{
  "best_metric": 1.5933494567871094,
  "best_model_checkpoint": "output/scriptonite/checkpoint-608",
  "epoch": 2.0,
  "global_step": 608,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00013710963595739938,
      "loss": 2.6067,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001368387818954924,
      "loss": 2.3107,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013638815138477438,
      "loss": 2.1302,
      "step": 15
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013575893162042516,
      "loss": 2.1562,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013495278029461931,
      "loss": 2.0081,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013397182122930294,
      "loss": 1.9735,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001328186387809415,
      "loss": 2.0752,
      "step": 35
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001314962710319808,
      "loss": 2.0235,
      "step": 40
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001300082017869573,
      "loss": 2.0059,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001283583513943447,
      "loss": 1.8462,
      "step": 50
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00012655106641831695,
      "loss": 1.8365,
      "step": 55
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012459110818763681,
      "loss": 2.0625,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012248364025183937,
      "loss": 1.9252,
      "step": 65
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00012023421477775639,
      "loss": 1.9528,
      "step": 70
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00011784875792222071,
      "loss": 1.7558,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011533355421948647,
      "loss": 1.8522,
      "step": 80
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011269523002449659,
      "loss": 1.7714,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000109940736055617,
      "loss": 1.8545,
      "step": 90
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001070773290828286,
      "loss": 1.856,
      "step": 95
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00010411255280962044,
      "loss": 1.7938,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001010542179989503,
      "loss": 1.8907,
      "step": 105
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.791038189563213e-05,
      "loss": 1.8999,
      "step": 110
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.468932699936187e-05,
      "loss": 1.8537,
      "step": 115
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.139953924430466e-05,
      "loss": 1.8283,
      "step": 120
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.804968564273005e-05,
      "loss": 1.6966,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.46485914515931e-05,
      "loss": 1.8649,
      "step": 130
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.120521692221673e-05,
      "loss": 1.8703,
      "step": 135
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.772863369432873e-05,
      "loss": 1.7685,
      "step": 140
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.422800089664365e-05,
      "loss": 1.8474,
      "step": 145
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.071254101695329e-05,
      "loss": 1.7611,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.719151560529643e-05,
      "loss": 1.7199,
      "step": 155
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.367420087421813e-05,
      "loss": 1.7935,
      "step": 160
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.016986326040062e-05,
      "loss": 1.7749,
      "step": 165
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.668773501204858e-05,
      "loss": 1.8416,
      "step": 170
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.323698986634498e-05,
      "loss": 1.7939,
      "step": 175
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.982671888105512e-05,
      "loss": 1.6949,
      "step": 180
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.646590648395145e-05,
      "loss": 1.7562,
      "step": 185
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.316340680315709e-05,
      "loss": 1.6271,
      "step": 190
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.992792034076668e-05,
      "loss": 1.713,
      "step": 195
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.6767971051197685e-05,
      "loss": 1.7105,
      "step": 200
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.369188388466058e-05,
      "loss": 1.7335,
      "step": 205
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0707762854909304e-05,
      "loss": 1.6748,
      "step": 210
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.7823469689053436e-05,
      "loss": 1.7346,
      "step": 215
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.50466031156793e-05,
      "loss": 1.8197,
      "step": 220
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.2384478845846175e-05,
      "loss": 1.6761,
      "step": 225
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.9844110299697732e-05,
      "loss": 1.7013,
      "step": 230
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.7432190129464996e-05,
      "loss": 1.7646,
      "step": 235
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.5155072587539005e-05,
      "loss": 1.5319,
      "step": 240
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3018756786064535e-05,
      "loss": 1.79,
      "step": 245
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1028870892157994e-05,
      "loss": 1.6705,
      "step": 250
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.190657300387505e-06,
      "loss": 1.6285,
      "step": 255
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.508958821578629e-06,
      "loss": 1.706,
      "step": 260
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.988205924331354e-06,
      "loss": 1.6291,
      "step": 265
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.6324050628611986e-06,
      "loss": 1.7411,
      "step": 270
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.445128121914628e-06,
      "loss": 1.7647,
      "step": 275
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.4295030065665785e-06,
      "loss": 1.7888,
      "step": 280
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5882054016913933e-06,
      "loss": 1.6871,
      "step": 285
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.234517228169584e-07,
      "loss": 1.7539,
      "step": 290
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.3699327693326474e-07,
      "loss": 1.6844,
      "step": 295
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3011164863877445e-07,
      "loss": 1.6774,
      "step": 300
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.6153237799239955e-09,
      "loss": 1.7028,
      "step": 305
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.727362871170044,
      "eval_runtime": 20.8096,
      "eval_samples_per_second": 21.336,
      "eval_steps_per_second": 2.691,
      "step": 306
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.3182872524144475e-07,
      "loss": 1.7503,
      "step": 310
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.427558891872417e-07,
      "loss": 1.7186,
      "step": 315
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.35614586573241e-07,
      "loss": 1.7355,
      "step": 320
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.6090892340046806e-06,
      "loss": 1.7325,
      "step": 325
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.461382131516746e-06,
      "loss": 1.5602,
      "step": 330
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.4902182611592783e-06,
      "loss": 1.5739,
      "step": 335
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.692851359682261e-06,
      "loss": 1.7024,
      "step": 340
    },
    {
      "epoch": 1.13,
      "learning_rate": 6.066071249112177e-06,
      "loss": 1.7912,
      "step": 345
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.606212405651899e-06,
      "loss": 1.7776,
      "step": 350
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.309163744031197e-06,
      "loss": 1.8068,
      "step": 355
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.1170379591190527e-05,
      "loss": 1.7059,
      "step": 360
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3184891820006337e-05,
      "loss": 1.7498,
      "step": 365
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.5347323110669033e-05,
      "loss": 1.7696,
      "step": 370
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7651901304315657e-05,
      "loss": 1.703,
      "step": 375
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.009247481060283e-05,
      "loss": 1.6793,
      "step": 380
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.2662529028092886e-05,
      "loss": 1.7064,
      "step": 385
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.5355203733622272e-05,
      "loss": 1.6889,
      "step": 390
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.816331139423508e-05,
      "loss": 1.7357,
      "step": 395
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.1079356352801514e-05,
      "loss": 1.6548,
      "step": 400
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.4095554836109936e-05,
      "loss": 1.7133,
      "step": 405
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.7203855732024184e-05,
      "loss": 1.6095,
      "step": 410
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.039596208024663e-05,
      "loss": 1.6151,
      "step": 415
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.3663353219321276e-05,
      "loss": 1.6988,
      "step": 420
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.6997307530760796e-05,
      "loss": 1.8323,
      "step": 425
    },
    {
      "epoch": 1.41,
      "learning_rate": 5.038892571958626e-05,
      "loss": 1.6735,
      "step": 430
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.382915456913676e-05,
      "loss": 1.6212,
      "step": 435
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.7308811106741675e-05,
      "loss": 1.7788,
      "step": 440
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.0818607115748475e-05,
      "loss": 1.6847,
      "step": 445
    },
    {
      "epoch": 1.48,
      "learning_rate": 6.434917392847842e-05,
      "loss": 1.6746,
      "step": 450
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.78910874339285e-05,
      "loss": 1.7122,
      "step": 455
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.143489323346855e-05,
      "loss": 1.6207,
      "step": 460
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.497113187738444e-05,
      "loss": 1.719,
      "step": 465
    },
    {
      "epoch": 1.55,
      "learning_rate": 7.849036411490396e-05,
      "loss": 1.814,
      "step": 470
    },
    {
      "epoch": 1.56,
      "learning_rate": 8.19831960903064e-05,
      "loss": 1.7822,
      "step": 475
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.54403044178588e-05,
      "loss": 1.7602,
      "step": 480
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.885246106864805e-05,
      "loss": 1.6178,
      "step": 485
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.221055800287699e-05,
      "loss": 1.7397,
      "step": 490
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.550563148187563e-05,
      "loss": 1.6071,
      "step": 495
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.87288859949296e-05,
      "loss": 1.66,
      "step": 500
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00010187171773706003,
      "loss": 1.6028,
      "step": 505
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00010492573757508462,
      "loss": 1.697,
      "step": 510
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001078827934406569,
      "loss": 1.5973,
      "step": 515
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00011073499209051121,
      "loss": 1.6779,
      "step": 520
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00011347472017582718,
      "loss": 1.639,
      "step": 525
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011609466456447531,
      "loss": 1.7209,
      "step": 530
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011858783186189604,
      "loss": 1.7896,
      "step": 535
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012094756707850673,
      "loss": 1.7093,
      "step": 540
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00012316757139380674,
      "loss": 1.614,
      "step": 545
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001252419189697637,
      "loss": 1.7043,
      "step": 550
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001271650727686013,
      "loss": 1.6544,
      "step": 555
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00012893189933276512,
      "loss": 1.6355,
      "step": 560
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00013053768248761616,
      "loss": 1.7327,
      "step": 565
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013197813593027427,
      "loss": 1.5672,
      "step": 570
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00013324941467100882,
      "loss": 1.6036,
      "step": 575
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013434812529663614,
      "loss": 1.5748,
      "step": 580
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013527133502852737,
      "loss": 1.6181,
      "step": 585
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013601657955104887,
      "loss": 1.6947,
      "step": 590
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013658186958953817,
      "loss": 1.6579,
      "step": 595
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013696569622025754,
      "loss": 1.6297,
      "step": 600
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013716703489815072,
      "loss": 1.6272,
      "step": 605
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5933494567871094,
      "eval_runtime": 22.1769,
      "eval_samples_per_second": 20.968,
      "eval_steps_per_second": 2.66,
      "step": 608
    }
  ],
  "max_steps": 608,
  "num_train_epochs": 2,
  "total_flos": 634286407680000.0,
  "trial_name": null,
  "trial_params": null
}