{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9964556962025317,
  "eval_steps": 500,
  "global_step": 1479,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 2.881640763497059,
      "learning_rate": 5e-06,
      "loss": 0.7569,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.0337939479231464,
      "learning_rate": 5e-06,
      "loss": 0.6507,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.673785425051781,
      "learning_rate": 5e-06,
      "loss": 0.6295,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 3.3956320905602704,
      "learning_rate": 5e-06,
      "loss": 0.615,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 2.4989053137375143,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.8362600995228775,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.6812600364217105,
      "learning_rate": 5e-06,
      "loss": 0.5919,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.7204729721312917,
      "learning_rate": 5e-06,
      "loss": 0.5885,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.5280049113720315,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 2.0183706809796145,
      "learning_rate": 5e-06,
      "loss": 0.5912,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.3728348794112124,
      "learning_rate": 5e-06,
      "loss": 0.5834,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.815358729258882,
      "learning_rate": 5e-06,
      "loss": 0.5806,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 1.6815731840354737,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.225903486666645,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.5251383950821966,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 2.6329119810915365,
      "learning_rate": 5e-06,
      "loss": 0.5782,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.7167868191479003,
      "learning_rate": 5e-06,
      "loss": 0.5764,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.73285303403399,
      "learning_rate": 5e-06,
      "loss": 0.5716,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.3746990652975846,
      "learning_rate": 5e-06,
      "loss": 0.5719,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.4936398849590744,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.2921614371273473,
      "learning_rate": 5e-06,
      "loss": 0.5636,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.442945179409374,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.4946631499646226,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.2982882675858225,
      "learning_rate": 5e-06,
      "loss": 0.5633,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.201139136446853,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.221681422450315,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.3764079520580204,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.2769215201401323,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.658435241290474,
      "learning_rate": 5e-06,
      "loss": 0.5589,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.3208774206825835,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.3732535087662892,
      "learning_rate": 5e-06,
      "loss": 0.5641,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.7757004131781444,
      "learning_rate": 5e-06,
      "loss": 0.5602,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.4157657120348899,
      "learning_rate": 5e-06,
      "loss": 0.5598,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.2554752448180828,
      "learning_rate": 5e-06,
      "loss": 0.5592,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.4796331594217829,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.2444877557169038,
      "learning_rate": 5e-06,
      "loss": 0.5627,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.3700404053887212,
      "learning_rate": 5e-06,
      "loss": 0.5553,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.399982865718864,
      "learning_rate": 5e-06,
      "loss": 0.5523,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.7626359294815905,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.2003485909233378,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.1749218008708648,
      "learning_rate": 5e-06,
      "loss": 0.5499,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.1170828766358432,
      "learning_rate": 5e-06,
      "loss": 0.5583,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.1913684385210768,
      "learning_rate": 5e-06,
      "loss": 0.552,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.158491457002269,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.2440014645948327,
      "learning_rate": 5e-06,
      "loss": 0.5486,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.0624082894155582,
      "learning_rate": 5e-06,
      "loss": 0.553,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.3891566012880086,
      "learning_rate": 5e-06,
      "loss": 0.5537,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.2000412125972895,
      "learning_rate": 5e-06,
      "loss": 0.5511,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.0973875984510393,
      "learning_rate": 5e-06,
      "loss": 0.5475,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.13758791983127594,
      "eval_runtime": 254.1278,
      "eval_samples_per_second": 52.352,
      "eval_steps_per_second": 0.409,
      "step": 493
    },
    {
      "epoch": 1.0131645569620253,
      "grad_norm": 1.8117531834466138,
      "learning_rate": 5e-06,
      "loss": 0.5044,
      "step": 500
    },
    {
      "epoch": 1.0334177215189873,
      "grad_norm": 1.3053921965302375,
      "learning_rate": 5e-06,
      "loss": 0.4698,
      "step": 510
    },
    {
      "epoch": 1.0536708860759494,
      "grad_norm": 1.1687624258615774,
      "learning_rate": 5e-06,
      "loss": 0.4664,
      "step": 520
    },
    {
      "epoch": 1.0739240506329113,
      "grad_norm": 1.1072989424160442,
      "learning_rate": 5e-06,
      "loss": 0.4678,
      "step": 530
    },
    {
      "epoch": 1.0941772151898734,
      "grad_norm": 1.2175965077481026,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 540
    },
    {
      "epoch": 1.1144303797468353,
      "grad_norm": 1.2541248804984217,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 550
    },
    {
      "epoch": 1.1346835443037975,
      "grad_norm": 1.2263184938833407,
      "learning_rate": 5e-06,
      "loss": 0.4652,
      "step": 560
    },
    {
      "epoch": 1.1549367088607596,
      "grad_norm": 1.2335018260186486,
      "learning_rate": 5e-06,
      "loss": 0.4741,
      "step": 570
    },
    {
      "epoch": 1.1751898734177215,
      "grad_norm": 1.1651843980725467,
      "learning_rate": 5e-06,
      "loss": 0.4698,
      "step": 580
    },
    {
      "epoch": 1.1954430379746834,
      "grad_norm": 1.3299683670971845,
      "learning_rate": 5e-06,
      "loss": 0.4648,
      "step": 590
    },
    {
      "epoch": 1.2156962025316456,
      "grad_norm": 1.5406403193173543,
      "learning_rate": 5e-06,
      "loss": 0.4728,
      "step": 600
    },
    {
      "epoch": 1.2359493670886077,
      "grad_norm": 1.3994137841579308,
      "learning_rate": 5e-06,
      "loss": 0.4672,
      "step": 610
    },
    {
      "epoch": 1.2562025316455696,
      "grad_norm": 1.4687039924759018,
      "learning_rate": 5e-06,
      "loss": 0.4722,
      "step": 620
    },
    {
      "epoch": 1.2764556962025315,
      "grad_norm": 1.1767001591548043,
      "learning_rate": 5e-06,
      "loss": 0.4707,
      "step": 630
    },
    {
      "epoch": 1.2967088607594937,
      "grad_norm": 1.377209586857746,
      "learning_rate": 5e-06,
      "loss": 0.4703,
      "step": 640
    },
    {
      "epoch": 1.3169620253164558,
      "grad_norm": 1.3280966356632122,
      "learning_rate": 5e-06,
      "loss": 0.4743,
      "step": 650
    },
    {
      "epoch": 1.3372151898734177,
      "grad_norm": 1.172194594770593,
      "learning_rate": 5e-06,
      "loss": 0.4625,
      "step": 660
    },
    {
      "epoch": 1.3574683544303796,
      "grad_norm": 1.1815616623629874,
      "learning_rate": 5e-06,
      "loss": 0.4772,
      "step": 670
    },
    {
      "epoch": 1.3777215189873417,
      "grad_norm": 1.2788117947587072,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 680
    },
    {
      "epoch": 1.3979746835443039,
      "grad_norm": 1.2120662888757698,
      "learning_rate": 5e-06,
      "loss": 0.4737,
      "step": 690
    },
    {
      "epoch": 1.4182278481012658,
      "grad_norm": 1.196686900725073,
      "learning_rate": 5e-06,
      "loss": 0.4706,
      "step": 700
    },
    {
      "epoch": 1.438481012658228,
      "grad_norm": 1.198300916867019,
      "learning_rate": 5e-06,
      "loss": 0.4766,
      "step": 710
    },
    {
      "epoch": 1.4587341772151898,
      "grad_norm": 1.2100463670783117,
      "learning_rate": 5e-06,
      "loss": 0.4764,
      "step": 720
    },
    {
      "epoch": 1.478987341772152,
      "grad_norm": 1.1505710467148873,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 730
    },
    {
      "epoch": 1.4992405063291139,
      "grad_norm": 1.1514955759509187,
      "learning_rate": 5e-06,
      "loss": 0.4729,
      "step": 740
    },
    {
      "epoch": 1.5194936708860758,
      "grad_norm": 1.2756859859117555,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 750
    },
    {
      "epoch": 1.539746835443038,
      "grad_norm": 1.1669815187630872,
      "learning_rate": 5e-06,
      "loss": 0.4751,
      "step": 760
    },
    {
      "epoch": 1.56,
      "grad_norm": 1.1950794033571506,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 770
    },
    {
      "epoch": 1.5802531645569622,
      "grad_norm": 1.2518137614638525,
      "learning_rate": 5e-06,
      "loss": 0.4744,
      "step": 780
    },
    {
      "epoch": 1.600506329113924,
      "grad_norm": 1.164886747372712,
      "learning_rate": 5e-06,
      "loss": 0.4778,
      "step": 790
    },
    {
      "epoch": 1.620759493670886,
      "grad_norm": 1.3963551349425976,
      "learning_rate": 5e-06,
      "loss": 0.4749,
      "step": 800
    },
    {
      "epoch": 1.6410126582278481,
      "grad_norm": 1.2170674697519668,
      "learning_rate": 5e-06,
      "loss": 0.4668,
      "step": 810
    },
    {
      "epoch": 1.6612658227848103,
      "grad_norm": 1.2362608113225955,
      "learning_rate": 5e-06,
      "loss": 0.4755,
      "step": 820
    },
    {
      "epoch": 1.6815189873417722,
      "grad_norm": 1.186974044583489,
      "learning_rate": 5e-06,
      "loss": 0.4709,
      "step": 830
    },
    {
      "epoch": 1.701772151898734,
      "grad_norm": 1.1120094436131531,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 840
    },
    {
      "epoch": 1.7220253164556962,
      "grad_norm": 1.1801749965556498,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 850
    },
    {
      "epoch": 1.7422784810126584,
      "grad_norm": 1.1457854356860961,
      "learning_rate": 5e-06,
      "loss": 0.4751,
      "step": 860
    },
    {
      "epoch": 1.7625316455696203,
      "grad_norm": 1.096573157780436,
      "learning_rate": 5e-06,
      "loss": 0.476,
      "step": 870
    },
    {
      "epoch": 1.7827848101265822,
      "grad_norm": 1.1968883544722357,
      "learning_rate": 5e-06,
      "loss": 0.48,
      "step": 880
    },
    {
      "epoch": 1.8030379746835443,
      "grad_norm": 1.3462695661737496,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 890
    },
    {
      "epoch": 1.8232911392405065,
      "grad_norm": 1.2981459167417944,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 900
    },
    {
      "epoch": 1.8435443037974684,
      "grad_norm": 1.4277375961136556,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 910
    },
    {
      "epoch": 1.8637974683544303,
      "grad_norm": 1.4551182850778734,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 920
    },
    {
      "epoch": 1.8840506329113924,
      "grad_norm": 1.3405721129672685,
      "learning_rate": 5e-06,
      "loss": 0.4726,
      "step": 930
    },
    {
      "epoch": 1.9043037974683545,
      "grad_norm": 1.2634029223509275,
      "learning_rate": 5e-06,
      "loss": 0.4749,
      "step": 940
    },
    {
      "epoch": 1.9245569620253165,
      "grad_norm": 1.3160409770893926,
      "learning_rate": 5e-06,
      "loss": 0.4776,
      "step": 950
    },
    {
      "epoch": 1.9448101265822784,
      "grad_norm": 1.0750739382136794,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 960
    },
    {
      "epoch": 1.9650632911392405,
      "grad_norm": 1.215667249435148,
      "learning_rate": 5e-06,
      "loss": 0.4789,
      "step": 970
    },
    {
      "epoch": 1.9853164556962026,
      "grad_norm": 1.1020704754247843,
      "learning_rate": 5e-06,
      "loss": 0.4805,
      "step": 980
    },
    {
      "epoch": 1.999493670886076,
      "eval_loss": 0.13782347738742828,
      "eval_runtime": 255.1699,
      "eval_samples_per_second": 52.138,
      "eval_steps_per_second": 0.408,
      "step": 987
    },
    {
      "epoch": 2.0060759493670886,
      "grad_norm": 2.2320392744750532,
      "learning_rate": 5e-06,
      "loss": 0.4496,
      "step": 990
    },
    {
      "epoch": 2.0263291139240507,
      "grad_norm": 1.6264522271278852,
      "learning_rate": 5e-06,
      "loss": 0.3864,
      "step": 1000
    },
    {
      "epoch": 2.046582278481013,
      "grad_norm": 1.4022257575865094,
      "learning_rate": 5e-06,
      "loss": 0.3795,
      "step": 1010
    },
    {
      "epoch": 2.0668354430379745,
      "grad_norm": 1.5383595004674644,
      "learning_rate": 5e-06,
      "loss": 0.377,
      "step": 1020
    },
    {
      "epoch": 2.0870886075949366,
      "grad_norm": 1.3513330118475093,
      "learning_rate": 5e-06,
      "loss": 0.3767,
      "step": 1030
    },
    {
      "epoch": 2.1073417721518988,
      "grad_norm": 1.3272367266437448,
      "learning_rate": 5e-06,
      "loss": 0.3739,
      "step": 1040
    },
    {
      "epoch": 2.127594936708861,
      "grad_norm": 1.3073032398087094,
      "learning_rate": 5e-06,
      "loss": 0.3846,
      "step": 1050
    },
    {
      "epoch": 2.1478481012658226,
      "grad_norm": 1.5607458954840778,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 1060
    },
    {
      "epoch": 2.1681012658227847,
      "grad_norm": 1.3955276924826612,
      "learning_rate": 5e-06,
      "loss": 0.382,
      "step": 1070
    },
    {
      "epoch": 2.188354430379747,
      "grad_norm": 1.5667776972963814,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 1080
    },
    {
      "epoch": 2.208607594936709,
      "grad_norm": 1.4260082058645476,
      "learning_rate": 5e-06,
      "loss": 0.3787,
      "step": 1090
    },
    {
      "epoch": 2.2288607594936707,
      "grad_norm": 1.5562857213046708,
      "learning_rate": 5e-06,
      "loss": 0.3876,
      "step": 1100
    },
    {
      "epoch": 2.249113924050633,
      "grad_norm": 1.9917004448182953,
      "learning_rate": 5e-06,
      "loss": 0.3856,
      "step": 1110
    },
    {
      "epoch": 2.269367088607595,
      "grad_norm": 2.388764780653022,
      "learning_rate": 5e-06,
      "loss": 0.3843,
      "step": 1120
    },
    {
      "epoch": 2.289620253164557,
      "grad_norm": 1.974750270308368,
      "learning_rate": 5e-06,
      "loss": 0.3873,
      "step": 1130
    },
    {
      "epoch": 2.309873417721519,
      "grad_norm": 1.447456780610406,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 1140
    },
    {
      "epoch": 2.330126582278481,
      "grad_norm": 1.3927022295027611,
      "learning_rate": 5e-06,
      "loss": 0.3869,
      "step": 1150
    },
    {
      "epoch": 2.350379746835443,
      "grad_norm": 1.215373362438277,
      "learning_rate": 5e-06,
      "loss": 0.3871,
      "step": 1160
    },
    {
      "epoch": 2.370632911392405,
      "grad_norm": 1.4491184946598725,
      "learning_rate": 5e-06,
      "loss": 0.3888,
      "step": 1170
    },
    {
      "epoch": 2.390886075949367,
      "grad_norm": 1.4189426863567351,
      "learning_rate": 5e-06,
      "loss": 0.3901,
      "step": 1180
    },
    {
      "epoch": 2.411139240506329,
      "grad_norm": 1.3984787319231367,
      "learning_rate": 5e-06,
      "loss": 0.3874,
      "step": 1190
    },
    {
      "epoch": 2.431392405063291,
      "grad_norm": 1.5285728590269927,
      "learning_rate": 5e-06,
      "loss": 0.3885,
      "step": 1200
    },
    {
      "epoch": 2.4516455696202533,
      "grad_norm": 1.6526724638756385,
      "learning_rate": 5e-06,
      "loss": 0.3866,
      "step": 1210
    },
    {
      "epoch": 2.4718987341772154,
      "grad_norm": 1.7189706408748655,
      "learning_rate": 5e-06,
      "loss": 0.3892,
      "step": 1220
    },
    {
      "epoch": 2.492151898734177,
      "grad_norm": 1.3142654182229083,
      "learning_rate": 5e-06,
      "loss": 0.3914,
      "step": 1230
    },
    {
      "epoch": 2.512405063291139,
      "grad_norm": 1.735979097692375,
      "learning_rate": 5e-06,
      "loss": 0.3895,
      "step": 1240
    },
    {
      "epoch": 2.5326582278481014,
      "grad_norm": 1.8356865092298218,
      "learning_rate": 5e-06,
      "loss": 0.3876,
      "step": 1250
    },
    {
      "epoch": 2.552911392405063,
      "grad_norm": 1.2680188524532179,
      "learning_rate": 5e-06,
      "loss": 0.3808,
      "step": 1260
    },
    {
      "epoch": 2.573164556962025,
      "grad_norm": 1.4512168828739789,
      "learning_rate": 5e-06,
      "loss": 0.3891,
      "step": 1270
    },
    {
      "epoch": 2.5934177215189873,
      "grad_norm": 1.3295995678864736,
      "learning_rate": 5e-06,
      "loss": 0.3921,
      "step": 1280
    },
    {
      "epoch": 2.6136708860759494,
      "grad_norm": 1.3912435194150836,
      "learning_rate": 5e-06,
      "loss": 0.3958,
      "step": 1290
    },
    {
      "epoch": 2.6339240506329116,
      "grad_norm": 1.3175096081971012,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1300
    },
    {
      "epoch": 2.6541772151898733,
      "grad_norm": 1.5566817774133672,
      "learning_rate": 5e-06,
      "loss": 0.3917,
      "step": 1310
    },
    {
      "epoch": 2.6744303797468354,
      "grad_norm": 1.3878720965690428,
      "learning_rate": 5e-06,
      "loss": 0.3945,
      "step": 1320
    },
    {
      "epoch": 2.6946835443037975,
      "grad_norm": 1.3785817403015144,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1330
    },
    {
      "epoch": 2.714936708860759,
      "grad_norm": 1.4183014258875806,
      "learning_rate": 5e-06,
      "loss": 0.3974,
      "step": 1340
    },
    {
      "epoch": 2.7351898734177214,
      "grad_norm": 1.3491695029291941,
      "learning_rate": 5e-06,
      "loss": 0.3946,
      "step": 1350
    },
    {
      "epoch": 2.7554430379746835,
      "grad_norm": 1.2428699126707001,
      "learning_rate": 5e-06,
      "loss": 0.3904,
      "step": 1360
    },
    {
      "epoch": 2.7756962025316456,
      "grad_norm": 1.433548321717136,
      "learning_rate": 5e-06,
      "loss": 0.3973,
      "step": 1370
    },
    {
      "epoch": 2.7959493670886078,
      "grad_norm": 1.5285229294068068,
      "learning_rate": 5e-06,
      "loss": 0.395,
      "step": 1380
    },
    {
      "epoch": 2.81620253164557,
      "grad_norm": 1.3717745770912413,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1390
    },
    {
      "epoch": 2.8364556962025316,
      "grad_norm": 1.6107209557365296,
      "learning_rate": 5e-06,
      "loss": 0.3919,
      "step": 1400
    },
    {
      "epoch": 2.8567088607594937,
      "grad_norm": 1.4417849324011554,
      "learning_rate": 5e-06,
      "loss": 0.3977,
      "step": 1410
    },
    {
      "epoch": 2.876962025316456,
      "grad_norm": 1.3890939860087244,
      "learning_rate": 5e-06,
      "loss": 0.3945,
      "step": 1420
    },
    {
      "epoch": 2.8972151898734175,
      "grad_norm": 1.340958614241595,
      "learning_rate": 5e-06,
      "loss": 0.3944,
      "step": 1430
    },
    {
      "epoch": 2.9174683544303797,
      "grad_norm": 1.6057483136323554,
      "learning_rate": 5e-06,
      "loss": 0.3974,
      "step": 1440
    },
    {
      "epoch": 2.937721518987342,
      "grad_norm": 1.3480539514146224,
      "learning_rate": 5e-06,
      "loss": 0.4065,
      "step": 1450
    },
    {
      "epoch": 2.957974683544304,
      "grad_norm": 1.4215727797263549,
      "learning_rate": 5e-06,
      "loss": 0.3949,
      "step": 1460
    },
    {
      "epoch": 2.978227848101266,
      "grad_norm": 1.3718015666487833,
      "learning_rate": 5e-06,
      "loss": 0.3987,
      "step": 1470
    },
    {
      "epoch": 2.9964556962025317,
      "eval_loss": 0.14610780775547028,
      "eval_runtime": 253.7654,
      "eval_samples_per_second": 52.426,
      "eval_steps_per_second": 0.41,
      "step": 1479
    },
    {
      "epoch": 2.9964556962025317,
      "step": 1479,
      "total_flos": 2476961326694400.0,
      "train_loss": 0.47900067526718665,
      "train_runtime": 42754.8995,
      "train_samples_per_second": 17.735,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 1479,
  "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": 2476961326694400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}