{ "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": 24.380937576293945, "learning_rate": 1.8595041322314052e-07, "loss": 1.1434167861938476, "step": 10 }, { "epoch": 0.02481389578163772, "grad_norm": 21.075366973876953, "learning_rate": 3.925619834710744e-07, "loss": 1.0735555648803712, "step": 20 }, { "epoch": 0.03722084367245657, "grad_norm": 16.02638053894043, "learning_rate": 5.991735537190084e-07, "loss": 0.9607119560241699, "step": 30 }, { "epoch": 0.04962779156327544, "grad_norm": 10.198869705200195, "learning_rate": 8.057851239669421e-07, "loss": 0.8850795745849609, "step": 40 }, { "epoch": 0.062034739454094295, "grad_norm": 3.556870222091675, "learning_rate": 1.012396694214876e-06, "loss": 0.718876838684082, "step": 50 }, { "epoch": 0.07444168734491315, "grad_norm": 4.056130886077881, "learning_rate": 1.21900826446281e-06, "loss": 0.6400353908538818, "step": 60 }, { "epoch": 0.08684863523573201, "grad_norm": 3.1343917846679688, "learning_rate": 1.425619834710744e-06, "loss": 0.6471079826354981, "step": 70 }, { "epoch": 0.09925558312655088, "grad_norm": 3.1576831340789795, "learning_rate": 1.632231404958678e-06, "loss": 0.6312197685241699, "step": 80 }, { "epoch": 0.11166253101736973, "grad_norm": 3.7458317279815674, "learning_rate": 1.8388429752066117e-06, "loss": 0.6425768375396729, "step": 90 }, { "epoch": 0.12406947890818859, "grad_norm": 3.5856683254241943, "learning_rate": 2.0454545454545457e-06, "loss": 0.5865562438964844, "step": 100 }, { "epoch": 0.13647642679900746, "grad_norm": 3.186936616897583, "learning_rate": 2.2520661157024796e-06, "loss": 0.5968480110168457, "step": 110 }, { "epoch": 0.1488833746898263, "grad_norm": 2.963216781616211, "learning_rate": 2.4586776859504134e-06, "loss": 0.6055496215820313, "step": 120 }, { "epoch": 0.16129032258064516, "grad_norm": 3.0101115703582764, "learning_rate": 2.6652892561983473e-06, "loss": 0.5692682266235352, "step": 130 }, { "epoch": 0.17369727047146402, "grad_norm": 2.968893527984619, "learning_rate": 2.871900826446281e-06, "loss": 0.5657201290130616, "step": 140 }, { "epoch": 0.18610421836228289, "grad_norm": 3.103032112121582, "learning_rate": 3.078512396694215e-06, "loss": 0.5565766334533692, "step": 150 }, { "epoch": 0.19851116625310175, "grad_norm": 3.6906442642211914, "learning_rate": 3.2851239669421493e-06, "loss": 0.5623440742492676, "step": 160 }, { "epoch": 0.2109181141439206, "grad_norm": 3.6191394329071045, "learning_rate": 3.491735537190083e-06, "loss": 0.5390286445617676, "step": 170 }, { "epoch": 0.22332506203473945, "grad_norm": 3.119192600250244, "learning_rate": 3.6983471074380165e-06, "loss": 0.504794979095459, "step": 180 }, { "epoch": 0.23573200992555832, "grad_norm": 3.5379598140716553, "learning_rate": 3.904958677685951e-06, "loss": 0.5398801326751709, "step": 190 }, { "epoch": 0.24813895781637718, "grad_norm": 3.455927848815918, "learning_rate": 4.111570247933885e-06, "loss": 0.5164627075195313, "step": 200 }, { "epoch": 0.26054590570719605, "grad_norm": 3.3440027236938477, "learning_rate": 4.3181818181818185e-06, "loss": 0.5611258506774902, "step": 210 }, { "epoch": 0.2729528535980149, "grad_norm": 3.941814661026001, "learning_rate": 4.524793388429753e-06, "loss": 0.5151082038879394, "step": 220 }, { "epoch": 0.2853598014888337, "grad_norm": 3.3939054012298584, "learning_rate": 4.731404958677686e-06, "loss": 0.5357322216033935, "step": 230 }, { "epoch": 0.2977667493796526, "grad_norm": 3.399260997772217, "learning_rate": 4.9380165289256205e-06, "loss": 0.5303369998931885, "step": 240 }, { "epoch": 0.31017369727047145, "grad_norm": 3.109227180480957, "learning_rate": 4.999872331322402e-06, "loss": 0.49518985748291017, "step": 250 }, { "epoch": 0.3225806451612903, "grad_norm": 3.147308588027954, "learning_rate": 4.999247046740511e-06, "loss": 0.505528736114502, "step": 260 }, { "epoch": 0.3349875930521092, "grad_norm": 2.949301242828369, "learning_rate": 4.998100827074778e-06, "loss": 0.542401123046875, "step": 270 }, { "epoch": 0.34739454094292804, "grad_norm": 3.650075912475586, "learning_rate": 4.996433911239573e-06, "loss": 0.511073637008667, "step": 280 }, { "epoch": 0.3598014888337469, "grad_norm": 3.273531675338745, "learning_rate": 4.994246646681518e-06, "loss": 0.5162837982177735, "step": 290 }, { "epoch": 0.37220843672456577, "grad_norm": 3.32936954498291, "learning_rate": 4.991539489307062e-06, "loss": 0.4840500831604004, "step": 300 }, { "epoch": 0.38461538461538464, "grad_norm": 2.9847359657287598, "learning_rate": 4.988313003387454e-06, "loss": 0.48565964698791503, "step": 310 }, { "epoch": 0.3970223325062035, "grad_norm": 3.2663910388946533, "learning_rate": 4.984567861441129e-06, "loss": 0.5017996788024902, "step": 320 }, { "epoch": 0.4094292803970223, "grad_norm": 2.7149908542633057, "learning_rate": 4.980304844093531e-06, "loss": 0.4949507713317871, "step": 330 }, { "epoch": 0.4218362282878412, "grad_norm": 3.2583069801330566, "learning_rate": 4.975524839914399e-06, "loss": 0.4920314311981201, "step": 340 }, { "epoch": 0.43424317617866004, "grad_norm": 3.2360751628875732, "learning_rate": 4.970228845232561e-06, "loss": 0.4833060264587402, "step": 350 }, { "epoch": 0.4466501240694789, "grad_norm": 3.0809836387634277, "learning_rate": 4.9644179639282595e-06, "loss": 0.4611049652099609, "step": 360 }, { "epoch": 0.45905707196029777, "grad_norm": 2.903007984161377, "learning_rate": 4.958093407203059e-06, "loss": 0.4815668106079102, "step": 370 }, { "epoch": 0.47146401985111663, "grad_norm": 3.1230084896087646, "learning_rate": 4.951256493327394e-06, "loss": 0.5097352981567382, "step": 380 }, { "epoch": 0.4838709677419355, "grad_norm": 3.1644937992095947, "learning_rate": 4.943908647365789e-06, "loss": 0.46744871139526367, "step": 390 }, { "epoch": 0.49627791563275436, "grad_norm": 3.0167317390441895, "learning_rate": 4.936051400879823e-06, "loss": 0.49645652770996096, "step": 400 }, { "epoch": 0.5086848635235732, "grad_norm": 3.1851320266723633, "learning_rate": 4.9276863916088944e-06, "loss": 0.45388307571411135, "step": 410 }, { "epoch": 0.5210918114143921, "grad_norm": 3.688347578048706, "learning_rate": 4.9188153631288584e-06, "loss": 0.48491249084472654, "step": 420 }, { "epoch": 0.533498759305211, "grad_norm": 2.895963668823242, "learning_rate": 4.9094401644886e-06, "loss": 0.48116121292114256, "step": 430 }, { "epoch": 0.5459057071960298, "grad_norm": 2.6067240238189697, "learning_rate": 4.899562749824624e-06, "loss": 0.45473780632019045, "step": 440 }, { "epoch": 0.5583126550868487, "grad_norm": 2.9146952629089355, "learning_rate": 4.889185177953743e-06, "loss": 0.5124542236328125, "step": 450 }, { "epoch": 0.5707196029776674, "grad_norm": 3.009894847869873, "learning_rate": 4.878309611943939e-06, "loss": 0.4542418956756592, "step": 460 }, { "epoch": 0.5831265508684863, "grad_norm": 2.952033042907715, "learning_rate": 4.86693831866351e-06, "loss": 0.4757439136505127, "step": 470 }, { "epoch": 0.5955334987593052, "grad_norm": 2.9270098209381104, "learning_rate": 4.855073668308561e-06, "loss": 0.48748092651367186, "step": 480 }, { "epoch": 0.607940446650124, "grad_norm": 2.9587056636810303, "learning_rate": 4.842718133908973e-06, "loss": 0.48392572402954104, "step": 490 }, { "epoch": 0.6203473945409429, "grad_norm": 2.895169734954834, "learning_rate": 4.829874290812932e-06, "loss": 0.49219765663146975, "step": 500 }, { "epoch": 0.6327543424317618, "grad_norm": 2.6126275062561035, "learning_rate": 4.816544816150132e-06, "loss": 0.46747660636901855, "step": 510 }, { "epoch": 0.6451612903225806, "grad_norm": 2.7628698348999023, "learning_rate": 4.802732488273762e-06, "loss": 0.4878196716308594, "step": 520 }, { "epoch": 0.6575682382133995, "grad_norm": 2.8378942012786865, "learning_rate": 4.788440186181393e-06, "loss": 0.4586039066314697, "step": 530 }, { "epoch": 0.6699751861042184, "grad_norm": 2.957749605178833, "learning_rate": 4.773670888914891e-06, "loss": 0.5078807353973389, "step": 540 }, { "epoch": 0.6823821339950372, "grad_norm": 3.1145918369293213, "learning_rate": 4.75842767493948e-06, "loss": 0.4683982372283936, "step": 550 }, { "epoch": 0.6947890818858561, "grad_norm": 2.674837827682495, "learning_rate": 4.742713721502065e-06, "loss": 0.45024881362915037, "step": 560 }, { "epoch": 0.707196029776675, "grad_norm": 3.1005373001098633, "learning_rate": 4.726532303968986e-06, "loss": 0.45893230438232424, "step": 570 }, { "epoch": 0.7196029776674938, "grad_norm": 2.7729763984680176, "learning_rate": 4.709886795143307e-06, "loss": 0.4667107582092285, "step": 580 }, { "epoch": 0.7320099255583127, "grad_norm": 4.1112060546875, "learning_rate": 4.6927806645618034e-06, "loss": 0.43797926902770995, "step": 590 }, { "epoch": 0.7444168734491315, "grad_norm": 3.006535291671753, "learning_rate": 4.675217477771779e-06, "loss": 0.4455252647399902, "step": 600 }, { "epoch": 0.7568238213399504, "grad_norm": 2.7127737998962402, "learning_rate": 4.657200895587874e-06, "loss": 0.48641119003295896, "step": 610 }, { "epoch": 0.7692307692307693, "grad_norm": 3.1489853858947754, "learning_rate": 4.638734673329023e-06, "loss": 0.4687007427215576, "step": 620 }, { "epoch": 0.7816377171215881, "grad_norm": 2.6937718391418457, "learning_rate": 4.6198226600357e-06, "loss": 0.48453760147094727, "step": 630 }, { "epoch": 0.794044665012407, "grad_norm": 3.03733229637146, "learning_rate": 4.600468797667641e-06, "loss": 0.44130840301513674, "step": 640 }, { "epoch": 0.8064516129032258, "grad_norm": 2.9481587409973145, "learning_rate": 4.580677120282197e-06, "loss": 0.42711877822875977, "step": 650 }, { "epoch": 0.8188585607940446, "grad_norm": 2.9542925357818604, "learning_rate": 4.56045175319348e-06, "loss": 0.4542987823486328, "step": 660 }, { "epoch": 0.8312655086848635, "grad_norm": 2.777961492538452, "learning_rate": 4.539796912112505e-06, "loss": 0.42932806015014646, "step": 670 }, { "epoch": 0.8436724565756824, "grad_norm": 3.0970194339752197, "learning_rate": 4.518716902268475e-06, "loss": 0.46704769134521484, "step": 680 }, { "epoch": 0.8560794044665012, "grad_norm": 2.6771323680877686, "learning_rate": 4.497216117511413e-06, "loss": 0.4675713539123535, "step": 690 }, { "epoch": 0.8684863523573201, "grad_norm": 3.0414323806762695, "learning_rate": 4.475299039396324e-06, "loss": 0.4250528335571289, "step": 700 }, { "epoch": 0.8808933002481389, "grad_norm": 2.52348256111145, "learning_rate": 4.452970236249071e-06, "loss": 0.4666771411895752, "step": 710 }, { "epoch": 0.8933002481389578, "grad_norm": 3.3117287158966064, "learning_rate": 4.4302343622141734e-06, "loss": 0.4492027282714844, "step": 720 }, { "epoch": 0.9057071960297767, "grad_norm": 2.8878304958343506, "learning_rate": 4.4070961562847044e-06, "loss": 0.428986644744873, "step": 730 }, { "epoch": 0.9181141439205955, "grad_norm": 2.7645702362060547, "learning_rate": 4.3835604413145175e-06, "loss": 0.4693061351776123, "step": 740 }, { "epoch": 0.9305210918114144, "grad_norm": 2.759788751602173, "learning_rate": 4.3596321230129786e-06, "loss": 0.46426753997802733, "step": 750 }, { "epoch": 0.9429280397022333, "grad_norm": 2.815812349319458, "learning_rate": 4.335316188922444e-06, "loss": 0.42464771270751955, "step": 760 }, { "epoch": 0.9553349875930521, "grad_norm": 2.893314838409424, "learning_rate": 4.3106177073786684e-06, "loss": 0.4731471061706543, "step": 770 }, { "epoch": 0.967741935483871, "grad_norm": 2.6007916927337646, "learning_rate": 4.285541826454374e-06, "loss": 0.43342103958129885, "step": 780 }, { "epoch": 0.9801488833746899, "grad_norm": 2.937251329421997, "learning_rate": 4.26009377288621e-06, "loss": 0.4437389850616455, "step": 790 }, { "epoch": 0.9925558312655087, "grad_norm": 2.6743578910827637, "learning_rate": 4.234278850985305e-06, "loss": 0.4493260860443115, "step": 800 }, { "epoch": 1.0049627791563276, "grad_norm": 2.905144214630127, "learning_rate": 4.208102441531648e-06, "loss": 0.4088118553161621, "step": 810 }, { "epoch": 1.0173697270471465, "grad_norm": 2.634845495223999, "learning_rate": 4.181570000652547e-06, "loss": 0.33449294567108157, "step": 820 }, { "epoch": 1.0297766749379653, "grad_norm": 2.6692142486572266, "learning_rate": 4.15468705868536e-06, "loss": 0.3250420093536377, "step": 830 }, { "epoch": 1.0421836228287842, "grad_norm": 2.6853787899017334, "learning_rate": 4.127459219024778e-06, "loss": 0.35315914154052735, "step": 840 }, { "epoch": 1.054590570719603, "grad_norm": 3.406165361404419, "learning_rate": 4.099892156954861e-06, "loss": 0.3586670637130737, "step": 850 }, { "epoch": 1.066997518610422, "grad_norm": 2.948725461959839, "learning_rate": 4.071991618466114e-06, "loss": 0.3647527933120728, "step": 860 }, { "epoch": 1.0794044665012408, "grad_norm": 2.896860122680664, "learning_rate": 4.043763419057797e-06, "loss": 0.32327847480773925, "step": 870 }, { "epoch": 1.0918114143920596, "grad_norm": 3.324622869491577, "learning_rate": 4.015213442525771e-06, "loss": 0.35637316703796384, "step": 880 }, { "epoch": 1.1042183622828785, "grad_norm": 3.4257752895355225, "learning_rate": 3.986347639736092e-06, "loss": 0.33382978439331057, "step": 890 }, { "epoch": 1.1166253101736974, "grad_norm": 3.2966017723083496, "learning_rate": 3.957172027384635e-06, "loss": 0.33941695690155027, "step": 900 }, { "epoch": 1.129032258064516, "grad_norm": 3.0130667686462402, "learning_rate": 3.927692686742993e-06, "loss": 0.3642054319381714, "step": 910 }, { "epoch": 1.141439205955335, "grad_norm": 3.649632453918457, "learning_rate": 3.897915762390912e-06, "loss": 0.3299143314361572, "step": 920 }, { "epoch": 1.1538461538461537, "grad_norm": 3.1730785369873047, "learning_rate": 3.867847460935542e-06, "loss": 0.34182562828063967, "step": 930 }, { "epoch": 1.1662531017369726, "grad_norm": 3.1270976066589355, "learning_rate": 3.8374940497177435e-06, "loss": 0.36127467155456544, "step": 940 }, { "epoch": 1.1786600496277915, "grad_norm": 2.9266204833984375, "learning_rate": 3.806861855505748e-06, "loss": 0.3463557958602905, "step": 950 }, { "epoch": 1.1910669975186103, "grad_norm": 3.1734328269958496, "learning_rate": 3.7759572631764243e-06, "loss": 0.34737136363983157, "step": 960 }, { "epoch": 1.2034739454094292, "grad_norm": 3.387535333633423, "learning_rate": 3.7447867143844373e-06, "loss": 0.3464951038360596, "step": 970 }, { "epoch": 1.215880893300248, "grad_norm": 3.2590081691741943, "learning_rate": 3.7133567062195697e-06, "loss": 0.3240300178527832, "step": 980 }, { "epoch": 1.228287841191067, "grad_norm": 2.911224603652954, "learning_rate": 3.6816737898524844e-06, "loss": 0.33942902088165283, "step": 990 }, { "epoch": 1.2406947890818858, "grad_norm": 3.3266444206237793, "learning_rate": 3.649744569169229e-06, "loss": 0.3586859226226807, "step": 1000 }, { "epoch": 1.2531017369727047, "grad_norm": 3.285763740539551, "learning_rate": 3.617575699394732e-06, "loss": 0.33882172107696534, "step": 1010 }, { "epoch": 1.2655086848635235, "grad_norm": 3.605529308319092, "learning_rate": 3.5851738857056174e-06, "loss": 0.34563610553741453, "step": 1020 }, { "epoch": 1.2779156327543424, "grad_norm": 2.4176876544952393, "learning_rate": 3.552545881832594e-06, "loss": 0.3259500741958618, "step": 1030 }, { "epoch": 1.2903225806451613, "grad_norm": 3.1849021911621094, "learning_rate": 3.519698488652734e-06, "loss": 0.35965259075164796, "step": 1040 }, { "epoch": 1.3027295285359801, "grad_norm": 3.008430004119873, "learning_rate": 3.486638552771914e-06, "loss": 0.34020233154296875, "step": 1050 }, { "epoch": 1.315136476426799, "grad_norm": 3.7227566242218018, "learning_rate": 3.4533729650977344e-06, "loss": 0.33164680004119873, "step": 1060 }, { "epoch": 1.3275434243176178, "grad_norm": 3.4713714122772217, "learning_rate": 3.4199086594031998e-06, "loss": 0.3493825435638428, "step": 1070 }, { "epoch": 1.3399503722084367, "grad_norm": 3.2516400814056396, "learning_rate": 3.386252610881465e-06, "loss": 0.3430775165557861, "step": 1080 }, { "epoch": 1.3523573200992556, "grad_norm": 3.756378650665283, "learning_rate": 3.3524118346919486e-06, "loss": 0.3269376277923584, "step": 1090 }, { "epoch": 1.3647642679900744, "grad_norm": 2.7790579795837402, "learning_rate": 3.318393384498114e-06, "loss": 0.3524430274963379, "step": 1100 }, { "epoch": 1.3771712158808933, "grad_norm": 3.254763603210449, "learning_rate": 3.2842043509972294e-06, "loss": 0.35284743309020994, "step": 1110 }, { "epoch": 1.3895781637717122, "grad_norm": 3.231228828430176, "learning_rate": 3.2498518604424005e-06, "loss": 0.35561535358428953, "step": 1120 }, { "epoch": 1.401985111662531, "grad_norm": 3.0170490741729736, "learning_rate": 3.215343073157204e-06, "loss": 0.36517820358276365, "step": 1130 }, { "epoch": 1.41439205955335, "grad_norm": 3.0740880966186523, "learning_rate": 3.180685182043205e-06, "loss": 0.34882569313049316, "step": 1140 }, { "epoch": 1.4267990074441688, "grad_norm": 3.487521171569824, "learning_rate": 3.1458854110806976e-06, "loss": 0.344951868057251, "step": 1150 }, { "epoch": 1.4392059553349876, "grad_norm": 2.7537150382995605, "learning_rate": 3.1109510138229565e-06, "loss": 0.3353364706039429, "step": 1160 }, { "epoch": 1.4516129032258065, "grad_norm": 2.8499064445495605, "learning_rate": 3.0758892718843352e-06, "loss": 0.33848204612731936, "step": 1170 }, { "epoch": 1.4640198511166254, "grad_norm": 3.2181148529052734, "learning_rate": 3.0407074934225038e-06, "loss": 0.3388556480407715, "step": 1180 }, { "epoch": 1.4764267990074442, "grad_norm": 3.099386215209961, "learning_rate": 3.005413011615165e-06, "loss": 0.3524498224258423, "step": 1190 }, { "epoch": 1.488833746898263, "grad_norm": 3.1054389476776123, "learning_rate": 2.9700131831315425e-06, "loss": 0.3347229719161987, "step": 1200 }, { "epoch": 1.501240694789082, "grad_norm": 2.9575774669647217, "learning_rate": 2.9345153865989918e-06, "loss": 0.321802020072937, "step": 1210 }, { "epoch": 1.5136476426799006, "grad_norm": 2.824366569519043, "learning_rate": 2.898927021065011e-06, "loss": 0.3323647499084473, "step": 1220 }, { "epoch": 1.5260545905707197, "grad_norm": 3.0914690494537354, "learning_rate": 2.8632555044550152e-06, "loss": 0.3432508945465088, "step": 1230 }, { "epoch": 1.5384615384615383, "grad_norm": 3.0662307739257812, "learning_rate": 2.8275082720261623e-06, "loss": 0.3417309522628784, "step": 1240 }, { "epoch": 1.5508684863523574, "grad_norm": 3.1436731815338135, "learning_rate": 2.791692774817576e-06, "loss": 0.3290053606033325, "step": 1250 }, { "epoch": 1.563275434243176, "grad_norm": 2.940727472305298, "learning_rate": 2.75581647809727e-06, "loss": 0.33008174896240233, "step": 1260 }, { "epoch": 1.5756823821339951, "grad_norm": 2.7560057640075684, "learning_rate": 2.7198868598061177e-06, "loss": 0.3164780616760254, "step": 1270 }, { "epoch": 1.5880893300248138, "grad_norm": 3.87307071685791, "learning_rate": 2.683911408999169e-06, "loss": 0.3081036567687988, "step": 1280 }, { "epoch": 1.6004962779156329, "grad_norm": 2.84149169921875, "learning_rate": 2.6478976242846576e-06, "loss": 0.35092926025390625, "step": 1290 }, { "epoch": 1.6129032258064515, "grad_norm": 3.040497303009033, "learning_rate": 2.6118530122610138e-06, "loss": 0.37850337028503417, "step": 1300 }, { "epoch": 1.6253101736972706, "grad_norm": 2.946133613586426, "learning_rate": 2.575785085952216e-06, "loss": 0.35753021240234373, "step": 1310 }, { "epoch": 1.6377171215880892, "grad_norm": 3.4700191020965576, "learning_rate": 2.539701363241795e-06, "loss": 0.34999761581420896, "step": 1320 }, { "epoch": 1.6501240694789083, "grad_norm": 2.9002044200897217, "learning_rate": 2.503609365305835e-06, "loss": 0.3304608345031738, "step": 1330 }, { "epoch": 1.662531017369727, "grad_norm": 3.0107545852661133, "learning_rate": 2.4675166150452814e-06, "loss": 0.3420397281646729, "step": 1340 }, { "epoch": 1.674937965260546, "grad_norm": 2.818993330001831, "learning_rate": 2.4314306355178924e-06, "loss": 0.31749625205993653, "step": 1350 }, { "epoch": 1.6873449131513647, "grad_norm": 2.8868680000305176, "learning_rate": 2.3953589483701556e-06, "loss": 0.33247082233428954, "step": 1360 }, { "epoch": 1.6997518610421838, "grad_norm": 2.5516133308410645, "learning_rate": 2.3593090722694995e-06, "loss": 0.3121840000152588, "step": 1370 }, { "epoch": 1.7121588089330024, "grad_norm": 2.8889875411987305, "learning_rate": 2.3232885213371297e-06, "loss": 0.3375117778778076, "step": 1380 }, { "epoch": 1.7245657568238213, "grad_norm": 3.4715304374694824, "learning_rate": 2.2873048035818043e-06, "loss": 0.3526495695114136, "step": 1390 }, { "epoch": 1.7369727047146402, "grad_norm": 2.6388895511627197, "learning_rate": 2.251365419334895e-06, "loss": 0.3385695219039917, "step": 1400 }, { "epoch": 1.749379652605459, "grad_norm": 3.295314311981201, "learning_rate": 2.2154778596870365e-06, "loss": 0.3281654119491577, "step": 1410 }, { "epoch": 1.7617866004962779, "grad_norm": 2.9345321655273438, "learning_rate": 2.179649604926708e-06, "loss": 0.3286000728607178, "step": 1420 }, { "epoch": 1.7741935483870968, "grad_norm": 3.245892286300659, "learning_rate": 2.14388812298107e-06, "loss": 0.31292095184326174, "step": 1430 }, { "epoch": 1.7866004962779156, "grad_norm": 2.8466174602508545, "learning_rate": 2.108200867859369e-06, "loss": 0.32442235946655273, "step": 1440 }, { "epoch": 1.7990074441687345, "grad_norm": 3.2279984951019287, "learning_rate": 2.072595278099247e-06, "loss": 0.3294026851654053, "step": 1450 }, { "epoch": 1.8114143920595533, "grad_norm": 3.1583516597747803, "learning_rate": 2.037078775216283e-06, "loss": 0.3263838768005371, "step": 1460 }, { "epoch": 1.8238213399503722, "grad_norm": 3.04581356048584, "learning_rate": 2.0016587621570682e-06, "loss": 0.33864445686340333, "step": 1470 }, { "epoch": 1.836228287841191, "grad_norm": 3.7386040687561035, "learning_rate": 1.966342621756163e-06, "loss": 0.31294050216674807, "step": 1480 }, { "epoch": 1.84863523573201, "grad_norm": 2.868602991104126, "learning_rate": 1.931137715197242e-06, "loss": 0.31308484077453613, "step": 1490 }, { "epoch": 1.8610421836228288, "grad_norm": 3.055979013442993, "learning_rate": 1.8960513804787557e-06, "loss": 0.333689284324646, "step": 1500 }, { "epoch": 1.8734491315136477, "grad_norm": 3.1473002433776855, "learning_rate": 1.861090930884412e-06, "loss": 0.33293652534484863, "step": 1510 }, { "epoch": 1.8858560794044665, "grad_norm": 2.9485549926757812, "learning_rate": 1.8262636534588316e-06, "loss": 0.3332956790924072, "step": 1520 }, { "epoch": 1.8982630272952854, "grad_norm": 2.9611082077026367, "learning_rate": 1.7915768074886497e-06, "loss": 0.32119269371032716, "step": 1530 }, { "epoch": 1.9106699751861043, "grad_norm": 2.7273433208465576, "learning_rate": 1.7570376229894164e-06, "loss": 0.32526330947875975, "step": 1540 }, { "epoch": 1.9230769230769231, "grad_norm": 3.0661497116088867, "learning_rate": 1.7226532991985976e-06, "loss": 0.3218840599060059, "step": 1550 }, { "epoch": 1.935483870967742, "grad_norm": 2.9829108715057373, "learning_rate": 1.688431003074985e-06, "loss": 0.3307999610900879, "step": 1560 }, { "epoch": 1.9478908188585606, "grad_norm": 3.018162488937378, "learning_rate": 1.654377867804841e-06, "loss": 0.34044556617736815, "step": 1570 }, { "epoch": 1.9602977667493797, "grad_norm": 2.9301137924194336, "learning_rate": 1.6205009913150815e-06, "loss": 0.31292636394500734, "step": 1580 }, { "epoch": 1.9727047146401984, "grad_norm": 2.9100582599639893, "learning_rate": 1.5868074347937993e-06, "loss": 0.32329092025756834, "step": 1590 }, { "epoch": 1.9851116625310175, "grad_norm": 2.979872465133667, "learning_rate": 1.553304221218462e-06, "loss": 0.3566758155822754, "step": 1600 }, { "epoch": 1.997518610421836, "grad_norm": 2.6494853496551514, "learning_rate": 1.5199983338920594e-06, "loss": 0.3069176197052002, "step": 1610 }, { "epoch": 2.009925558312655, "grad_norm": 2.3948535919189453, "learning_rate": 1.4868967149875257e-06, "loss": 0.25013885498046873, "step": 1620 }, { "epoch": 2.022332506203474, "grad_norm": 2.941615343093872, "learning_rate": 1.4540062641007383e-06, "loss": 0.22131125926971434, "step": 1630 }, { "epoch": 2.034739454094293, "grad_norm": 3.205547332763672, "learning_rate": 1.421333836812387e-06, "loss": 0.2237858295440674, "step": 1640 }, { "epoch": 2.0471464019851116, "grad_norm": 3.0743908882141113, "learning_rate": 1.3888862432590167e-06, "loss": 0.22658278942108154, "step": 1650 }, { "epoch": 2.0595533498759306, "grad_norm": 2.8300976753234863, "learning_rate": 1.3566702467135445e-06, "loss": 0.2289585828781128, "step": 1660 }, { "epoch": 2.0719602977667493, "grad_norm": 2.5701904296875, "learning_rate": 1.3246925621755496e-06, "loss": 0.22105908393859863, "step": 1670 }, { "epoch": 2.0843672456575684, "grad_norm": 2.67372727394104, "learning_rate": 1.2929598549716122e-06, "loss": 0.20758159160614015, "step": 1680 }, { "epoch": 2.096774193548387, "grad_norm": 3.0295441150665283, "learning_rate": 1.2614787393660215e-06, "loss": 0.2294921875, "step": 1690 }, { "epoch": 2.109181141439206, "grad_norm": 3.321169137954712, "learning_rate": 1.2302557771821154e-06, "loss": 0.22693567276000975, "step": 1700 }, { "epoch": 2.1215880893300247, "grad_norm": 3.0045440196990967, "learning_rate": 1.199297476434553e-06, "loss": 0.23366827964782716, "step": 1710 }, { "epoch": 2.133995037220844, "grad_norm": 3.3027615547180176, "learning_rate": 1.168610289972813e-06, "loss": 0.204612398147583, "step": 1720 }, { "epoch": 2.1464019851116625, "grad_norm": 3.4568586349487305, "learning_rate": 1.138200614136172e-06, "loss": 0.23412892818450928, "step": 1730 }, { "epoch": 2.1588089330024816, "grad_norm": 3.1891727447509766, "learning_rate": 1.1080747874204809e-06, "loss": 0.23051118850708008, "step": 1740 }, { "epoch": 2.1712158808933, "grad_norm": 2.898972511291504, "learning_rate": 1.0782390891569822e-06, "loss": 0.223101806640625, "step": 1750 }, { "epoch": 2.1836228287841193, "grad_norm": 3.198352098464966, "learning_rate": 1.0486997382034695e-06, "loss": 0.21067981719970702, "step": 1760 }, { "epoch": 2.196029776674938, "grad_norm": 3.239396095275879, "learning_rate": 1.0194628916480504e-06, "loss": 0.21455581188201905, "step": 1770 }, { "epoch": 2.208436724565757, "grad_norm": 3.6431620121002197, "learning_rate": 9.905346435257784e-07, "loss": 0.25631544589996336, "step": 1780 }, { "epoch": 2.2208436724565757, "grad_norm": 3.2421746253967285, "learning_rate": 9.619210235484333e-07, "loss": 0.2324852466583252, "step": 1790 }, { "epoch": 2.2332506203473947, "grad_norm": 3.0301804542541504, "learning_rate": 9.336279958477096e-07, "loss": 0.2013075351715088, "step": 1800 }, { "epoch": 2.2456575682382134, "grad_norm": 3.0917258262634277, "learning_rate": 9.056614577320702e-07, "loss": 0.23809702396392823, "step": 1810 }, { "epoch": 2.258064516129032, "grad_norm": 3.2016923427581787, "learning_rate": 8.780272384575289e-07, "loss": 0.22165682315826415, "step": 1820 }, { "epoch": 2.270471464019851, "grad_norm": 3.2964746952056885, "learning_rate": 8.507310980126188e-07, "loss": 0.21906075477600098, "step": 1830 }, { "epoch": 2.28287841191067, "grad_norm": 3.021667242050171, "learning_rate": 8.237787259178037e-07, "loss": 0.21673779487609862, "step": 1840 }, { "epoch": 2.295285359801489, "grad_norm": 3.4305264949798584, "learning_rate": 7.971757400395652e-07, "loss": 0.23625686168670654, "step": 1850 }, { "epoch": 2.3076923076923075, "grad_norm": 2.7715115547180176, "learning_rate": 7.709276854194392e-07, "loss": 0.21259665489196777, "step": 1860 }, { "epoch": 2.3200992555831266, "grad_norm": 3.520462989807129, "learning_rate": 7.450400331182198e-07, "loss": 0.23154499530792236, "step": 1870 }, { "epoch": 2.332506203473945, "grad_norm": 3.7826356887817383, "learning_rate": 7.19518179075591e-07, "loss": 0.2277855396270752, "step": 1880 }, { "epoch": 2.3449131513647643, "grad_norm": 3.4630792140960693, "learning_rate": 6.943674429854172e-07, "loss": 0.22485933303833008, "step": 1890 }, { "epoch": 2.357320099255583, "grad_norm": 3.305630922317505, "learning_rate": 6.695930671869175e-07, "loss": 0.23359484672546388, "step": 1900 }, { "epoch": 2.369727047146402, "grad_norm": 2.659604787826538, "learning_rate": 6.452002155719725e-07, "loss": 0.19909019470214845, "step": 1910 }, { "epoch": 2.3821339950372207, "grad_norm": 3.414795398712158, "learning_rate": 6.211939725087806e-07, "loss": 0.23796792030334474, "step": 1920 }, { "epoch": 2.3945409429280398, "grad_norm": 3.0635950565338135, "learning_rate": 5.975793417820841e-07, "loss": 0.22071402072906493, "step": 1930 }, { "epoch": 2.4069478908188584, "grad_norm": 3.123188018798828, "learning_rate": 5.743612455502016e-07, "loss": 0.22007994651794432, "step": 1940 }, { "epoch": 2.4193548387096775, "grad_norm": 2.785230875015259, "learning_rate": 5.515445233190636e-07, "loss": 0.21707756519317628, "step": 1950 }, { "epoch": 2.431761786600496, "grad_norm": 3.8641016483306885, "learning_rate": 5.291339309334845e-07, "loss": 0.2090601682662964, "step": 1960 }, { "epoch": 2.444168734491315, "grad_norm": 2.880202054977417, "learning_rate": 5.071341395858703e-07, "loss": 0.2203066825866699, "step": 1970 }, { "epoch": 2.456575682382134, "grad_norm": 3.224031448364258, "learning_rate": 4.855497348425686e-07, "loss": 0.22847747802734375, "step": 1980 }, { "epoch": 2.468982630272953, "grad_norm": 3.334984302520752, "learning_rate": 4.6438521568806625e-07, "loss": 0.20745439529418946, "step": 1990 }, { "epoch": 2.4813895781637716, "grad_norm": 3.121742010116577, "learning_rate": 4.436449935872378e-07, "loss": 0.23231451511383056, "step": 2000 }, { "epoch": 2.4937965260545907, "grad_norm": 2.765779972076416, "learning_rate": 4.2333339156583467e-07, "loss": 0.2055814266204834, "step": 2010 }, { "epoch": 2.5062034739454093, "grad_norm": 3.019102096557617, "learning_rate": 4.034546433094036e-07, "loss": 0.22689828872680665, "step": 2020 }, { "epoch": 2.5186104218362284, "grad_norm": 3.2937521934509277, "learning_rate": 3.8401289228083395e-07, "loss": 0.23529858589172364, "step": 2030 }, { "epoch": 2.531017369727047, "grad_norm": 3.353877544403076, "learning_rate": 3.6501219085670724e-07, "loss": 0.2225353479385376, "step": 2040 }, { "epoch": 2.543424317617866, "grad_norm": 3.6522250175476074, "learning_rate": 3.4645649948263085e-07, "loss": 0.2311680793762207, "step": 2050 }, { "epoch": 2.555831265508685, "grad_norm": 3.3297574520111084, "learning_rate": 3.2834968584773754e-07, "loss": 0.21333532333374022, "step": 2060 }, { "epoch": 2.568238213399504, "grad_norm": 3.3023574352264404, "learning_rate": 3.106955240785153e-07, "loss": 0.2413243293762207, "step": 2070 }, { "epoch": 2.5806451612903225, "grad_norm": 2.7704153060913086, "learning_rate": 2.9349769395214e-07, "loss": 0.21133730411529542, "step": 2080 }, { "epoch": 2.5930521091811416, "grad_norm": 3.1937754154205322, "learning_rate": 2.767597801294772e-07, "loss": 0.21675755977630615, "step": 2090 }, { "epoch": 2.6054590570719602, "grad_norm": 3.397535562515259, "learning_rate": 2.604852714079023e-07, "loss": 0.22542505264282225, "step": 2100 }, { "epoch": 2.617866004962779, "grad_norm": 3.3038713932037354, "learning_rate": 2.4467755999411204e-07, "loss": 0.23392457962036134, "step": 2110 }, { "epoch": 2.630272952853598, "grad_norm": 4.148429870605469, "learning_rate": 2.2933994079705896e-07, "loss": 0.19952282905578614, "step": 2120 }, { "epoch": 2.642679900744417, "grad_norm": 3.0992136001586914, "learning_rate": 2.144756107411733e-07, "loss": 0.2230466365814209, "step": 2130 }, { "epoch": 2.6550868486352357, "grad_norm": 3.451746940612793, "learning_rate": 2.0008766810000801e-07, "loss": 0.23057200908660888, "step": 2140 }, { "epoch": 2.6674937965260543, "grad_norm": 3.058110237121582, "learning_rate": 1.861791118504408e-07, "loss": 0.2180851459503174, "step": 2150 }, { "epoch": 2.6799007444168734, "grad_norm": 2.745176315307617, "learning_rate": 1.7275284104757844e-07, "loss": 0.2167917251586914, "step": 2160 }, { "epoch": 2.6923076923076925, "grad_norm": 3.708021402359009, "learning_rate": 1.598116542204889e-07, "loss": 0.22899148464202881, "step": 2170 }, { "epoch": 2.704714640198511, "grad_norm": 3.6781704425811768, "learning_rate": 1.4735824878888277e-07, "loss": 0.2170346736907959, "step": 2180 }, { "epoch": 2.71712158808933, "grad_norm": 2.478654623031616, "learning_rate": 1.353952205008713e-07, "loss": 0.2242295265197754, "step": 2190 }, { "epoch": 2.729528535980149, "grad_norm": 2.7087976932525635, "learning_rate": 1.2392506289191837e-07, "loss": 0.2131351947784424, "step": 2200 }, { "epoch": 2.741935483870968, "grad_norm": 2.867835283279419, "learning_rate": 1.1295016676509618e-07, "loss": 0.21861982345581055, "step": 2210 }, { "epoch": 2.7543424317617866, "grad_norm": 2.9449636936187744, "learning_rate": 1.0247281969275131e-07, "loss": 0.1985526442527771, "step": 2220 }, { "epoch": 2.7667493796526053, "grad_norm": 3.0885448455810547, "learning_rate": 9.249520553969465e-08, "loss": 0.23580389022827147, "step": 2230 }, { "epoch": 2.7791563275434243, "grad_norm": 3.1814591884613037, "learning_rate": 8.301940400799818e-08, "loss": 0.21973462104797364, "step": 2240 }, { "epoch": 2.7915632754342434, "grad_norm": 3.26047682762146, "learning_rate": 7.404739020351381e-08, "loss": 0.22958881855010987, "step": 2250 }, { "epoch": 2.803970223325062, "grad_norm": 3.2021138668060303, "learning_rate": 6.558103422418555e-08, "loss": 0.23037824630737305, "step": 2260 }, { "epoch": 2.8163771712158807, "grad_norm": 3.562350273132324, "learning_rate": 5.762210077025293e-08, "loss": 0.2314563512802124, "step": 2270 }, { "epoch": 2.8287841191067, "grad_norm": 3.15472412109375, "learning_rate": 5.017224877642196e-08, "loss": 0.21394333839416504, "step": 2280 }, { "epoch": 2.8411910669975184, "grad_norm": 2.9189085960388184, "learning_rate": 4.323303106608362e-08, "loss": 0.22109608650207518, "step": 2290 }, { "epoch": 2.8535980148883375, "grad_norm": 3.364637851715088, "learning_rate": 3.680589402764695e-08, "loss": 0.21065773963928222, "step": 2300 }, { "epoch": 2.866004962779156, "grad_norm": 3.1239407062530518, "learning_rate": 3.089217731305882e-08, "loss": 0.21384596824645996, "step": 2310 }, { "epoch": 2.8784119106699753, "grad_norm": 3.2410709857940674, "learning_rate": 2.5493113558571203e-08, "loss": 0.2103095531463623, "step": 2320 }, { "epoch": 2.890818858560794, "grad_norm": 3.29823899269104, "learning_rate": 2.0609828127814425e-08, "loss": 0.22623074054718018, "step": 2330 }, { "epoch": 2.903225806451613, "grad_norm": 3.447692632675171, "learning_rate": 1.624333887723012e-08, "loss": 0.2561406373977661, "step": 2340 }, { "epoch": 2.9156327543424316, "grad_norm": 3.5823864936828613, "learning_rate": 1.2394555943911757e-08, "loss": 0.22645580768585205, "step": 2350 }, { "epoch": 2.9280397022332507, "grad_norm": 3.032896041870117, "learning_rate": 9.0642815559e-09, "loss": 0.21149790287017822, "step": 2360 }, { "epoch": 2.9404466501240694, "grad_norm": 3.0762665271759033, "learning_rate": 6.253209864966747e-09, "loss": 0.2031836986541748, "step": 2370 }, { "epoch": 2.9528535980148884, "grad_norm": 3.5435872077941895, "learning_rate": 3.9619268019305825e-09, "loss": 0.2176318883895874, "step": 2380 }, { "epoch": 2.965260545905707, "grad_norm": 3.506044387817383, "learning_rate": 2.190909954525866e-09, "loss": 0.2153688907623291, "step": 2390 }, { "epoch": 2.977667493796526, "grad_norm": 3.4698026180267334, "learning_rate": 9.405284678556948e-10, "loss": 0.21965882778167725, "step": 2400 }, { "epoch": 2.990074441687345, "grad_norm": 3.0432729721069336, "learning_rate": 2.1104296745011466e-10, "loss": 0.2195052146911621, "step": 2410 }, { "epoch": 3.0, "step": 2418, "total_flos": 1.329254778357678e+18, "train_loss": 0.361527387419449, "train_runtime": 121252.8356, "train_samples_per_second": 0.16, "train_steps_per_second": 0.02 } ], "logging_steps": 10, "max_steps": 2418, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.329254778357678e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }