{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 2418, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01240694789081886, "grad_norm": 16.390365600585938, "learning_rate": 1.8595041322314052e-07, "loss": 0.9563, "step": 10 }, { "epoch": 0.02481389578163772, "grad_norm": 12.768733024597168, "learning_rate": 3.925619834710744e-07, "loss": 0.8863, "step": 20 }, { "epoch": 0.03722084367245657, "grad_norm": 11.104592323303223, "learning_rate": 5.991735537190084e-07, "loss": 0.8221, "step": 30 }, { "epoch": 0.04962779156327544, "grad_norm": 5.34985876083374, "learning_rate": 8.057851239669421e-07, "loss": 0.8111, "step": 40 }, { "epoch": 0.062034739454094295, "grad_norm": 2.7398500442504883, "learning_rate": 1.012396694214876e-06, "loss": 0.7023, "step": 50 }, { "epoch": 0.07444168734491315, "grad_norm": 2.6916472911834717, "learning_rate": 1.21900826446281e-06, "loss": 0.6293, "step": 60 }, { "epoch": 0.08684863523573201, "grad_norm": 2.3419530391693115, "learning_rate": 1.425619834710744e-06, "loss": 0.6475, "step": 70 }, { "epoch": 0.09925558312655088, "grad_norm": 2.3448750972747803, "learning_rate": 1.632231404958678e-06, "loss": 0.6337, "step": 80 }, { "epoch": 0.11166253101736973, "grad_norm": 2.843895673751831, "learning_rate": 1.8388429752066117e-06, "loss": 0.6405, "step": 90 }, { "epoch": 0.12406947890818859, "grad_norm": 2.8064634799957275, "learning_rate": 2.0454545454545457e-06, "loss": 0.5887, "step": 100 }, { "epoch": 0.13647642679900746, "grad_norm": 3.651322603225708, "learning_rate": 2.2520661157024796e-06, "loss": 0.5977, "step": 110 }, { "epoch": 0.1488833746898263, "grad_norm": 2.239910125732422, "learning_rate": 2.4586776859504134e-06, "loss": 0.6064, "step": 120 }, { "epoch": 0.16129032258064516, "grad_norm": 2.256722927093506, "learning_rate": 2.6652892561983473e-06, "loss": 0.5678, "step": 130 }, { "epoch": 0.17369727047146402, "grad_norm": 2.6449544429779053, "learning_rate": 2.871900826446281e-06, "loss": 0.5649, "step": 140 }, { "epoch": 0.18610421836228289, "grad_norm": 2.2811496257781982, "learning_rate": 3.078512396694215e-06, "loss": 0.5514, "step": 150 }, { "epoch": 0.19851116625310175, "grad_norm": 2.6085822582244873, "learning_rate": 3.2851239669421493e-06, "loss": 0.5533, "step": 160 }, { "epoch": 0.2109181141439206, "grad_norm": 2.6738383769989014, "learning_rate": 3.491735537190083e-06, "loss": 0.5295, "step": 170 }, { "epoch": 0.22332506203473945, "grad_norm": 2.390183210372925, "learning_rate": 3.6983471074380165e-06, "loss": 0.4984, "step": 180 }, { "epoch": 0.23573200992555832, "grad_norm": 2.6387181282043457, "learning_rate": 3.904958677685951e-06, "loss": 0.5315, "step": 190 }, { "epoch": 0.24813895781637718, "grad_norm": 2.661820411682129, "learning_rate": 4.111570247933885e-06, "loss": 0.5101, "step": 200 }, { "epoch": 0.26054590570719605, "grad_norm": 2.504303455352783, "learning_rate": 4.3181818181818185e-06, "loss": 0.5528, "step": 210 }, { "epoch": 0.2729528535980149, "grad_norm": 2.5912747383117676, "learning_rate": 4.524793388429753e-06, "loss": 0.5005, "step": 220 }, { "epoch": 0.2853598014888337, "grad_norm": 2.588153839111328, "learning_rate": 4.731404958677686e-06, "loss": 0.5279, "step": 230 }, { "epoch": 0.2977667493796526, "grad_norm": 2.543455123901367, "learning_rate": 4.9380165289256205e-06, "loss": 0.5218, "step": 240 }, { "epoch": 0.31017369727047145, "grad_norm": 2.369999647140503, "learning_rate": 4.999872331322402e-06, "loss": 0.4881, "step": 250 }, { "epoch": 0.3225806451612903, "grad_norm": 2.2144715785980225, "learning_rate": 4.999247046740511e-06, "loss": 0.4947, "step": 260 }, { "epoch": 0.3349875930521092, "grad_norm": 2.442784547805786, "learning_rate": 4.998100827074778e-06, "loss": 0.5321, "step": 270 }, { "epoch": 0.34739454094292804, "grad_norm": 2.784367799758911, "learning_rate": 4.996433911239573e-06, "loss": 0.4967, "step": 280 }, { "epoch": 0.3598014888337469, "grad_norm": 2.43532133102417, "learning_rate": 4.994246646681518e-06, "loss": 0.5049, "step": 290 }, { "epoch": 0.37220843672456577, "grad_norm": 2.3138585090637207, "learning_rate": 4.991539489307062e-06, "loss": 0.4711, "step": 300 }, { "epoch": 0.38461538461538464, "grad_norm": 2.2641096115112305, "learning_rate": 4.988313003387454e-06, "loss": 0.473, "step": 310 }, { "epoch": 0.3970223325062035, "grad_norm": 2.277608633041382, "learning_rate": 4.984567861441129e-06, "loss": 0.4914, "step": 320 }, { "epoch": 0.4094292803970223, "grad_norm": 2.1489667892456055, "learning_rate": 4.980304844093531e-06, "loss": 0.4815, "step": 330 }, { "epoch": 0.4218362282878412, "grad_norm": 2.5077874660491943, "learning_rate": 4.975524839914399e-06, "loss": 0.4808, "step": 340 }, { "epoch": 0.43424317617866004, "grad_norm": 2.3492398262023926, "learning_rate": 4.970228845232561e-06, "loss": 0.4734, "step": 350 }, { "epoch": 0.4466501240694789, "grad_norm": 2.7925798892974854, "learning_rate": 4.9644179639282595e-06, "loss": 0.4483, "step": 360 }, { "epoch": 0.45905707196029777, "grad_norm": 2.23964786529541, "learning_rate": 4.958093407203059e-06, "loss": 0.4706, "step": 370 }, { "epoch": 0.47146401985111663, "grad_norm": 2.698669195175171, "learning_rate": 4.951256493327394e-06, "loss": 0.4986, "step": 380 }, { "epoch": 0.4838709677419355, "grad_norm": 2.4865877628326416, "learning_rate": 4.943908647365789e-06, "loss": 0.4485, "step": 390 }, { "epoch": 0.49627791563275436, "grad_norm": 2.3900320529937744, "learning_rate": 4.936051400879823e-06, "loss": 0.4834, "step": 400 }, { "epoch": 0.5086848635235732, "grad_norm": 2.1887104511260986, "learning_rate": 4.9276863916088944e-06, "loss": 0.4399, "step": 410 }, { "epoch": 0.5210918114143921, "grad_norm": 2.235128402709961, "learning_rate": 4.9188153631288584e-06, "loss": 0.4723, "step": 420 }, { "epoch": 0.533498759305211, "grad_norm": 2.149345874786377, "learning_rate": 4.9094401644886e-06, "loss": 0.4644, "step": 430 }, { "epoch": 0.5459057071960298, "grad_norm": 2.0289762020111084, "learning_rate": 4.899562749824624e-06, "loss": 0.4429, "step": 440 }, { "epoch": 0.5583126550868487, "grad_norm": 2.1282219886779785, "learning_rate": 4.889185177953743e-06, "loss": 0.497, "step": 450 }, { "epoch": 0.5707196029776674, "grad_norm": 2.247293472290039, "learning_rate": 4.878309611943939e-06, "loss": 0.446, "step": 460 }, { "epoch": 0.5831265508684863, "grad_norm": 2.298889398574829, "learning_rate": 4.86693831866351e-06, "loss": 0.4557, "step": 470 }, { "epoch": 0.5955334987593052, "grad_norm": 2.12593412399292, "learning_rate": 4.855073668308561e-06, "loss": 0.4739, "step": 480 }, { "epoch": 0.607940446650124, "grad_norm": 2.381096601486206, "learning_rate": 4.842718133908973e-06, "loss": 0.4683, "step": 490 }, { "epoch": 0.6203473945409429, "grad_norm": 2.2420785427093506, "learning_rate": 4.829874290812932e-06, "loss": 0.4804, "step": 500 }, { "epoch": 0.6327543424317618, "grad_norm": 2.4104809761047363, "learning_rate": 4.816544816150132e-06, "loss": 0.4511, "step": 510 }, { "epoch": 0.6451612903225806, "grad_norm": 2.349477529525757, "learning_rate": 4.802732488273762e-06, "loss": 0.4761, "step": 520 }, { "epoch": 0.6575682382133995, "grad_norm": 2.2981739044189453, "learning_rate": 4.788440186181393e-06, "loss": 0.442, "step": 530 }, { "epoch": 0.6699751861042184, "grad_norm": 2.232135772705078, "learning_rate": 4.773670888914891e-06, "loss": 0.49, "step": 540 }, { "epoch": 0.6823821339950372, "grad_norm": 2.2173194885253906, "learning_rate": 4.75842767493948e-06, "loss": 0.4547, "step": 550 }, { "epoch": 0.6947890818858561, "grad_norm": 2.1684892177581787, "learning_rate": 4.742713721502065e-06, "loss": 0.4341, "step": 560 }, { "epoch": 0.707196029776675, "grad_norm": 2.1500906944274902, "learning_rate": 4.726532303968986e-06, "loss": 0.4443, "step": 570 }, { "epoch": 0.7196029776674938, "grad_norm": 1.8363852500915527, "learning_rate": 4.709886795143307e-06, "loss": 0.4535, "step": 580 }, { "epoch": 0.7320099255583127, "grad_norm": 2.815446138381958, "learning_rate": 4.6927806645618034e-06, "loss": 0.4281, "step": 590 }, { "epoch": 0.7444168734491315, "grad_norm": 2.3070578575134277, "learning_rate": 4.675217477771779e-06, "loss": 0.4306, "step": 600 }, { "epoch": 0.7568238213399504, "grad_norm": 2.0180327892303467, "learning_rate": 4.657200895587874e-06, "loss": 0.4709, "step": 610 }, { "epoch": 0.7692307692307693, "grad_norm": 2.419917106628418, "learning_rate": 4.638734673329023e-06, "loss": 0.4568, "step": 620 }, { "epoch": 0.7816377171215881, "grad_norm": 2.152839183807373, "learning_rate": 4.6198226600357e-06, "loss": 0.465, "step": 630 }, { "epoch": 0.794044665012407, "grad_norm": 3.456455707550049, "learning_rate": 4.600468797667641e-06, "loss": 0.4267, "step": 640 }, { "epoch": 0.8064516129032258, "grad_norm": 2.165318250656128, "learning_rate": 4.580677120282197e-06, "loss": 0.4132, "step": 650 }, { "epoch": 0.8188585607940446, "grad_norm": 2.507446527481079, "learning_rate": 4.56045175319348e-06, "loss": 0.4406, "step": 660 }, { "epoch": 0.8312655086848635, "grad_norm": 2.179778814315796, "learning_rate": 4.539796912112505e-06, "loss": 0.4144, "step": 670 }, { "epoch": 0.8436724565756824, "grad_norm": 2.211622476577759, "learning_rate": 4.518716902268475e-06, "loss": 0.4507, "step": 680 }, { "epoch": 0.8560794044665012, "grad_norm": 2.1155405044555664, "learning_rate": 4.497216117511413e-06, "loss": 0.4471, "step": 690 }, { "epoch": 0.8684863523573201, "grad_norm": 1.896468162536621, "learning_rate": 4.475299039396324e-06, "loss": 0.4108, "step": 700 }, { "epoch": 0.8808933002481389, "grad_norm": 2.016505241394043, "learning_rate": 4.452970236249071e-06, "loss": 0.4497, "step": 710 }, { "epoch": 0.8933002481389578, "grad_norm": 2.395714282989502, "learning_rate": 4.4302343622141734e-06, "loss": 0.4339, "step": 720 }, { "epoch": 0.9057071960297767, "grad_norm": 2.3998799324035645, "learning_rate": 4.4070961562847044e-06, "loss": 0.4185, "step": 730 }, { "epoch": 0.9181141439205955, "grad_norm": 2.3228061199188232, "learning_rate": 4.3835604413145175e-06, "loss": 0.4522, "step": 740 }, { "epoch": 0.9305210918114144, "grad_norm": 2.172651529312134, "learning_rate": 4.3596321230129786e-06, "loss": 0.4482, "step": 750 }, { "epoch": 0.9429280397022333, "grad_norm": 2.0701658725738525, "learning_rate": 4.335316188922444e-06, "loss": 0.4104, "step": 760 }, { "epoch": 0.9553349875930521, "grad_norm": 2.334995985031128, "learning_rate": 4.3106177073786684e-06, "loss": 0.4583, "step": 770 }, { "epoch": 0.967741935483871, "grad_norm": 2.1355791091918945, "learning_rate": 4.285541826454374e-06, "loss": 0.4227, "step": 780 }, { "epoch": 0.9801488833746899, "grad_norm": 2.314973831176758, "learning_rate": 4.26009377288621e-06, "loss": 0.4289, "step": 790 }, { "epoch": 0.9925558312655087, "grad_norm": 2.586134910583496, "learning_rate": 4.234278850985305e-06, "loss": 0.4293, "step": 800 }, { "epoch": 1.0049627791563276, "grad_norm": 2.2796523571014404, "learning_rate": 4.208102441531648e-06, "loss": 0.3924, "step": 810 }, { "epoch": 1.0173697270471465, "grad_norm": 2.1317861080169678, "learning_rate": 4.181570000652547e-06, "loss": 0.3117, "step": 820 }, { "epoch": 1.0297766749379653, "grad_norm": 2.121368169784546, "learning_rate": 4.15468705868536e-06, "loss": 0.3011, "step": 830 }, { "epoch": 1.0421836228287842, "grad_norm": 2.055232286453247, "learning_rate": 4.127459219024778e-06, "loss": 0.3335, "step": 840 }, { "epoch": 1.054590570719603, "grad_norm": 2.703763723373413, "learning_rate": 4.099892156954861e-06, "loss": 0.3363, "step": 850 }, { "epoch": 1.066997518610422, "grad_norm": 2.2500298023223877, "learning_rate": 4.071991618466114e-06, "loss": 0.3421, "step": 860 }, { "epoch": 1.0794044665012408, "grad_norm": 2.4340980052948, "learning_rate": 4.043763419057797e-06, "loss": 0.3033, "step": 870 }, { "epoch": 1.0918114143920596, "grad_norm": 2.7019355297088623, "learning_rate": 4.015213442525771e-06, "loss": 0.3312, "step": 880 }, { "epoch": 1.1042183622828785, "grad_norm": 4.140330791473389, "learning_rate": 3.986347639736092e-06, "loss": 0.309, "step": 890 }, { "epoch": 1.1166253101736974, "grad_norm": 2.7328405380249023, "learning_rate": 3.957172027384635e-06, "loss": 0.3217, "step": 900 }, { "epoch": 1.129032258064516, "grad_norm": 2.3123362064361572, "learning_rate": 3.927692686742993e-06, "loss": 0.3435, "step": 910 }, { "epoch": 1.141439205955335, "grad_norm": 2.4278299808502197, "learning_rate": 3.897915762390912e-06, "loss": 0.3112, "step": 920 }, { "epoch": 1.1538461538461537, "grad_norm": 2.7734603881835938, "learning_rate": 3.867847460935542e-06, "loss": 0.3226, "step": 930 }, { "epoch": 1.1662531017369726, "grad_norm": 2.356139898300171, "learning_rate": 3.8374940497177435e-06, "loss": 0.3407, "step": 940 }, { "epoch": 1.1786600496277915, "grad_norm": 3.6035654544830322, "learning_rate": 3.806861855505748e-06, "loss": 0.3229, "step": 950 }, { "epoch": 1.1910669975186103, "grad_norm": 2.4229462146759033, "learning_rate": 3.7759572631764243e-06, "loss": 0.3283, "step": 960 }, { "epoch": 1.2034739454094292, "grad_norm": 2.470399856567383, "learning_rate": 3.7447867143844373e-06, "loss": 0.3262, "step": 970 }, { "epoch": 1.215880893300248, "grad_norm": 2.6044392585754395, "learning_rate": 3.7133567062195697e-06, "loss": 0.3003, "step": 980 }, { "epoch": 1.228287841191067, "grad_norm": 2.2043936252593994, "learning_rate": 3.6816737898524844e-06, "loss": 0.3192, "step": 990 }, { "epoch": 1.2406947890818858, "grad_norm": 2.577247381210327, "learning_rate": 3.649744569169229e-06, "loss": 0.34, "step": 1000 }, { "epoch": 1.2531017369727047, "grad_norm": 2.4202823638916016, "learning_rate": 3.617575699394732e-06, "loss": 0.3137, "step": 1010 }, { "epoch": 1.2655086848635235, "grad_norm": 2.666287899017334, "learning_rate": 3.5851738857056174e-06, "loss": 0.3207, "step": 1020 }, { "epoch": 1.2779156327543424, "grad_norm": 1.9252305030822754, "learning_rate": 3.552545881832594e-06, "loss": 0.3065, "step": 1030 }, { "epoch": 1.2903225806451613, "grad_norm": 2.2043473720550537, "learning_rate": 3.519698488652734e-06, "loss": 0.3375, "step": 1040 }, { "epoch": 1.3027295285359801, "grad_norm": 2.390878915786743, "learning_rate": 3.486638552771914e-06, "loss": 0.3185, "step": 1050 }, { "epoch": 1.315136476426799, "grad_norm": 3.049697160720825, "learning_rate": 3.4533729650977344e-06, "loss": 0.3169, "step": 1060 }, { "epoch": 1.3275434243176178, "grad_norm": 2.5571250915527344, "learning_rate": 3.4199086594031998e-06, "loss": 0.3281, "step": 1070 }, { "epoch": 1.3399503722084367, "grad_norm": 2.283221960067749, "learning_rate": 3.386252610881465e-06, "loss": 0.323, "step": 1080 }, { "epoch": 1.3523573200992556, "grad_norm": 2.4951066970825195, "learning_rate": 3.3524118346919486e-06, "loss": 0.305, "step": 1090 }, { "epoch": 1.3647642679900744, "grad_norm": 2.9804282188415527, "learning_rate": 3.318393384498114e-06, "loss": 0.3264, "step": 1100 }, { "epoch": 1.3771712158808933, "grad_norm": 2.51991868019104, "learning_rate": 3.2842043509972294e-06, "loss": 0.3363, "step": 1110 }, { "epoch": 1.3895781637717122, "grad_norm": 2.5440149307250977, "learning_rate": 3.2498518604424005e-06, "loss": 0.3299, "step": 1120 }, { "epoch": 1.401985111662531, "grad_norm": 2.374427318572998, "learning_rate": 3.215343073157204e-06, "loss": 0.3441, "step": 1130 }, { "epoch": 1.41439205955335, "grad_norm": 2.6223983764648438, "learning_rate": 3.180685182043205e-06, "loss": 0.3226, "step": 1140 }, { "epoch": 1.4267990074441688, "grad_norm": 2.9452157020568848, "learning_rate": 3.1458854110806976e-06, "loss": 0.3203, "step": 1150 }, { "epoch": 1.4392059553349876, "grad_norm": 2.3863351345062256, "learning_rate": 3.1109510138229565e-06, "loss": 0.3153, "step": 1160 }, { "epoch": 1.4516129032258065, "grad_norm": 2.2827560901641846, "learning_rate": 3.0758892718843352e-06, "loss": 0.324, "step": 1170 }, { "epoch": 1.4640198511166254, "grad_norm": 2.419977903366089, "learning_rate": 3.0407074934225038e-06, "loss": 0.3191, "step": 1180 }, { "epoch": 1.4764267990074442, "grad_norm": 2.53828763961792, "learning_rate": 3.005413011615165e-06, "loss": 0.3297, "step": 1190 }, { "epoch": 1.488833746898263, "grad_norm": 2.3521668910980225, "learning_rate": 2.9700131831315425e-06, "loss": 0.3158, "step": 1200 }, { "epoch": 1.501240694789082, "grad_norm": 2.2729012966156006, "learning_rate": 2.9345153865989918e-06, "loss": 0.3018, "step": 1210 }, { "epoch": 1.5136476426799006, "grad_norm": 2.538878917694092, "learning_rate": 2.898927021065011e-06, "loss": 0.3086, "step": 1220 }, { "epoch": 1.5260545905707197, "grad_norm": 2.501476287841797, "learning_rate": 2.8632555044550152e-06, "loss": 0.324, "step": 1230 }, { "epoch": 1.5384615384615383, "grad_norm": 2.6243369579315186, "learning_rate": 2.8275082720261623e-06, "loss": 0.3245, "step": 1240 }, { "epoch": 1.5508684863523574, "grad_norm": 2.3413476943969727, "learning_rate": 2.791692774817576e-06, "loss": 0.3059, "step": 1250 }, { "epoch": 1.563275434243176, "grad_norm": 3.795300245285034, "learning_rate": 2.75581647809727e-06, "loss": 0.3064, "step": 1260 }, { "epoch": 1.5756823821339951, "grad_norm": 2.2006099224090576, "learning_rate": 2.7198868598061177e-06, "loss": 0.2972, "step": 1270 }, { "epoch": 1.5880893300248138, "grad_norm": 2.4078879356384277, "learning_rate": 2.683911408999169e-06, "loss": 0.2889, "step": 1280 }, { "epoch": 1.6004962779156329, "grad_norm": 2.237532615661621, "learning_rate": 2.6478976242846576e-06, "loss": 0.3269, "step": 1290 }, { "epoch": 1.6129032258064515, "grad_norm": 2.452491044998169, "learning_rate": 2.6118530122610138e-06, "loss": 0.3565, "step": 1300 }, { "epoch": 1.6253101736972706, "grad_norm": 2.4190964698791504, "learning_rate": 2.575785085952216e-06, "loss": 0.3347, "step": 1310 }, { "epoch": 1.6377171215880892, "grad_norm": 2.40696120262146, "learning_rate": 2.539701363241795e-06, "loss": 0.3318, "step": 1320 }, { "epoch": 1.6501240694789083, "grad_norm": 2.3521053791046143, "learning_rate": 2.503609365305835e-06, "loss": 0.3103, "step": 1330 }, { "epoch": 1.662531017369727, "grad_norm": 4.692817211151123, "learning_rate": 2.4675166150452814e-06, "loss": 0.3209, "step": 1340 }, { "epoch": 1.674937965260546, "grad_norm": 2.256093740463257, "learning_rate": 2.4314306355178924e-06, "loss": 0.2967, "step": 1350 }, { "epoch": 1.6873449131513647, "grad_norm": 2.3067562580108643, "learning_rate": 2.3953589483701556e-06, "loss": 0.3138, "step": 1360 }, { "epoch": 1.6997518610421838, "grad_norm": 2.066192626953125, "learning_rate": 2.3593090722694995e-06, "loss": 0.2999, "step": 1370 }, { "epoch": 1.7121588089330024, "grad_norm": 2.263817548751831, "learning_rate": 2.3232885213371297e-06, "loss": 0.3176, "step": 1380 }, { "epoch": 1.7245657568238213, "grad_norm": 2.7961695194244385, "learning_rate": 2.2873048035818043e-06, "loss": 0.3349, "step": 1390 }, { "epoch": 1.7369727047146402, "grad_norm": 2.062469244003296, "learning_rate": 2.251365419334895e-06, "loss": 0.3192, "step": 1400 }, { "epoch": 1.749379652605459, "grad_norm": 2.6666066646575928, "learning_rate": 2.2154778596870365e-06, "loss": 0.3112, "step": 1410 }, { "epoch": 1.7617866004962779, "grad_norm": 2.921236276626587, "learning_rate": 2.179649604926708e-06, "loss": 0.3108, "step": 1420 }, { "epoch": 1.7741935483870968, "grad_norm": 2.4960734844207764, "learning_rate": 2.14388812298107e-06, "loss": 0.294, "step": 1430 }, { "epoch": 1.7866004962779156, "grad_norm": 2.4389822483062744, "learning_rate": 2.108200867859369e-06, "loss": 0.3064, "step": 1440 }, { "epoch": 1.7990074441687345, "grad_norm": 2.7640597820281982, "learning_rate": 2.072595278099247e-06, "loss": 0.3108, "step": 1450 }, { "epoch": 1.8114143920595533, "grad_norm": 2.5597686767578125, "learning_rate": 2.037078775216283e-06, "loss": 0.3069, "step": 1460 }, { "epoch": 1.8238213399503722, "grad_norm": 2.3862650394439697, "learning_rate": 2.0016587621570682e-06, "loss": 0.3183, "step": 1470 }, { "epoch": 1.836228287841191, "grad_norm": 2.220792293548584, "learning_rate": 1.966342621756163e-06, "loss": 0.2927, "step": 1480 }, { "epoch": 1.84863523573201, "grad_norm": 2.2265381813049316, "learning_rate": 1.931137715197242e-06, "loss": 0.2974, "step": 1490 }, { "epoch": 1.8610421836228288, "grad_norm": 2.4014625549316406, "learning_rate": 1.8960513804787557e-06, "loss": 0.3201, "step": 1500 }, { "epoch": 1.8734491315136477, "grad_norm": 2.3966963291168213, "learning_rate": 1.861090930884412e-06, "loss": 0.3117, "step": 1510 }, { "epoch": 1.8858560794044665, "grad_norm": 2.302567481994629, "learning_rate": 1.8262636534588316e-06, "loss": 0.3119, "step": 1520 }, { "epoch": 1.8982630272952854, "grad_norm": 2.2789454460144043, "learning_rate": 1.7915768074886497e-06, "loss": 0.3024, "step": 1530 }, { "epoch": 1.9106699751861043, "grad_norm": 2.2109439373016357, "learning_rate": 1.7570376229894164e-06, "loss": 0.3069, "step": 1540 }, { "epoch": 1.9230769230769231, "grad_norm": 2.5564117431640625, "learning_rate": 1.7226532991985976e-06, "loss": 0.3019, "step": 1550 }, { "epoch": 1.935483870967742, "grad_norm": 2.3430604934692383, "learning_rate": 1.688431003074985e-06, "loss": 0.3102, "step": 1560 }, { "epoch": 1.9478908188585606, "grad_norm": 2.3001058101654053, "learning_rate": 1.654377867804841e-06, "loss": 0.3191, "step": 1570 }, { "epoch": 1.9602977667493797, "grad_norm": 2.4590320587158203, "learning_rate": 1.6205009913150815e-06, "loss": 0.2944, "step": 1580 }, { "epoch": 1.9727047146401984, "grad_norm": 2.215261697769165, "learning_rate": 1.5868074347937993e-06, "loss": 0.3052, "step": 1590 }, { "epoch": 1.9851116625310175, "grad_norm": 3.3200316429138184, "learning_rate": 1.553304221218462e-06, "loss": 0.341, "step": 1600 }, { "epoch": 1.997518610421836, "grad_norm": 2.3766589164733887, "learning_rate": 1.5199983338920594e-06, "loss": 0.2897, "step": 1610 }, { "epoch": 2.009925558312655, "grad_norm": 1.96999990940094, "learning_rate": 1.4868967149875257e-06, "loss": 0.2204, "step": 1620 }, { "epoch": 2.022332506203474, "grad_norm": 2.700394868850708, "learning_rate": 1.4540062641007383e-06, "loss": 0.1954, "step": 1630 }, { "epoch": 2.034739454094293, "grad_norm": 2.6681501865386963, "learning_rate": 1.421333836812387e-06, "loss": 0.1918, "step": 1640 }, { "epoch": 2.0471464019851116, "grad_norm": 2.2484800815582275, "learning_rate": 1.3888862432590167e-06, "loss": 0.1992, "step": 1650 }, { "epoch": 2.0595533498759306, "grad_norm": 2.1768691539764404, "learning_rate": 1.3566702467135445e-06, "loss": 0.1999, "step": 1660 }, { "epoch": 2.0719602977667493, "grad_norm": 2.409804344177246, "learning_rate": 1.3246925621755496e-06, "loss": 0.1907, "step": 1670 }, { "epoch": 2.0843672456575684, "grad_norm": 2.167759656906128, "learning_rate": 1.2929598549716122e-06, "loss": 0.1773, "step": 1680 }, { "epoch": 2.096774193548387, "grad_norm": 2.289466619491577, "learning_rate": 1.2614787393660215e-06, "loss": 0.1966, "step": 1690 }, { "epoch": 2.109181141439206, "grad_norm": 5.157329082489014, "learning_rate": 1.2302557771821154e-06, "loss": 0.1983, "step": 1700 }, { "epoch": 2.1215880893300247, "grad_norm": 2.607748508453369, "learning_rate": 1.199297476434553e-06, "loss": 0.2023, "step": 1710 }, { "epoch": 2.133995037220844, "grad_norm": 2.6827666759490967, "learning_rate": 1.168610289972813e-06, "loss": 0.1792, "step": 1720 }, { "epoch": 2.1464019851116625, "grad_norm": 2.842087745666504, "learning_rate": 1.138200614136172e-06, "loss": 0.2037, "step": 1730 }, { "epoch": 2.1588089330024816, "grad_norm": 2.7642550468444824, "learning_rate": 1.1080747874204809e-06, "loss": 0.2015, "step": 1740 }, { "epoch": 2.1712158808933, "grad_norm": 2.5028483867645264, "learning_rate": 1.0782390891569822e-06, "loss": 0.1911, "step": 1750 }, { "epoch": 2.1836228287841193, "grad_norm": 2.524568796157837, "learning_rate": 1.0486997382034695e-06, "loss": 0.1879, "step": 1760 }, { "epoch": 2.196029776674938, "grad_norm": 2.7087483406066895, "learning_rate": 1.0194628916480504e-06, "loss": 0.1836, "step": 1770 }, { "epoch": 2.208436724565757, "grad_norm": 2.9708335399627686, "learning_rate": 9.905346435257784e-07, "loss": 0.2179, "step": 1780 }, { "epoch": 2.2208436724565757, "grad_norm": 2.7953109741210938, "learning_rate": 9.619210235484333e-07, "loss": 0.2012, "step": 1790 }, { "epoch": 2.2332506203473947, "grad_norm": 2.6220216751098633, "learning_rate": 9.336279958477096e-07, "loss": 0.1697, "step": 1800 }, { "epoch": 2.2456575682382134, "grad_norm": 2.4170567989349365, "learning_rate": 9.056614577320702e-07, "loss": 0.2072, "step": 1810 }, { "epoch": 2.258064516129032, "grad_norm": 2.6579396724700928, "learning_rate": 8.780272384575289e-07, "loss": 0.1946, "step": 1820 }, { "epoch": 2.270471464019851, "grad_norm": 2.900634765625, "learning_rate": 8.507310980126188e-07, "loss": 0.1857, "step": 1830 }, { "epoch": 2.28287841191067, "grad_norm": 2.5147194862365723, "learning_rate": 8.237787259178037e-07, "loss": 0.1839, "step": 1840 }, { "epoch": 2.295285359801489, "grad_norm": 2.861794948577881, "learning_rate": 7.971757400395652e-07, "loss": 0.2081, "step": 1850 }, { "epoch": 2.3076923076923075, "grad_norm": 2.2229387760162354, "learning_rate": 7.709276854194392e-07, "loss": 0.1819, "step": 1860 }, { "epoch": 2.3200992555831266, "grad_norm": 2.687779664993286, "learning_rate": 7.450400331182198e-07, "loss": 0.2019, "step": 1870 }, { "epoch": 2.332506203473945, "grad_norm": 2.5793938636779785, "learning_rate": 7.19518179075591e-07, "loss": 0.2024, "step": 1880 }, { "epoch": 2.3449131513647643, "grad_norm": 3.0393989086151123, "learning_rate": 6.943674429854172e-07, "loss": 0.1985, "step": 1890 }, { "epoch": 2.357320099255583, "grad_norm": 2.7549092769622803, "learning_rate": 6.695930671869175e-07, "loss": 0.1992, "step": 1900 }, { "epoch": 2.369727047146402, "grad_norm": 2.1820151805877686, "learning_rate": 6.452002155719725e-07, "loss": 0.1749, "step": 1910 }, { "epoch": 2.3821339950372207, "grad_norm": 2.836665630340576, "learning_rate": 6.211939725087806e-07, "loss": 0.2067, "step": 1920 }, { "epoch": 2.3945409429280398, "grad_norm": 3.459502935409546, "learning_rate": 5.975793417820841e-07, "loss": 0.1892, "step": 1930 }, { "epoch": 2.4069478908188584, "grad_norm": 2.6067864894866943, "learning_rate": 5.743612455502016e-07, "loss": 0.1897, "step": 1940 }, { "epoch": 2.4193548387096775, "grad_norm": 2.528135061264038, "learning_rate": 5.515445233190636e-07, "loss": 0.1897, "step": 1950 }, { "epoch": 2.431761786600496, "grad_norm": 3.0083165168762207, "learning_rate": 5.291339309334845e-07, "loss": 0.1767, "step": 1960 }, { "epoch": 2.444168734491315, "grad_norm": 2.441368341445923, "learning_rate": 5.071341395858703e-07, "loss": 0.1929, "step": 1970 }, { "epoch": 2.456575682382134, "grad_norm": 2.6075940132141113, "learning_rate": 4.855497348425686e-07, "loss": 0.1922, "step": 1980 }, { "epoch": 2.468982630272953, "grad_norm": 2.6798899173736572, "learning_rate": 4.6438521568806625e-07, "loss": 0.1805, "step": 1990 }, { "epoch": 2.4813895781637716, "grad_norm": 2.541343927383423, "learning_rate": 4.436449935872378e-07, "loss": 0.2076, "step": 2000 }, { "epoch": 2.4937965260545907, "grad_norm": 2.33888578414917, "learning_rate": 4.2333339156583467e-07, "loss": 0.1791, "step": 2010 }, { "epoch": 2.5062034739454093, "grad_norm": 2.571502208709717, "learning_rate": 4.034546433094036e-07, "loss": 0.1955, "step": 2020 }, { "epoch": 2.5186104218362284, "grad_norm": 2.687593936920166, "learning_rate": 3.8401289228083395e-07, "loss": 0.2005, "step": 2030 }, { "epoch": 2.531017369727047, "grad_norm": 2.73337721824646, "learning_rate": 3.6501219085670724e-07, "loss": 0.1935, "step": 2040 }, { "epoch": 2.543424317617866, "grad_norm": 2.884833812713623, "learning_rate": 3.4645649948263085e-07, "loss": 0.1977, "step": 2050 }, { "epoch": 2.555831265508685, "grad_norm": 2.921278238296509, "learning_rate": 3.2834968584773754e-07, "loss": 0.1851, "step": 2060 }, { "epoch": 2.568238213399504, "grad_norm": 2.7360055446624756, "learning_rate": 3.106955240785153e-07, "loss": 0.2092, "step": 2070 }, { "epoch": 2.5806451612903225, "grad_norm": 2.3619930744171143, "learning_rate": 2.9349769395214e-07, "loss": 0.1844, "step": 2080 }, { "epoch": 2.5930521091811416, "grad_norm": 2.5118324756622314, "learning_rate": 2.767597801294772e-07, "loss": 0.1896, "step": 2090 }, { "epoch": 2.6054590570719602, "grad_norm": 2.856184720993042, "learning_rate": 2.604852714079023e-07, "loss": 0.1935, "step": 2100 }, { "epoch": 2.617866004962779, "grad_norm": 2.7495625019073486, "learning_rate": 2.4467755999411204e-07, "loss": 0.2018, "step": 2110 }, { "epoch": 2.630272952853598, "grad_norm": 2.666712999343872, "learning_rate": 2.2933994079705896e-07, "loss": 0.1674, "step": 2120 }, { "epoch": 2.642679900744417, "grad_norm": 2.8785924911499023, "learning_rate": 2.144756107411733e-07, "loss": 0.1939, "step": 2130 }, { "epoch": 2.6550868486352357, "grad_norm": 3.0495386123657227, "learning_rate": 2.0008766810000801e-07, "loss": 0.2007, "step": 2140 }, { "epoch": 2.6674937965260543, "grad_norm": 6.222862720489502, "learning_rate": 1.861791118504408e-07, "loss": 0.1887, "step": 2150 }, { "epoch": 2.6799007444168734, "grad_norm": 2.5191469192504883, "learning_rate": 1.7275284104757844e-07, "loss": 0.1901, "step": 2160 }, { "epoch": 2.6923076923076925, "grad_norm": 2.9002139568328857, "learning_rate": 1.598116542204889e-07, "loss": 0.2007, "step": 2170 }, { "epoch": 2.704714640198511, "grad_norm": 3.201275587081909, "learning_rate": 1.4735824878888277e-07, "loss": 0.1886, "step": 2180 }, { "epoch": 2.71712158808933, "grad_norm": 2.263383388519287, "learning_rate": 1.353952205008713e-07, "loss": 0.1936, "step": 2190 }, { "epoch": 2.729528535980149, "grad_norm": 3.259072780609131, "learning_rate": 1.2392506289191837e-07, "loss": 0.1842, "step": 2200 }, { "epoch": 2.741935483870968, "grad_norm": 2.3213393688201904, "learning_rate": 1.1295016676509618e-07, "loss": 0.1853, "step": 2210 }, { "epoch": 2.7543424317617866, "grad_norm": 2.5578935146331787, "learning_rate": 1.0247281969275131e-07, "loss": 0.1712, "step": 2220 }, { "epoch": 2.7667493796526053, "grad_norm": 2.6057956218719482, "learning_rate": 9.249520553969465e-08, "loss": 0.2043, "step": 2230 }, { "epoch": 2.7791563275434243, "grad_norm": 2.5771260261535645, "learning_rate": 8.301940400799818e-08, "loss": 0.1945, "step": 2240 }, { "epoch": 2.7915632754342434, "grad_norm": 2.859959602355957, "learning_rate": 7.404739020351381e-08, "loss": 0.1986, "step": 2250 }, { "epoch": 2.803970223325062, "grad_norm": 3.0193612575531006, "learning_rate": 6.558103422418555e-08, "loss": 0.1956, "step": 2260 }, { "epoch": 2.8163771712158807, "grad_norm": 3.3084332942962646, "learning_rate": 5.762210077025293e-08, "loss": 0.2055, "step": 2270 }, { "epoch": 2.8287841191067, "grad_norm": 2.5870261192321777, "learning_rate": 5.017224877642196e-08, "loss": 0.186, "step": 2280 }, { "epoch": 2.8411910669975184, "grad_norm": 2.3661649227142334, "learning_rate": 4.323303106608362e-08, "loss": 0.1905, "step": 2290 }, { "epoch": 2.8535980148883375, "grad_norm": 2.7544636726379395, "learning_rate": 3.680589402764695e-08, "loss": 0.1856, "step": 2300 }, { "epoch": 2.866004962779156, "grad_norm": 2.5989158153533936, "learning_rate": 3.089217731305882e-08, "loss": 0.1795, "step": 2310 }, { "epoch": 2.8784119106699753, "grad_norm": 2.5642173290252686, "learning_rate": 2.5493113558571203e-08, "loss": 0.1853, "step": 2320 }, { "epoch": 2.890818858560794, "grad_norm": 2.682210922241211, "learning_rate": 2.0609828127814425e-08, "loss": 0.1945, "step": 2330 }, { "epoch": 2.903225806451613, "grad_norm": 2.878221273422241, "learning_rate": 1.624333887723012e-08, "loss": 0.226, "step": 2340 }, { "epoch": 2.9156327543424316, "grad_norm": 3.1238839626312256, "learning_rate": 1.2394555943911757e-08, "loss": 0.1975, "step": 2350 }, { "epoch": 2.9280397022332507, "grad_norm": 2.5719997882843018, "learning_rate": 9.0642815559e-09, "loss": 0.1831, "step": 2360 }, { "epoch": 2.9404466501240694, "grad_norm": 2.789083480834961, "learning_rate": 6.253209864966747e-09, "loss": 0.1752, "step": 2370 }, { "epoch": 2.9528535980148884, "grad_norm": 2.6296520233154297, "learning_rate": 3.9619268019305825e-09, "loss": 0.1894, "step": 2380 }, { "epoch": 2.965260545905707, "grad_norm": 2.849618434906006, "learning_rate": 2.190909954525866e-09, "loss": 0.1848, "step": 2390 }, { "epoch": 2.977667493796526, "grad_norm": 2.884972333908081, "learning_rate": 9.405284678556948e-10, "loss": 0.1932, "step": 2400 }, { "epoch": 2.990074441687345, "grad_norm": 2.356898307800293, "learning_rate": 2.1104296745011466e-10, "loss": 0.1858, "step": 2410 }, { "epoch": 3.0, "step": 2418, "total_flos": 2.7690448659152896e+18, "train_loss": 0.3387052197412975, "train_runtime": 130620.9048, "train_samples_per_second": 0.148, "train_steps_per_second": 0.019 } ], "logging_steps": 10, "max_steps": 2418, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.7690448659152896e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }