{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "global_step": 41656,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.0004939984636066834,
      "loss": 1.91,
      "step": 500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004879969272133666,
      "loss": 1.7724,
      "step": 1000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00048199539082004997,
      "loss": 1.7095,
      "step": 1500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00047599385442673327,
      "loss": 1.6602,
      "step": 2000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0004699923180334166,
      "loss": 1.6298,
      "step": 2500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004639907816400999,
      "loss": 1.6032,
      "step": 3000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004579892452467832,
      "loss": 1.5764,
      "step": 3500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00045198770885346653,
      "loss": 1.5442,
      "step": 4000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044598617246014983,
      "loss": 1.5179,
      "step": 4500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00043998463606683314,
      "loss": 1.5161,
      "step": 5000
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004339830996735164,
      "loss": 1.421,
      "step": 5500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00042798156328019974,
      "loss": 1.3698,
      "step": 6000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00042198002688688304,
      "loss": 1.389,
      "step": 6500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00041597849049356634,
      "loss": 1.3715,
      "step": 7000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00040997695410024965,
      "loss": 1.3656,
      "step": 7500
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00040397541770693295,
      "loss": 1.3575,
      "step": 8000
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0003979738813136163,
      "loss": 1.3539,
      "step": 8500
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0003919723449202996,
      "loss": 1.3292,
      "step": 9000
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0003859708085269829,
      "loss": 1.3215,
      "step": 9500
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0003799692721336662,
      "loss": 1.3067,
      "step": 10000
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0003739677357403495,
      "loss": 1.2928,
      "step": 10500
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00036796619934703287,
      "loss": 1.2058,
      "step": 11000
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00036196466295371617,
      "loss": 1.2242,
      "step": 11500
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00035596312656039947,
      "loss": 1.2148,
      "step": 12000
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00034996159016708277,
      "loss": 1.2109,
      "step": 12500
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0003439600537737661,
      "loss": 1.2241,
      "step": 13000
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00033795851738044943,
      "loss": 1.221,
      "step": 13500
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00033195698098713273,
      "loss": 1.2042,
      "step": 14000
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00032595544459381603,
      "loss": 1.2028,
      "step": 14500
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00031995390820049933,
      "loss": 1.2017,
      "step": 15000
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0003139523718071827,
      "loss": 1.1904,
      "step": 15500
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.000307950835413866,
      "loss": 1.1294,
      "step": 16000
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00030194929902054924,
      "loss": 1.1156,
      "step": 16500
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00029594776262723254,
      "loss": 1.1174,
      "step": 17000
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00028994622623391584,
      "loss": 1.1084,
      "step": 17500
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0002839446898405992,
      "loss": 1.1026,
      "step": 18000
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0002779431534472825,
      "loss": 1.1107,
      "step": 18500
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0002719416170539658,
      "loss": 1.1061,
      "step": 19000
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0002659400806606491,
      "loss": 1.1148,
      "step": 19500
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0002599385442673324,
      "loss": 1.1097,
      "step": 20000
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00025393700787401576,
      "loss": 1.1013,
      "step": 20500
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00024793547148069906,
      "loss": 1.0682,
      "step": 21000
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.00024193393508738237,
      "loss": 1.0297,
      "step": 21500
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0002359323986940657,
      "loss": 1.0325,
      "step": 22000
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.000229930862300749,
      "loss": 1.0255,
      "step": 22500
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.00022392932590743232,
      "loss": 1.0325,
      "step": 23000
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.00021792778951411563,
      "loss": 1.0336,
      "step": 23500
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.00021192625312079893,
      "loss": 1.0434,
      "step": 24000
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00020592471672748226,
      "loss": 1.0244,
      "step": 24500
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.00019992318033416553,
      "loss": 1.0333,
      "step": 25000
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00019392164394084886,
      "loss": 1.033,
      "step": 25500
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.00018792010754753216,
      "loss": 1.0327,
      "step": 26000
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0001819185711542155,
      "loss": 0.9682,
      "step": 26500
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.0001759170347608988,
      "loss": 0.9799,
      "step": 27000
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.0001699154983675821,
      "loss": 0.9725,
      "step": 27500
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.00016391396197426542,
      "loss": 0.9675,
      "step": 28000
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00015791242558094873,
      "loss": 0.9746,
      "step": 28500
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.00015191088918763205,
      "loss": 0.9726,
      "step": 29000
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.00014590935279431536,
      "loss": 0.9804,
      "step": 29500
    },
    {
      "epoch": 5.76,
      "learning_rate": 0.00013990781640099868,
      "loss": 0.9677,
      "step": 30000
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.00013390628000768196,
      "loss": 0.9757,
      "step": 30500
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.00012790474361436526,
      "loss": 0.9504,
      "step": 31000
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.00012190320722104859,
      "loss": 0.9511,
      "step": 31500
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.00011590167082773189,
      "loss": 0.9176,
      "step": 32000
    },
    {
      "epoch": 6.24,
      "learning_rate": 0.00010990013443441521,
      "loss": 0.9248,
      "step": 32500
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.00010389859804109852,
      "loss": 0.9145,
      "step": 33000
    },
    {
      "epoch": 6.43,
      "learning_rate": 9.789706164778184e-05,
      "loss": 0.9163,
      "step": 33500
    },
    {
      "epoch": 6.53,
      "learning_rate": 9.189552525446515e-05,
      "loss": 0.9233,
      "step": 34000
    },
    {
      "epoch": 6.63,
      "learning_rate": 8.589398886114845e-05,
      "loss": 0.9315,
      "step": 34500
    },
    {
      "epoch": 6.72,
      "learning_rate": 7.989245246783177e-05,
      "loss": 0.9184,
      "step": 35000
    },
    {
      "epoch": 6.82,
      "learning_rate": 7.389091607451507e-05,
      "loss": 0.9263,
      "step": 35500
    },
    {
      "epoch": 6.91,
      "learning_rate": 6.788937968119839e-05,
      "loss": 0.9189,
      "step": 36000
    },
    {
      "epoch": 7.01,
      "learning_rate": 6.18878432878817e-05,
      "loss": 0.912,
      "step": 36500
    },
    {
      "epoch": 7.11,
      "learning_rate": 5.588630689456501e-05,
      "loss": 0.89,
      "step": 37000
    },
    {
      "epoch": 7.2,
      "learning_rate": 4.9884770501248326e-05,
      "loss": 0.8878,
      "step": 37500
    },
    {
      "epoch": 7.3,
      "learning_rate": 4.388323410793163e-05,
      "loss": 0.8822,
      "step": 38000
    },
    {
      "epoch": 7.39,
      "learning_rate": 3.7881697714614944e-05,
      "loss": 0.8887,
      "step": 38500
    },
    {
      "epoch": 7.49,
      "learning_rate": 3.188016132129825e-05,
      "loss": 0.8717,
      "step": 39000
    },
    {
      "epoch": 7.59,
      "learning_rate": 2.5878624927981564e-05,
      "loss": 0.8945,
      "step": 39500
    },
    {
      "epoch": 7.68,
      "learning_rate": 1.9877088534664873e-05,
      "loss": 0.8851,
      "step": 40000
    },
    {
      "epoch": 7.78,
      "learning_rate": 1.3875552141348186e-05,
      "loss": 0.8871,
      "step": 40500
    },
    {
      "epoch": 7.87,
      "learning_rate": 7.874015748031496e-06,
      "loss": 0.8934,
      "step": 41000
    },
    {
      "epoch": 7.97,
      "learning_rate": 1.872479354714807e-06,
      "loss": 0.8863,
      "step": 41500
    },
    {
      "epoch": 8.0,
      "step": 41656,
      "total_flos": 4.8424619578097664e+17,
      "train_loss": 1.139437837565909,
      "train_runtime": 38132.6596,
      "train_samples_per_second": 34.957,
      "train_steps_per_second": 1.092
    }
  ],
  "max_steps": 41656,
  "num_train_epochs": 8,
  "total_flos": 4.8424619578097664e+17,
  "trial_name": null,
  "trial_params": null
}