{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 655,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.0303030303030305e-07,
      "loss": 2.7433,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 2.672,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 2.5663,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 2.6422,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.060606060606061e-06,
      "loss": 2.2644,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 2.5506,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.3298,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0606060606060606e-05,
      "loss": 2.1904,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 2.0981,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.8446,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 1.8529,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.7525,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.7954,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.96969696969697e-05,
      "loss": 1.6559,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9997724155059836e-05,
      "loss": 1.7205,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9988480310346606e-05,
      "loss": 1.6599,
      "step": 75
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9972132794589515e-05,
      "loss": 1.4984,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.994869323391895e-05,
      "loss": 1.5442,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9918178298230955e-05,
      "loss": 1.7301,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9880609689331837e-05,
      "loss": 1.5913,
      "step": 95
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9836014125504146e-05,
      "loss": 1.5133,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9784423322505e-05,
      "loss": 1.4516,
      "step": 105
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9725873971010256e-05,
      "loss": 1.3623,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9660407710520613e-05,
      "loss": 1.3844,
      "step": 115
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.958807109974816e-05,
      "loss": 1.4235,
      "step": 120
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.950891558350446e-05,
      "loss": 1.3142,
      "step": 125
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9422997456113695e-05,
      "loss": 1.3499,
      "step": 130
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9330377821376916e-05,
      "loss": 1.4318,
      "step": 135
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9231122549115854e-05,
      "loss": 1.4776,
      "step": 140
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9125302228327194e-05,
      "loss": 1.4596,
      "step": 145
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.901299211698064e-05,
      "loss": 1.506,
      "step": 150
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8894272088496488e-05,
      "loss": 1.4941,
      "step": 155
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8769226574940727e-05,
      "loss": 1.495,
      "step": 160
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8637944506978093e-05,
      "loss": 1.3905,
      "step": 165
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8500519250625833e-05,
      "loss": 1.3955,
      "step": 170
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8357048540853005e-05,
      "loss": 1.4266,
      "step": 175
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8207634412072765e-05,
      "loss": 1.4394,
      "step": 180
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8052383125576833e-05,
      "loss": 1.4724,
      "step": 185
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.789140509396394e-05,
      "loss": 1.4783,
      "step": 190
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.772481480261587e-05,
      "loss": 1.4837,
      "step": 195
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7552730728277052e-05,
      "loss": 1.5081,
      "step": 200
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7375275254795474e-05,
      "loss": 1.4547,
      "step": 205
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.719257458608498e-05,
      "loss": 1.5518,
      "step": 210
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.700475865637077e-05,
      "loss": 1.4316,
      "step": 215
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6811961037781936e-05,
      "loss": 1.442,
      "step": 220
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.66143188453568e-05,
      "loss": 1.5635,
      "step": 225
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.6411972639528555e-05,
      "loss": 1.4194,
      "step": 230
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.620506632616061e-05,
      "loss": 1.4804,
      "step": 235
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.5993747054202683e-05,
      "loss": 1.6032,
      "step": 240
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.5778165111040512e-05,
      "loss": 1.2669,
      "step": 245
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.5558473815613476e-05,
      "loss": 1.4045,
      "step": 250
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.5334829409376272e-05,
      "loss": 1.4802,
      "step": 255
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.5107390945182119e-05,
      "loss": 1.5424,
      "step": 260
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.4876320174166544e-05,
      "loss": 1.4566,
      "step": 265
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.464178143071217e-05,
      "loss": 1.5269,
      "step": 270
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.4403941515576344e-05,
      "loss": 1.5352,
      "step": 275
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.416296957726472e-05,
      "loss": 1.3673,
      "step": 280
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.391903699173514e-05,
      "loss": 1.354,
      "step": 285
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.3672317240517388e-05,
      "loss": 1.5526,
      "step": 290
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.3422985787335494e-05,
      "loss": 1.4736,
      "step": 295
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.3171219953320331e-05,
      "loss": 1.4636,
      "step": 300
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.2917198790901231e-05,
      "loss": 1.4855,
      "step": 305
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.2661102956466345e-05,
      "loss": 1.4595,
      "step": 310
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.240311458188229e-05,
      "loss": 1.6073,
      "step": 315
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.2143417144964425e-05,
      "loss": 1.5,
      "step": 320
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.1882195338989959e-05,
      "loss": 1.5174,
      "step": 325
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.1619634941346587e-05,
      "loss": 1.5918,
      "step": 330
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.1355922681410155e-05,
      "loss": 1.4199,
      "step": 335
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.109124610774527e-05,
      "loss": 1.4567,
      "step": 340
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 1.3144,
      "step": 345
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.055975350865276e-05,
      "loss": 1.3933,
      "step": 350
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.0293315473516833e-05,
      "loss": 1.5519,
      "step": 355
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.0026668836414325e-05,
      "loss": 1.4626,
      "step": 360
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.760003232798879e-06,
      "loss": 1.428,
      "step": 365
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.493508311612874e-06,
      "loss": 1.3678,
      "step": 370
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.227373600411668e-06,
      "loss": 1.4338,
      "step": 375
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.961788370574184e-06,
      "loss": 1.4409,
      "step": 380
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.6969415026957e-06,
      "loss": 1.3239,
      "step": 385
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.433021352258522e-06,
      "loss": 1.457,
      "step": 390
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.170215615676145e-06,
      "loss": 1.4046,
      "step": 395
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.908711196806131e-06,
      "loss": 1.516,
      "step": 400
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.648694074026616e-06,
      "loss": 1.3609,
      "step": 405
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.390349167971026e-06,
      "loss": 1.3218,
      "step": 410
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.133860210015049e-06,
      "loss": 1.6356,
      "step": 415
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.879409611609394e-06,
      "loss": 1.3087,
      "step": 420
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.627178334551227e-06,
      "loss": 1.3472,
      "step": 425
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.377345762286633e-06,
      "loss": 1.4116,
      "step": 430
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.130089572335536e-06,
      "loss": 1.3421,
      "step": 435
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.885585609929891e-06,
      "loss": 1.2693,
      "step": 440
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.644007762954926e-06,
      "loss": 1.4595,
      "step": 445
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.405527838282458e-06,
      "loss": 1.553,
      "step": 450
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.170315439584212e-06,
      "loss": 1.5539,
      "step": 455
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.938537846711953e-06,
      "loss": 1.4485,
      "step": 460
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.710359896730379e-06,
      "loss": 1.4261,
      "step": 465
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.485943866687217e-06,
      "loss": 1.5028,
      "step": 470
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.2654493582040345e-06,
      "loss": 1.4476,
      "step": 475
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.049033183969697e-06,
      "loss": 1.3764,
      "step": 480
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.836849256217356e-06,
      "loss": 1.4286,
      "step": 485
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.629048477264152e-06,
      "loss": 1.4175,
      "step": 490
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.425778632191551e-06,
      "loss": 1.4036,
      "step": 495
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2271842837425917e-06,
      "loss": 1.4983,
      "step": 500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.0334066695108566e-06,
      "loss": 1.5578,
      "step": 505
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8445836014942073e-06,
      "loss": 1.4271,
      "step": 510
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6608493680847757e-06,
      "loss": 1.5306,
      "step": 515
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4823346385648774e-06,
      "loss": 1.4684,
      "step": 520
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3091663701768165e-06,
      "loss": 1.3496,
      "step": 525
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.141467717832616e-06,
      "loss": 1.4561,
      "step": 530
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9793579465279245e-06,
      "loss": 1.3217,
      "step": 535
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8229523465223787e-06,
      "loss": 1.377,
      "step": 540
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6723621513467381e-06,
      "loss": 1.5578,
      "step": 545
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5276944586951204e-06,
      "loss": 1.6085,
      "step": 550
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3890521542585723e-06,
      "loss": 1.4866,
      "step": 555
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2565338385541792e-06,
      "loss": 1.3809,
      "step": 560
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1302337568017142e-06,
      "loss": 1.5613,
      "step": 565
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0102417318977253e-06,
      "loss": 1.3391,
      "step": 570
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.966431005347109e-07,
      "loss": 1.3588,
      "step": 575
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.895186525108411e-07,
      "loss": 1.4464,
      "step": 580
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.889445732733324e-07,
      "loss": 1.5436,
      "step": 585
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.949923897364174e-07,
      "loss": 1.5203,
      "step": 590
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.077289194123624e-07,
      "loss": 1.3951,
      "step": 595
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.272162228917809e-07,
      "loss": 1.4145,
      "step": 600
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5351155970696603e-07,
      "loss": 1.4482,
      "step": 605
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8666734760970927e-07,
      "loss": 1.4787,
      "step": 610
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.2673112529249752e-07,
      "loss": 1.4071,
      "step": 615
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.7374551857965882e-07,
      "loss": 1.4387,
      "step": 620
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.277482101124383e-07,
      "loss": 1.3938,
      "step": 625
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.87719125496278e-08,
      "loss": 1.4241,
      "step": 630
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.684434530277005e-08,
      "loss": 1.3593,
      "step": 635
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.198821482248593e-08,
      "loss": 1.4297,
      "step": 640
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4221198449960727e-08,
      "loss": 1.4025,
      "step": 645
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.555931845053984e-09,
      "loss": 1.4367,
      "step": 650
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.5173,
      "step": 655
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4042837619781494,
      "eval_runtime": 40.6612,
      "eval_samples_per_second": 3.517,
      "eval_steps_per_second": 3.517,
      "step": 655
    },
    {
      "epoch": 1.0,
      "step": 655,
      "total_flos": 5.756872988557312e+16,
      "train_loss": 1.5273605372159536,
      "train_runtime": 1271.7396,
      "train_samples_per_second": 1.03,
      "train_steps_per_second": 0.515
    }
  ],
  "logging_steps": 5,
  "max_steps": 655,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 5.756872988557312e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}