 0.3984, "step": 2830 }, { "epoch": 1.988795518207283, "grad_norm": 2.7347014131885015, "learning_rate": 1.079582213983632e-09, "loss": 0.4515, "step": 2840 }, { "epoch": 1.995798319327731, "grad_norm": 1.8502359446882066, "learning_rate": 1.830488216442161e-10, "loss": 0.4036, "step": 2850 }, { "epoch": 2.0, "step": 2856, "total_flos": 137777518706688.0, "train_loss": 0.5963595523720696, "train_runtime": 4888.1806, "train_samples_per_second": 9.347, "train_steps_per_second": 0.584 } ], "logging_steps": 10, "max_steps": 2856, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 137777518706688.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }