{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.769124264451367,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.8461538461538456e-05,
      "loss": 3.0784,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.692307692307691e-05,
      "loss": 2.3977,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011538461538461538,
      "loss": 1.443,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00015384615384615382,
      "loss": 0.8912,
      "step": 100
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001923076923076923,
      "loss": 1.1574,
      "step": 125
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00023076923076923076,
      "loss": 0.8311,
      "step": 150
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002692307692307692,
      "loss": 1.1308,
      "step": 175
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002999995341928201,
      "loss": 0.7901,
      "step": 200
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002999832312452881,
      "loss": 1.1048,
      "step": 225
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002999436408316976,
      "loss": 0.7632,
      "step": 250
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002998807690991386,
      "loss": 1.1239,
      "step": 275
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00029979462580952446,
      "loss": 0.7622,
      "step": 300
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029968522433807687,
      "loss": 1.105,
      "step": 325
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00029955258167124835,
      "loss": 0.7669,
      "step": 350
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002993967184040853,
      "loss": 1.0854,
      "step": 375
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00029921765873703004,
      "loss": 0.7586,
      "step": 400
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002990154304721634,
      "loss": 1.0849,
      "step": 425
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000298790065008888,
      "loss": 0.7403,
      "step": 450
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002985415973390528,
      "loss": 1.0786,
      "step": 475
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00029827006604152,
      "loss": 0.7676,
      "step": 500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029797551327617543,
      "loss": 1.087,
      "step": 525
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002976579847773818,
      "loss": 0.7685,
      "step": 550
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00029731752984687835,
      "loss": 1.072,
      "step": 575
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002969542013461254,
      "loss": 0.7611,
      "step": 600
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000296568055688097,
      "loss": 1.0691,
      "step": 625
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029615915282852175,
      "loss": 0.7512,
      "step": 650
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00029572755625657365,
      "loss": 1.0789,
      "step": 675
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029527333298501427,
      "loss": 0.739,
      "step": 700
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002947965535397879,
      "loss": 1.0944,
      "step": 725
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002942972919490714,
      "loss": 0.7681,
      "step": 750
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002937756257317797,
      "loss": 1.0773,
      "step": 775
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00029323163588552975,
      "loss": 0.7541,
      "step": 800
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002926654068740645,
      "loss": 1.0885,
      "step": 825
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002920770266141382,
      "loss": 0.7505,
      "step": 850
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000291466586461866,
      "loss": 1.0623,
      "step": 875
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00029083418119853904,
      "loss": 0.7429,
      "step": 900
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002901799090159085,
      "loss": 1.0523,
      "step": 925
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00028950387150093916,
      "loss": 0.7258,
      "step": 950
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002888061736200367,
      "loss": 1.0618,
      "step": 975
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002880869237027496,
      "loss": 0.739,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002873462334249492,
      "loss": 1.063,
      "step": 1025
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028658421779149,
      "loss": 0.7298,
      "step": 1050
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002858009951183536,
      "loss": 1.0526,
      "step": 1075
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002849966870142775,
      "loss": 0.7322,
      "step": 1100
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00028417141836187374,
      "loss": 1.0509,
      "step": 1125
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002833253172982385,
      "loss": 0.7245,
      "step": 1150
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002824585151950568,
      "loss": 1.0746,
      "step": 1175
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00028157114663820445,
      "loss": 0.7327,
      "step": 1200
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002806633494068519,
      "loss": 1.0685,
      "step": 1225
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00027973526445207084,
      "loss": 0.7457,
      "step": 1250
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00027878703587495,
      "loss": 1.0731,
      "step": 1275
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00027781881090422017,
      "loss": 0.728,
      "step": 1300
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00027683073987339523,
      "loss": 1.0638,
      "step": 1325
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002758229761974294,
      "loss": 0.734,
      "step": 1350
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002747956763488979,
      "loss": 1.0548,
      "step": 1375
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002737489998337011,
      "loss": 0.7357,
      "step": 1400
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00027268310916629885,
      "loss": 1.0528,
      "step": 1425
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002715981698444775,
      "loss": 0.7227,
      "step": 1450
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002704943503236531,
      "loss": 1.0546,
      "step": 1475
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00026937182199071613,
      "loss": 0.7228,
      "step": 1500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002682307591374206,
      "loss": 1.052,
      "step": 1525
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002670713389333225,
      "loss": 0.729,
      "step": 1550
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002658937413982708,
      "loss": 1.0472,
      "step": 1575
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00026469814937445655,
      "loss": 0.7294,
      "step": 1600
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00026348474849802357,
      "loss": 1.0383,
      "step": 1625
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000262253727170245,
      "loss": 0.723,
      "step": 1650
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002610052765282711,
      "loss": 1.0467,
      "step": 1675
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002597395904154515,
      "loss": 0.7191,
      "step": 1700
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002584568653512381,
      "loss": 1.0481,
      "step": 1725
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002571573005006718,
      "loss": 0.6965,
      "step": 1750
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00025584109764345905,
      "loss": 1.0579,
      "step": 1775
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002545084611426415,
      "loss": 0.7132,
      "step": 1800
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00025315959791286585,
      "loss": 1.0537,
      "step": 1825
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002517947173882562,
      "loss": 0.7253,
      "step": 1850
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002504140314898962,
      "loss": 1.0335,
      "step": 1875
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002490177545929246,
      "loss": 0.7112,
      "step": 1900
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024760610349324955,
      "loss": 1.07,
      "step": 1925
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002461792973738878,
      "loss": 0.7135,
      "step": 1950
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024473755777093244,
      "loss": 1.0404,
      "step": 1975
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024328110853915556,
      "loss": 0.714,
      "step": 2000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00024181017581725143,
      "loss": 1.051,
      "step": 2025
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00024032498799272402,
      "loss": 0.725,
      "step": 2050
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002388257756664263,
      "loss": 1.054,
      "step": 2075
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00023731277161675532,
      "loss": 0.7111,
      "step": 2100
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00023578621076350965,
      "loss": 1.0462,
      "step": 2125
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00023424633013141363,
      "loss": 0.7244,
      "step": 2150
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00023269336881331565,
      "loss": 0.9686,
      "step": 2175
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00023112756793306445,
      "loss": 0.8741,
      "step": 2200
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000229549170608071,
      "loss": 0.7772,
      "step": 2225
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00022795842191156,
      "loss": 0.8901,
      "step": 2250
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00022635556883451806,
      "loss": 0.8139,
      "step": 2275
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00022474086024734443,
      "loss": 0.8782,
      "step": 2300
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002231145468612094,
      "loss": 0.8002,
      "step": 2325
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00022147688118912695,
      "loss": 0.9184,
      "step": 2350
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000219828117506748,
      "loss": 0.7961,
      "step": 2375
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002181685118128797,
      "loss": 0.9099,
      "step": 2400
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00021649832178973727,
      "loss": 0.8191,
      "step": 2425
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00021481780676293428,
      "loss": 0.925,
      "step": 2450
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00021312722766121808,
      "loss": 0.7863,
      "step": 2475
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00021142684697595605,
      "loss": 0.9065,
      "step": 2500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00020971692872037923,
      "loss": 0.7908,
      "step": 2525
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00020799773838859004,
      "loss": 0.9115,
      "step": 2550
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00020626954291433935,
      "loss": 0.7844,
      "step": 2575
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002045326106295808,
      "loss": 0.9132,
      "step": 2600
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002027872112228075,
      "loss": 0.7805,
      "step": 2625
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00020103361569717837,
      "loss": 0.9106,
      "step": 2650
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019927209632844006,
      "loss": 0.791,
      "step": 2675
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019750292662265174,
      "loss": 0.8947,
      "step": 2700
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019572638127371837,
      "loss": 0.7896,
      "step": 2725
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019394273612073992,
      "loss": 0.8987,
      "step": 2750
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019215226810518254,
      "loss": 0.8036,
      "step": 2775
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001903552552278787,
      "loss": 0.9274,
      "step": 2800
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001885519765058627,
      "loss": 0.7937,
      "step": 2825
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001867427119290488,
      "loss": 0.8966,
      "step": 2850
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00018492774241675742,
      "loss": 0.7985,
      "step": 2875
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00018310734977409826,
      "loss": 0.8964,
      "step": 2900
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00018128181664821475,
      "loss": 0.7905,
      "step": 2925
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017945142648439843,
      "loss": 0.8919,
      "step": 2950
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017761646348207917,
      "loss": 0.8017,
      "step": 2975
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001757772125506984,
      "loss": 0.8873,
      "step": 3000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00017393395926547202,
      "loss": 0.7904,
      "step": 3025
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00017208698982304984,
      "loss": 0.9017,
      "step": 3050
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00017023659099707876,
      "loss": 0.7917,
      "step": 3075
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016838305009367628,
      "loss": 0.9097,
      "step": 3100
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016652665490682128,
      "loss": 0.8175,
      "step": 3125
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016466769367366887,
      "loss": 0.8899,
      "step": 3150
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016280645502979695,
      "loss": 0.7847,
      "step": 3175
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016094322796439043,
      "loss": 0.8796,
      "step": 3200
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00015907830177537078,
      "loss": 0.7959,
      "step": 3225
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00015721196602447735,
      "loss": 0.888,
      "step": 3250
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001553445104923083,
      "loss": 0.7741,
      "step": 3275
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00015347622513332685,
      "loss": 0.9118,
      "step": 3300
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00015160740003084127,
      "loss": 0.7928,
      "step": 3325
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00014973832535196402,
      "loss": 0.8985,
      "step": 3350
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00014786929130255872,
      "loss": 0.7885,
      "step": 3375
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00014600058808218047,
      "loss": 0.8915,
      "step": 3400
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001441325058390176,
      "loss": 0.775,
      "step": 3425
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00014226533462484097,
      "loss": 0.9084,
      "step": 3450
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001403993643499688,
      "loss": 0.783,
      "step": 3475
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00013853488473825263,
      "loss": 0.897,
      "step": 3500
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00013667218528209314,
      "loss": 0.7799,
      "step": 3525
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00013481155519749142,
      "loss": 0.9029,
      "step": 3550
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001329532833791431,
      "loss": 0.7867,
      "step": 3575
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00013109765835558256,
      "loss": 0.8932,
      "step": 3600
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00012924496824438401,
      "loss": 0.7868,
      "step": 3625
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00012739550070742616,
      "loss": 0.8851,
      "step": 3650
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00012554954290622798,
      "loss": 0.7783,
      "step": 3675
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001237073814573617,
      "loss": 0.8929,
      "step": 3700
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00012186930238795088,
      "loss": 0.8003,
      "step": 3725
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00012003559109125972,
      "loss": 0.8833,
      "step": 3750
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011820653228238095,
      "loss": 0.7831,
      "step": 3775
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00011638240995402873,
      "loss": 0.8936,
      "step": 3800
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00011456350733244412,
      "loss": 0.7678,
      "step": 3825
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00011275010683341939,
      "loss": 0.9017,
      "step": 3850
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00011094249001844783,
      "loss": 0.7693,
      "step": 3875
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001091409375510068,
      "loss": 0.8821,
      "step": 3900
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00010734572915297985,
      "loss": 0.7796,
      "step": 3925
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.000105557143561225,
      "loss": 0.8948,
      "step": 3950
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00010377545848429614,
      "loss": 0.7797,
      "step": 3975
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00010200095055932406,
      "loss": 0.8789,
      "step": 4000
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00010023389530906374,
      "loss": 0.791,
      "step": 4025
    },
    {
      "epoch": 1.87,
      "learning_rate": 9.847456709911478e-05,
      "loss": 0.8838,
      "step": 4050
    },
    {
      "epoch": 1.88,
      "learning_rate": 9.672323909532129e-05,
      "loss": 0.7831,
      "step": 4075
    },
    {
      "epoch": 1.89,
      "learning_rate": 9.498018322135838e-05,
      "loss": 0.8763,
      "step": 4100
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.324567011651136e-05,
      "loss": 0.8028,
      "step": 4125
    },
    {
      "epoch": 1.92,
      "learning_rate": 9.151996909365419e-05,
      "loss": 0.9126,
      "step": 4150
    },
    {
      "epoch": 1.93,
      "learning_rate": 8.980334809743414e-05,
      "loss": 0.7953,
      "step": 4175
    },
    {
      "epoch": 1.94,
      "learning_rate": 8.809607366266878e-05,
      "loss": 0.8934,
      "step": 4200
    },
    {
      "epoch": 1.95,
      "learning_rate": 8.639841087296207e-05,
      "loss": 0.7763,
      "step": 4225
    },
    {
      "epoch": 1.96,
      "learning_rate": 8.471062331954525e-05,
      "loss": 0.8913,
      "step": 4250
    },
    {
      "epoch": 1.97,
      "learning_rate": 8.303297306034988e-05,
      "loss": 0.7765,
      "step": 4275
    },
    {
      "epoch": 1.98,
      "learning_rate": 8.136572057931912e-05,
      "loss": 0.8763,
      "step": 4300
    },
    {
      "epoch": 2.0,
      "learning_rate": 7.970912474596287e-05,
      "loss": 0.7483,
      "step": 4325
    },
    {
      "epoch": 2.01,
      "learning_rate": 7.806344277516381e-05,
      "loss": 0.9051,
      "step": 4350
    },
    {
      "epoch": 2.02,
      "learning_rate": 7.642893018724062e-05,
      "loss": 0.703,
      "step": 4375
    },
    {
      "epoch": 2.03,
      "learning_rate": 7.480584076827394e-05,
      "loss": 0.8799,
      "step": 4400
    },
    {
      "epoch": 2.04,
      "learning_rate": 7.319442653070165e-05,
      "loss": 0.7338,
      "step": 4425
    },
    {
      "epoch": 2.05,
      "learning_rate": 7.159493767418978e-05,
      "loss": 0.8673,
      "step": 4450
    },
    {
      "epoch": 2.07,
      "learning_rate": 7.000762254678456e-05,
      "loss": 0.7347,
      "step": 4475
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.843272760635235e-05,
      "loss": 0.8641,
      "step": 4500
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.687049738231268e-05,
      "loss": 0.7346,
      "step": 4525
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.532117443767072e-05,
      "loss": 0.8766,
      "step": 4550
    },
    {
      "epoch": 2.11,
      "learning_rate": 6.378499933135577e-05,
      "loss": 0.7404,
      "step": 4575
    },
    {
      "epoch": 2.12,
      "learning_rate": 6.226221058086958e-05,
      "loss": 0.8855,
      "step": 4600
    },
    {
      "epoch": 2.13,
      "learning_rate": 6.0753044625253063e-05,
      "loss": 0.741,
      "step": 4625
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.9257735788374854e-05,
      "loss": 0.8679,
      "step": 4650
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.7776516242548395e-05,
      "loss": 0.7291,
      "step": 4675
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.6309615972483455e-05,
      "loss": 0.8408,
      "step": 4700
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.485726273957677e-05,
      "loss": 0.7349,
      "step": 4725
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.341968204654852e-05,
      "loss": 0.8473,
      "step": 4750
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.199709710242896e-05,
      "loss": 0.7233,
      "step": 4775
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.058972878790129e-05,
      "loss": 0.8649,
      "step": 4800
    },
    {
      "epoch": 2.23,
      "learning_rate": 4.919779562100643e-05,
      "loss": 0.7435,
      "step": 4825
    },
    {
      "epoch": 2.24,
      "learning_rate": 4.782151372321425e-05,
      "loss": 0.8768,
      "step": 4850
    },
    {
      "epoch": 2.25,
      "learning_rate": 4.646109678586675e-05,
      "loss": 0.7419,
      "step": 4875
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.511675603699927e-05,
      "loss": 0.8745,
      "step": 4900
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.3788700208543235e-05,
      "loss": 0.7294,
      "step": 4925
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.2477135503917515e-05,
      "loss": 0.8768,
      "step": 4950
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.1182265566011184e-05,
      "loss": 0.74,
      "step": 4975
    },
    {
      "epoch": 2.31,
      "learning_rate": 3.9904291445564937e-05,
      "loss": 0.8695,
      "step": 5000
    },
    {
      "epoch": 2.32,
      "learning_rate": 3.864341156995439e-05,
      "loss": 0.7214,
      "step": 5025
    },
    {
      "epoch": 2.33,
      "learning_rate": 3.739982171238066e-05,
      "loss": 0.8579,
      "step": 5050
    },
    {
      "epoch": 2.34,
      "learning_rate": 3.617371496147347e-05,
      "loss": 0.7466,
      "step": 5075
    },
    {
      "epoch": 2.35,
      "learning_rate": 3.4965281691310755e-05,
      "loss": 0.8625,
      "step": 5100
    },
    {
      "epoch": 2.37,
      "learning_rate": 3.3774709531859636e-05,
      "loss": 0.7496,
      "step": 5125
    },
    {
      "epoch": 2.38,
      "learning_rate": 3.260218333984402e-05,
      "loss": 0.8741,
      "step": 5150
    },
    {
      "epoch": 2.39,
      "learning_rate": 3.144788517004204e-05,
      "loss": 0.7245,
      "step": 5175
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.0311994247019213e-05,
      "loss": 0.8712,
      "step": 5200
    },
    {
      "epoch": 2.41,
      "learning_rate": 2.9194686937300664e-05,
      "loss": 0.7163,
      "step": 5225
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.8096136721987088e-05,
      "loss": 0.8638,
      "step": 5250
    },
    {
      "epoch": 2.43,
      "learning_rate": 2.7016514169819016e-05,
      "loss": 0.7206,
      "step": 5275
    },
    {
      "epoch": 2.45,
      "learning_rate": 2.595598691069304e-05,
      "loss": 0.8693,
      "step": 5300
    },
    {
      "epoch": 2.46,
      "learning_rate": 2.491471960963434e-05,
      "loss": 0.7308,
      "step": 5325
    },
    {
      "epoch": 2.47,
      "learning_rate": 2.3892873941229695e-05,
      "loss": 0.8619,
      "step": 5350
    },
    {
      "epoch": 2.48,
      "learning_rate": 2.2890608564524616e-05,
      "loss": 0.7062,
      "step": 5375
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.190807909838896e-05,
      "loss": 0.8553,
      "step": 5400
    },
    {
      "epoch": 2.5,
      "learning_rate": 2.0945438097354384e-05,
      "loss": 0.7415,
      "step": 5425
    },
    {
      "epoch": 2.52,
      "learning_rate": 2.0002835027927544e-05,
      "loss": 0.8702,
      "step": 5450
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.908041624538304e-05,
      "loss": 0.7552,
      "step": 5475
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.817832497103901e-05,
      "loss": 0.8496,
      "step": 5500
    },
    {
      "epoch": 2.55,
      "learning_rate": 1.729670127001987e-05,
      "loss": 0.7167,
      "step": 5525
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.643568202950854e-05,
      "loss": 0.8556,
      "step": 5550
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.559540093749247e-05,
      "loss": 0.7245,
      "step": 5575
    },
    {
      "epoch": 2.58,
      "learning_rate": 1.4775988462006316e-05,
      "loss": 0.8672,
      "step": 5600
    },
    {
      "epoch": 2.6,
      "learning_rate": 1.3977571830874524e-05,
      "loss": 0.7386,
      "step": 5625
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.3200275011956901e-05,
      "loss": 0.862,
      "step": 5650
    },
    {
      "epoch": 2.62,
      "learning_rate": 1.2444218693900826e-05,
      "loss": 0.7431,
      "step": 5675
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.170952026740178e-05,
      "loss": 0.8653,
      "step": 5700
    },
    {
      "epoch": 2.64,
      "learning_rate": 1.0996293806976907e-05,
      "loss": 0.743,
      "step": 5725
    },
    {
      "epoch": 2.65,
      "learning_rate": 1.0304650053252634e-05,
      "loss": 0.8539,
      "step": 5750
    },
    {
      "epoch": 2.67,
      "learning_rate": 9.63469639577048e-06,
      "loss": 0.7485,
      "step": 5775
    },
    {
      "epoch": 2.68,
      "learning_rate": 8.986536856312987e-06,
      "loss": 0.861,
      "step": 5800
    },
    {
      "epoch": 2.69,
      "learning_rate": 8.360272072752406e-06,
      "loss": 0.7405,
      "step": 5825
    },
    {
      "epoch": 2.7,
      "learning_rate": 7.755999283425168e-06,
      "loss": 0.8565,
      "step": 5850
    },
    {
      "epoch": 2.71,
      "learning_rate": 7.1738123120338e-06,
      "loss": 0.7328,
      "step": 5875
    },
    {
      "epoch": 2.72,
      "learning_rate": 6.613801553079184e-06,
      "loss": 0.8614,
      "step": 5900
    },
    {
      "epoch": 2.73,
      "learning_rate": 6.076053957825411e-06,
      "loss": 0.7389,
      "step": 5925
    },
    {
      "epoch": 2.75,
      "learning_rate": 5.560653020798906e-06,
      "loss": 0.8642,
      "step": 5950
    },
    {
      "epoch": 2.76,
      "learning_rate": 5.067678766824651e-06,
      "loss": 0.7141,
      "step": 5975
    },
    {
      "epoch": 2.77,
      "learning_rate": 4.597207738600911e-06,
      "loss": 0.8602,
      "step": 6000
    }
  ],
  "max_steps": 6498,
  "num_train_epochs": 3,
  "total_flos": 4.8008476405304525e+17,
  "trial_name": null,
  "trial_params": null
}