{
  "best_metric": 6.020912170410156,
  "best_model_checkpoint": "./results/models/checkpoint-139568",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 174460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0019994268027054914,
      "loss": 6.8812,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019988536054109823,
      "loss": 6.7318,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019982804081164736,
      "loss": 6.7006,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001997707210821965,
      "loss": 6.6761,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019971340135274563,
      "loss": 6.6478,
      "step": 2500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001996560816232947,
      "loss": 6.6334,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019959876189384385,
      "loss": 6.6285,
      "step": 3500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00199541442164393,
      "loss": 6.6122,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019948412243494212,
      "loss": 6.6007,
      "step": 4500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001994268027054912,
      "loss": 6.5815,
      "step": 5000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019936948297604035,
      "loss": 6.5741,
      "step": 5500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001993121632465895,
      "loss": 6.5711,
      "step": 6000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001992548435171386,
      "loss": 6.5854,
      "step": 6500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001991975237876877,
      "loss": 6.5759,
      "step": 7000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0019914020405823684,
      "loss": 6.5474,
      "step": 7500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0019908288432878597,
      "loss": 6.5431,
      "step": 8000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001990255645993351,
      "loss": 6.5421,
      "step": 8500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001989682448698842,
      "loss": 6.532,
      "step": 9000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0019891092514043333,
      "loss": 6.5349,
      "step": 9500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0019885360541098246,
      "loss": 6.5146,
      "step": 10000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001987962856815316,
      "loss": 6.5103,
      "step": 10500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0019873896595208073,
      "loss": 6.5063,
      "step": 11000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0019868164622262982,
      "loss": 6.494,
      "step": 11500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0019862432649317896,
      "loss": 6.5092,
      "step": 12000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001985670067637281,
      "loss": 6.4969,
      "step": 12500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0019850968703427722,
      "loss": 6.4886,
      "step": 13000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001984523673048263,
      "loss": 6.4776,
      "step": 13500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0019839504757537545,
      "loss": 6.4729,
      "step": 14000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001983377278459246,
      "loss": 6.4706,
      "step": 14500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001982804081164737,
      "loss": 6.4803,
      "step": 15000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001982230883870228,
      "loss": 6.4827,
      "step": 15500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0019816576865757194,
      "loss": 6.4716,
      "step": 16000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0019810844892812107,
      "loss": 6.4559,
      "step": 16500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001980511291986702,
      "loss": 6.4458,
      "step": 17000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001979938094692193,
      "loss": 6.4338,
      "step": 17500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0019793648973976843,
      "loss": 6.4282,
      "step": 18000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0019787917001031757,
      "loss": 6.438,
      "step": 18500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0019782185028086666,
      "loss": 6.4408,
      "step": 19000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001977645305514158,
      "loss": 6.4282,
      "step": 19500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0019770721082196492,
      "loss": 6.43,
      "step": 20000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0019764989109251406,
      "loss": 6.4287,
      "step": 20500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0019759257136306315,
      "loss": 6.4267,
      "step": 21000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.001975352516336123,
      "loss": 6.4148,
      "step": 21500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.001974779319041614,
      "loss": 6.4,
      "step": 22000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0019742061217471055,
      "loss": 6.3894,
      "step": 22500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0019736329244525964,
      "loss": 6.395,
      "step": 23000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0019730597271580877,
      "loss": 6.3977,
      "step": 23500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.001972486529863579,
      "loss": 6.4017,
      "step": 24000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0019719133325690704,
      "loss": 6.3995,
      "step": 24500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019713401352745613,
      "loss": 6.3949,
      "step": 25000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0019707669379800527,
      "loss": 6.3947,
      "step": 25500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001970193740685544,
      "loss": 6.4071,
      "step": 26000
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0019696205433910353,
      "loss": 6.3988,
      "step": 26500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0019690473460965262,
      "loss": 6.3915,
      "step": 27000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0019684741488020176,
      "loss": 6.3869,
      "step": 27500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001967900951507509,
      "loss": 6.3724,
      "step": 28000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0019673277542130003,
      "loss": 6.3722,
      "step": 28500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0019667545569184916,
      "loss": 6.3742,
      "step": 29000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0019661813596239825,
      "loss": 6.3672,
      "step": 29500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.001965608162329474,
      "loss": 6.3707,
      "step": 30000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.001965034965034965,
      "loss": 6.3687,
      "step": 30500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0019644617677404565,
      "loss": 6.3644,
      "step": 31000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0019638885704459474,
      "loss": 6.3596,
      "step": 31500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0019633153731514388,
      "loss": 6.3613,
      "step": 32000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00196274217585693,
      "loss": 6.3542,
      "step": 32500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0019621689785624214,
      "loss": 6.3539,
      "step": 33000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0019615957812679123,
      "loss": 6.3551,
      "step": 33500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0019610225839734037,
      "loss": 6.3491,
      "step": 34000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.001960449386678895,
      "loss": 6.3431,
      "step": 34500
    },
    {
      "epoch": 1.0,
      "eval_loss": 6.34874963760376,
      "eval_runtime": 28.5,
      "eval_samples_per_second": 39.228,
      "eval_steps_per_second": 1.228,
      "step": 34892
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0019598761893843864,
      "loss": 6.3416,
      "step": 35000
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0019593029920898773,
      "loss": 6.343,
      "step": 35500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0019587297947953686,
      "loss": 6.3372,
      "step": 36000
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0019581565975008595,
      "loss": 6.3392,
      "step": 36500
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001957583400206351,
      "loss": 6.3235,
      "step": 37000
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.001957010202911842,
      "loss": 6.3273,
      "step": 37500
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0019564370056173335,
      "loss": 6.3301,
      "step": 38000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.001955863808322825,
      "loss": 6.3422,
      "step": 38500
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0019552906110283158,
      "loss": 6.3314,
      "step": 39000
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.001954717413733807,
      "loss": 6.3208,
      "step": 39500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0019541442164392984,
      "loss": 6.3132,
      "step": 40000
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00195357101914479,
      "loss": 6.3034,
      "step": 40500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.001952997821850281,
      "loss": 6.2984,
      "step": 41000
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0019524246245557722,
      "loss": 6.3067,
      "step": 41500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0019518514272612634,
      "loss": 6.2983,
      "step": 42000
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0019512782299667547,
      "loss": 6.2971,
      "step": 42500
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0019507050326722458,
      "loss": 6.2949,
      "step": 43000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0019501318353777372,
      "loss": 6.2861,
      "step": 43500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0019495586380832283,
      "loss": 6.2903,
      "step": 44000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0019489854407887196,
      "loss": 6.2845,
      "step": 44500
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0019484122434942107,
      "loss": 6.2811,
      "step": 45000
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.001947839046199702,
      "loss": 6.2832,
      "step": 45500
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0019472658489051932,
      "loss": 6.2748,
      "step": 46000
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0019466926516106843,
      "loss": 6.2664,
      "step": 46500
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0019461194543161757,
      "loss": 6.2707,
      "step": 47000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0019455462570216668,
      "loss": 6.2626,
      "step": 47500
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0019449730597271581,
      "loss": 6.2621,
      "step": 48000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0019443998624326493,
      "loss": 6.2637,
      "step": 48500
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0019438266651381406,
      "loss": 6.2644,
      "step": 49000
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0019432534678436317,
      "loss": 6.2595,
      "step": 49500
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.001942680270549123,
      "loss": 6.2502,
      "step": 50000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0019421070732546142,
      "loss": 6.2373,
      "step": 50500
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0019415338759601055,
      "loss": 6.2397,
      "step": 51000
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0019409606786655966,
      "loss": 6.2358,
      "step": 51500
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.001940387481371088,
      "loss": 6.2362,
      "step": 52000
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.001939814284076579,
      "loss": 6.2348,
      "step": 52500
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0019392410867820704,
      "loss": 6.2401,
      "step": 53000
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0019386678894875616,
      "loss": 6.2407,
      "step": 53500
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0019380946921930529,
      "loss": 6.2371,
      "step": 54000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.001937521494898544,
      "loss": 6.2278,
      "step": 54500
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0019369482976040354,
      "loss": 6.222,
      "step": 55000
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0019363751003095267,
      "loss": 6.219,
      "step": 55500
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0019358019030150178,
      "loss": 6.2236,
      "step": 56000
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0019352287057205091,
      "loss": 6.2238,
      "step": 56500
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0019346555084260003,
      "loss": 6.2226,
      "step": 57000
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0019340823111314916,
      "loss": 6.2154,
      "step": 57500
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0019335091138369827,
      "loss": 6.2112,
      "step": 58000
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.001932935916542474,
      "loss": 6.2077,
      "step": 58500
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0019323627192479652,
      "loss": 6.211,
      "step": 59000
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0019317895219534565,
      "loss": 6.2161,
      "step": 59500
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0019312163246589477,
      "loss": 6.2132,
      "step": 60000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.001930643127364439,
      "loss": 6.2179,
      "step": 60500
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0019300699300699301,
      "loss": 6.222,
      "step": 61000
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0019294967327754215,
      "loss": 6.2136,
      "step": 61500
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0019289235354809126,
      "loss": 6.2057,
      "step": 62000
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.001928350338186404,
      "loss": 6.2021,
      "step": 62500
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.001927777140891895,
      "loss": 6.1955,
      "step": 63000
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0019272039435973864,
      "loss": 6.2036,
      "step": 63500
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0019266307463028773,
      "loss": 6.196,
      "step": 64000
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0019260575490083686,
      "loss": 6.199,
      "step": 64500
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00192548435171386,
      "loss": 6.1965,
      "step": 65000
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.001924911154419351,
      "loss": 6.199,
      "step": 65500
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0019243379571248424,
      "loss": 6.1923,
      "step": 66000
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0019237647598303335,
      "loss": 6.1953,
      "step": 66500
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0019231915625358249,
      "loss": 6.1907,
      "step": 67000
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.001922618365241316,
      "loss": 6.195,
      "step": 67500
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0019220451679468073,
      "loss": 6.1954,
      "step": 68000
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0019214719706522985,
      "loss": 6.1866,
      "step": 68500
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0019208987733577898,
      "loss": 6.1891,
      "step": 69000
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.001920325576063281,
      "loss": 6.1892,
      "step": 69500
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.193855285644531,
      "eval_runtime": 29.902,
      "eval_samples_per_second": 37.389,
      "eval_steps_per_second": 1.17,
      "step": 69784
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0019197523787687723,
      "loss": 6.1899,
      "step": 70000
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0019191791814742634,
      "loss": 6.1933,
      "step": 70500
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0019186059841797547,
      "loss": 6.1924,
      "step": 71000
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0019180327868852458,
      "loss": 6.1888,
      "step": 71500
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0019174595895907372,
      "loss": 6.1943,
      "step": 72000
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0019168863922962283,
      "loss": 6.1907,
      "step": 72500
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0019163131950017196,
      "loss": 6.1904,
      "step": 73000
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.001915739997707211,
      "loss": 6.1815,
      "step": 73500
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.001915166800412702,
      "loss": 6.1816,
      "step": 74000
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0019145936031181934,
      "loss": 6.1742,
      "step": 74500
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0019140204058236846,
      "loss": 6.1747,
      "step": 75000
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.001913447208529176,
      "loss": 6.1707,
      "step": 75500
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.001912874011234667,
      "loss": 6.1718,
      "step": 76000
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0019123008139401584,
      "loss": 6.1677,
      "step": 76500
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0019117276166456495,
      "loss": 6.1584,
      "step": 77000
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0019111544193511408,
      "loss": 6.1722,
      "step": 77500
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.001910581222056632,
      "loss": 6.1628,
      "step": 78000
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0019100080247621233,
      "loss": 6.156,
      "step": 78500
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0019094348274676144,
      "loss": 6.1512,
      "step": 79000
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0019088616301731057,
      "loss": 6.1462,
      "step": 79500
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0019082884328785969,
      "loss": 6.1388,
      "step": 80000
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0019077152355840882,
      "loss": 6.1404,
      "step": 80500
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0019071420382895793,
      "loss": 6.1397,
      "step": 81000
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0019065688409950707,
      "loss": 6.1493,
      "step": 81500
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0019059956437005616,
      "loss": 6.1431,
      "step": 82000
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.001905422446406053,
      "loss": 6.1521,
      "step": 82500
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0019048492491115442,
      "loss": 6.1409,
      "step": 83000
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0019042760518170354,
      "loss": 6.1408,
      "step": 83500
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0019037028545225267,
      "loss": 6.1416,
      "step": 84000
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0019031296572280178,
      "loss": 6.1371,
      "step": 84500
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0019025564599335092,
      "loss": 6.1367,
      "step": 85000
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0019019832626390003,
      "loss": 6.1372,
      "step": 85500
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0019014100653444916,
      "loss": 6.1358,
      "step": 86000
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0019008368680499827,
      "loss": 6.1283,
      "step": 86500
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.001900263670755474,
      "loss": 6.1347,
      "step": 87000
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0018996904734609652,
      "loss": 6.135,
      "step": 87500
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0018991172761664565,
      "loss": 6.1352,
      "step": 88000
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0018985440788719477,
      "loss": 6.1378,
      "step": 88500
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.001897970881577439,
      "loss": 6.1335,
      "step": 89000
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0018973976842829301,
      "loss": 6.1267,
      "step": 89500
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0018968244869884215,
      "loss": 6.1266,
      "step": 90000
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0018962512896939126,
      "loss": 6.1195,
      "step": 90500
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.001895678092399404,
      "loss": 6.1167,
      "step": 91000
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0018951048951048953,
      "loss": 6.1108,
      "step": 91500
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0018945316978103864,
      "loss": 6.1093,
      "step": 92000
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0018939585005158777,
      "loss": 6.1124,
      "step": 92500
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0018933853032213688,
      "loss": 6.1069,
      "step": 93000
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0018928121059268602,
      "loss": 6.1051,
      "step": 93500
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0018922389086323513,
      "loss": 6.1192,
      "step": 94000
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0018916657113378426,
      "loss": 6.1231,
      "step": 94500
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0018910925140433338,
      "loss": 6.1156,
      "step": 95000
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.001890519316748825,
      "loss": 6.1098,
      "step": 95500
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0018899461194543162,
      "loss": 6.0978,
      "step": 96000
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0018893729221598076,
      "loss": 6.0956,
      "step": 96500
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0018887997248652987,
      "loss": 6.0932,
      "step": 97000
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00188822652757079,
      "loss": 6.0938,
      "step": 97500
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0018876533302762811,
      "loss": 6.0921,
      "step": 98000
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0018870801329817725,
      "loss": 6.0834,
      "step": 98500
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0018865069356872636,
      "loss": 6.0833,
      "step": 99000
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.001885933738392755,
      "loss": 6.0827,
      "step": 99500
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.001885360541098246,
      "loss": 6.0858,
      "step": 100000
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0018847873438037372,
      "loss": 6.0814,
      "step": 100500
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0018842141465092285,
      "loss": 6.0793,
      "step": 101000
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0018836409492147196,
      "loss": 6.0743,
      "step": 101500
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.001883067751920211,
      "loss": 6.0821,
      "step": 102000
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.001882494554625702,
      "loss": 6.0827,
      "step": 102500
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0018819213573311934,
      "loss": 6.0723,
      "step": 103000
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0018813481600366846,
      "loss": 6.0692,
      "step": 103500
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.001880774962742176,
      "loss": 6.065,
      "step": 104000
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.001880201765447667,
      "loss": 6.0677,
      "step": 104500
    },
    {
      "epoch": 3.0,
      "eval_loss": 6.062596321105957,
      "eval_runtime": 26.9494,
      "eval_samples_per_second": 41.485,
      "eval_steps_per_second": 1.299,
      "step": 104676
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0018796285681531584,
      "loss": 6.0603,
      "step": 105000
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0018790553708586495,
      "loss": 6.0606,
      "step": 105500
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0018784821735641408,
      "loss": 6.0603,
      "step": 106000
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.001877908976269632,
      "loss": 6.066,
      "step": 106500
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0018773357789751233,
      "loss": 6.0745,
      "step": 107000
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0018767625816806144,
      "loss": 6.0723,
      "step": 107500
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0018761893843861057,
      "loss": 6.0678,
      "step": 108000
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0018756161870915969,
      "loss": 6.0639,
      "step": 108500
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0018750429897970882,
      "loss": 6.0588,
      "step": 109000
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0018744697925025793,
      "loss": 6.0602,
      "step": 109500
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0018738965952080707,
      "loss": 6.054,
      "step": 110000
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.001873323397913562,
      "loss": 6.0581,
      "step": 110500
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0018727502006190531,
      "loss": 6.0562,
      "step": 111000
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0018721770033245445,
      "loss": 6.0482,
      "step": 111500
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0018716038060300356,
      "loss": 6.0504,
      "step": 112000
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.001871030608735527,
      "loss": 6.0509,
      "step": 112500
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.001870457411441018,
      "loss": 6.0545,
      "step": 113000
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0018698842141465094,
      "loss": 6.0529,
      "step": 113500
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0018693110168520005,
      "loss": 6.0509,
      "step": 114000
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0018687378195574918,
      "loss": 6.0604,
      "step": 114500
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.001868164622262983,
      "loss": 6.0547,
      "step": 115000
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0018675914249684743,
      "loss": 6.0622,
      "step": 115500
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0018670182276739654,
      "loss": 6.0639,
      "step": 116000
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0018664450303794568,
      "loss": 6.0567,
      "step": 116500
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0018658718330849479,
      "loss": 6.0493,
      "step": 117000
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0018652986357904392,
      "loss": 6.0514,
      "step": 117500
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0018647254384959303,
      "loss": 6.0456,
      "step": 118000
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0018641522412014217,
      "loss": 6.0514,
      "step": 118500
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0018635790439069128,
      "loss": 6.0442,
      "step": 119000
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.001863005846612404,
      "loss": 6.0402,
      "step": 119500
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0018624326493178953,
      "loss": 6.0444,
      "step": 120000
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0018618594520233864,
      "loss": 6.0423,
      "step": 120500
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0018612862547288777,
      "loss": 6.0527,
      "step": 121000
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0018607130574343688,
      "loss": 6.0419,
      "step": 121500
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0018601398601398602,
      "loss": 6.0386,
      "step": 122000
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0018595666628453513,
      "loss": 6.0389,
      "step": 122500
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0018589934655508426,
      "loss": 6.0372,
      "step": 123000
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0018584202682563338,
      "loss": 6.03,
      "step": 123500
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.001857847070961825,
      "loss": 6.031,
      "step": 124000
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0018572738736673162,
      "loss": 6.038,
      "step": 124500
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0018567006763728076,
      "loss": 6.0285,
      "step": 125000
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0018561274790782987,
      "loss": 6.0309,
      "step": 125500
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.00185555428178379,
      "loss": 6.0351,
      "step": 126000
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0018549810844892811,
      "loss": 6.0312,
      "step": 126500
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0018544078871947725,
      "loss": 6.0369,
      "step": 127000
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0018538346899002636,
      "loss": 6.0317,
      "step": 127500
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.001853261492605755,
      "loss": 6.036,
      "step": 128000
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0018526882953112463,
      "loss": 6.038,
      "step": 128500
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0018521150980167374,
      "loss": 6.034,
      "step": 129000
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0018515419007222287,
      "loss": 6.0312,
      "step": 129500
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0018509687034277199,
      "loss": 6.0305,
      "step": 130000
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0018503955061332112,
      "loss": 6.0283,
      "step": 130500
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0018498223088387023,
      "loss": 6.0298,
      "step": 131000
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0018492491115441937,
      "loss": 6.0355,
      "step": 131500
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0018486759142496848,
      "loss": 6.0299,
      "step": 132000
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0018481027169551761,
      "loss": 6.0283,
      "step": 132500
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0018475295196606672,
      "loss": 6.0302,
      "step": 133000
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0018469563223661586,
      "loss": 6.022,
      "step": 133500
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0018463831250716497,
      "loss": 6.023,
      "step": 134000
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.001845809927777141,
      "loss": 6.0229,
      "step": 134500
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0018452367304826322,
      "loss": 6.0253,
      "step": 135000
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0018446635331881235,
      "loss": 6.0343,
      "step": 135500
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0018440903358936146,
      "loss": 6.0315,
      "step": 136000
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.001843517138599106,
      "loss": 6.031,
      "step": 136500
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0018429439413045969,
      "loss": 6.0269,
      "step": 137000
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0018423707440100882,
      "loss": 6.0263,
      "step": 137500
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0018417975467155795,
      "loss": 6.0277,
      "step": 138000
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0018412243494210707,
      "loss": 6.0346,
      "step": 138500
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.001840651152126562,
      "loss": 6.0296,
      "step": 139000
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0018400779548320531,
      "loss": 6.0229,
      "step": 139500
    },
    {
      "epoch": 4.0,
      "eval_loss": 6.020912170410156,
      "eval_runtime": 27.2309,
      "eval_samples_per_second": 41.056,
      "eval_steps_per_second": 1.285,
      "step": 139568
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0018395047575375445,
      "loss": 6.0199,
      "step": 140000
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0018389315602430356,
      "loss": 6.0325,
      "step": 140500
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.001838358362948527,
      "loss": 6.0448,
      "step": 141000
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.001837785165654018,
      "loss": 6.0367,
      "step": 141500
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0018372119683595094,
      "loss": 6.0357,
      "step": 142000
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0018366387710650005,
      "loss": 6.0411,
      "step": 142500
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0018360655737704918,
      "loss": 6.0365,
      "step": 143000
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.001835492376475983,
      "loss": 6.0269,
      "step": 143500
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0018349191791814743,
      "loss": 6.0342,
      "step": 144000
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0018343459818869654,
      "loss": 6.0291,
      "step": 144500
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0018337727845924568,
      "loss": 6.0281,
      "step": 145000
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0018331995872979479,
      "loss": 6.027,
      "step": 145500
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0018326263900034392,
      "loss": 6.0249,
      "step": 146000
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0018320531927089306,
      "loss": 6.0276,
      "step": 146500
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0018314799954144217,
      "loss": 6.0251,
      "step": 147000
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.001830906798119913,
      "loss": 6.021,
      "step": 147500
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0018303336008254041,
      "loss": 6.0251,
      "step": 148000
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0018297604035308955,
      "loss": 6.0278,
      "step": 148500
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0018291872062363866,
      "loss": 6.0329,
      "step": 149000
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.001828614008941878,
      "loss": 6.0398,
      "step": 149500
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.001828040811647369,
      "loss": 6.0468,
      "step": 150000
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0018274676143528604,
      "loss": 6.0485,
      "step": 150500
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0018268944170583515,
      "loss": 6.0523,
      "step": 151000
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0018263212197638429,
      "loss": 6.0604,
      "step": 151500
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.001825748022469334,
      "loss": 6.0486,
      "step": 152000
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0018251748251748253,
      "loss": 6.0446,
      "step": 152500
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.0018246016278803164,
      "loss": 6.0368,
      "step": 153000
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0018240284305858078,
      "loss": 6.0323,
      "step": 153500
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.001823455233291299,
      "loss": 6.0308,
      "step": 154000
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0018228820359967902,
      "loss": 6.0291,
      "step": 154500
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0018223088387022812,
      "loss": 6.0372,
      "step": 155000
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0018217356414077725,
      "loss": 6.0355,
      "step": 155500
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0018211624441132638,
      "loss": 6.0415,
      "step": 156000
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.001820589246818755,
      "loss": 6.0396,
      "step": 156500
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0018200160495242463,
      "loss": 6.034,
      "step": 157000
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0018194428522297374,
      "loss": 6.0322,
      "step": 157500
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0018188696549352287,
      "loss": 6.0336,
      "step": 158000
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0018182964576407199,
      "loss": 6.0386,
      "step": 158500
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0018177232603462112,
      "loss": 6.0294,
      "step": 159000
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0018171500630517023,
      "loss": 6.0288,
      "step": 159500
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0018165768657571937,
      "loss": 6.0205,
      "step": 160000
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0018160036684626848,
      "loss": 6.0317,
      "step": 160500
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0018154304711681761,
      "loss": 6.0411,
      "step": 161000
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0018148572738736672,
      "loss": 6.0329,
      "step": 161500
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0018142840765791586,
      "loss": 6.0292,
      "step": 162000
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0018137108792846497,
      "loss": 6.0329,
      "step": 162500
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.001813137681990141,
      "loss": 6.0332,
      "step": 163000
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0018125644846956322,
      "loss": 6.0351,
      "step": 163500
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0018119912874011235,
      "loss": 6.0342,
      "step": 164000
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0018114180901066146,
      "loss": 6.0428,
      "step": 164500
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.001810844892812106,
      "loss": 6.039,
      "step": 165000
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0018102716955175973,
      "loss": 6.0341,
      "step": 165500
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0018096984982230884,
      "loss": 6.035,
      "step": 166000
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0018091253009285798,
      "loss": 6.0465,
      "step": 166500
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0018085521036340709,
      "loss": 6.0363,
      "step": 167000
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0018079789063395622,
      "loss": 6.045,
      "step": 167500
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0018074057090450533,
      "loss": 6.0442,
      "step": 168000
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0018068325117505447,
      "loss": 6.0453,
      "step": 168500
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0018062593144560358,
      "loss": 6.0351,
      "step": 169000
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0018056861171615271,
      "loss": 6.0323,
      "step": 169500
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0018051129198670183,
      "loss": 6.0308,
      "step": 170000
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0018045397225725096,
      "loss": 6.0335,
      "step": 170500
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0018039665252780007,
      "loss": 6.037,
      "step": 171000
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.001803393327983492,
      "loss": 6.0301,
      "step": 171500
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0018028201306889832,
      "loss": 6.0363,
      "step": 172000
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0018022469333944745,
      "loss": 6.0376,
      "step": 172500
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0018016737360999656,
      "loss": 6.0319,
      "step": 173000
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0018011005388054568,
      "loss": 6.0311,
      "step": 173500
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0018005273415109481,
      "loss": 6.0321,
      "step": 174000
    },
    {
      "epoch": 5.0,
      "eval_loss": 6.036427974700928,
      "eval_runtime": 27.0381,
      "eval_samples_per_second": 41.349,
      "eval_steps_per_second": 1.294,
      "step": 174460
    }
  ],
  "logging_steps": 500,
  "max_steps": 1744600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 2.390379476809689e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}