{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.25029072367832544, "eval_steps": 500, "global_step": 2798, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008945343948474819, "grad_norm": 5.675168037414551, "learning_rate": 1.1061797752808989e-06, "loss": 2.1196, "step": 10 }, { "epoch": 0.0017890687896949637, "grad_norm": 2.9707770347595215, "learning_rate": 2.2241573033707866e-06, "loss": 2.0311, "step": 20 }, { "epoch": 0.0026836031845424457, "grad_norm": 1.5259026288986206, "learning_rate": 3.342134831460675e-06, "loss": 1.6404, "step": 30 }, { "epoch": 0.0035781375793899274, "grad_norm": 0.9031808376312256, "learning_rate": 4.4601123595505624e-06, "loss": 1.4353, "step": 40 }, { "epoch": 0.00447267197423741, "grad_norm": 0.7855185270309448, "learning_rate": 5.5780898876404495e-06, "loss": 1.2916, "step": 50 }, { "epoch": 0.005367206369084891, "grad_norm": 0.7476404905319214, "learning_rate": 6.6960674157303374e-06, "loss": 1.1757, "step": 60 }, { "epoch": 0.006261740763932373, "grad_norm": 0.7190150022506714, "learning_rate": 7.814044943820226e-06, "loss": 1.1344, "step": 70 }, { "epoch": 0.007156275158779855, "grad_norm": 0.6955579519271851, "learning_rate": 8.932022471910112e-06, "loss": 1.0784, "step": 80 }, { "epoch": 0.008050809553627337, "grad_norm": 0.613128662109375, "learning_rate": 1.005e-05, "loss": 1.0716, "step": 90 }, { "epoch": 0.00894534394847482, "grad_norm": 0.6427867412567139, "learning_rate": 1.1167977528089888e-05, "loss": 1.0965, "step": 100 }, { "epoch": 0.009839878343322301, "grad_norm": 0.6494929194450378, "learning_rate": 1.2285955056179776e-05, "loss": 1.0301, "step": 110 }, { "epoch": 0.010734412738169783, "grad_norm": 0.656710684299469, "learning_rate": 1.3403932584269664e-05, "loss": 1.0766, "step": 120 }, { "epoch": 0.011628947133017264, "grad_norm": 0.6478440165519714, "learning_rate": 1.4521910112359552e-05, "loss": 1.0263, "step": 130 }, { "epoch": 0.012523481527864746, "grad_norm": 0.6425960659980774, "learning_rate": 1.563988764044944e-05, "loss": 1.0401, "step": 140 }, { "epoch": 0.013418015922712228, "grad_norm": 0.6716069579124451, "learning_rate": 1.6757865168539328e-05, "loss": 1.0294, "step": 150 }, { "epoch": 0.01431255031755971, "grad_norm": 0.6451089978218079, "learning_rate": 1.7875842696629214e-05, "loss": 1.002, "step": 160 }, { "epoch": 0.015207084712407191, "grad_norm": 0.6245432496070862, "learning_rate": 1.89938202247191e-05, "loss": 1.0152, "step": 170 }, { "epoch": 0.016101619107254675, "grad_norm": 0.5898470878601074, "learning_rate": 2e-05, "loss": 1.0188, "step": 180 }, { "epoch": 0.016996153502102155, "grad_norm": 0.612930953502655, "learning_rate": 2e-05, "loss": 1.0252, "step": 190 }, { "epoch": 0.01789068789694964, "grad_norm": 0.5948618054389954, "learning_rate": 2e-05, "loss": 0.9977, "step": 200 }, { "epoch": 0.01878522229179712, "grad_norm": 0.6210647821426392, "learning_rate": 2e-05, "loss": 1.0267, "step": 210 }, { "epoch": 0.019679756686644602, "grad_norm": 0.580319344997406, "learning_rate": 2e-05, "loss": 1.0047, "step": 220 }, { "epoch": 0.020574291081492082, "grad_norm": 0.5656352639198303, "learning_rate": 2e-05, "loss": 0.9926, "step": 230 }, { "epoch": 0.021468825476339565, "grad_norm": 0.6239637136459351, "learning_rate": 2e-05, "loss": 1.0122, "step": 240 }, { "epoch": 0.022363359871187045, "grad_norm": 0.5792014002799988, "learning_rate": 2e-05, "loss": 1.0079, "step": 250 }, { "epoch": 0.02325789426603453, "grad_norm": 0.5544520616531372, "learning_rate": 2e-05, "loss": 1.0014, "step": 260 }, { "epoch": 0.024152428660882012, "grad_norm": 0.5646398663520813, "learning_rate": 2e-05, "loss": 1.0073, "step": 270 }, { "epoch": 0.025046963055729492, "grad_norm": 0.5469699501991272, "learning_rate": 2e-05, "loss": 0.9744, "step": 280 }, { "epoch": 0.025941497450576976, "grad_norm": 0.5659817457199097, "learning_rate": 2e-05, "loss": 1.0111, "step": 290 }, { "epoch": 0.026836031845424456, "grad_norm": 0.5720058679580688, "learning_rate": 2e-05, "loss": 0.9685, "step": 300 }, { "epoch": 0.02773056624027194, "grad_norm": 0.5695531964302063, "learning_rate": 2e-05, "loss": 0.9996, "step": 310 }, { "epoch": 0.02862510063511942, "grad_norm": 0.5718349814414978, "learning_rate": 2e-05, "loss": 1.0562, "step": 320 }, { "epoch": 0.029519635029966903, "grad_norm": 0.5322186946868896, "learning_rate": 2e-05, "loss": 0.9927, "step": 330 }, { "epoch": 0.030414169424814383, "grad_norm": 0.5264423489570618, "learning_rate": 2e-05, "loss": 0.9787, "step": 340 }, { "epoch": 0.031308703819661866, "grad_norm": 0.5364736318588257, "learning_rate": 2e-05, "loss": 0.9557, "step": 350 }, { "epoch": 0.03220323821450935, "grad_norm": 0.5510904788970947, "learning_rate": 2e-05, "loss": 0.9946, "step": 360 }, { "epoch": 0.033097772609356826, "grad_norm": 0.5201677083969116, "learning_rate": 2e-05, "loss": 0.9811, "step": 370 }, { "epoch": 0.03399230700420431, "grad_norm": 0.5272532105445862, "learning_rate": 2e-05, "loss": 0.9672, "step": 380 }, { "epoch": 0.03488684139905179, "grad_norm": 0.5318697690963745, "learning_rate": 2e-05, "loss": 0.9779, "step": 390 }, { "epoch": 0.03578137579389928, "grad_norm": 0.5327851176261902, "learning_rate": 2e-05, "loss": 0.9924, "step": 400 }, { "epoch": 0.03667591018874676, "grad_norm": 0.5506769418716431, "learning_rate": 2e-05, "loss": 0.9944, "step": 410 }, { "epoch": 0.03757044458359424, "grad_norm": 0.5046197772026062, "learning_rate": 2e-05, "loss": 0.955, "step": 420 }, { "epoch": 0.03846497897844172, "grad_norm": 0.514418363571167, "learning_rate": 2e-05, "loss": 0.9716, "step": 430 }, { "epoch": 0.039359513373289204, "grad_norm": 0.5306272506713867, "learning_rate": 2e-05, "loss": 0.9573, "step": 440 }, { "epoch": 0.04025404776813669, "grad_norm": 0.5712807178497314, "learning_rate": 2e-05, "loss": 0.9735, "step": 450 }, { "epoch": 0.041148582162984164, "grad_norm": 0.5208743810653687, "learning_rate": 2e-05, "loss": 0.9579, "step": 460 }, { "epoch": 0.04204311655783165, "grad_norm": 0.5234618782997131, "learning_rate": 2e-05, "loss": 0.972, "step": 470 }, { "epoch": 0.04293765095267913, "grad_norm": 0.5433705449104309, "learning_rate": 2e-05, "loss": 0.9576, "step": 480 }, { "epoch": 0.043832185347526614, "grad_norm": 0.4861101806163788, "learning_rate": 2e-05, "loss": 0.9465, "step": 490 }, { "epoch": 0.04472671974237409, "grad_norm": 0.5443506240844727, "learning_rate": 2e-05, "loss": 0.9752, "step": 500 }, { "epoch": 0.045621254137221574, "grad_norm": 0.516825258731842, "learning_rate": 2e-05, "loss": 0.9402, "step": 510 }, { "epoch": 0.04651578853206906, "grad_norm": 0.5197014212608337, "learning_rate": 2e-05, "loss": 0.9663, "step": 520 }, { "epoch": 0.04741032292691654, "grad_norm": 0.4976901710033417, "learning_rate": 2e-05, "loss": 0.955, "step": 530 }, { "epoch": 0.048304857321764025, "grad_norm": 0.5131090879440308, "learning_rate": 2e-05, "loss": 0.9645, "step": 540 }, { "epoch": 0.0491993917166115, "grad_norm": 0.5310055017471313, "learning_rate": 2e-05, "loss": 0.9546, "step": 550 }, { "epoch": 0.050093926111458985, "grad_norm": 0.4865564703941345, "learning_rate": 2e-05, "loss": 0.9513, "step": 560 }, { "epoch": 0.05098846050630647, "grad_norm": 0.5074427723884583, "learning_rate": 2e-05, "loss": 0.941, "step": 570 }, { "epoch": 0.05188299490115395, "grad_norm": 0.5017594695091248, "learning_rate": 2e-05, "loss": 0.9416, "step": 580 }, { "epoch": 0.05277752929600143, "grad_norm": 0.5020937919616699, "learning_rate": 2e-05, "loss": 0.9775, "step": 590 }, { "epoch": 0.05367206369084891, "grad_norm": 0.5406600832939148, "learning_rate": 2e-05, "loss": 0.9408, "step": 600 }, { "epoch": 0.054566598085696395, "grad_norm": 0.529053807258606, "learning_rate": 2e-05, "loss": 0.95, "step": 610 }, { "epoch": 0.05546113248054388, "grad_norm": 0.5157285332679749, "learning_rate": 2e-05, "loss": 0.9448, "step": 620 }, { "epoch": 0.056355666875391355, "grad_norm": 0.48365968465805054, "learning_rate": 2e-05, "loss": 0.9539, "step": 630 }, { "epoch": 0.05725020127023884, "grad_norm": 0.5019218921661377, "learning_rate": 2e-05, "loss": 0.9138, "step": 640 }, { "epoch": 0.05814473566508632, "grad_norm": 0.4997801184654236, "learning_rate": 2e-05, "loss": 0.9519, "step": 650 }, { "epoch": 0.059039270059933806, "grad_norm": 0.49150338768959045, "learning_rate": 2e-05, "loss": 0.9393, "step": 660 }, { "epoch": 0.05993380445478129, "grad_norm": 0.49385330080986023, "learning_rate": 2e-05, "loss": 0.9255, "step": 670 }, { "epoch": 0.060828338849628766, "grad_norm": 0.48065996170043945, "learning_rate": 2e-05, "loss": 0.9436, "step": 680 }, { "epoch": 0.06172287324447625, "grad_norm": 0.48475712537765503, "learning_rate": 2e-05, "loss": 0.962, "step": 690 }, { "epoch": 0.06261740763932373, "grad_norm": 0.48432332277297974, "learning_rate": 2e-05, "loss": 0.9409, "step": 700 }, { "epoch": 0.06351194203417121, "grad_norm": 0.5160853862762451, "learning_rate": 2e-05, "loss": 0.9439, "step": 710 }, { "epoch": 0.0644064764290187, "grad_norm": 0.5108107924461365, "learning_rate": 2e-05, "loss": 0.9427, "step": 720 }, { "epoch": 0.06530101082386618, "grad_norm": 0.5226851105690002, "learning_rate": 2e-05, "loss": 0.9465, "step": 730 }, { "epoch": 0.06619554521871365, "grad_norm": 0.5101060271263123, "learning_rate": 2e-05, "loss": 0.9428, "step": 740 }, { "epoch": 0.06709007961356114, "grad_norm": 0.5003637671470642, "learning_rate": 2e-05, "loss": 0.9553, "step": 750 }, { "epoch": 0.06798461400840862, "grad_norm": 0.4850715100765228, "learning_rate": 2e-05, "loss": 0.9295, "step": 760 }, { "epoch": 0.06887914840325611, "grad_norm": 0.4759562313556671, "learning_rate": 2e-05, "loss": 0.9413, "step": 770 }, { "epoch": 0.06977368279810359, "grad_norm": 0.4925222396850586, "learning_rate": 2e-05, "loss": 0.947, "step": 780 }, { "epoch": 0.07066821719295106, "grad_norm": 0.47600677609443665, "learning_rate": 2e-05, "loss": 0.9349, "step": 790 }, { "epoch": 0.07156275158779855, "grad_norm": 0.5029114484786987, "learning_rate": 2e-05, "loss": 0.9341, "step": 800 }, { "epoch": 0.07245728598264603, "grad_norm": 0.4818347692489624, "learning_rate": 2e-05, "loss": 0.9505, "step": 810 }, { "epoch": 0.07335182037749352, "grad_norm": 0.5230589509010315, "learning_rate": 2e-05, "loss": 0.9279, "step": 820 }, { "epoch": 0.074246354772341, "grad_norm": 0.5369635224342346, "learning_rate": 2e-05, "loss": 0.9117, "step": 830 }, { "epoch": 0.07514088916718847, "grad_norm": 0.4927598536014557, "learning_rate": 2e-05, "loss": 0.9225, "step": 840 }, { "epoch": 0.07603542356203596, "grad_norm": 0.4878654479980469, "learning_rate": 2e-05, "loss": 0.9588, "step": 850 }, { "epoch": 0.07692995795688344, "grad_norm": 0.589440643787384, "learning_rate": 2e-05, "loss": 0.9388, "step": 860 }, { "epoch": 0.07782449235173092, "grad_norm": 0.48455187678337097, "learning_rate": 2e-05, "loss": 0.9194, "step": 870 }, { "epoch": 0.07871902674657841, "grad_norm": 0.49978625774383545, "learning_rate": 2e-05, "loss": 0.9324, "step": 880 }, { "epoch": 0.07961356114142588, "grad_norm": 0.5087828040122986, "learning_rate": 2e-05, "loss": 0.9421, "step": 890 }, { "epoch": 0.08050809553627337, "grad_norm": 0.49013105034828186, "learning_rate": 2e-05, "loss": 0.9463, "step": 900 }, { "epoch": 0.08140262993112085, "grad_norm": 0.46859070658683777, "learning_rate": 2e-05, "loss": 0.9414, "step": 910 }, { "epoch": 0.08229716432596833, "grad_norm": 0.48060163855552673, "learning_rate": 2e-05, "loss": 0.9308, "step": 920 }, { "epoch": 0.08319169872081582, "grad_norm": 0.4641304314136505, "learning_rate": 2e-05, "loss": 0.9334, "step": 930 }, { "epoch": 0.0840862331156633, "grad_norm": 0.4877597689628601, "learning_rate": 2e-05, "loss": 0.9328, "step": 940 }, { "epoch": 0.08498076751051079, "grad_norm": 0.4985778033733368, "learning_rate": 2e-05, "loss": 0.9366, "step": 950 }, { "epoch": 0.08587530190535826, "grad_norm": 0.46850451827049255, "learning_rate": 2e-05, "loss": 0.949, "step": 960 }, { "epoch": 0.08676983630020574, "grad_norm": 0.4797747731208801, "learning_rate": 2e-05, "loss": 0.9228, "step": 970 }, { "epoch": 0.08766437069505323, "grad_norm": 0.4770503640174866, "learning_rate": 2e-05, "loss": 0.9281, "step": 980 }, { "epoch": 0.0885589050899007, "grad_norm": 0.4758184552192688, "learning_rate": 2e-05, "loss": 0.9478, "step": 990 }, { "epoch": 0.08945343948474818, "grad_norm": 0.4701295793056488, "learning_rate": 2e-05, "loss": 0.9192, "step": 1000 }, { "epoch": 0.09034797387959567, "grad_norm": 0.49357926845550537, "learning_rate": 2e-05, "loss": 0.9252, "step": 1010 }, { "epoch": 0.09124250827444315, "grad_norm": 0.45938366651535034, "learning_rate": 2e-05, "loss": 0.931, "step": 1020 }, { "epoch": 0.09213704266929064, "grad_norm": 0.47234824299812317, "learning_rate": 2e-05, "loss": 0.9305, "step": 1030 }, { "epoch": 0.09303157706413812, "grad_norm": 0.49671849608421326, "learning_rate": 2e-05, "loss": 0.9313, "step": 1040 }, { "epoch": 0.09392611145898559, "grad_norm": 0.49155551195144653, "learning_rate": 2e-05, "loss": 0.9429, "step": 1050 }, { "epoch": 0.09482064585383308, "grad_norm": 0.48902663588523865, "learning_rate": 2e-05, "loss": 0.9191, "step": 1060 }, { "epoch": 0.09571518024868056, "grad_norm": 0.4676748812198639, "learning_rate": 2e-05, "loss": 0.9313, "step": 1070 }, { "epoch": 0.09660971464352805, "grad_norm": 0.4561516344547272, "learning_rate": 2e-05, "loss": 0.9209, "step": 1080 }, { "epoch": 0.09750424903837553, "grad_norm": 0.4574839174747467, "learning_rate": 2e-05, "loss": 0.9282, "step": 1090 }, { "epoch": 0.098398783433223, "grad_norm": 0.6882016658782959, "learning_rate": 2e-05, "loss": 0.9194, "step": 1100 }, { "epoch": 0.0992933178280705, "grad_norm": 0.5273155570030212, "learning_rate": 2e-05, "loss": 0.9447, "step": 1110 }, { "epoch": 0.10018785222291797, "grad_norm": 0.4704069495201111, "learning_rate": 2e-05, "loss": 0.9131, "step": 1120 }, { "epoch": 0.10108238661776545, "grad_norm": 0.46409177780151367, "learning_rate": 2e-05, "loss": 0.9012, "step": 1130 }, { "epoch": 0.10197692101261294, "grad_norm": 0.47346293926239014, "learning_rate": 2e-05, "loss": 0.9129, "step": 1140 }, { "epoch": 0.10287145540746041, "grad_norm": 0.4725669026374817, "learning_rate": 2e-05, "loss": 0.9222, "step": 1150 }, { "epoch": 0.1037659898023079, "grad_norm": 0.45462873578071594, "learning_rate": 2e-05, "loss": 0.9069, "step": 1160 }, { "epoch": 0.10466052419715538, "grad_norm": 0.4361211359500885, "learning_rate": 2e-05, "loss": 0.93, "step": 1170 }, { "epoch": 0.10555505859200286, "grad_norm": 0.4952946901321411, "learning_rate": 2e-05, "loss": 0.9222, "step": 1180 }, { "epoch": 0.10644959298685035, "grad_norm": 0.48436594009399414, "learning_rate": 2e-05, "loss": 0.9311, "step": 1190 }, { "epoch": 0.10734412738169782, "grad_norm": 0.47711387276649475, "learning_rate": 2e-05, "loss": 0.9228, "step": 1200 }, { "epoch": 0.10823866177654531, "grad_norm": 0.46835336089134216, "learning_rate": 2e-05, "loss": 0.9027, "step": 1210 }, { "epoch": 0.10913319617139279, "grad_norm": 0.5128036737442017, "learning_rate": 2e-05, "loss": 0.9198, "step": 1220 }, { "epoch": 0.11002773056624027, "grad_norm": 0.47244781255722046, "learning_rate": 2e-05, "loss": 0.9344, "step": 1230 }, { "epoch": 0.11092226496108776, "grad_norm": 0.47003787755966187, "learning_rate": 2e-05, "loss": 0.8993, "step": 1240 }, { "epoch": 0.11181679935593523, "grad_norm": 0.4747315049171448, "learning_rate": 2e-05, "loss": 0.9155, "step": 1250 }, { "epoch": 0.11271133375078271, "grad_norm": 0.5968290567398071, "learning_rate": 2e-05, "loss": 0.9, "step": 1260 }, { "epoch": 0.1136058681456302, "grad_norm": 0.4795837700366974, "learning_rate": 2e-05, "loss": 0.8999, "step": 1270 }, { "epoch": 0.11450040254047768, "grad_norm": 0.4849240481853485, "learning_rate": 2e-05, "loss": 0.9043, "step": 1280 }, { "epoch": 0.11539493693532517, "grad_norm": 0.45396119356155396, "learning_rate": 2e-05, "loss": 0.9236, "step": 1290 }, { "epoch": 0.11628947133017264, "grad_norm": 0.4486008286476135, "learning_rate": 2e-05, "loss": 0.883, "step": 1300 }, { "epoch": 0.11718400572502012, "grad_norm": 0.4643603265285492, "learning_rate": 2e-05, "loss": 0.9053, "step": 1310 }, { "epoch": 0.11807854011986761, "grad_norm": 0.48251062631607056, "learning_rate": 2e-05, "loss": 0.91, "step": 1320 }, { "epoch": 0.11897307451471509, "grad_norm": 0.4961690306663513, "learning_rate": 2e-05, "loss": 0.9044, "step": 1330 }, { "epoch": 0.11986760890956258, "grad_norm": 0.4803570806980133, "learning_rate": 2e-05, "loss": 0.935, "step": 1340 }, { "epoch": 0.12076214330441006, "grad_norm": 0.46828046441078186, "learning_rate": 2e-05, "loss": 0.9122, "step": 1350 }, { "epoch": 0.12165667769925753, "grad_norm": 0.5151194334030151, "learning_rate": 2e-05, "loss": 0.9189, "step": 1360 }, { "epoch": 0.12255121209410502, "grad_norm": 0.4741526246070862, "learning_rate": 2e-05, "loss": 0.9142, "step": 1370 }, { "epoch": 0.1234457464889525, "grad_norm": 0.4384336471557617, "learning_rate": 2e-05, "loss": 0.9204, "step": 1380 }, { "epoch": 0.12434028088379999, "grad_norm": 0.5426257252693176, "learning_rate": 2e-05, "loss": 0.9038, "step": 1390 }, { "epoch": 0.12523481527864747, "grad_norm": 0.4690248966217041, "learning_rate": 2e-05, "loss": 0.9014, "step": 1400 }, { "epoch": 0.12612934967349496, "grad_norm": 0.44816529750823975, "learning_rate": 2e-05, "loss": 0.8798, "step": 1410 }, { "epoch": 0.12702388406834242, "grad_norm": 0.45386165380477905, "learning_rate": 2e-05, "loss": 0.9177, "step": 1420 }, { "epoch": 0.1279184184631899, "grad_norm": 0.47421979904174805, "learning_rate": 2e-05, "loss": 0.8928, "step": 1430 }, { "epoch": 0.1288129528580374, "grad_norm": 0.47659310698509216, "learning_rate": 2e-05, "loss": 0.9019, "step": 1440 }, { "epoch": 0.12970748725288486, "grad_norm": 0.45950847864151, "learning_rate": 2e-05, "loss": 0.9254, "step": 1450 }, { "epoch": 0.13060202164773235, "grad_norm": 0.4390353858470917, "learning_rate": 2e-05, "loss": 0.9061, "step": 1460 }, { "epoch": 0.13149655604257984, "grad_norm": 0.5103998780250549, "learning_rate": 2e-05, "loss": 0.9362, "step": 1470 }, { "epoch": 0.1323910904374273, "grad_norm": 0.48334017395973206, "learning_rate": 2e-05, "loss": 0.9005, "step": 1480 }, { "epoch": 0.1332856248322748, "grad_norm": 0.45984673500061035, "learning_rate": 2e-05, "loss": 0.8878, "step": 1490 }, { "epoch": 0.1341801592271223, "grad_norm": 0.4718729555606842, "learning_rate": 2e-05, "loss": 0.9176, "step": 1500 }, { "epoch": 0.13507469362196978, "grad_norm": 0.4789274334907532, "learning_rate": 2e-05, "loss": 0.9029, "step": 1510 }, { "epoch": 0.13596922801681724, "grad_norm": 0.45665860176086426, "learning_rate": 2e-05, "loss": 0.9085, "step": 1520 }, { "epoch": 0.13686376241166473, "grad_norm": 0.4554169774055481, "learning_rate": 2e-05, "loss": 0.9031, "step": 1530 }, { "epoch": 0.13775829680651222, "grad_norm": 0.4741033613681793, "learning_rate": 2e-05, "loss": 0.9122, "step": 1540 }, { "epoch": 0.13865283120135968, "grad_norm": 0.48835477232933044, "learning_rate": 2e-05, "loss": 0.9215, "step": 1550 }, { "epoch": 0.13954736559620717, "grad_norm": 0.4369822144508362, "learning_rate": 2e-05, "loss": 0.8953, "step": 1560 }, { "epoch": 0.14044189999105466, "grad_norm": 0.4376717805862427, "learning_rate": 2e-05, "loss": 0.9003, "step": 1570 }, { "epoch": 0.14133643438590213, "grad_norm": 0.4347819685935974, "learning_rate": 2e-05, "loss": 0.8993, "step": 1580 }, { "epoch": 0.14223096878074962, "grad_norm": 0.4427725076675415, "learning_rate": 2e-05, "loss": 0.9025, "step": 1590 }, { "epoch": 0.1431255031755971, "grad_norm": 0.45390942692756653, "learning_rate": 2e-05, "loss": 0.9003, "step": 1600 }, { "epoch": 0.14402003757044457, "grad_norm": 0.45958849787712097, "learning_rate": 2e-05, "loss": 0.9039, "step": 1610 }, { "epoch": 0.14491457196529206, "grad_norm": 0.45375823974609375, "learning_rate": 2e-05, "loss": 0.8962, "step": 1620 }, { "epoch": 0.14580910636013955, "grad_norm": 0.4949476718902588, "learning_rate": 2e-05, "loss": 0.8817, "step": 1630 }, { "epoch": 0.14670364075498704, "grad_norm": 0.4698850214481354, "learning_rate": 2e-05, "loss": 0.8954, "step": 1640 }, { "epoch": 0.1475981751498345, "grad_norm": 0.4654884338378906, "learning_rate": 2e-05, "loss": 0.909, "step": 1650 }, { "epoch": 0.148492709544682, "grad_norm": 0.45599988102912903, "learning_rate": 2e-05, "loss": 0.9082, "step": 1660 }, { "epoch": 0.14938724393952948, "grad_norm": 0.4717373847961426, "learning_rate": 2e-05, "loss": 0.9158, "step": 1670 }, { "epoch": 0.15028177833437695, "grad_norm": 0.48511821031570435, "learning_rate": 2e-05, "loss": 0.9123, "step": 1680 }, { "epoch": 0.15117631272922444, "grad_norm": 0.45996376872062683, "learning_rate": 2e-05, "loss": 0.9081, "step": 1690 }, { "epoch": 0.15207084712407193, "grad_norm": 0.46202340722084045, "learning_rate": 2e-05, "loss": 0.9267, "step": 1700 }, { "epoch": 0.1529653815189194, "grad_norm": 0.4501361846923828, "learning_rate": 2e-05, "loss": 0.9107, "step": 1710 }, { "epoch": 0.15385991591376688, "grad_norm": 0.46675220131874084, "learning_rate": 2e-05, "loss": 0.9009, "step": 1720 }, { "epoch": 0.15475445030861437, "grad_norm": 0.4796220064163208, "learning_rate": 2e-05, "loss": 0.9012, "step": 1730 }, { "epoch": 0.15564898470346183, "grad_norm": 0.4852994978427887, "learning_rate": 2e-05, "loss": 0.9032, "step": 1740 }, { "epoch": 0.15654351909830932, "grad_norm": 0.4488218128681183, "learning_rate": 2e-05, "loss": 0.8956, "step": 1750 }, { "epoch": 0.15743805349315682, "grad_norm": 0.4514853060245514, "learning_rate": 2e-05, "loss": 0.9065, "step": 1760 }, { "epoch": 0.1583325878880043, "grad_norm": 0.45019781589508057, "learning_rate": 2e-05, "loss": 0.8699, "step": 1770 }, { "epoch": 0.15922712228285177, "grad_norm": 0.4355997145175934, "learning_rate": 2e-05, "loss": 0.882, "step": 1780 }, { "epoch": 0.16012165667769926, "grad_norm": 0.45496049523353577, "learning_rate": 2e-05, "loss": 0.8822, "step": 1790 }, { "epoch": 0.16101619107254675, "grad_norm": 0.4723767936229706, "learning_rate": 2e-05, "loss": 0.8843, "step": 1800 }, { "epoch": 0.1619107254673942, "grad_norm": 0.44647493958473206, "learning_rate": 2e-05, "loss": 0.9143, "step": 1810 }, { "epoch": 0.1628052598622417, "grad_norm": 0.4418398439884186, "learning_rate": 2e-05, "loss": 0.8893, "step": 1820 }, { "epoch": 0.1636997942570892, "grad_norm": 0.45358505845069885, "learning_rate": 2e-05, "loss": 0.9136, "step": 1830 }, { "epoch": 0.16459432865193666, "grad_norm": 0.43691468238830566, "learning_rate": 2e-05, "loss": 0.9098, "step": 1840 }, { "epoch": 0.16548886304678415, "grad_norm": 0.43452972173690796, "learning_rate": 2e-05, "loss": 0.9034, "step": 1850 }, { "epoch": 0.16638339744163164, "grad_norm": 0.4491502046585083, "learning_rate": 2e-05, "loss": 0.8972, "step": 1860 }, { "epoch": 0.1672779318364791, "grad_norm": 0.4505089223384857, "learning_rate": 2e-05, "loss": 0.8686, "step": 1870 }, { "epoch": 0.1681724662313266, "grad_norm": 0.44601932168006897, "learning_rate": 2e-05, "loss": 0.8819, "step": 1880 }, { "epoch": 0.16906700062617408, "grad_norm": 0.4459923803806305, "learning_rate": 2e-05, "loss": 0.8992, "step": 1890 }, { "epoch": 0.16996153502102157, "grad_norm": 0.5818774700164795, "learning_rate": 2e-05, "loss": 0.8939, "step": 1900 }, { "epoch": 0.17085606941586903, "grad_norm": 0.4722735583782196, "learning_rate": 2e-05, "loss": 0.9326, "step": 1910 }, { "epoch": 0.17175060381071652, "grad_norm": 0.4823867976665497, "learning_rate": 2e-05, "loss": 0.8946, "step": 1920 }, { "epoch": 0.172645138205564, "grad_norm": 0.44365358352661133, "learning_rate": 2e-05, "loss": 0.8925, "step": 1930 }, { "epoch": 0.17353967260041148, "grad_norm": 0.4581582248210907, "learning_rate": 2e-05, "loss": 0.8966, "step": 1940 }, { "epoch": 0.17443420699525897, "grad_norm": 0.4919745624065399, "learning_rate": 2e-05, "loss": 0.9013, "step": 1950 }, { "epoch": 0.17532874139010646, "grad_norm": 0.44615697860717773, "learning_rate": 2e-05, "loss": 0.8969, "step": 1960 }, { "epoch": 0.17622327578495392, "grad_norm": 0.45378655195236206, "learning_rate": 2e-05, "loss": 0.874, "step": 1970 }, { "epoch": 0.1771178101798014, "grad_norm": 0.45912545919418335, "learning_rate": 2e-05, "loss": 0.8976, "step": 1980 }, { "epoch": 0.1780123445746489, "grad_norm": 0.4544883966445923, "learning_rate": 2e-05, "loss": 0.8899, "step": 1990 }, { "epoch": 0.17890687896949636, "grad_norm": 0.4370812475681305, "learning_rate": 2e-05, "loss": 0.8977, "step": 2000 }, { "epoch": 0.17980141336434385, "grad_norm": 0.44847485423088074, "learning_rate": 2e-05, "loss": 0.8791, "step": 2010 }, { "epoch": 0.18069594775919134, "grad_norm": 0.4509333074092865, "learning_rate": 2e-05, "loss": 0.8899, "step": 2020 }, { "epoch": 0.18159048215403883, "grad_norm": 0.44739288091659546, "learning_rate": 2e-05, "loss": 0.9084, "step": 2030 }, { "epoch": 0.1824850165488863, "grad_norm": 0.449127733707428, "learning_rate": 2e-05, "loss": 0.8859, "step": 2040 }, { "epoch": 0.1833795509437338, "grad_norm": 0.4499713182449341, "learning_rate": 2e-05, "loss": 0.8903, "step": 2050 }, { "epoch": 0.18427408533858128, "grad_norm": 0.4185994267463684, "learning_rate": 2e-05, "loss": 0.8626, "step": 2060 }, { "epoch": 0.18516861973342874, "grad_norm": 0.4529339075088501, "learning_rate": 2e-05, "loss": 0.878, "step": 2070 }, { "epoch": 0.18606315412827623, "grad_norm": 0.4742617905139923, "learning_rate": 2e-05, "loss": 0.8982, "step": 2080 }, { "epoch": 0.18695768852312372, "grad_norm": 0.4461440145969391, "learning_rate": 2e-05, "loss": 0.8736, "step": 2090 }, { "epoch": 0.18785222291797118, "grad_norm": 0.4527934193611145, "learning_rate": 2e-05, "loss": 0.882, "step": 2100 }, { "epoch": 0.18874675731281867, "grad_norm": 0.43730732798576355, "learning_rate": 2e-05, "loss": 0.8802, "step": 2110 }, { "epoch": 0.18964129170766617, "grad_norm": 0.44257083535194397, "learning_rate": 2e-05, "loss": 0.877, "step": 2120 }, { "epoch": 0.19053582610251363, "grad_norm": 0.4498806595802307, "learning_rate": 2e-05, "loss": 0.9177, "step": 2130 }, { "epoch": 0.19143036049736112, "grad_norm": 0.43403714895248413, "learning_rate": 2e-05, "loss": 0.8874, "step": 2140 }, { "epoch": 0.1923248948922086, "grad_norm": 0.4649515151977539, "learning_rate": 2e-05, "loss": 0.882, "step": 2150 }, { "epoch": 0.1932194292870561, "grad_norm": 0.43300893902778625, "learning_rate": 2e-05, "loss": 0.8978, "step": 2160 }, { "epoch": 0.19411396368190356, "grad_norm": 0.4571026861667633, "learning_rate": 2e-05, "loss": 0.904, "step": 2170 }, { "epoch": 0.19500849807675105, "grad_norm": 0.4482812285423279, "learning_rate": 2e-05, "loss": 0.8768, "step": 2180 }, { "epoch": 0.19590303247159854, "grad_norm": 0.44305941462516785, "learning_rate": 2e-05, "loss": 0.892, "step": 2190 }, { "epoch": 0.196797566866446, "grad_norm": 0.4517887532711029, "learning_rate": 2e-05, "loss": 0.8776, "step": 2200 }, { "epoch": 0.1976921012612935, "grad_norm": 0.4652104675769806, "learning_rate": 2e-05, "loss": 0.8825, "step": 2210 }, { "epoch": 0.198586635656141, "grad_norm": 0.4824739694595337, "learning_rate": 2e-05, "loss": 0.898, "step": 2220 }, { "epoch": 0.19948117005098845, "grad_norm": 0.4381744861602783, "learning_rate": 2e-05, "loss": 0.8702, "step": 2230 }, { "epoch": 0.20037570444583594, "grad_norm": 0.4330578148365021, "learning_rate": 2e-05, "loss": 0.8806, "step": 2240 }, { "epoch": 0.20127023884068343, "grad_norm": 0.44513505697250366, "learning_rate": 2e-05, "loss": 0.8892, "step": 2250 }, { "epoch": 0.2021647732355309, "grad_norm": 0.42694783210754395, "learning_rate": 2e-05, "loss": 0.8741, "step": 2260 }, { "epoch": 0.20305930763037838, "grad_norm": 0.4454619884490967, "learning_rate": 2e-05, "loss": 0.871, "step": 2270 }, { "epoch": 0.20395384202522587, "grad_norm": 0.4577361047267914, "learning_rate": 2e-05, "loss": 0.8874, "step": 2280 }, { "epoch": 0.20484837642007336, "grad_norm": 0.4306597113609314, "learning_rate": 2e-05, "loss": 0.8895, "step": 2290 }, { "epoch": 0.20574291081492083, "grad_norm": 0.4854651391506195, "learning_rate": 2e-05, "loss": 0.8888, "step": 2300 }, { "epoch": 0.20663744520976832, "grad_norm": 0.44619086384773254, "learning_rate": 2e-05, "loss": 0.8871, "step": 2310 }, { "epoch": 0.2075319796046158, "grad_norm": 0.47804850339889526, "learning_rate": 2e-05, "loss": 0.878, "step": 2320 }, { "epoch": 0.20842651399946327, "grad_norm": 0.4363088607788086, "learning_rate": 2e-05, "loss": 0.8831, "step": 2330 }, { "epoch": 0.20932104839431076, "grad_norm": 0.46656882762908936, "learning_rate": 2e-05, "loss": 0.8938, "step": 2340 }, { "epoch": 0.21021558278915825, "grad_norm": 0.44763514399528503, "learning_rate": 2e-05, "loss": 0.8854, "step": 2350 }, { "epoch": 0.2111101171840057, "grad_norm": 0.433299720287323, "learning_rate": 2e-05, "loss": 0.8665, "step": 2360 }, { "epoch": 0.2120046515788532, "grad_norm": 0.4781743288040161, "learning_rate": 2e-05, "loss": 0.8985, "step": 2370 }, { "epoch": 0.2128991859737007, "grad_norm": 0.4406478703022003, "learning_rate": 2e-05, "loss": 0.8802, "step": 2380 }, { "epoch": 0.21379372036854816, "grad_norm": 0.47858351469039917, "learning_rate": 2e-05, "loss": 0.8958, "step": 2390 }, { "epoch": 0.21468825476339565, "grad_norm": 0.45086878538131714, "learning_rate": 2e-05, "loss": 0.8771, "step": 2400 }, { "epoch": 0.21558278915824314, "grad_norm": 0.4594736695289612, "learning_rate": 2e-05, "loss": 0.8762, "step": 2410 }, { "epoch": 0.21647732355309063, "grad_norm": 0.45185622572898865, "learning_rate": 2e-05, "loss": 0.9032, "step": 2420 }, { "epoch": 0.2173718579479381, "grad_norm": 0.4313936233520508, "learning_rate": 2e-05, "loss": 0.8611, "step": 2430 }, { "epoch": 0.21826639234278558, "grad_norm": 0.4434468746185303, "learning_rate": 2e-05, "loss": 0.8803, "step": 2440 }, { "epoch": 0.21916092673763307, "grad_norm": 0.4205702245235443, "learning_rate": 2e-05, "loss": 0.8628, "step": 2450 }, { "epoch": 0.22005546113248053, "grad_norm": 0.44990837574005127, "learning_rate": 2e-05, "loss": 0.8886, "step": 2460 }, { "epoch": 0.22094999552732802, "grad_norm": 0.4437563717365265, "learning_rate": 2e-05, "loss": 0.877, "step": 2470 }, { "epoch": 0.22184452992217552, "grad_norm": 0.4536307156085968, "learning_rate": 2e-05, "loss": 0.8767, "step": 2480 }, { "epoch": 0.22273906431702298, "grad_norm": 0.4591897428035736, "learning_rate": 2e-05, "loss": 0.9098, "step": 2490 }, { "epoch": 0.22363359871187047, "grad_norm": 0.4403884708881378, "learning_rate": 2e-05, "loss": 0.883, "step": 2500 }, { "epoch": 0.22452813310671796, "grad_norm": 0.4733695089817047, "learning_rate": 2e-05, "loss": 0.8779, "step": 2510 }, { "epoch": 0.22542266750156542, "grad_norm": 0.4368247985839844, "learning_rate": 2e-05, "loss": 0.8813, "step": 2520 }, { "epoch": 0.2263172018964129, "grad_norm": 0.4843006730079651, "learning_rate": 2e-05, "loss": 0.8819, "step": 2530 }, { "epoch": 0.2272117362912604, "grad_norm": 0.4408707022666931, "learning_rate": 2e-05, "loss": 0.8836, "step": 2540 }, { "epoch": 0.2281062706861079, "grad_norm": 0.46025708317756653, "learning_rate": 1.9980979278401095e-05, "loss": 0.8587, "step": 2550 }, { "epoch": 0.22900080508095536, "grad_norm": 0.4575076997280121, "learning_rate": 1.982924955463327e-05, "loss": 0.9006, "step": 2560 }, { "epoch": 0.22989533947580285, "grad_norm": 0.44038093090057373, "learning_rate": 1.9528108298328235e-05, "loss": 0.8911, "step": 2570 }, { "epoch": 0.23078987387065034, "grad_norm": 0.43975573778152466, "learning_rate": 1.9082156473635994e-05, "loss": 0.8965, "step": 2580 }, { "epoch": 0.2316844082654978, "grad_norm": 0.44760194420814514, "learning_rate": 1.8498207522139434e-05, "loss": 0.8712, "step": 2590 }, { "epoch": 0.2325789426603453, "grad_norm": 0.46463868021965027, "learning_rate": 1.7785183264196977e-05, "loss": 0.8822, "step": 2600 }, { "epoch": 0.23347347705519278, "grad_norm": 0.46464139223098755, "learning_rate": 1.6953977587577846e-05, "loss": 0.8819, "step": 2610 }, { "epoch": 0.23436801145004024, "grad_norm": 0.4356214106082916, "learning_rate": 1.601729000601297e-05, "loss": 0.8659, "step": 2620 }, { "epoch": 0.23526254584488773, "grad_norm": 0.40483734011650085, "learning_rate": 1.4989431630624763e-05, "loss": 0.8763, "step": 2630 }, { "epoch": 0.23615708023973522, "grad_norm": 0.43536725640296936, "learning_rate": 1.3886106518686746e-05, "loss": 0.876, "step": 2640 }, { "epoch": 0.2370516146345827, "grad_norm": 0.44640520215034485, "learning_rate": 1.2724171740359612e-05, "loss": 0.8562, "step": 2650 }, { "epoch": 0.23794614902943018, "grad_norm": 0.5255842208862305, "learning_rate": 1.1521379829206218e-05, "loss": 0.8617, "step": 2660 }, { "epoch": 0.23884068342427767, "grad_norm": 0.41223350167274475, "learning_rate": 1.029610755143595e-05, "loss": 0.8468, "step": 2670 }, { "epoch": 0.23973521781912516, "grad_norm": 0.4402216970920563, "learning_rate": 9.067075137857348e-06, "loss": 0.8725, "step": 2680 }, { "epoch": 0.24062975221397262, "grad_norm": 0.4099200367927551, "learning_rate": 7.853060268232525e-06, "loss": 0.872, "step": 2690 }, { "epoch": 0.2415242866088201, "grad_norm": 0.4035118818283081, "learning_rate": 6.672611177902054e-06, "loss": 0.8642, "step": 2700 }, { "epoch": 0.2424188210036676, "grad_norm": 0.4037860333919525, "learning_rate": 5.543763269959312e-06, "loss": 0.8539, "step": 2710 }, { "epoch": 0.24331335539851506, "grad_norm": 0.42922675609588623, "learning_rate": 4.483763562693867e-06, "loss": 0.8584, "step": 2720 }, { "epoch": 0.24420788979336255, "grad_norm": 0.4086989760398865, "learning_rate": 3.508807182313187e-06, "loss": 0.8428, "step": 2730 }, { "epoch": 0.24510242418821004, "grad_norm": 0.4165908694267273, "learning_rate": 2.6337899269187294e-06, "loss": 0.8448, "step": 2740 }, { "epoch": 0.2459969585830575, "grad_norm": 0.43217164278030396, "learning_rate": 1.8720806821693126e-06, "loss": 0.8429, "step": 2750 }, { "epoch": 0.246891492977905, "grad_norm": 0.41365790367126465, "learning_rate": 1.2353171657619887e-06, "loss": 0.8559, "step": 2760 }, { "epoch": 0.2477860273727525, "grad_norm": 0.413800448179245, "learning_rate": 7.332281214330356e-07, "loss": 0.8453, "step": 2770 }, { "epoch": 0.24868056176759998, "grad_norm": 0.4116990566253662, "learning_rate": 3.73484679074808e-07, "loss": 0.8559, "step": 2780 }, { "epoch": 0.24957509616244744, "grad_norm": 0.4760894179344177, "learning_rate": 1.61583151951702e-07, "loss": 0.8797, "step": 2790 }, { "epoch": 0.25029072367832544, "step": 2798, "total_flos": 1.1366756130249245e+19, "train_loss": 0.07891935139915789, "train_runtime": 2310.0434, "train_samples_per_second": 14.535, "train_steps_per_second": 1.211 } ], "logging_steps": 10, "max_steps": 2798, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 159, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.1366756130249245e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }