{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999438727782975,
  "eval_steps": 500,
  "global_step": 2004,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014967259120673527,
      "grad_norm": 1.687756308961026,
      "learning_rate": 5e-06,
      "loss": 0.7782,
      "step": 10
    },
    {
      "epoch": 0.029934518241347054,
      "grad_norm": 1.0698249639597102,
      "learning_rate": 5e-06,
      "loss": 0.6964,
      "step": 20
    },
    {
      "epoch": 0.04490177736202058,
      "grad_norm": 0.9332705468658162,
      "learning_rate": 5e-06,
      "loss": 0.6801,
      "step": 30
    },
    {
      "epoch": 0.05986903648269411,
      "grad_norm": 1.0261038631793118,
      "learning_rate": 5e-06,
      "loss": 0.6742,
      "step": 40
    },
    {
      "epoch": 0.07483629560336763,
      "grad_norm": 1.0825159776525728,
      "learning_rate": 5e-06,
      "loss": 0.6556,
      "step": 50
    },
    {
      "epoch": 0.08980355472404115,
      "grad_norm": 0.9332530055423296,
      "learning_rate": 5e-06,
      "loss": 0.6652,
      "step": 60
    },
    {
      "epoch": 0.10477081384471469,
      "grad_norm": 0.9484632557878909,
      "learning_rate": 5e-06,
      "loss": 0.6606,
      "step": 70
    },
    {
      "epoch": 0.11973807296538821,
      "grad_norm": 0.9214146261571381,
      "learning_rate": 5e-06,
      "loss": 0.6575,
      "step": 80
    },
    {
      "epoch": 0.13470533208606175,
      "grad_norm": 0.8461055206709674,
      "learning_rate": 5e-06,
      "loss": 0.6513,
      "step": 90
    },
    {
      "epoch": 0.14967259120673526,
      "grad_norm": 0.8808098299747461,
      "learning_rate": 5e-06,
      "loss": 0.6523,
      "step": 100
    },
    {
      "epoch": 0.1646398503274088,
      "grad_norm": 0.9553360689545759,
      "learning_rate": 5e-06,
      "loss": 0.6433,
      "step": 110
    },
    {
      "epoch": 0.1796071094480823,
      "grad_norm": 0.9441374712008397,
      "learning_rate": 5e-06,
      "loss": 0.6484,
      "step": 120
    },
    {
      "epoch": 0.19457436856875585,
      "grad_norm": 0.9974947150622011,
      "learning_rate": 5e-06,
      "loss": 0.6465,
      "step": 130
    },
    {
      "epoch": 0.20954162768942938,
      "grad_norm": 0.95784361345895,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 140
    },
    {
      "epoch": 0.2245088868101029,
      "grad_norm": 1.0031066143657386,
      "learning_rate": 5e-06,
      "loss": 0.6465,
      "step": 150
    },
    {
      "epoch": 0.23947614593077643,
      "grad_norm": 0.8807529231290085,
      "learning_rate": 5e-06,
      "loss": 0.6439,
      "step": 160
    },
    {
      "epoch": 0.25444340505144997,
      "grad_norm": 0.8581508220580464,
      "learning_rate": 5e-06,
      "loss": 0.6338,
      "step": 170
    },
    {
      "epoch": 0.2694106641721235,
      "grad_norm": 0.9615203351934102,
      "learning_rate": 5e-06,
      "loss": 0.639,
      "step": 180
    },
    {
      "epoch": 0.284377923292797,
      "grad_norm": 0.9820491322429695,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 190
    },
    {
      "epoch": 0.2993451824134705,
      "grad_norm": 0.879620392692244,
      "learning_rate": 5e-06,
      "loss": 0.6324,
      "step": 200
    },
    {
      "epoch": 0.31431244153414406,
      "grad_norm": 0.8606567983645269,
      "learning_rate": 5e-06,
      "loss": 0.6353,
      "step": 210
    },
    {
      "epoch": 0.3292797006548176,
      "grad_norm": 0.9252734163250933,
      "learning_rate": 5e-06,
      "loss": 0.6336,
      "step": 220
    },
    {
      "epoch": 0.34424695977549113,
      "grad_norm": 0.8597262458946381,
      "learning_rate": 5e-06,
      "loss": 0.6354,
      "step": 230
    },
    {
      "epoch": 0.3592142188961646,
      "grad_norm": 0.9103837292008289,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 240
    },
    {
      "epoch": 0.37418147801683815,
      "grad_norm": 0.8625582037347029,
      "learning_rate": 5e-06,
      "loss": 0.6324,
      "step": 250
    },
    {
      "epoch": 0.3891487371375117,
      "grad_norm": 0.9419041560521573,
      "learning_rate": 5e-06,
      "loss": 0.6341,
      "step": 260
    },
    {
      "epoch": 0.40411599625818523,
      "grad_norm": 0.9207852193278893,
      "learning_rate": 5e-06,
      "loss": 0.6279,
      "step": 270
    },
    {
      "epoch": 0.41908325537885877,
      "grad_norm": 0.8561852049872601,
      "learning_rate": 5e-06,
      "loss": 0.6265,
      "step": 280
    },
    {
      "epoch": 0.43405051449953225,
      "grad_norm": 0.8247824829057294,
      "learning_rate": 5e-06,
      "loss": 0.6326,
      "step": 290
    },
    {
      "epoch": 0.4490177736202058,
      "grad_norm": 0.8461841915943655,
      "learning_rate": 5e-06,
      "loss": 0.6251,
      "step": 300
    },
    {
      "epoch": 0.4639850327408793,
      "grad_norm": 0.8176471461298459,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 310
    },
    {
      "epoch": 0.47895229186155286,
      "grad_norm": 0.9037831884480791,
      "learning_rate": 5e-06,
      "loss": 0.6246,
      "step": 320
    },
    {
      "epoch": 0.4939195509822264,
      "grad_norm": 0.8825444951097245,
      "learning_rate": 5e-06,
      "loss": 0.617,
      "step": 330
    },
    {
      "epoch": 0.5088868101028999,
      "grad_norm": 0.9033949174314017,
      "learning_rate": 5e-06,
      "loss": 0.6283,
      "step": 340
    },
    {
      "epoch": 0.5238540692235735,
      "grad_norm": 0.8364452971579758,
      "learning_rate": 5e-06,
      "loss": 0.6231,
      "step": 350
    },
    {
      "epoch": 0.538821328344247,
      "grad_norm": 0.8460940073048903,
      "learning_rate": 5e-06,
      "loss": 0.6252,
      "step": 360
    },
    {
      "epoch": 0.5537885874649204,
      "grad_norm": 0.8790251342086226,
      "learning_rate": 5e-06,
      "loss": 0.6276,
      "step": 370
    },
    {
      "epoch": 0.568755846585594,
      "grad_norm": 0.8127680920941638,
      "learning_rate": 5e-06,
      "loss": 0.6161,
      "step": 380
    },
    {
      "epoch": 0.5837231057062675,
      "grad_norm": 0.865147274963386,
      "learning_rate": 5e-06,
      "loss": 0.6319,
      "step": 390
    },
    {
      "epoch": 0.598690364826941,
      "grad_norm": 0.8860907128639037,
      "learning_rate": 5e-06,
      "loss": 0.6283,
      "step": 400
    },
    {
      "epoch": 0.6136576239476146,
      "grad_norm": 0.9019064432421782,
      "learning_rate": 5e-06,
      "loss": 0.6242,
      "step": 410
    },
    {
      "epoch": 0.6286248830682881,
      "grad_norm": 0.7873993321653365,
      "learning_rate": 5e-06,
      "loss": 0.6229,
      "step": 420
    },
    {
      "epoch": 0.6435921421889617,
      "grad_norm": 0.8088646306397351,
      "learning_rate": 5e-06,
      "loss": 0.6222,
      "step": 430
    },
    {
      "epoch": 0.6585594013096352,
      "grad_norm": 0.7970354985534349,
      "learning_rate": 5e-06,
      "loss": 0.6214,
      "step": 440
    },
    {
      "epoch": 0.6735266604303087,
      "grad_norm": 0.8487199770026921,
      "learning_rate": 5e-06,
      "loss": 0.6257,
      "step": 450
    },
    {
      "epoch": 0.6884939195509823,
      "grad_norm": 0.8038765739674171,
      "learning_rate": 5e-06,
      "loss": 0.6239,
      "step": 460
    },
    {
      "epoch": 0.7034611786716558,
      "grad_norm": 0.8346700710585229,
      "learning_rate": 5e-06,
      "loss": 0.6278,
      "step": 470
    },
    {
      "epoch": 0.7184284377923292,
      "grad_norm": 0.8401008391739484,
      "learning_rate": 5e-06,
      "loss": 0.6195,
      "step": 480
    },
    {
      "epoch": 0.7333956969130028,
      "grad_norm": 0.7920161471043963,
      "learning_rate": 5e-06,
      "loss": 0.6261,
      "step": 490
    },
    {
      "epoch": 0.7483629560336763,
      "grad_norm": 0.742346241473902,
      "learning_rate": 5e-06,
      "loss": 0.6147,
      "step": 500
    },
    {
      "epoch": 0.7633302151543498,
      "grad_norm": 0.7737935579266697,
      "learning_rate": 5e-06,
      "loss": 0.6156,
      "step": 510
    },
    {
      "epoch": 0.7782974742750234,
      "grad_norm": 0.8249292013488594,
      "learning_rate": 5e-06,
      "loss": 0.6218,
      "step": 520
    },
    {
      "epoch": 0.7932647333956969,
      "grad_norm": 0.7994259446398758,
      "learning_rate": 5e-06,
      "loss": 0.6255,
      "step": 530
    },
    {
      "epoch": 0.8082319925163705,
      "grad_norm": 0.818039661398219,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 540
    },
    {
      "epoch": 0.823199251637044,
      "grad_norm": 0.8143406491781928,
      "learning_rate": 5e-06,
      "loss": 0.6156,
      "step": 550
    },
    {
      "epoch": 0.8381665107577175,
      "grad_norm": 0.8345755477839126,
      "learning_rate": 5e-06,
      "loss": 0.6183,
      "step": 560
    },
    {
      "epoch": 0.8531337698783911,
      "grad_norm": 0.7539802888013517,
      "learning_rate": 5e-06,
      "loss": 0.6148,
      "step": 570
    },
    {
      "epoch": 0.8681010289990645,
      "grad_norm": 0.845269986126954,
      "learning_rate": 5e-06,
      "loss": 0.6126,
      "step": 580
    },
    {
      "epoch": 0.883068288119738,
      "grad_norm": 0.7806668944488291,
      "learning_rate": 5e-06,
      "loss": 0.6147,
      "step": 590
    },
    {
      "epoch": 0.8980355472404116,
      "grad_norm": 0.7746590227889528,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 600
    },
    {
      "epoch": 0.9130028063610851,
      "grad_norm": 0.8139764519397722,
      "learning_rate": 5e-06,
      "loss": 0.6167,
      "step": 610
    },
    {
      "epoch": 0.9279700654817586,
      "grad_norm": 0.8275119990423779,
      "learning_rate": 5e-06,
      "loss": 0.6106,
      "step": 620
    },
    {
      "epoch": 0.9429373246024322,
      "grad_norm": 0.9237585417267786,
      "learning_rate": 5e-06,
      "loss": 0.6176,
      "step": 630
    },
    {
      "epoch": 0.9579045837231057,
      "grad_norm": 0.8243049750976574,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 640
    },
    {
      "epoch": 0.9728718428437793,
      "grad_norm": 0.8165581310754791,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 650
    },
    {
      "epoch": 0.9878391019644528,
      "grad_norm": 0.7663177196293486,
      "learning_rate": 5e-06,
      "loss": 0.616,
      "step": 660
    },
    {
      "epoch": 0.9998129092609915,
      "eval_loss": 0.6200858950614929,
      "eval_runtime": 516.187,
      "eval_samples_per_second": 17.437,
      "eval_steps_per_second": 0.546,
      "step": 668
    },
    {
      "epoch": 1.0028063610851263,
      "grad_norm": 1.1170536124486408,
      "learning_rate": 5e-06,
      "loss": 0.6487,
      "step": 670
    },
    {
      "epoch": 1.0177736202057999,
      "grad_norm": 0.8856574281903234,
      "learning_rate": 5e-06,
      "loss": 0.545,
      "step": 680
    },
    {
      "epoch": 1.0327408793264734,
      "grad_norm": 1.898658638864262,
      "learning_rate": 5e-06,
      "loss": 0.5337,
      "step": 690
    },
    {
      "epoch": 1.047708138447147,
      "grad_norm": 0.8459912707822864,
      "learning_rate": 5e-06,
      "loss": 0.5325,
      "step": 700
    },
    {
      "epoch": 1.0626753975678205,
      "grad_norm": 0.8248329338575271,
      "learning_rate": 5e-06,
      "loss": 0.5318,
      "step": 710
    },
    {
      "epoch": 1.077642656688494,
      "grad_norm": 0.813954594100977,
      "learning_rate": 5e-06,
      "loss": 0.5295,
      "step": 720
    },
    {
      "epoch": 1.0926099158091676,
      "grad_norm": 0.8086922756009814,
      "learning_rate": 5e-06,
      "loss": 0.5317,
      "step": 730
    },
    {
      "epoch": 1.1075771749298409,
      "grad_norm": 0.8535855916459573,
      "learning_rate": 5e-06,
      "loss": 0.5315,
      "step": 740
    },
    {
      "epoch": 1.1225444340505144,
      "grad_norm": 0.8672492316583479,
      "learning_rate": 5e-06,
      "loss": 0.533,
      "step": 750
    },
    {
      "epoch": 1.137511693171188,
      "grad_norm": 0.849809374888646,
      "learning_rate": 5e-06,
      "loss": 0.5316,
      "step": 760
    },
    {
      "epoch": 1.1524789522918615,
      "grad_norm": 0.8734792854015357,
      "learning_rate": 5e-06,
      "loss": 0.5359,
      "step": 770
    },
    {
      "epoch": 1.167446211412535,
      "grad_norm": 0.8777387743337014,
      "learning_rate": 5e-06,
      "loss": 0.5335,
      "step": 780
    },
    {
      "epoch": 1.1824134705332086,
      "grad_norm": 0.8041848975604132,
      "learning_rate": 5e-06,
      "loss": 0.5353,
      "step": 790
    },
    {
      "epoch": 1.197380729653882,
      "grad_norm": 0.7912034492290017,
      "learning_rate": 5e-06,
      "loss": 0.534,
      "step": 800
    },
    {
      "epoch": 1.2123479887745556,
      "grad_norm": 0.8735534255189403,
      "learning_rate": 5e-06,
      "loss": 0.5342,
      "step": 810
    },
    {
      "epoch": 1.2273152478952292,
      "grad_norm": 0.8162372778454181,
      "learning_rate": 5e-06,
      "loss": 0.5406,
      "step": 820
    },
    {
      "epoch": 1.2422825070159027,
      "grad_norm": 0.8722296317071789,
      "learning_rate": 5e-06,
      "loss": 0.5402,
      "step": 830
    },
    {
      "epoch": 1.2572497661365762,
      "grad_norm": 0.7892298563846264,
      "learning_rate": 5e-06,
      "loss": 0.5421,
      "step": 840
    },
    {
      "epoch": 1.2722170252572498,
      "grad_norm": 0.8406828468259798,
      "learning_rate": 5e-06,
      "loss": 0.5341,
      "step": 850
    },
    {
      "epoch": 1.2871842843779233,
      "grad_norm": 0.8447770419704688,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 860
    },
    {
      "epoch": 1.3021515434985969,
      "grad_norm": 0.8164589565791014,
      "learning_rate": 5e-06,
      "loss": 0.5401,
      "step": 870
    },
    {
      "epoch": 1.3171188026192704,
      "grad_norm": 0.856927501195802,
      "learning_rate": 5e-06,
      "loss": 0.5379,
      "step": 880
    },
    {
      "epoch": 1.332086061739944,
      "grad_norm": 0.814303049641248,
      "learning_rate": 5e-06,
      "loss": 0.5338,
      "step": 890
    },
    {
      "epoch": 1.3470533208606175,
      "grad_norm": 0.7959421345588171,
      "learning_rate": 5e-06,
      "loss": 0.5341,
      "step": 900
    },
    {
      "epoch": 1.362020579981291,
      "grad_norm": 0.931061520444297,
      "learning_rate": 5e-06,
      "loss": 0.5465,
      "step": 910
    },
    {
      "epoch": 1.3769878391019645,
      "grad_norm": 0.7951083389588972,
      "learning_rate": 5e-06,
      "loss": 0.5419,
      "step": 920
    },
    {
      "epoch": 1.3919550982226379,
      "grad_norm": 0.9720390181024717,
      "learning_rate": 5e-06,
      "loss": 0.5431,
      "step": 930
    },
    {
      "epoch": 1.4069223573433116,
      "grad_norm": 0.9012675576162279,
      "learning_rate": 5e-06,
      "loss": 0.5432,
      "step": 940
    },
    {
      "epoch": 1.421889616463985,
      "grad_norm": 0.852351543061142,
      "learning_rate": 5e-06,
      "loss": 0.5419,
      "step": 950
    },
    {
      "epoch": 1.4368568755846587,
      "grad_norm": 0.8898678479179962,
      "learning_rate": 5e-06,
      "loss": 0.5491,
      "step": 960
    },
    {
      "epoch": 1.451824134705332,
      "grad_norm": 0.7828658877758132,
      "learning_rate": 5e-06,
      "loss": 0.5508,
      "step": 970
    },
    {
      "epoch": 1.4667913938260055,
      "grad_norm": 0.9174782134021202,
      "learning_rate": 5e-06,
      "loss": 0.5394,
      "step": 980
    },
    {
      "epoch": 1.481758652946679,
      "grad_norm": 0.8489514473528214,
      "learning_rate": 5e-06,
      "loss": 0.5439,
      "step": 990
    },
    {
      "epoch": 1.4967259120673526,
      "grad_norm": 0.8043224208585217,
      "learning_rate": 5e-06,
      "loss": 0.5382,
      "step": 1000
    },
    {
      "epoch": 1.5116931711880262,
      "grad_norm": 0.8111311622922805,
      "learning_rate": 5e-06,
      "loss": 0.5421,
      "step": 1010
    },
    {
      "epoch": 1.5266604303086997,
      "grad_norm": 0.831411017482453,
      "learning_rate": 5e-06,
      "loss": 0.5465,
      "step": 1020
    },
    {
      "epoch": 1.5416276894293732,
      "grad_norm": 0.8748452706018791,
      "learning_rate": 5e-06,
      "loss": 0.5403,
      "step": 1030
    },
    {
      "epoch": 1.5565949485500468,
      "grad_norm": 0.8437823970471942,
      "learning_rate": 5e-06,
      "loss": 0.5451,
      "step": 1040
    },
    {
      "epoch": 1.5715622076707203,
      "grad_norm": 0.9079465616112685,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 1050
    },
    {
      "epoch": 1.5865294667913938,
      "grad_norm": 0.8455609362427332,
      "learning_rate": 5e-06,
      "loss": 0.5462,
      "step": 1060
    },
    {
      "epoch": 1.6014967259120674,
      "grad_norm": 0.889134512252003,
      "learning_rate": 5e-06,
      "loss": 0.5455,
      "step": 1070
    },
    {
      "epoch": 1.616463985032741,
      "grad_norm": 0.7889243088357086,
      "learning_rate": 5e-06,
      "loss": 0.5487,
      "step": 1080
    },
    {
      "epoch": 1.6314312441534145,
      "grad_norm": 0.8444191418764766,
      "learning_rate": 5e-06,
      "loss": 0.5449,
      "step": 1090
    },
    {
      "epoch": 1.646398503274088,
      "grad_norm": 0.7713234865594601,
      "learning_rate": 5e-06,
      "loss": 0.5485,
      "step": 1100
    },
    {
      "epoch": 1.6613657623947615,
      "grad_norm": 0.7959175277328504,
      "learning_rate": 5e-06,
      "loss": 0.5378,
      "step": 1110
    },
    {
      "epoch": 1.6763330215154348,
      "grad_norm": 0.7911572585508888,
      "learning_rate": 5e-06,
      "loss": 0.5366,
      "step": 1120
    },
    {
      "epoch": 1.6913002806361086,
      "grad_norm": 0.7662962056931449,
      "learning_rate": 5e-06,
      "loss": 0.5378,
      "step": 1130
    },
    {
      "epoch": 1.706267539756782,
      "grad_norm": 0.7749402738184956,
      "learning_rate": 5e-06,
      "loss": 0.5406,
      "step": 1140
    },
    {
      "epoch": 1.7212347988774557,
      "grad_norm": 0.7689120620357122,
      "learning_rate": 5e-06,
      "loss": 0.5381,
      "step": 1150
    },
    {
      "epoch": 1.736202057998129,
      "grad_norm": 0.8311106901690507,
      "learning_rate": 5e-06,
      "loss": 0.5418,
      "step": 1160
    },
    {
      "epoch": 1.7511693171188027,
      "grad_norm": 0.7991618750196898,
      "learning_rate": 5e-06,
      "loss": 0.5403,
      "step": 1170
    },
    {
      "epoch": 1.766136576239476,
      "grad_norm": 0.7946772907410126,
      "learning_rate": 5e-06,
      "loss": 0.5469,
      "step": 1180
    },
    {
      "epoch": 1.7811038353601498,
      "grad_norm": 0.8142059419435724,
      "learning_rate": 5e-06,
      "loss": 0.5467,
      "step": 1190
    },
    {
      "epoch": 1.7960710944808231,
      "grad_norm": 0.8541004900745022,
      "learning_rate": 5e-06,
      "loss": 0.5421,
      "step": 1200
    },
    {
      "epoch": 1.8110383536014967,
      "grad_norm": 0.8990943829718473,
      "learning_rate": 5e-06,
      "loss": 0.5488,
      "step": 1210
    },
    {
      "epoch": 1.8260056127221702,
      "grad_norm": 0.8052802773215911,
      "learning_rate": 5e-06,
      "loss": 0.5363,
      "step": 1220
    },
    {
      "epoch": 1.8409728718428437,
      "grad_norm": 0.8790682955427265,
      "learning_rate": 5e-06,
      "loss": 0.54,
      "step": 1230
    },
    {
      "epoch": 1.8559401309635173,
      "grad_norm": 0.7889047940536035,
      "learning_rate": 5e-06,
      "loss": 0.5417,
      "step": 1240
    },
    {
      "epoch": 1.8709073900841908,
      "grad_norm": 0.7862127524262026,
      "learning_rate": 5e-06,
      "loss": 0.5469,
      "step": 1250
    },
    {
      "epoch": 1.8858746492048644,
      "grad_norm": 0.813942106139366,
      "learning_rate": 5e-06,
      "loss": 0.5376,
      "step": 1260
    },
    {
      "epoch": 1.900841908325538,
      "grad_norm": 0.7718984772376001,
      "learning_rate": 5e-06,
      "loss": 0.5439,
      "step": 1270
    },
    {
      "epoch": 1.9158091674462114,
      "grad_norm": 0.8990133826528317,
      "learning_rate": 5e-06,
      "loss": 0.5444,
      "step": 1280
    },
    {
      "epoch": 1.930776426566885,
      "grad_norm": 0.8451999953010673,
      "learning_rate": 5e-06,
      "loss": 0.5419,
      "step": 1290
    },
    {
      "epoch": 1.9457436856875585,
      "grad_norm": 0.8693925655067402,
      "learning_rate": 5e-06,
      "loss": 0.5433,
      "step": 1300
    },
    {
      "epoch": 1.960710944808232,
      "grad_norm": 0.7792559033290458,
      "learning_rate": 5e-06,
      "loss": 0.5503,
      "step": 1310
    },
    {
      "epoch": 1.9756782039289056,
      "grad_norm": 0.8082303654186193,
      "learning_rate": 5e-06,
      "loss": 0.5438,
      "step": 1320
    },
    {
      "epoch": 1.990645463049579,
      "grad_norm": 0.7892786724937234,
      "learning_rate": 5e-06,
      "loss": 0.5488,
      "step": 1330
    },
    {
      "epoch": 1.999625818521983,
      "eval_loss": 0.6217324733734131,
      "eval_runtime": 515.8781,
      "eval_samples_per_second": 17.448,
      "eval_steps_per_second": 0.547,
      "step": 1336
    },
    {
      "epoch": 2.0056127221702527,
      "grad_norm": 1.3394082173648911,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 1340
    },
    {
      "epoch": 2.020579981290926,
      "grad_norm": 0.9455500711158181,
      "learning_rate": 5e-06,
      "loss": 0.4541,
      "step": 1350
    },
    {
      "epoch": 2.0355472404115997,
      "grad_norm": 0.8919037738913939,
      "learning_rate": 5e-06,
      "loss": 0.443,
      "step": 1360
    },
    {
      "epoch": 2.050514499532273,
      "grad_norm": 0.8853456844504819,
      "learning_rate": 5e-06,
      "loss": 0.4414,
      "step": 1370
    },
    {
      "epoch": 2.065481758652947,
      "grad_norm": 0.8485892114312167,
      "learning_rate": 5e-06,
      "loss": 0.4524,
      "step": 1380
    },
    {
      "epoch": 2.08044901777362,
      "grad_norm": 0.9463847501605079,
      "learning_rate": 5e-06,
      "loss": 0.4531,
      "step": 1390
    },
    {
      "epoch": 2.095416276894294,
      "grad_norm": 0.9497257544030023,
      "learning_rate": 5e-06,
      "loss": 0.4517,
      "step": 1400
    },
    {
      "epoch": 2.110383536014967,
      "grad_norm": 0.8189561585322297,
      "learning_rate": 5e-06,
      "loss": 0.4551,
      "step": 1410
    },
    {
      "epoch": 2.125350795135641,
      "grad_norm": 0.8476584842991027,
      "learning_rate": 5e-06,
      "loss": 0.4516,
      "step": 1420
    },
    {
      "epoch": 2.1403180542563143,
      "grad_norm": 0.9531083392798131,
      "learning_rate": 5e-06,
      "loss": 0.4585,
      "step": 1430
    },
    {
      "epoch": 2.155285313376988,
      "grad_norm": 0.858332341068255,
      "learning_rate": 5e-06,
      "loss": 0.4559,
      "step": 1440
    },
    {
      "epoch": 2.1702525724976613,
      "grad_norm": 0.8528045417109313,
      "learning_rate": 5e-06,
      "loss": 0.4568,
      "step": 1450
    },
    {
      "epoch": 2.185219831618335,
      "grad_norm": 0.8586450212292938,
      "learning_rate": 5e-06,
      "loss": 0.4586,
      "step": 1460
    },
    {
      "epoch": 2.2001870907390084,
      "grad_norm": 0.9090116266013308,
      "learning_rate": 5e-06,
      "loss": 0.457,
      "step": 1470
    },
    {
      "epoch": 2.2151543498596817,
      "grad_norm": 0.925903855994679,
      "learning_rate": 5e-06,
      "loss": 0.4601,
      "step": 1480
    },
    {
      "epoch": 2.2301216089803555,
      "grad_norm": 0.9831619333579624,
      "learning_rate": 5e-06,
      "loss": 0.4642,
      "step": 1490
    },
    {
      "epoch": 2.245088868101029,
      "grad_norm": 0.9302811017506633,
      "learning_rate": 5e-06,
      "loss": 0.4581,
      "step": 1500
    },
    {
      "epoch": 2.2600561272217026,
      "grad_norm": 0.8465567985897775,
      "learning_rate": 5e-06,
      "loss": 0.4603,
      "step": 1510
    },
    {
      "epoch": 2.275023386342376,
      "grad_norm": 0.8665564335262731,
      "learning_rate": 5e-06,
      "loss": 0.453,
      "step": 1520
    },
    {
      "epoch": 2.2899906454630496,
      "grad_norm": 0.8797294889850988,
      "learning_rate": 5e-06,
      "loss": 0.4579,
      "step": 1530
    },
    {
      "epoch": 2.304957904583723,
      "grad_norm": 0.8654118820461358,
      "learning_rate": 5e-06,
      "loss": 0.4645,
      "step": 1540
    },
    {
      "epoch": 2.3199251637043967,
      "grad_norm": 0.8632491603380537,
      "learning_rate": 5e-06,
      "loss": 0.4581,
      "step": 1550
    },
    {
      "epoch": 2.33489242282507,
      "grad_norm": 0.9034853086019253,
      "learning_rate": 5e-06,
      "loss": 0.4599,
      "step": 1560
    },
    {
      "epoch": 2.349859681945744,
      "grad_norm": 0.9096284097262972,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 1570
    },
    {
      "epoch": 2.364826941066417,
      "grad_norm": 0.8752531162177063,
      "learning_rate": 5e-06,
      "loss": 0.4585,
      "step": 1580
    },
    {
      "epoch": 2.379794200187091,
      "grad_norm": 0.8332695421546112,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 1590
    },
    {
      "epoch": 2.394761459307764,
      "grad_norm": 0.9099668666415236,
      "learning_rate": 5e-06,
      "loss": 0.4603,
      "step": 1600
    },
    {
      "epoch": 2.409728718428438,
      "grad_norm": 0.8831411766109868,
      "learning_rate": 5e-06,
      "loss": 0.4657,
      "step": 1610
    },
    {
      "epoch": 2.4246959775491113,
      "grad_norm": 0.9763791447338257,
      "learning_rate": 5e-06,
      "loss": 0.4739,
      "step": 1620
    },
    {
      "epoch": 2.439663236669785,
      "grad_norm": 0.9074326365606225,
      "learning_rate": 5e-06,
      "loss": 0.4682,
      "step": 1630
    },
    {
      "epoch": 2.4546304957904583,
      "grad_norm": 0.8477921350667745,
      "learning_rate": 5e-06,
      "loss": 0.4675,
      "step": 1640
    },
    {
      "epoch": 2.469597754911132,
      "grad_norm": 0.832684309059508,
      "learning_rate": 5e-06,
      "loss": 0.4688,
      "step": 1650
    },
    {
      "epoch": 2.4845650140318054,
      "grad_norm": 0.8919058825305353,
      "learning_rate": 5e-06,
      "loss": 0.4673,
      "step": 1660
    },
    {
      "epoch": 2.4995322731524787,
      "grad_norm": 0.8844059574299349,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 1670
    },
    {
      "epoch": 2.5144995322731525,
      "grad_norm": 0.8601569824524091,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 1680
    },
    {
      "epoch": 2.5294667913938262,
      "grad_norm": 0.883071765836154,
      "learning_rate": 5e-06,
      "loss": 0.4674,
      "step": 1690
    },
    {
      "epoch": 2.5444340505144996,
      "grad_norm": 0.8717224493457566,
      "learning_rate": 5e-06,
      "loss": 0.4702,
      "step": 1700
    },
    {
      "epoch": 2.559401309635173,
      "grad_norm": 0.8922020617219165,
      "learning_rate": 5e-06,
      "loss": 0.4669,
      "step": 1710
    },
    {
      "epoch": 2.5743685687558466,
      "grad_norm": 0.8354683345264201,
      "learning_rate": 5e-06,
      "loss": 0.467,
      "step": 1720
    },
    {
      "epoch": 2.58933582787652,
      "grad_norm": 0.8673596229248286,
      "learning_rate": 5e-06,
      "loss": 0.469,
      "step": 1730
    },
    {
      "epoch": 2.6043030869971937,
      "grad_norm": 0.8628331585724999,
      "learning_rate": 5e-06,
      "loss": 0.4617,
      "step": 1740
    },
    {
      "epoch": 2.619270346117867,
      "grad_norm": 0.8146285875998882,
      "learning_rate": 5e-06,
      "loss": 0.4657,
      "step": 1750
    },
    {
      "epoch": 2.634237605238541,
      "grad_norm": 0.8534971402058302,
      "learning_rate": 5e-06,
      "loss": 0.4614,
      "step": 1760
    },
    {
      "epoch": 2.649204864359214,
      "grad_norm": 0.8652275924625911,
      "learning_rate": 5e-06,
      "loss": 0.4658,
      "step": 1770
    },
    {
      "epoch": 2.664172123479888,
      "grad_norm": 0.8692322617550208,
      "learning_rate": 5e-06,
      "loss": 0.4732,
      "step": 1780
    },
    {
      "epoch": 2.679139382600561,
      "grad_norm": 0.8822353906769295,
      "learning_rate": 5e-06,
      "loss": 0.4716,
      "step": 1790
    },
    {
      "epoch": 2.694106641721235,
      "grad_norm": 0.8401378668695283,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 1800
    },
    {
      "epoch": 2.7090739008419082,
      "grad_norm": 0.8353505448369987,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 1810
    },
    {
      "epoch": 2.724041159962582,
      "grad_norm": 0.9000754870851337,
      "learning_rate": 5e-06,
      "loss": 0.465,
      "step": 1820
    },
    {
      "epoch": 2.7390084190832553,
      "grad_norm": 0.8685249309404239,
      "learning_rate": 5e-06,
      "loss": 0.4662,
      "step": 1830
    },
    {
      "epoch": 2.753975678203929,
      "grad_norm": 0.8433079759693618,
      "learning_rate": 5e-06,
      "loss": 0.4688,
      "step": 1840
    },
    {
      "epoch": 2.7689429373246024,
      "grad_norm": 0.8411252961295581,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 1850
    },
    {
      "epoch": 2.7839101964452757,
      "grad_norm": 0.8473894583029798,
      "learning_rate": 5e-06,
      "loss": 0.47,
      "step": 1860
    },
    {
      "epoch": 2.7988774555659495,
      "grad_norm": 0.8632095664549414,
      "learning_rate": 5e-06,
      "loss": 0.4776,
      "step": 1870
    },
    {
      "epoch": 2.8138447146866232,
      "grad_norm": 0.8645641459711358,
      "learning_rate": 5e-06,
      "loss": 0.4649,
      "step": 1880
    },
    {
      "epoch": 2.8288119738072965,
      "grad_norm": 0.8638107799317755,
      "learning_rate": 5e-06,
      "loss": 0.4706,
      "step": 1890
    },
    {
      "epoch": 2.84377923292797,
      "grad_norm": 0.8359849143453539,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 1900
    },
    {
      "epoch": 2.8587464920486436,
      "grad_norm": 0.84885710579356,
      "learning_rate": 5e-06,
      "loss": 0.474,
      "step": 1910
    },
    {
      "epoch": 2.8737137511693174,
      "grad_norm": 0.8431178231849168,
      "learning_rate": 5e-06,
      "loss": 0.4709,
      "step": 1920
    },
    {
      "epoch": 2.8886810102899907,
      "grad_norm": 0.884477394048243,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 1930
    },
    {
      "epoch": 2.903648269410664,
      "grad_norm": 0.8957560621466105,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 1940
    },
    {
      "epoch": 2.9186155285313378,
      "grad_norm": 0.9172738068834246,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 1950
    },
    {
      "epoch": 2.933582787652011,
      "grad_norm": 0.8403477279988669,
      "learning_rate": 5e-06,
      "loss": 0.4719,
      "step": 1960
    },
    {
      "epoch": 2.948550046772685,
      "grad_norm": 0.8160050688672092,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 1970
    },
    {
      "epoch": 2.963517305893358,
      "grad_norm": 0.8444390881850173,
      "learning_rate": 5e-06,
      "loss": 0.4777,
      "step": 1980
    },
    {
      "epoch": 2.978484565014032,
      "grad_norm": 0.8412672372417249,
      "learning_rate": 5e-06,
      "loss": 0.4719,
      "step": 1990
    },
    {
      "epoch": 2.9934518241347052,
      "grad_norm": 0.8542510657083464,
      "learning_rate": 5e-06,
      "loss": 0.4829,
      "step": 2000
    },
    {
      "epoch": 2.999438727782975,
      "eval_loss": 0.655114471912384,
      "eval_runtime": 515.5784,
      "eval_samples_per_second": 17.458,
      "eval_steps_per_second": 0.547,
      "step": 2004
    },
    {
      "epoch": 2.999438727782975,
      "step": 2004,
      "total_flos": 3818092983484416.0,
      "train_loss": 0.5468447483823209,
      "train_runtime": 90937.6916,
      "train_samples_per_second": 5.642,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 10,
  "max_steps": 2004,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3818092983484416.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}