{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 1.4735389691796648,
      "learning_rate": 9.999298177883903e-05,
      "loss": 2.0846,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.574973327270963,
      "learning_rate": 9.997192908557323e-05,
      "loss": 1.0283,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 2.0498267249856488,
      "learning_rate": 9.993684783030088e-05,
      "loss": 0.686,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.2702818493413723,
      "learning_rate": 9.988774786134234e-05,
      "loss": 0.587,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6979872055713617,
      "learning_rate": 9.982464296247522e-05,
      "loss": 0.5667,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.0417497433733047,
      "learning_rate": 9.974755084906502e-05,
      "loss": 0.5057,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.8791937337247481,
      "learning_rate": 9.965649316309178e-05,
      "loss": 0.5095,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.6707662533067278,
      "learning_rate": 9.955149546707465e-05,
      "loss": 0.5589,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.8382574790909684,
      "learning_rate": 9.94325872368957e-05,
      "loss": 0.4037,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.3977581534529162,
      "learning_rate": 9.929980185352526e-05,
      "loss": 0.476,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.7995346930439355,
      "learning_rate": 9.915317659365077e-05,
      "loss": 0.4732,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.0293778342519209,
      "learning_rate": 9.899275261921234e-05,
      "loss": 0.4808,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.7924054746311283,
      "learning_rate": 9.881857496584726e-05,
      "loss": 0.4359,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.899393132949154,
      "learning_rate": 9.863069253024719e-05,
      "loss": 0.377,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.9174662358653375,
      "learning_rate": 9.842915805643155e-05,
      "loss": 0.4143,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.080440113976801,
      "learning_rate": 9.821402812094073e-05,
      "loss": 0.4396,
      "step": 160
    },
    {
      "epoch": 0.272,
      "grad_norm": 1.7023365502074517,
      "learning_rate": 9.798536311695334e-05,
      "loss": 0.4219,
      "step": 170
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.0019239067011896,
      "learning_rate": 9.774322723733216e-05,
      "loss": 0.4189,
      "step": 180
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.8717425800117149,
      "learning_rate": 9.748768845660334e-05,
      "loss": 0.399,
      "step": 190
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0137511699320638,
      "learning_rate": 9.721881851187406e-05,
      "loss": 0.434,
      "step": 200
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.9295547515585622,
      "learning_rate": 9.693669288269372e-05,
      "loss": 0.3684,
      "step": 210
    },
    {
      "epoch": 0.352,
      "grad_norm": 2.034518417888826,
      "learning_rate": 9.664139076986473e-05,
      "loss": 0.3468,
      "step": 220
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.9229607408434366,
      "learning_rate": 9.63329950732086e-05,
      "loss": 0.4119,
      "step": 230
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.0004931328900635,
      "learning_rate": 9.601159236829352e-05,
      "loss": 0.3904,
      "step": 240
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.9012457023667851,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.423,
      "step": 250
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.9087395867147162,
      "learning_rate": 9.533013046784189e-05,
      "loss": 0.3761,
      "step": 260
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.9173174623162017,
      "learning_rate": 9.497026257831855e-05,
      "loss": 0.3351,
      "step": 270
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.7699242514964085,
      "learning_rate": 9.459777023885755e-05,
      "loss": 0.3282,
      "step": 280
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.9501543328230019,
      "learning_rate": 9.421275801880362e-05,
      "loss": 0.4125,
      "step": 290
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.21516103198593,
      "learning_rate": 9.381533400219318e-05,
      "loss": 0.3728,
      "step": 300
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.9020121880449892,
      "learning_rate": 9.340560975741197e-05,
      "loss": 0.3094,
      "step": 310
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.8137757312519368,
      "learning_rate": 9.298370030587456e-05,
      "loss": 0.3853,
      "step": 320
    },
    {
      "epoch": 0.528,
      "grad_norm": 1.0040829480628546,
      "learning_rate": 9.254972408973461e-05,
      "loss": 0.3391,
      "step": 330
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.2904098253200862,
      "learning_rate": 9.210380293863462e-05,
      "loss": 0.397,
      "step": 340
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.8956729634317536,
      "learning_rate": 9.164606203550497e-05,
      "loss": 0.3878,
      "step": 350
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.522665457627724,
      "learning_rate": 9.117662988142138e-05,
      "loss": 0.3415,
      "step": 360
    },
    {
      "epoch": 0.592,
      "grad_norm": 1.0284487945989331,
      "learning_rate": 9.069563825953092e-05,
      "loss": 0.4046,
      "step": 370
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.8916994827228245,
      "learning_rate": 9.020322219805674e-05,
      "loss": 0.3674,
      "step": 380
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.8857668635539665,
      "learning_rate": 8.969951993239177e-05,
      "loss": 0.3478,
      "step": 390
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.8050131549764538,
      "learning_rate": 8.9184672866292e-05,
      "loss": 0.375,
      "step": 400
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.8436775930299412,
      "learning_rate": 8.865882553218037e-05,
      "loss": 0.381,
      "step": 410
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.849143512269743,
      "learning_rate": 8.81221255505724e-05,
      "loss": 0.3594,
      "step": 420
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.6585410149269071,
      "learning_rate": 8.757472358863481e-05,
      "loss": 0.3813,
      "step": 430
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.7554756750287495,
      "learning_rate": 8.701677331788891e-05,
      "loss": 0.3614,
      "step": 440
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6356206323184476,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.3459,
      "step": 450
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.7202075692536539,
      "learning_rate": 8.586985729815894e-05,
      "loss": 0.3318,
      "step": 460
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.971675376179715,
      "learning_rate": 8.528121352158604e-05,
      "loss": 0.3727,
      "step": 470
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.5834787172725806,
      "learning_rate": 8.468266529064025e-05,
      "loss": 0.3283,
      "step": 480
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.9138752831493647,
      "learning_rate": 8.4074380635076e-05,
      "loss": 0.3466,
      "step": 490
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6628442550543788,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.3554,
      "step": 500
    },
    {
      "epoch": 0.816,
      "grad_norm": 1.1376540025434019,
      "learning_rate": 8.282928778764783e-05,
      "loss": 0.3495,
      "step": 510
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.7241154857095444,
      "learning_rate": 8.21928291292627e-05,
      "loss": 0.3239,
      "step": 520
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.9670287777704916,
      "learning_rate": 8.154733301509248e-05,
      "loss": 0.3288,
      "step": 530
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.7396477232733722,
      "learning_rate": 8.089298065451672e-05,
      "loss": 0.2646,
      "step": 540
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.8545577142602087,
      "learning_rate": 8.022995574311876e-05,
      "loss": 0.3072,
      "step": 550
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.8730541522413842,
      "learning_rate": 7.95584444111171e-05,
      "loss": 0.3707,
      "step": 560
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.977218932636251,
      "learning_rate": 7.887863517111338e-05,
      "loss": 0.3262,
      "step": 570
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.7836322626790029,
      "learning_rate": 7.819071886517134e-05,
      "loss": 0.3383,
      "step": 580
    },
    {
      "epoch": 0.944,
      "grad_norm": 1.0708289653309697,
      "learning_rate": 7.7494888611242e-05,
      "loss": 0.311,
      "step": 590
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7697129892326693,
      "learning_rate": 7.679133974894983e-05,
      "loss": 0.3093,
      "step": 600
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.9966052229687813,
      "learning_rate": 7.60802697847554e-05,
      "loss": 0.3547,
      "step": 610
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.6690526939456714,
      "learning_rate": 7.536187833650947e-05,
      "loss": 0.3314,
      "step": 620
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.75821824874568,
      "learning_rate": 7.463636707741458e-05,
      "loss": 0.3445,
      "step": 630
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.9242081895927273,
      "learning_rate": 7.390393967940962e-05,
      "loss": 0.2962,
      "step": 640
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.8108496898331262,
      "learning_rate": 7.316480175599309e-05,
      "loss": 0.283,
      "step": 650
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.8921672080734943,
      "learning_rate": 7.241916080450163e-05,
      "loss": 0.2599,
      "step": 660
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.7491655839339207,
      "learning_rate": 7.166722614785937e-05,
      "loss": 0.28,
      "step": 670
    },
    {
      "epoch": 1.088,
      "grad_norm": 1.0334160738514429,
      "learning_rate": 7.090920887581506e-05,
      "loss": 0.2348,
      "step": 680
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.6704114246937775,
      "learning_rate": 7.014532178568314e-05,
      "loss": 0.2721,
      "step": 690
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.899064629989069,
      "learning_rate": 6.937577932260515e-05,
      "loss": 0.3143,
      "step": 700
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 1.0158660631109402,
      "learning_rate": 6.860079751934908e-05,
      "loss": 0.2943,
      "step": 710
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.5842709942575061,
      "learning_rate": 6.782059393566253e-05,
      "loss": 0.2593,
      "step": 720
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.9083888380038305,
      "learning_rate": 6.70353875971976e-05,
      "loss": 0.3074,
      "step": 730
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.9956074892974983,
      "learning_rate": 6.624539893402382e-05,
      "loss": 0.2933,
      "step": 740
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.0364494081920752,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2836,
      "step": 750
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.8661955533396878,
      "learning_rate": 6.465196300425287e-05,
      "loss": 0.3033,
      "step": 760
    },
    {
      "epoch": 1.232,
      "grad_norm": 1.051469403032706,
      "learning_rate": 6.384896306108612e-05,
      "loss": 0.3165,
      "step": 770
    },
    {
      "epoch": 1.248,
      "grad_norm": 1.1430816578003544,
      "learning_rate": 6.304207531449486e-05,
      "loss": 0.2612,
      "step": 780
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.962612175196701,
      "learning_rate": 6.223152628114537e-05,
      "loss": 0.2885,
      "step": 790
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.131939828433401,
      "learning_rate": 6.141754350553279e-05,
      "loss": 0.3141,
      "step": 800
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.9286238079054427,
      "learning_rate": 6.0600355496102745e-05,
      "loss": 0.2858,
      "step": 810
    },
    {
      "epoch": 1.312,
      "grad_norm": 1.0517327514857011,
      "learning_rate": 5.9780191661102415e-05,
      "loss": 0.2567,
      "step": 820
    },
    {
      "epoch": 1.328,
      "grad_norm": 1.2021599801342249,
      "learning_rate": 5.8957282244179124e-05,
      "loss": 0.2991,
      "step": 830
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 1.0319160295400196,
      "learning_rate": 5.813185825974419e-05,
      "loss": 0.2465,
      "step": 840
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.089231154026881,
      "learning_rate": 5.730415142812059e-05,
      "loss": 0.2682,
      "step": 850
    },
    {
      "epoch": 1.376,
      "grad_norm": 1.0066143745415537,
      "learning_rate": 5.6474394110492344e-05,
      "loss": 0.2987,
      "step": 860
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.795049556260502,
      "learning_rate": 5.564281924367408e-05,
      "loss": 0.2888,
      "step": 870
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.9657717918565559,
      "learning_rate": 5.480966027471889e-05,
      "loss": 0.2946,
      "step": 880
    },
    {
      "epoch": 1.424,
      "grad_norm": 1.0388183419341974,
      "learning_rate": 5.3975151095382995e-05,
      "loss": 0.282,
      "step": 890
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.9202218639117007,
      "learning_rate": 5.313952597646568e-05,
      "loss": 0.2832,
      "step": 900
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.8584135552405918,
      "learning_rate": 5.230301950204262e-05,
      "loss": 0.3014,
      "step": 910
    },
    {
      "epoch": 1.472,
      "grad_norm": 1.2062260258019901,
      "learning_rate": 5.1465866503611426e-05,
      "loss": 0.2739,
      "step": 920
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.8260337878703716,
      "learning_rate": 5.062830199416764e-05,
      "loss": 0.2696,
      "step": 930
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.8342686340750022,
      "learning_rate": 4.979056110222981e-05,
      "loss": 0.2958,
      "step": 940
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.06260253365328,
      "learning_rate": 4.895287900583216e-05,
      "loss": 0.2482,
      "step": 950
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.9317052193070622,
      "learning_rate": 4.811549086650327e-05,
      "loss": 0.2789,
      "step": 960
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.8622399411448186,
      "learning_rate": 4.7278631763249554e-05,
      "loss": 0.2563,
      "step": 970
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.8857610071118638,
      "learning_rate": 4.6442536626561675e-05,
      "loss": 0.259,
      "step": 980
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.835587570091306,
      "learning_rate": 4.560744017246284e-05,
      "loss": 0.2623,
      "step": 990
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2092740152455195,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2867,
      "step": 1000
    },
    {
      "epoch": 1.616,
      "grad_norm": 1.0784101902719292,
      "learning_rate": 4.394118070851749e-05,
      "loss": 0.2851,
      "step": 1010
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.6431130954370421,
      "learning_rate": 4.31104854657681e-05,
      "loss": 0.269,
      "step": 1020
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.9482573850706428,
      "learning_rate": 4.228172430848644e-05,
      "loss": 0.2526,
      "step": 1030
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 1.0967329813764932,
      "learning_rate": 4.1455129893836174e-05,
      "loss": 0.2788,
      "step": 1040
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.1253690039254327,
      "learning_rate": 4.063093427071376e-05,
      "loss": 0.2439,
      "step": 1050
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.8922820572124287,
      "learning_rate": 3.9809368814605766e-05,
      "loss": 0.2701,
      "step": 1060
    },
    {
      "epoch": 1.712,
      "grad_norm": 1.136807663569628,
      "learning_rate": 3.899066416263493e-05,
      "loss": 0.2665,
      "step": 1070
    },
    {
      "epoch": 1.728,
      "grad_norm": 1.2239439019933025,
      "learning_rate": 3.817505014881378e-05,
      "loss": 0.3048,
      "step": 1080
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.9827246945743642,
      "learning_rate": 3.736275573952354e-05,
      "loss": 0.2298,
      "step": 1090
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.7866612401659844,
      "learning_rate": 3.655400896923672e-05,
      "loss": 0.2568,
      "step": 1100
    },
    {
      "epoch": 1.776,
      "grad_norm": 1.022737765446411,
      "learning_rate": 3.5749036876501194e-05,
      "loss": 0.2685,
      "step": 1110
    },
    {
      "epoch": 1.792,
      "grad_norm": 1.0652939313746896,
      "learning_rate": 3.494806544020398e-05,
      "loss": 0.2675,
      "step": 1120
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.9728776797500178,
      "learning_rate": 3.4151319516132416e-05,
      "loss": 0.2539,
      "step": 1130
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 1.2874137173478253,
      "learning_rate": 3.335902277385067e-05,
      "loss": 0.26,
      "step": 1140
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 1.0831032362899013,
      "learning_rate": 3.257139763390925e-05,
      "loss": 0.262,
      "step": 1150
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 1.0111985690545156,
      "learning_rate": 3.178866520540509e-05,
      "loss": 0.2381,
      "step": 1160
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.9036562356484744,
      "learning_rate": 3.101104522390995e-05,
      "loss": 0.2682,
      "step": 1170
    },
    {
      "epoch": 1.888,
      "grad_norm": 1.5014307278329708,
      "learning_rate": 3.023875598978419e-05,
      "loss": 0.2902,
      "step": 1180
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.9785446712411401,
      "learning_rate": 2.9472014306893603e-05,
      "loss": 0.2624,
      "step": 1190
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.1319999391176576,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.2686,
      "step": 1200
    },
    {
      "epoch": 1.936,
      "grad_norm": 1.1056089612154159,
      "learning_rate": 2.795603296306708e-05,
      "loss": 0.2443,
      "step": 1210
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.8376972874868366,
      "learning_rate": 2.7207218881825014e-05,
      "loss": 0.2752,
      "step": 1220
    },
    {
      "epoch": 1.968,
      "grad_norm": 1.34403239117131,
      "learning_rate": 2.6464803391733374e-05,
      "loss": 0.3108,
      "step": 1230
    },
    {
      "epoch": 1.984,
      "grad_norm": 1.0963825979352566,
      "learning_rate": 2.5728994910236304e-05,
      "loss": 0.2517,
      "step": 1240
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0786181456785247,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2494,
      "step": 1250
    },
    {
      "epoch": 2.016,
      "grad_norm": 1.0920867485450798,
      "learning_rate": 2.4278023310924673e-05,
      "loss": 0.2276,
      "step": 1260
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.9377652164830973,
      "learning_rate": 2.3563267522693415e-05,
      "loss": 0.2145,
      "step": 1270
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.9386939202846237,
      "learning_rate": 2.2855933287874138e-05,
      "loss": 0.1993,
      "step": 1280
    },
    {
      "epoch": 2.064,
      "grad_norm": 1.08768521136953,
      "learning_rate": 2.215621917559062e-05,
      "loss": 0.2402,
      "step": 1290
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.1126946097754096,
      "learning_rate": 2.1464321615778422e-05,
      "loss": 0.198,
      "step": 1300
    },
    {
      "epoch": 2.096,
      "grad_norm": 1.144472975970789,
      "learning_rate": 2.07804348440414e-05,
      "loss": 0.1847,
      "step": 1310
    },
    {
      "epoch": 2.112,
      "grad_norm": 1.0016887934690482,
      "learning_rate": 2.0104750847124075e-05,
      "loss": 0.2217,
      "step": 1320
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.8561793503114183,
      "learning_rate": 1.9437459309015427e-05,
      "loss": 0.219,
      "step": 1330
    },
    {
      "epoch": 2.144,
      "grad_norm": 1.3046968600575892,
      "learning_rate": 1.8778747557699224e-05,
      "loss": 0.2219,
      "step": 1340
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.2565120133034997,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 0.2043,
      "step": 1350
    },
    {
      "epoch": 2.176,
      "grad_norm": 1.0340866475830222,
      "learning_rate": 1.7487800632498545e-05,
      "loss": 0.1848,
      "step": 1360
    },
    {
      "epoch": 2.192,
      "grad_norm": 1.2687371164495156,
      "learning_rate": 1.685592786465524e-05,
      "loss": 0.2063,
      "step": 1370
    },
    {
      "epoch": 2.208,
      "grad_norm": 4.410575395721385,
      "learning_rate": 1.6233359593948777e-05,
      "loss": 0.203,
      "step": 1380
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.896414168502828,
      "learning_rate": 1.5620270593251635e-05,
      "loss": 0.1998,
      "step": 1390
    },
    {
      "epoch": 2.24,
      "grad_norm": 1.1594043127204923,
      "learning_rate": 1.5016832974331724e-05,
      "loss": 0.2029,
      "step": 1400
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.9694525860243126,
      "learning_rate": 1.4423216139535734e-05,
      "loss": 0.1829,
      "step": 1410
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.7781970327573788,
      "learning_rate": 1.3839586734232906e-05,
      "loss": 0.2131,
      "step": 1420
    },
    {
      "epoch": 2.288,
      "grad_norm": 0.9924970297588063,
      "learning_rate": 1.3266108600032929e-05,
      "loss": 0.2099,
      "step": 1430
    },
    {
      "epoch": 2.304,
      "grad_norm": 1.0619144372673828,
      "learning_rate": 1.2702942728790895e-05,
      "loss": 0.203,
      "step": 1440
    },
    {
      "epoch": 2.32,
      "grad_norm": 1.1568706885012912,
      "learning_rate": 1.2150247217412186e-05,
      "loss": 0.2154,
      "step": 1450
    },
    {
      "epoch": 2.336,
      "grad_norm": 1.0110226875096215,
      "learning_rate": 1.160817722347014e-05,
      "loss": 0.1994,
      "step": 1460
    },
    {
      "epoch": 2.352,
      "grad_norm": 1.2186938894345578,
      "learning_rate": 1.1076884921648834e-05,
      "loss": 0.2255,
      "step": 1470
    },
    {
      "epoch": 2.368,
      "grad_norm": 1.0321133111544947,
      "learning_rate": 1.0556519461023301e-05,
      "loss": 0.2216,
      "step": 1480
    },
    {
      "epoch": 2.384,
      "grad_norm": 1.154074546283637,
      "learning_rate": 1.0047226923189024e-05,
      "loss": 0.1979,
      "step": 1490
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.1620581009185202,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2081,
      "step": 1500
    },
    {
      "epoch": 2.416,
      "grad_norm": 1.0946269046711545,
      "learning_rate": 9.06242935969528e-06,
      "loss": 0.2061,
      "step": 1510
    },
    {
      "epoch": 2.432,
      "grad_norm": 1.3740666369662087,
      "learning_rate": 8.587200795119793e-06,
      "loss": 0.2066,
      "step": 1520
    },
    {
      "epoch": 2.448,
      "grad_norm": 0.9801350633493024,
      "learning_rate": 8.123597997892918e-06,
      "loss": 0.2144,
      "step": 1530
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.9114459647246573,
      "learning_rate": 7.671751114693104e-06,
      "loss": 0.1854,
      "step": 1540
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.020041105806084,
      "learning_rate": 7.2317869919746705e-06,
      "loss": 0.2095,
      "step": 1550
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.8590881829290263,
      "learning_rate": 6.803829140358237e-06,
      "loss": 0.1815,
      "step": 1560
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.8341531305601159,
      "learning_rate": 6.3879976999578154e-06,
      "loss": 0.2091,
      "step": 1570
    },
    {
      "epoch": 2.528,
      "grad_norm": 1.0395797814111882,
      "learning_rate": 5.98440940665399e-06,
      "loss": 0.2112,
      "step": 1580
    },
    {
      "epoch": 2.544,
      "grad_norm": 0.950529878731894,
      "learning_rate": 5.593177559322777e-06,
      "loss": 0.1965,
      "step": 1590
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.274310745570913,
      "learning_rate": 5.214411988029355e-06,
      "loss": 0.209,
      "step": 1600
    },
    {
      "epoch": 2.576,
      "grad_norm": 1.2921735659034017,
      "learning_rate": 4.848219023195644e-06,
      "loss": 0.2227,
      "step": 1610
    },
    {
      "epoch": 2.592,
      "grad_norm": 1.0127209415412022,
      "learning_rate": 4.494701465750217e-06,
      "loss": 0.1875,
      "step": 1620
    },
    {
      "epoch": 2.608,
      "grad_norm": 1.068518391858498,
      "learning_rate": 4.153958558269189e-06,
      "loss": 0.1887,
      "step": 1630
    },
    {
      "epoch": 2.624,
      "grad_norm": 1.1843724236696493,
      "learning_rate": 3.826085957115888e-06,
      "loss": 0.1833,
      "step": 1640
    },
    {
      "epoch": 2.64,
      "grad_norm": 1.3793247614185251,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.2001,
      "step": 1650
    },
    {
      "epoch": 2.656,
      "grad_norm": 1.1786689211718118,
      "learning_rate": 3.2093162080754637e-06,
      "loss": 0.2341,
      "step": 1660
    },
    {
      "epoch": 2.672,
      "grad_norm": 1.1876075782168105,
      "learning_rate": 2.9205922052484958e-06,
      "loss": 0.2251,
      "step": 1670
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 1.1105275881217318,
      "learning_rate": 2.6450847502627884e-06,
      "loss": 0.1915,
      "step": 1680
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 1.2615653662572164,
      "learning_rate": 2.3828711860083674e-06,
      "loss": 0.2241,
      "step": 1690
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 1.2336183045142934,
      "learning_rate": 2.134025123396638e-06,
      "loss": 0.1899,
      "step": 1700
    },
    {
      "epoch": 2.7359999999999998,
      "grad_norm": 1.2995831378990832,
      "learning_rate": 1.8986164206957035e-06,
      "loss": 0.1965,
      "step": 1710
    },
    {
      "epoch": 2.752,
      "grad_norm": 1.0738462699292388,
      "learning_rate": 1.6767111639191202e-06,
      "loss": 0.2192,
      "step": 1720
    },
    {
      "epoch": 2.768,
      "grad_norm": 1.0132612835074417,
      "learning_rate": 1.4683716482736366e-06,
      "loss": 0.2056,
      "step": 1730
    },
    {
      "epoch": 2.784,
      "grad_norm": 1.0015783236034024,
      "learning_rate": 1.2736563606711382e-06,
      "loss": 0.1803,
      "step": 1740
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.2842164055412226,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.24,
      "step": 1750
    },
    {
      "epoch": 2.816,
      "grad_norm": 1.0294787685775484,
      "learning_rate": 9.253132783283547e-07,
      "loss": 0.1914,
      "step": 1760
    },
    {
      "epoch": 2.832,
      "grad_norm": 1.0434750413131526,
      "learning_rate": 7.717832735397335e-07,
      "loss": 0.1935,
      "step": 1770
    },
    {
      "epoch": 2.848,
      "grad_norm": 1.0184364682600762,
      "learning_rate": 6.3207304924498e-07,
      "loss": 0.1771,
      "step": 1780
    },
    {
      "epoch": 2.864,
      "grad_norm": 1.0821144737056598,
      "learning_rate": 5.062218261342122e-07,
      "loss": 0.1955,
      "step": 1790
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.1413490215179685,
      "learning_rate": 3.9426493427611177e-07,
      "loss": 0.1867,
      "step": 1800
    },
    {
      "epoch": 2.896,
      "grad_norm": 1.1954337890031224,
      "learning_rate": 2.962338031997691e-07,
      "loss": 0.2164,
      "step": 1810
    },
    {
      "epoch": 2.912,
      "grad_norm": 1.24853908918597,
      "learning_rate": 2.1215595307154667e-07,
      "loss": 0.2154,
      "step": 1820
    },
    {
      "epoch": 2.928,
      "grad_norm": 1.1438437987577612,
      "learning_rate": 1.420549869693033e-07,
      "loss": 0.2006,
      "step": 1830
    },
    {
      "epoch": 2.944,
      "grad_norm": 1.106366481038807,
      "learning_rate": 8.595058425640013e-08,
      "loss": 0.1884,
      "step": 1840
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.0427024327416816,
      "learning_rate": 4.385849505708084e-08,
      "loss": 0.1914,
      "step": 1850
    },
    {
      "epoch": 2.976,
      "grad_norm": 1.379711472754783,
      "learning_rate": 1.5790535835003008e-08,
      "loss": 0.2049,
      "step": 1860
    },
    {
      "epoch": 2.992,
      "grad_norm": 1.095540989141702,
      "learning_rate": 1.7545860759693445e-09,
      "loss": 0.2074,
      "step": 1870
    },
    {
      "epoch": 3.0,
      "step": 1875,
      "total_flos": 302283383111680.0,
      "train_loss": 0.3027080503463745,
      "train_runtime": 17327.47,
      "train_samples_per_second": 0.866,
      "train_steps_per_second": 0.108
    }
  ],
  "logging_steps": 10,
  "max_steps": 1875,
  "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": 302283383111680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}