{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9716123619074253,
  "global_step": 42500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.941733090942992e-05,
      "loss": 3.2035,
      "step": 500
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8834661818859834e-05,
      "loss": 3.1734,
      "step": 1000
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.825199272828975e-05,
      "loss": 3.1439,
      "step": 1500
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.766932363771967e-05,
      "loss": 3.1277,
      "step": 2000
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7086654547149584e-05,
      "loss": 3.1302,
      "step": 2500
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.65039854565795e-05,
      "loss": 3.1091,
      "step": 3000
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.592131636600942e-05,
      "loss": 3.115,
      "step": 3500
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5338647275439334e-05,
      "loss": 3.0718,
      "step": 4000
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4755978184869253e-05,
      "loss": 3.0977,
      "step": 4500
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.417330909429917e-05,
      "loss": 3.1092,
      "step": 5000
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.3590640003729085e-05,
      "loss": 3.0919,
      "step": 5500
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.3007970913159004e-05,
      "loss": 3.0868,
      "step": 6000
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.242530182258892e-05,
      "loss": 3.0913,
      "step": 6500
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.1842632732018835e-05,
      "loss": 3.0817,
      "step": 7000
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.1259963641448754e-05,
      "loss": 3.0835,
      "step": 7500
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.0677294550878666e-05,
      "loss": 3.059,
      "step": 8000
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.0094625460308585e-05,
      "loss": 3.0757,
      "step": 8500
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.95119563697385e-05,
      "loss": 3.0767,
      "step": 9000
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.892928727916842e-05,
      "loss": 3.0637,
      "step": 9500
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.834661818859833e-05,
      "loss": 3.0504,
      "step": 10000
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.776394909802825e-05,
      "loss": 3.0339,
      "step": 10500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.718128000745816e-05,
      "loss": 3.0385,
      "step": 11000
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.659861091688808e-05,
      "loss": 3.064,
      "step": 11500
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.6015941826318e-05,
      "loss": 3.0685,
      "step": 12000
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.543327273574791e-05,
      "loss": 3.0366,
      "step": 12500
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.485060364517783e-05,
      "loss": 3.0512,
      "step": 13000
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.426793455460775e-05,
      "loss": 3.0179,
      "step": 13500
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.368526546403766e-05,
      "loss": 3.0113,
      "step": 14000
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.310259637346758e-05,
      "loss": 2.9934,
      "step": 14500
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.25199272828975e-05,
      "loss": 3.0166,
      "step": 15000
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.193725819232741e-05,
      "loss": 3.0001,
      "step": 15500
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.135458910175733e-05,
      "loss": 2.9672,
      "step": 16000
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.077192001118725e-05,
      "loss": 2.9892,
      "step": 16500
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.018925092061716e-05,
      "loss": 2.9614,
      "step": 17000
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.960658183004708e-05,
      "loss": 2.9961,
      "step": 17500
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.9023912739477e-05,
      "loss": 2.9779,
      "step": 18000
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8441243648906912e-05,
      "loss": 2.9579,
      "step": 18500
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.785857455833683e-05,
      "loss": 2.973,
      "step": 19000
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.727590546776675e-05,
      "loss": 2.9722,
      "step": 19500
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.6693236377196662e-05,
      "loss": 2.9646,
      "step": 20000
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.611056728662658e-05,
      "loss": 2.9623,
      "step": 20500
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.55278981960565e-05,
      "loss": 2.9916,
      "step": 21000
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.4945229105486416e-05,
      "loss": 2.9656,
      "step": 21500
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.436256001491633e-05,
      "loss": 2.9928,
      "step": 22000
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.3779890924346247e-05,
      "loss": 2.9385,
      "step": 22500
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.3197221833776163e-05,
      "loss": 2.957,
      "step": 23000
    },
    {
      "epoch": 1.64,
      "learning_rate": 2.261455274320608e-05,
      "loss": 2.9654,
      "step": 23500
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.2031883652635994e-05,
      "loss": 2.97,
      "step": 24000
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.144921456206591e-05,
      "loss": 2.9741,
      "step": 24500
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.086654547149583e-05,
      "loss": 2.9547,
      "step": 25000
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.0283876380925745e-05,
      "loss": 2.9451,
      "step": 25500
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.970120729035566e-05,
      "loss": 2.9596,
      "step": 26000
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.911853819978558e-05,
      "loss": 2.9608,
      "step": 26500
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8535869109215495e-05,
      "loss": 2.9353,
      "step": 27000
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.795320001864541e-05,
      "loss": 2.9597,
      "step": 27500
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.737053092807533e-05,
      "loss": 2.9766,
      "step": 28000
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.6787861837505245e-05,
      "loss": 2.9663,
      "step": 28500
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.620519274693516e-05,
      "loss": 2.9407,
      "step": 29000
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.562252365636508e-05,
      "loss": 2.9297,
      "step": 29500
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.5039854565794994e-05,
      "loss": 2.8912,
      "step": 30000
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.445718547522491e-05,
      "loss": 2.9339,
      "step": 30500
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.3874516384654828e-05,
      "loss": 2.9428,
      "step": 31000
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.3291847294084744e-05,
      "loss": 2.9401,
      "step": 31500
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.270917820351466e-05,
      "loss": 2.9332,
      "step": 32000
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.2126509112944577e-05,
      "loss": 2.9101,
      "step": 32500
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.1543840022374494e-05,
      "loss": 2.9166,
      "step": 33000
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.096117093180441e-05,
      "loss": 2.9384,
      "step": 33500
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.0378501841234327e-05,
      "loss": 2.9133,
      "step": 34000
    },
    {
      "epoch": 2.41,
      "learning_rate": 9.795832750664243e-06,
      "loss": 2.8853,
      "step": 34500
    },
    {
      "epoch": 2.45,
      "learning_rate": 9.213163660094159e-06,
      "loss": 2.9052,
      "step": 35000
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.630494569524076e-06,
      "loss": 2.9147,
      "step": 35500
    },
    {
      "epoch": 2.52,
      "learning_rate": 8.047825478953992e-06,
      "loss": 2.9421,
      "step": 36000
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.465156388383909e-06,
      "loss": 2.9287,
      "step": 36500
    },
    {
      "epoch": 2.59,
      "learning_rate": 6.8824872978138264e-06,
      "loss": 2.9044,
      "step": 37000
    },
    {
      "epoch": 2.62,
      "learning_rate": 6.299818207243742e-06,
      "loss": 2.9015,
      "step": 37500
    },
    {
      "epoch": 2.66,
      "learning_rate": 5.7171491166736594e-06,
      "loss": 2.9207,
      "step": 38000
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.134480026103575e-06,
      "loss": 2.9307,
      "step": 38500
    },
    {
      "epoch": 2.73,
      "learning_rate": 4.5518109355334916e-06,
      "loss": 2.9315,
      "step": 39000
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.969141844963409e-06,
      "loss": 2.9047,
      "step": 39500
    },
    {
      "epoch": 2.8,
      "learning_rate": 3.386472754393325e-06,
      "loss": 2.9263,
      "step": 40000
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.8038036638232415e-06,
      "loss": 2.9154,
      "step": 40500
    },
    {
      "epoch": 2.87,
      "learning_rate": 2.2211345732531584e-06,
      "loss": 2.9042,
      "step": 41000
    },
    {
      "epoch": 2.9,
      "learning_rate": 1.6384654826830745e-06,
      "loss": 2.886,
      "step": 41500
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.0557963921129912e-06,
      "loss": 2.9167,
      "step": 42000
    },
    {
      "epoch": 2.97,
      "learning_rate": 4.731273015429078e-07,
      "loss": 2.8958,
      "step": 42500
    }
  ],
  "max_steps": 42906,
  "num_train_epochs": 3,
  "total_flos": 4.277802369024e+16,
  "trial_name": null,
  "trial_params": null
}