{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5918910920390648,
  "eval_steps": 200,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002959455460195324,
      "eval_loss": 10.376261711120605,
      "eval_runtime": 10.819,
      "eval_samples_per_second": 138.829,
      "eval_steps_per_second": 34.754,
      "step": 1
    },
    {
      "epoch": 0.002959455460195324,
      "grad_norm": 0.298828125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 10.3804,
      "step": 10
    },
    {
      "epoch": 0.005918910920390648,
      "grad_norm": 0.357421875,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 10.3767,
      "step": 20
    },
    {
      "epoch": 0.008878366380585973,
      "grad_norm": 0.443359375,
      "learning_rate": 4.8e-05,
      "loss": 10.3754,
      "step": 30
    },
    {
      "epoch": 0.011837821840781295,
      "grad_norm": 0.5625,
      "learning_rate": 6.400000000000001e-05,
      "loss": 10.3767,
      "step": 40
    },
    {
      "epoch": 0.01479727730097662,
      "grad_norm": 1.109375,
      "learning_rate": 8e-05,
      "loss": 10.3722,
      "step": 50
    },
    {
      "epoch": 0.017756732761171946,
      "grad_norm": 0.294921875,
      "learning_rate": 9.6e-05,
      "loss": 10.3804,
      "step": 60
    },
    {
      "epoch": 0.020716188221367268,
      "grad_norm": 0.373046875,
      "learning_rate": 0.00011200000000000001,
      "loss": 10.3739,
      "step": 70
    },
    {
      "epoch": 0.02367564368156259,
      "grad_norm": 0.42578125,
      "learning_rate": 0.00012800000000000002,
      "loss": 10.3736,
      "step": 80
    },
    {
      "epoch": 0.026635099141757917,
      "grad_norm": 0.70703125,
      "learning_rate": 0.000144,
      "loss": 10.3643,
      "step": 90
    },
    {
      "epoch": 0.02959455460195324,
      "grad_norm": 1.59375,
      "learning_rate": 0.00016,
      "loss": 10.364,
      "step": 100
    },
    {
      "epoch": 0.032554010062148565,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00017600000000000002,
      "loss": 10.3561,
      "step": 110
    },
    {
      "epoch": 0.03551346552234389,
      "grad_norm": 0.73046875,
      "learning_rate": 0.000192,
      "loss": 10.3211,
      "step": 120
    },
    {
      "epoch": 0.03847292098253921,
      "grad_norm": 0.84375,
      "learning_rate": 0.0001999978128380225,
      "loss": 10.2582,
      "step": 130
    },
    {
      "epoch": 0.041432376442734536,
      "grad_norm": 0.72265625,
      "learning_rate": 0.0001999803161162393,
      "loss": 10.172,
      "step": 140
    },
    {
      "epoch": 0.04439183190292986,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019994532573409262,
      "loss": 10.1033,
      "step": 150
    },
    {
      "epoch": 0.04735128736312518,
      "grad_norm": 0.43359375,
      "learning_rate": 0.00019989284781388617,
      "loss": 10.0041,
      "step": 160
    },
    {
      "epoch": 0.05031074282332051,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00019982289153773646,
      "loss": 9.9331,
      "step": 170
    },
    {
      "epoch": 0.053270198283515834,
      "grad_norm": 0.46875,
      "learning_rate": 0.00019973546914596623,
      "loss": 9.8548,
      "step": 180
    },
    {
      "epoch": 0.05622965374371116,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00019963059593496268,
      "loss": 9.7692,
      "step": 190
    },
    {
      "epoch": 0.05918910920390648,
      "grad_norm": 1.140625,
      "learning_rate": 0.00019950829025450114,
      "loss": 9.7054,
      "step": 200
    },
    {
      "epoch": 0.05918910920390648,
      "eval_loss": 9.686193466186523,
      "eval_runtime": 20.1405,
      "eval_samples_per_second": 74.576,
      "eval_steps_per_second": 18.669,
      "step": 200
    },
    {
      "epoch": 0.062148564664101805,
      "grad_norm": 0.46484375,
      "learning_rate": 0.0001993685735045343,
      "loss": 9.6486,
      "step": 210
    },
    {
      "epoch": 0.06510802012429713,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001992114701314478,
      "loss": 9.6029,
      "step": 220
    },
    {
      "epoch": 0.06806747558449246,
      "grad_norm": 0.5078125,
      "learning_rate": 0.000199037007623783,
      "loss": 9.5554,
      "step": 230
    },
    {
      "epoch": 0.07102693104468778,
      "grad_norm": 0.609375,
      "learning_rate": 0.00019884521650742715,
      "loss": 9.4941,
      "step": 240
    },
    {
      "epoch": 0.0739863865048831,
      "grad_norm": 1.78125,
      "learning_rate": 0.00019863613034027224,
      "loss": 9.508,
      "step": 250
    },
    {
      "epoch": 0.07694584196507842,
      "grad_norm": 0.5078125,
      "learning_rate": 0.0001984097857063434,
      "loss": 9.3502,
      "step": 260
    },
    {
      "epoch": 0.07990529742527375,
      "grad_norm": 0.55859375,
      "learning_rate": 0.0001981662222093976,
      "loss": 9.3473,
      "step": 270
    },
    {
      "epoch": 0.08286475288546907,
      "grad_norm": 0.5234375,
      "learning_rate": 0.00019790548246599447,
      "loss": 9.2955,
      "step": 280
    },
    {
      "epoch": 0.0858242083456644,
      "grad_norm": 0.625,
      "learning_rate": 0.00019762761209803927,
      "loss": 9.2712,
      "step": 290
    },
    {
      "epoch": 0.08878366380585972,
      "grad_norm": 1.140625,
      "learning_rate": 0.0001973326597248006,
      "loss": 9.2969,
      "step": 300
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 0.455078125,
      "learning_rate": 0.00019702067695440332,
      "loss": 9.1616,
      "step": 310
    },
    {
      "epoch": 0.09470257472625036,
      "grad_norm": 0.4609375,
      "learning_rate": 0.00019669171837479873,
      "loss": 9.1605,
      "step": 320
    },
    {
      "epoch": 0.09766203018644569,
      "grad_norm": 0.474609375,
      "learning_rate": 0.00019634584154421317,
      "loss": 9.1402,
      "step": 330
    },
    {
      "epoch": 0.10062148564664102,
      "grad_norm": 0.578125,
      "learning_rate": 0.00019598310698107702,
      "loss": 9.0839,
      "step": 340
    },
    {
      "epoch": 0.10358094110683634,
      "grad_norm": 1.296875,
      "learning_rate": 0.00019560357815343577,
      "loss": 9.0709,
      "step": 350
    },
    {
      "epoch": 0.10654039656703167,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00019520732146784491,
      "loss": 9.0372,
      "step": 360
    },
    {
      "epoch": 0.109499852027227,
      "grad_norm": 0.76953125,
      "learning_rate": 0.0001947944062577507,
      "loss": 9.0209,
      "step": 370
    },
    {
      "epoch": 0.11245930748742232,
      "grad_norm": 0.5390625,
      "learning_rate": 0.00019436490477135878,
      "loss": 8.9724,
      "step": 380
    },
    {
      "epoch": 0.11541876294761765,
      "grad_norm": 0.6171875,
      "learning_rate": 0.00019391889215899299,
      "loss": 9.0212,
      "step": 390
    },
    {
      "epoch": 0.11837821840781296,
      "grad_norm": 1.421875,
      "learning_rate": 0.0001934564464599461,
      "loss": 8.9091,
      "step": 400
    },
    {
      "epoch": 0.11837821840781296,
      "eval_loss": 8.961220741271973,
      "eval_runtime": 13.0065,
      "eval_samples_per_second": 115.48,
      "eval_steps_per_second": 28.909,
      "step": 400
    },
    {
      "epoch": 0.12133767386800828,
      "grad_norm": 0.443359375,
      "learning_rate": 0.00019297764858882514,
      "loss": 8.9547,
      "step": 410
    },
    {
      "epoch": 0.12429712932820361,
      "grad_norm": 0.466796875,
      "learning_rate": 0.00019248258232139388,
      "loss": 8.9394,
      "step": 420
    },
    {
      "epoch": 0.12725658478839894,
      "grad_norm": 0.61328125,
      "learning_rate": 0.00019197133427991436,
      "loss": 8.9748,
      "step": 430
    },
    {
      "epoch": 0.13021604024859426,
      "grad_norm": 0.73046875,
      "learning_rate": 0.00019144399391799043,
      "loss": 8.9198,
      "step": 440
    },
    {
      "epoch": 0.1331754957087896,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019090065350491626,
      "loss": 8.8904,
      "step": 450
    },
    {
      "epoch": 0.1361349511689849,
      "grad_norm": 0.494140625,
      "learning_rate": 0.0001903414081095315,
      "loss": 8.8971,
      "step": 460
    },
    {
      "epoch": 0.13909440662918024,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00018976635558358722,
      "loss": 8.84,
      "step": 470
    },
    {
      "epoch": 0.14205386208937557,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00018917559654462474,
      "loss": 8.838,
      "step": 480
    },
    {
      "epoch": 0.1450133175495709,
      "grad_norm": 0.5703125,
      "learning_rate": 0.00018856923435837022,
      "loss": 8.7761,
      "step": 490
    },
    {
      "epoch": 0.1479727730097662,
      "grad_norm": 0.96875,
      "learning_rate": 0.0001879473751206489,
      "loss": 8.8421,
      "step": 500
    },
    {
      "epoch": 0.15093222846996152,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00018731012763882133,
      "loss": 8.7691,
      "step": 510
    },
    {
      "epoch": 0.15389168393015684,
      "grad_norm": 0.4921875,
      "learning_rate": 0.00018665760341274505,
      "loss": 8.7749,
      "step": 520
    },
    {
      "epoch": 0.15685113939035217,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00018598991661526572,
      "loss": 8.79,
      "step": 530
    },
    {
      "epoch": 0.1598105948505475,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00018530718407223974,
      "loss": 8.8742,
      "step": 540
    },
    {
      "epoch": 0.16277005031074282,
      "grad_norm": 1.234375,
      "learning_rate": 0.00018460952524209355,
      "loss": 8.7845,
      "step": 550
    },
    {
      "epoch": 0.16572950577093815,
      "grad_norm": 0.470703125,
      "learning_rate": 0.00018389706219492147,
      "loss": 8.8165,
      "step": 560
    },
    {
      "epoch": 0.16868896123113347,
      "grad_norm": 0.486328125,
      "learning_rate": 0.00018316991959112716,
      "loss": 8.7024,
      "step": 570
    },
    {
      "epoch": 0.1716484166913288,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00018242822465961176,
      "loss": 8.7764,
      "step": 580
    },
    {
      "epoch": 0.17460787215152412,
      "grad_norm": 0.58984375,
      "learning_rate": 0.00018167210717551224,
      "loss": 8.7501,
      "step": 590
    },
    {
      "epoch": 0.17756732761171945,
      "grad_norm": 1.28125,
      "learning_rate": 0.00018090169943749476,
      "loss": 8.7257,
      "step": 600
    },
    {
      "epoch": 0.17756732761171945,
      "eval_loss": 8.762685775756836,
      "eval_runtime": 18.9408,
      "eval_samples_per_second": 79.3,
      "eval_steps_per_second": 19.851,
      "step": 600
    },
    {
      "epoch": 0.18052678307191478,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00018011713624460608,
      "loss": 8.7709,
      "step": 610
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00017931855487268782,
      "loss": 8.7334,
      "step": 620
    },
    {
      "epoch": 0.18644569399230543,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001785060950503568,
      "loss": 8.824,
      "step": 630
    },
    {
      "epoch": 0.18940514945250073,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00017767989893455698,
      "loss": 8.6731,
      "step": 640
    },
    {
      "epoch": 0.19236460491269605,
      "grad_norm": 0.90625,
      "learning_rate": 0.00017684011108568592,
      "loss": 8.7669,
      "step": 650
    },
    {
      "epoch": 0.19532406037289138,
      "grad_norm": 0.49609375,
      "learning_rate": 0.00017598687844230088,
      "loss": 8.6911,
      "step": 660
    },
    {
      "epoch": 0.1982835158330867,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00017512035029540885,
      "loss": 8.6932,
      "step": 670
    },
    {
      "epoch": 0.20124297129328203,
      "grad_norm": 0.52734375,
      "learning_rate": 0.000174240678262345,
      "loss": 8.71,
      "step": 680
    },
    {
      "epoch": 0.20420242675347736,
      "grad_norm": 0.59375,
      "learning_rate": 0.000173348016260244,
      "loss": 8.7219,
      "step": 690
    },
    {
      "epoch": 0.20716188221367268,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00017244252047910892,
      "loss": 8.6973,
      "step": 700
    },
    {
      "epoch": 0.210121337673868,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00017152434935448256,
      "loss": 8.6743,
      "step": 710
    },
    {
      "epoch": 0.21308079313406333,
      "grad_norm": 0.451171875,
      "learning_rate": 0.0001705936635397259,
      "loss": 8.7094,
      "step": 720
    },
    {
      "epoch": 0.21604024859425866,
      "grad_norm": 0.57421875,
      "learning_rate": 0.00016965062587790823,
      "loss": 8.7353,
      "step": 730
    },
    {
      "epoch": 0.218999704054454,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00016869540137331445,
      "loss": 8.6939,
      "step": 740
    },
    {
      "epoch": 0.2219591595146493,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00016772815716257412,
      "loss": 8.7202,
      "step": 750
    },
    {
      "epoch": 0.22491861497484464,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00016674906248541726,
      "loss": 8.6779,
      "step": 760
    },
    {
      "epoch": 0.22787807043503996,
      "grad_norm": 0.671875,
      "learning_rate": 0.00016575828865506245,
      "loss": 8.6627,
      "step": 770
    },
    {
      "epoch": 0.2308375258952353,
      "grad_norm": 0.4375,
      "learning_rate": 0.0001647560090282419,
      "loss": 8.7348,
      "step": 780
    },
    {
      "epoch": 0.2337969813554306,
      "grad_norm": 0.6875,
      "learning_rate": 0.000163742398974869,
      "loss": 8.7236,
      "step": 790
    },
    {
      "epoch": 0.23675643681562591,
      "grad_norm": 1.4140625,
      "learning_rate": 0.0001627176358473537,
      "loss": 8.7416,
      "step": 800
    },
    {
      "epoch": 0.23675643681562591,
      "eval_loss": 8.710856437683105,
      "eval_runtime": 16.7859,
      "eval_samples_per_second": 89.48,
      "eval_steps_per_second": 22.4,
      "step": 800
    },
    {
      "epoch": 0.23971589227582124,
      "grad_norm": 0.47265625,
      "learning_rate": 0.0001616818989495711,
      "loss": 8.7235,
      "step": 810
    },
    {
      "epoch": 0.24267534773601657,
      "grad_norm": 0.447265625,
      "learning_rate": 0.00016063536950548826,
      "loss": 8.7121,
      "step": 820
    },
    {
      "epoch": 0.2456348031962119,
      "grad_norm": 0.50390625,
      "learning_rate": 0.0001595782306274553,
      "loss": 8.741,
      "step": 830
    },
    {
      "epoch": 0.24859425865640722,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00015851066728416618,
      "loss": 8.6978,
      "step": 840
    },
    {
      "epoch": 0.25155371411660254,
      "grad_norm": 1.296875,
      "learning_rate": 0.00015743286626829437,
      "loss": 8.7496,
      "step": 850
    },
    {
      "epoch": 0.25451316957679787,
      "grad_norm": 0.455078125,
      "learning_rate": 0.00015634501616380967,
      "loss": 8.6913,
      "step": 860
    },
    {
      "epoch": 0.2574726250369932,
      "grad_norm": 0.5078125,
      "learning_rate": 0.00015524730731298134,
      "loss": 8.6728,
      "step": 870
    },
    {
      "epoch": 0.2604320804971885,
      "grad_norm": 0.5,
      "learning_rate": 0.0001541399317830738,
      "loss": 8.6724,
      "step": 880
    },
    {
      "epoch": 0.26339153595738385,
      "grad_norm": 0.8359375,
      "learning_rate": 0.0001530230833327405,
      "loss": 8.763,
      "step": 890
    },
    {
      "epoch": 0.2663509914175792,
      "grad_norm": 0.953125,
      "learning_rate": 0.00015189695737812152,
      "loss": 8.6008,
      "step": 900
    },
    {
      "epoch": 0.2693104468777745,
      "grad_norm": 0.455078125,
      "learning_rate": 0.0001507617509586517,
      "loss": 8.7395,
      "step": 910
    },
    {
      "epoch": 0.2722699023379698,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00014961766270258422,
      "loss": 8.6413,
      "step": 920
    },
    {
      "epoch": 0.27522935779816515,
      "grad_norm": 0.5078125,
      "learning_rate": 0.00014846489279223652,
      "loss": 8.7083,
      "step": 930
    },
    {
      "epoch": 0.2781888132583605,
      "grad_norm": 0.609375,
      "learning_rate": 0.0001473036429289641,
      "loss": 8.6829,
      "step": 940
    },
    {
      "epoch": 0.2811482687185558,
      "grad_norm": 1.34375,
      "learning_rate": 0.0001461341162978688,
      "loss": 8.6955,
      "step": 950
    },
    {
      "epoch": 0.28410772417875113,
      "grad_norm": 0.419921875,
      "learning_rate": 0.00014495651753224705,
      "loss": 8.6962,
      "step": 960
    },
    {
      "epoch": 0.28706717963894646,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00014377105267778518,
      "loss": 8.7166,
      "step": 970
    },
    {
      "epoch": 0.2900266350991418,
      "grad_norm": 0.55859375,
      "learning_rate": 0.00014257792915650728,
      "loss": 8.6469,
      "step": 980
    },
    {
      "epoch": 0.2929860905593371,
      "grad_norm": 0.6640625,
      "learning_rate": 0.00014137735573048233,
      "loss": 8.6999,
      "step": 990
    },
    {
      "epoch": 0.2959455460195324,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00014016954246529696,
      "loss": 8.5944,
      "step": 1000
    },
    {
      "epoch": 0.2959455460195324,
      "eval_loss": 8.698212623596191,
      "eval_runtime": 13.7844,
      "eval_samples_per_second": 108.964,
      "eval_steps_per_second": 27.277,
      "step": 1000
    },
    {
      "epoch": 0.2989050014797277,
      "grad_norm": 0.5546875,
      "learning_rate": 0.00013895470069330004,
      "loss": 8.7432,
      "step": 1010
    },
    {
      "epoch": 0.30186445693992303,
      "grad_norm": 0.498046875,
      "learning_rate": 0.00013773304297662559,
      "loss": 8.6772,
      "step": 1020
    },
    {
      "epoch": 0.30482391240011836,
      "grad_norm": 0.671875,
      "learning_rate": 0.00013650478307000057,
      "loss": 8.73,
      "step": 1030
    },
    {
      "epoch": 0.3077833678603137,
      "grad_norm": 0.77734375,
      "learning_rate": 0.00013527013588334415,
      "loss": 8.7362,
      "step": 1040
    },
    {
      "epoch": 0.310742823320509,
      "grad_norm": 1.296875,
      "learning_rate": 0.00013402931744416433,
      "loss": 8.6947,
      "step": 1050
    },
    {
      "epoch": 0.31370227878070434,
      "grad_norm": 0.451171875,
      "learning_rate": 0.00013278254485975976,
      "loss": 8.6919,
      "step": 1060
    },
    {
      "epoch": 0.31666173424089966,
      "grad_norm": 0.59375,
      "learning_rate": 0.00013153003627923218,
      "loss": 8.7202,
      "step": 1070
    },
    {
      "epoch": 0.319621189701095,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00013027201085531634,
      "loss": 8.7236,
      "step": 1080
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.640625,
      "learning_rate": 0.00012900868870603503,
      "loss": 8.7817,
      "step": 1090
    },
    {
      "epoch": 0.32554010062148564,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00012774029087618446,
      "loss": 8.8011,
      "step": 1100
    },
    {
      "epoch": 0.32849955608168097,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00012646703929865817,
      "loss": 8.687,
      "step": 1110
    },
    {
      "epoch": 0.3314590115418763,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00012518915675561483,
      "loss": 8.6354,
      "step": 1120
    },
    {
      "epoch": 0.3344184670020716,
      "grad_norm": 0.578125,
      "learning_rate": 0.00012390686683949798,
      "loss": 8.6407,
      "step": 1130
    },
    {
      "epoch": 0.33737792246226694,
      "grad_norm": 0.71875,
      "learning_rate": 0.00012262039391391404,
      "loss": 8.6823,
      "step": 1140
    },
    {
      "epoch": 0.34033737792246227,
      "grad_norm": 1.6484375,
      "learning_rate": 0.0001213299630743747,
      "loss": 8.7369,
      "step": 1150
    },
    {
      "epoch": 0.3432968333826576,
      "grad_norm": 0.48046875,
      "learning_rate": 0.00012003580010891213,
      "loss": 8.6849,
      "step": 1160
    },
    {
      "epoch": 0.3462562888428529,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00011873813145857249,
      "loss": 8.6571,
      "step": 1170
    },
    {
      "epoch": 0.34921574430304825,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00011743718417779517,
      "loss": 8.7425,
      "step": 1180
    },
    {
      "epoch": 0.3521751997632436,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00011613318589468511,
      "loss": 8.6455,
      "step": 1190
    },
    {
      "epoch": 0.3551346552234389,
      "grad_norm": 0.8203125,
      "learning_rate": 0.0001148263647711842,
      "loss": 8.673,
      "step": 1200
    },
    {
      "epoch": 0.3551346552234389,
      "eval_loss": 8.696282386779785,
      "eval_runtime": 20.1067,
      "eval_samples_per_second": 74.702,
      "eval_steps_per_second": 18.7,
      "step": 1200
    },
    {
      "epoch": 0.3580941106836342,
      "grad_norm": 0.466796875,
      "learning_rate": 0.0001135169494631497,
      "loss": 8.6666,
      "step": 1210
    },
    {
      "epoch": 0.36105356614382955,
      "grad_norm": 0.484375,
      "learning_rate": 0.00011220516908034601,
      "loss": 8.6954,
      "step": 1220
    },
    {
      "epoch": 0.3640130216040249,
      "grad_norm": 0.5,
      "learning_rate": 0.00011089125314635726,
      "loss": 8.7236,
      "step": 1230
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 0.62109375,
      "learning_rate": 0.00010957543155842702,
      "loss": 8.7772,
      "step": 1240
    },
    {
      "epoch": 0.36993193252441553,
      "grad_norm": 0.859375,
      "learning_rate": 0.00010825793454723325,
      "loss": 8.7222,
      "step": 1250
    },
    {
      "epoch": 0.37289138798461086,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00010693899263660441,
      "loss": 8.6544,
      "step": 1260
    },
    {
      "epoch": 0.3758508434448062,
      "grad_norm": 0.498046875,
      "learning_rate": 0.00010561883660318455,
      "loss": 8.6639,
      "step": 1270
    },
    {
      "epoch": 0.37881029890500145,
      "grad_norm": 0.53515625,
      "learning_rate": 0.00010429769743605407,
      "loss": 8.6819,
      "step": 1280
    },
    {
      "epoch": 0.3817697543651968,
      "grad_norm": 0.68359375,
      "learning_rate": 0.00010297580629631325,
      "loss": 8.6511,
      "step": 1290
    },
    {
      "epoch": 0.3847292098253921,
      "grad_norm": 1.03125,
      "learning_rate": 0.00010165339447663587,
      "loss": 8.6257,
      "step": 1300
    },
    {
      "epoch": 0.38768866528558743,
      "grad_norm": 0.43359375,
      "learning_rate": 0.00010033069336079952,
      "loss": 8.7457,
      "step": 1310
    },
    {
      "epoch": 0.39064812074578276,
      "grad_norm": 0.482421875,
      "learning_rate": 9.900793438320037e-05,
      "loss": 8.6771,
      "step": 1320
    },
    {
      "epoch": 0.3936075762059781,
      "grad_norm": 0.50390625,
      "learning_rate": 9.768534898835862e-05,
      "loss": 8.6776,
      "step": 1330
    },
    {
      "epoch": 0.3965670316661734,
      "grad_norm": 0.6171875,
      "learning_rate": 9.636316859042259e-05,
      "loss": 8.6742,
      "step": 1340
    },
    {
      "epoch": 0.39952648712636873,
      "grad_norm": 0.859375,
      "learning_rate": 9.504162453267777e-05,
      "loss": 8.6419,
      "step": 1350
    },
    {
      "epoch": 0.40248594258656406,
      "grad_norm": 0.451171875,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.7098,
      "step": 1360
    },
    {
      "epoch": 0.4054453980467594,
      "grad_norm": 0.546875,
      "learning_rate": 9.24013702137397e-05,
      "loss": 8.6633,
      "step": 1370
    },
    {
      "epoch": 0.4084048535069547,
      "grad_norm": 0.5859375,
      "learning_rate": 9.108312192060298e-05,
      "loss": 8.687,
      "step": 1380
    },
    {
      "epoch": 0.41136430896715004,
      "grad_norm": 0.890625,
      "learning_rate": 8.97664338229395e-05,
      "loss": 8.713,
      "step": 1390
    },
    {
      "epoch": 0.41432376442734536,
      "grad_norm": 1.6015625,
      "learning_rate": 8.845153630304139e-05,
      "loss": 8.7511,
      "step": 1400
    },
    {
      "epoch": 0.41432376442734536,
      "eval_loss": 8.69721794128418,
      "eval_runtime": 8.7762,
      "eval_samples_per_second": 171.145,
      "eval_steps_per_second": 42.843,
      "step": 1400
    },
    {
      "epoch": 0.4172832198875407,
      "grad_norm": 0.46484375,
      "learning_rate": 8.713865942990141e-05,
      "loss": 8.6655,
      "step": 1410
    },
    {
      "epoch": 0.420242675347736,
      "grad_norm": 0.55078125,
      "learning_rate": 8.582803291895758e-05,
      "loss": 8.6978,
      "step": 1420
    },
    {
      "epoch": 0.42320213080793134,
      "grad_norm": 0.515625,
      "learning_rate": 8.451988609189987e-05,
      "loss": 8.7573,
      "step": 1430
    },
    {
      "epoch": 0.42616158626812667,
      "grad_norm": 0.70703125,
      "learning_rate": 8.321444783654524e-05,
      "loss": 8.6963,
      "step": 1440
    },
    {
      "epoch": 0.429121041728322,
      "grad_norm": 1.1953125,
      "learning_rate": 8.191194656678904e-05,
      "loss": 8.7627,
      "step": 1450
    },
    {
      "epoch": 0.4320804971885173,
      "grad_norm": 0.53125,
      "learning_rate": 8.061261018263919e-05,
      "loss": 8.6564,
      "step": 1460
    },
    {
      "epoch": 0.43503995264871265,
      "grad_norm": 0.5546875,
      "learning_rate": 7.931666603034033e-05,
      "loss": 8.6641,
      "step": 1470
    },
    {
      "epoch": 0.437999408108908,
      "grad_norm": 0.83203125,
      "learning_rate": 7.80243408625947e-05,
      "loss": 8.6646,
      "step": 1480
    },
    {
      "epoch": 0.4409588635691033,
      "grad_norm": 0.71875,
      "learning_rate": 7.673586079888698e-05,
      "loss": 8.7323,
      "step": 1490
    },
    {
      "epoch": 0.4439183190292986,
      "grad_norm": 1.0078125,
      "learning_rate": 7.54514512859201e-05,
      "loss": 8.6167,
      "step": 1500
    },
    {
      "epoch": 0.44687777448949395,
      "grad_norm": 0.453125,
      "learning_rate": 7.417133705816837e-05,
      "loss": 8.6929,
      "step": 1510
    },
    {
      "epoch": 0.4498372299496893,
      "grad_norm": 0.482421875,
      "learning_rate": 7.289574209855559e-05,
      "loss": 8.6871,
      "step": 1520
    },
    {
      "epoch": 0.4527966854098846,
      "grad_norm": 0.484375,
      "learning_rate": 7.16248895992645e-05,
      "loss": 8.6881,
      "step": 1530
    },
    {
      "epoch": 0.45575614087007993,
      "grad_norm": 0.7578125,
      "learning_rate": 7.035900192268464e-05,
      "loss": 8.6753,
      "step": 1540
    },
    {
      "epoch": 0.45871559633027525,
      "grad_norm": 0.83203125,
      "learning_rate": 6.909830056250527e-05,
      "loss": 8.7056,
      "step": 1550
    },
    {
      "epoch": 0.4616750517904706,
      "grad_norm": 0.431640625,
      "learning_rate": 6.784300610496048e-05,
      "loss": 8.706,
      "step": 1560
    },
    {
      "epoch": 0.46463450725066585,
      "grad_norm": 0.482421875,
      "learning_rate": 6.65933381902329e-05,
      "loss": 8.6888,
      "step": 1570
    },
    {
      "epoch": 0.4675939627108612,
      "grad_norm": 0.67578125,
      "learning_rate": 6.534951547402322e-05,
      "loss": 8.7158,
      "step": 1580
    },
    {
      "epoch": 0.4705534181710565,
      "grad_norm": 0.63671875,
      "learning_rate": 6.411175558929152e-05,
      "loss": 8.728,
      "step": 1590
    },
    {
      "epoch": 0.47351287363125183,
      "grad_norm": 0.890625,
      "learning_rate": 6.28802751081779e-05,
      "loss": 8.729,
      "step": 1600
    },
    {
      "epoch": 0.47351287363125183,
      "eval_loss": 8.696118354797363,
      "eval_runtime": 19.8643,
      "eval_samples_per_second": 75.613,
      "eval_steps_per_second": 18.928,
      "step": 1600
    },
    {
      "epoch": 0.47647232909144716,
      "grad_norm": 0.52734375,
      "learning_rate": 6.165528950410884e-05,
      "loss": 8.6937,
      "step": 1610
    },
    {
      "epoch": 0.4794317845516425,
      "grad_norm": 0.486328125,
      "learning_rate": 6.0437013114095195e-05,
      "loss": 8.6631,
      "step": 1620
    },
    {
      "epoch": 0.4823912400118378,
      "grad_norm": 0.51953125,
      "learning_rate": 5.922565910122967e-05,
      "loss": 8.696,
      "step": 1630
    },
    {
      "epoch": 0.48535069547203313,
      "grad_norm": 0.75,
      "learning_rate": 5.8021439417389444e-05,
      "loss": 8.6176,
      "step": 1640
    },
    {
      "epoch": 0.48831015093222846,
      "grad_norm": 0.984375,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 8.7082,
      "step": 1650
    },
    {
      "epoch": 0.4912696063924238,
      "grad_norm": 0.470703125,
      "learning_rate": 5.563524456592163e-05,
      "loss": 8.6952,
      "step": 1660
    },
    {
      "epoch": 0.4942290618526191,
      "grad_norm": 0.5,
      "learning_rate": 5.4453686913300074e-05,
      "loss": 8.678,
      "step": 1670
    },
    {
      "epoch": 0.49718851731281444,
      "grad_norm": 0.5625,
      "learning_rate": 5.328009854666303e-05,
      "loss": 8.6815,
      "step": 1680
    },
    {
      "epoch": 0.5001479727730098,
      "grad_norm": 0.703125,
      "learning_rate": 5.2114684809993044e-05,
      "loss": 8.6626,
      "step": 1690
    },
    {
      "epoch": 0.5031074282332051,
      "grad_norm": 1.0390625,
      "learning_rate": 5.095764961694922e-05,
      "loss": 8.7641,
      "step": 1700
    },
    {
      "epoch": 0.5060668836934004,
      "grad_norm": 0.515625,
      "learning_rate": 4.980919541518796e-05,
      "loss": 8.6364,
      "step": 1710
    },
    {
      "epoch": 0.5090263391535957,
      "grad_norm": 0.482421875,
      "learning_rate": 4.866952315094088e-05,
      "loss": 8.689,
      "step": 1720
    },
    {
      "epoch": 0.511985794613791,
      "grad_norm": 0.51953125,
      "learning_rate": 4.753883223385467e-05,
      "loss": 8.7382,
      "step": 1730
    },
    {
      "epoch": 0.5149452500739864,
      "grad_norm": 0.62109375,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 8.6902,
      "step": 1740
    },
    {
      "epoch": 0.5179047055341817,
      "grad_norm": 1.0859375,
      "learning_rate": 4.530518418775733e-05,
      "loss": 8.6841,
      "step": 1750
    },
    {
      "epoch": 0.520864160994377,
      "grad_norm": 0.478515625,
      "learning_rate": 4.4202617882478405e-05,
      "loss": 8.708,
      "step": 1760
    },
    {
      "epoch": 0.5238236164545723,
      "grad_norm": 0.486328125,
      "learning_rate": 4.310981450344189e-05,
      "loss": 8.6534,
      "step": 1770
    },
    {
      "epoch": 0.5267830719147677,
      "grad_norm": 0.5234375,
      "learning_rate": 4.2026965259596666e-05,
      "loss": 8.6607,
      "step": 1780
    },
    {
      "epoch": 0.529742527374963,
      "grad_norm": 0.8515625,
      "learning_rate": 4.0954259618206295e-05,
      "loss": 8.6611,
      "step": 1790
    },
    {
      "epoch": 0.5327019828351583,
      "grad_norm": 1.8984375,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 8.6325,
      "step": 1800
    },
    {
      "epoch": 0.5327019828351583,
      "eval_loss": 8.694791793823242,
      "eval_runtime": 14.7074,
      "eval_samples_per_second": 102.126,
      "eval_steps_per_second": 25.565,
      "step": 1800
    },
    {
      "epoch": 0.5356614382953536,
      "grad_norm": 0.50390625,
      "learning_rate": 3.884002810481958e-05,
      "loss": 8.6837,
      "step": 1810
    },
    {
      "epoch": 0.538620893755549,
      "grad_norm": 0.490234375,
      "learning_rate": 3.779887216211995e-05,
      "loss": 8.6631,
      "step": 1820
    },
    {
      "epoch": 0.5415803492157443,
      "grad_norm": 0.5546875,
      "learning_rate": 3.676859961574162e-05,
      "loss": 8.6576,
      "step": 1830
    },
    {
      "epoch": 0.5445398046759397,
      "grad_norm": 0.69921875,
      "learning_rate": 3.574939073354838e-05,
      "loss": 8.7047,
      "step": 1840
    },
    {
      "epoch": 0.5474992601361349,
      "grad_norm": 1.0546875,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 8.7234,
      "step": 1850
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 0.48046875,
      "learning_rate": 3.3744875322865034e-05,
      "loss": 8.7565,
      "step": 1860
    },
    {
      "epoch": 0.5534181710565256,
      "grad_norm": 0.4609375,
      "learning_rate": 3.275991952653054e-05,
      "loss": 8.6812,
      "step": 1870
    },
    {
      "epoch": 0.556377626516721,
      "grad_norm": 0.54296875,
      "learning_rate": 3.178672879732435e-05,
      "loss": 8.7074,
      "step": 1880
    },
    {
      "epoch": 0.5593370819769162,
      "grad_norm": 0.6875,
      "learning_rate": 3.0825473415445074e-05,
      "loss": 8.6826,
      "step": 1890
    },
    {
      "epoch": 0.5622965374371116,
      "grad_norm": 1.3359375,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 8.7359,
      "step": 1900
    },
    {
      "epoch": 0.5652559928973069,
      "grad_norm": 0.49609375,
      "learning_rate": 2.8939439343332086e-05,
      "loss": 8.6599,
      "step": 1910
    },
    {
      "epoch": 0.5682154483575023,
      "grad_norm": 0.53515625,
      "learning_rate": 2.8014990654450325e-05,
      "loss": 8.631,
      "step": 1920
    },
    {
      "epoch": 0.5711749038176975,
      "grad_norm": 0.55859375,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.6579,
      "step": 1930
    },
    {
      "epoch": 0.5741343592778929,
      "grad_norm": 0.59765625,
      "learning_rate": 2.6204038701499056e-05,
      "loss": 8.7039,
      "step": 1940
    },
    {
      "epoch": 0.5770938147380882,
      "grad_norm": 1.2109375,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 8.6511,
      "step": 1950
    },
    {
      "epoch": 0.5800532701982836,
      "grad_norm": 0.4921875,
      "learning_rate": 2.4444733115075823e-05,
      "loss": 8.6733,
      "step": 1960
    },
    {
      "epoch": 0.5830127256584788,
      "grad_norm": 0.48828125,
      "learning_rate": 2.3584833912548888e-05,
      "loss": 8.6404,
      "step": 1970
    },
    {
      "epoch": 0.5859721811186742,
      "grad_norm": 0.53515625,
      "learning_rate": 2.2738305151465645e-05,
      "loss": 8.6784,
      "step": 1980
    },
    {
      "epoch": 0.5889316365788695,
      "grad_norm": 0.67578125,
      "learning_rate": 2.190529494984782e-05,
      "loss": 8.6897,
      "step": 1990
    },
    {
      "epoch": 0.5918910920390648,
      "grad_norm": 1.3046875,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 8.6338,
      "step": 2000
    },
    {
      "epoch": 0.5918910920390648,
      "eval_loss": 8.694610595703125,
      "eval_runtime": 15.9292,
      "eval_samples_per_second": 94.292,
      "eval_steps_per_second": 23.604,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 51272680734720.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}