{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6591957811470006,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.98901340364755e-05,
      "loss": 1.7796,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9780268072951005e-05,
      "loss": 1.7713,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.96704021094265e-05,
      "loss": 1.7176,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9560536145902e-05,
      "loss": 1.6604,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.94506701823775e-05,
      "loss": 1.6656,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9340804218853e-05,
      "loss": 1.6062,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.92309382553285e-05,
      "loss": 1.5675,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9121072291804e-05,
      "loss": 1.5991,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.90112063282795e-05,
      "loss": 1.5755,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8901340364755e-05,
      "loss": 1.5343,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8791474401230506e-05,
      "loss": 1.5777,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8681608437706e-05,
      "loss": 1.5148,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.85717424741815e-05,
      "loss": 1.514,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8461876510657e-05,
      "loss": 1.5594,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.83520105471325e-05,
      "loss": 1.5238,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8242144583608e-05,
      "loss": 1.5445,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.81322786200835e-05,
      "loss": 1.4958,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8022412656559004e-05,
      "loss": 1.531,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.79125466930345e-05,
      "loss": 1.4877,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.780268072951e-05,
      "loss": 1.5099,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.76928147659855e-05,
      "loss": 1.5628,
      "step": 210
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7582948802461e-05,
      "loss": 1.5843,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.74730828389365e-05,
      "loss": 1.4917,
      "step": 230
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7363216875412e-05,
      "loss": 1.5552,
      "step": 240
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.72533509118875e-05,
      "loss": 1.5284,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7143484948363e-05,
      "loss": 1.5283,
      "step": 260
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.70336189848385e-05,
      "loss": 1.5425,
      "step": 270
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.6923753021313996e-05,
      "loss": 1.5408,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.68138870577895e-05,
      "loss": 1.5508,
      "step": 290
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.6704021094265e-05,
      "loss": 1.5359,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.6594155130740496e-05,
      "loss": 1.5042,
      "step": 310
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.6484289167216e-05,
      "loss": 1.5511,
      "step": 320
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.63744232036915e-05,
      "loss": 1.5468,
      "step": 330
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.6264557240167003e-05,
      "loss": 1.4891,
      "step": 340
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6154691276642495e-05,
      "loss": 1.5386,
      "step": 350
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.6044825313118e-05,
      "loss": 1.525,
      "step": 360
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.59349593495935e-05,
      "loss": 1.5367,
      "step": 370
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5825093386068995e-05,
      "loss": 1.5011,
      "step": 380
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.57152274225445e-05,
      "loss": 1.5259,
      "step": 390
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.560536145902e-05,
      "loss": 1.4764,
      "step": 400
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.54954954954955e-05,
      "loss": 1.5166,
      "step": 410
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5385629531971e-05,
      "loss": 1.5049,
      "step": 420
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.52757635684465e-05,
      "loss": 1.5383,
      "step": 430
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5165897604921995e-05,
      "loss": 1.5166,
      "step": 440
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.505603164139749e-05,
      "loss": 1.5898,
      "step": 450
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.4946165677873e-05,
      "loss": 1.5512,
      "step": 460
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4836299714348496e-05,
      "loss": 1.5215,
      "step": 470
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.4726433750824e-05,
      "loss": 1.5372,
      "step": 480
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.46165677872995e-05,
      "loss": 1.4994,
      "step": 490
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.4506701823774996e-05,
      "loss": 1.5261,
      "step": 500
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.4396835860250494e-05,
      "loss": 1.523,
      "step": 510
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.428696989672599e-05,
      "loss": 1.5369,
      "step": 520
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.4177103933201496e-05,
      "loss": 1.5606,
      "step": 530
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.4067237969676994e-05,
      "loss": 1.5142,
      "step": 540
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.39573720061525e-05,
      "loss": 1.4941,
      "step": 550
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.3847506042627997e-05,
      "loss": 1.5467,
      "step": 560
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.37376400791035e-05,
      "loss": 1.5277,
      "step": 570
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.362777411557899e-05,
      "loss": 1.5358,
      "step": 580
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.351790815205449e-05,
      "loss": 1.5611,
      "step": 590
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.3408042188529995e-05,
      "loss": 1.4959,
      "step": 600
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.329817622500549e-05,
      "loss": 1.5214,
      "step": 610
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.3188310261481e-05,
      "loss": 1.4937,
      "step": 620
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.3078444297956495e-05,
      "loss": 1.5066,
      "step": 630
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.2968578334432e-05,
      "loss": 1.5101,
      "step": 640
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.28587123709075e-05,
      "loss": 1.5346,
      "step": 650
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.2748846407382995e-05,
      "loss": 1.5236,
      "step": 660
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.263898044385849e-05,
      "loss": 1.5401,
      "step": 670
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.252911448033399e-05,
      "loss": 1.5027,
      "step": 680
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.2419248516809496e-05,
      "loss": 1.5197,
      "step": 690
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.2309382553284993e-05,
      "loss": 1.5357,
      "step": 700
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.21995165897605e-05,
      "loss": 1.5042,
      "step": 710
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.2089650626235996e-05,
      "loss": 1.534,
      "step": 720
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.1979784662711494e-05,
      "loss": 1.4954,
      "step": 730
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.186991869918699e-05,
      "loss": 1.5142,
      "step": 740
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.176005273566249e-05,
      "loss": 1.4959,
      "step": 750
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.1650186772137994e-05,
      "loss": 1.529,
      "step": 760
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.154032080861349e-05,
      "loss": 1.5751,
      "step": 770
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.1430454845088996e-05,
      "loss": 1.4828,
      "step": 780
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.1320588881564494e-05,
      "loss": 1.5057,
      "step": 790
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.121072291804e-05,
      "loss": 1.5223,
      "step": 800
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.110085695451549e-05,
      "loss": 1.526,
      "step": 810
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.099099099099099e-05,
      "loss": 1.5107,
      "step": 820
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.088112502746649e-05,
      "loss": 1.5018,
      "step": 830
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.077125906394199e-05,
      "loss": 1.51,
      "step": 840
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.0661393100417495e-05,
      "loss": 1.5105,
      "step": 850
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.055152713689299e-05,
      "loss": 1.5267,
      "step": 860
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.04416611733685e-05,
      "loss": 1.5797,
      "step": 870
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.0331795209843995e-05,
      "loss": 1.476,
      "step": 880
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.022192924631949e-05,
      "loss": 1.5339,
      "step": 890
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.011206328279499e-05,
      "loss": 1.527,
      "step": 900
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.000219731927049e-05,
      "loss": 1.5095,
      "step": 910
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.989233135574599e-05,
      "loss": 1.5169,
      "step": 920
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.978246539222149e-05,
      "loss": 1.4762,
      "step": 930
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.9672599428696996e-05,
      "loss": 1.5396,
      "step": 940
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.9562733465172494e-05,
      "loss": 1.5001,
      "step": 950
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.945286750164799e-05,
      "loss": 1.491,
      "step": 960
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.934300153812349e-05,
      "loss": 1.5115,
      "step": 970
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.923313557459899e-05,
      "loss": 1.5134,
      "step": 980
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.912326961107449e-05,
      "loss": 1.5099,
      "step": 990
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.901340364754999e-05,
      "loss": 1.4916,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 4551,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 6.3202482192384e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}