{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8496176720475785,
  "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": 4.999919851200522e-05,
      "loss": 9.9461,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996428002198536e-05,
      "loss": 6.4908,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9992242747551964e-05,
      "loss": 3.708,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99857130295276e-05,
      "loss": 0.8908,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997720546222574e-05,
      "loss": 0.2454,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.996672071909866e-05,
      "loss": 0.1348,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.995425963011034e-05,
      "loss": 0.0487,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.993982318167074e-05,
      "loss": 0.0282,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.992341251655768e-05,
      "loss": 0.0455,
      "step": 90
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9905028933826435e-05,
      "loss": 0.0472,
      "step": 100
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.988467388870688e-05,
      "loss": 0.0526,
      "step": 110
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.986234899248826e-05,
      "loss": 0.0679,
      "step": 120
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.983805601239172e-05,
      "loss": 0.0314,
      "step": 130
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.981179687143034e-05,
      "loss": 0.0136,
      "step": 140
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.978357364825695e-05,
      "loss": 0.0409,
      "step": 150
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.975338857699956e-05,
      "loss": 0.0284,
      "step": 160
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.972124404708454e-05,
      "loss": 0.0364,
      "step": 170
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.968714260304743e-05,
      "loss": 0.0147,
      "step": 180
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.965108694433159e-05,
      "loss": 0.0174,
      "step": 190
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.961307992507443e-05,
      "loss": 0.0244,
      "step": 200
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.957312455388152e-05,
      "loss": 0.0387,
      "step": 210
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.953122399358845e-05,
      "loss": 0.0264,
      "step": 220
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.948738156101042e-05,
      "loss": 0.0291,
      "step": 230
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.9441600726679694e-05,
      "loss": 0.0214,
      "step": 240
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.939388511457092e-05,
      "loss": 0.0116,
      "step": 250
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.934423850181419e-05,
      "loss": 0.0191,
      "step": 260
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9292664818396117e-05,
      "loss": 0.0064,
      "step": 270
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.9239168146848666e-05,
      "loss": 0.0184,
      "step": 280
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9183752721926036e-05,
      "loss": 0.0026,
      "step": 290
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.912642293026942e-05,
      "loss": 0.0223,
      "step": 300
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.906718331005979e-05,
      "loss": 0.0405,
      "step": 310
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.900603855065861e-05,
      "loss": 0.0461,
      "step": 320
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.894299349223665e-05,
      "loss": 0.0199,
      "step": 330
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.8878053125390875e-05,
      "loss": 0.0193,
      "step": 340
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.881122259074935e-05,
      "loss": 0.004,
      "step": 350
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.874250717856433e-05,
      "loss": 0.0018,
      "step": 360
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.867191232829348e-05,
      "loss": 0.0021,
      "step": 370
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.8599443628169295e-05,
      "loss": 0.018,
      "step": 380
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.8525106814756754e-05,
      "loss": 0.0261,
      "step": 390
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.84489077724992e-05,
      "loss": 0.016,
      "step": 400
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8370852533252536e-05,
      "loss": 0.0402,
      "step": 410
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.8290947275807755e-05,
      "loss": 0.0038,
      "step": 420
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.8209198325401815e-05,
      "loss": 0.008,
      "step": 430
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.8125612153216976e-05,
      "loss": 0.0296,
      "step": 440
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.804019537586849e-05,
      "loss": 0.0012,
      "step": 450
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.7952954754880886e-05,
      "loss": 0.0142,
      "step": 460
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.7863897196152704e-05,
      "loss": 0.0163,
      "step": 470
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.7773029749409836e-05,
      "loss": 0.0021,
      "step": 480
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.76803596076475e-05,
      "loss": 0.0355,
      "step": 490
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.758589410656078e-05,
      "loss": 0.0199,
      "step": 500
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.010466881096363068,
      "eval_runtime": 88.037,
      "eval_samples_per_second": 22.525,
      "eval_steps_per_second": 2.817,
      "step": 500
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.748964072396403e-05,
      "loss": 0.0341,
      "step": 510
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.7391607079198876e-05,
      "loss": 0.0137,
      "step": 520
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7291800932531064e-05,
      "loss": 0.0138,
      "step": 530
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.719023018453623e-05,
      "loss": 0.0063,
      "step": 540
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.708690287547441e-05,
      "loss": 0.0376,
      "step": 550
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.698182718465368e-05,
      "loss": 0.006,
      "step": 560
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.687501142978258e-05,
      "loss": 0.0371,
      "step": 570
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.6766464066311765e-05,
      "loss": 0.0322,
      "step": 580
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.665619368676466e-05,
      "loss": 0.0086,
      "step": 590
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6544209020057285e-05,
      "loss": 0.002,
      "step": 600
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.643051893080725e-05,
      "loss": 0.0147,
      "step": 610
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.631513241863209e-05,
      "loss": 0.0038,
      "step": 620
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.619805861743683e-05,
      "loss": 0.0187,
      "step": 630
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.607930679469096e-05,
      "loss": 0.0063,
      "step": 640
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.595888635069481e-05,
      "loss": 0.0109,
      "step": 650
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.5836806817835475e-05,
      "loss": 0.005,
      "step": 660
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.57130778598322e-05,
      "loss": 0.0167,
      "step": 670
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.5587709270971425e-05,
      "loss": 0.0143,
      "step": 680
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.546071097533145e-05,
      "loss": 0.0015,
      "step": 690
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.533209302599691e-05,
      "loss": 0.0003,
      "step": 700
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.520186560426292e-05,
      "loss": 0.006,
      "step": 710
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.507003901882915e-05,
      "loss": 0.0093,
      "step": 720
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.493662370498383e-05,
      "loss": 0.0046,
      "step": 730
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.4801630223777665e-05,
      "loss": 0.0147,
      "step": 740
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.466506926118782e-05,
      "loss": 0.0102,
      "step": 750
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.4526951627272074e-05,
      "loss": 0.017,
      "step": 760
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.438728825531305e-05,
      "loss": 0.0033,
      "step": 770
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.4246090200952816e-05,
      "loss": 0.0061,
      "step": 780
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.410336864131762e-05,
      "loss": 0.0032,
      "step": 790
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.395913487413324e-05,
      "loss": 0.0043,
      "step": 800
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.3813400316830576e-05,
      "loss": 0.0063,
      "step": 810
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.36661765056419e-05,
      "loss": 0.0273,
      "step": 820
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.351747509468763e-05,
      "loss": 0.0125,
      "step": 830
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.336730785505382e-05,
      "loss": 0.0076,
      "step": 840
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.3215686673860384e-05,
      "loss": 0.0127,
      "step": 850
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.306262355332006e-05,
      "loss": 0.0161,
      "step": 860
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.290813060978839e-05,
      "loss": 0.0169,
      "step": 870
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.2752220072804564e-05,
      "loss": 0.0081,
      "step": 880
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.259490428412335e-05,
      "loss": 0.0131,
      "step": 890
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.243619569673814e-05,
      "loss": 0.0205,
      "step": 900
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.2276106873895143e-05,
      "loss": 0.0026,
      "step": 910
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.2114650488098936e-05,
      "loss": 0.018,
      "step": 920
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.19518393201093e-05,
      "loss": 0.0083,
      "step": 930
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.178768625792949e-05,
      "loss": 0.0291,
      "step": 940
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.162220429578605e-05,
      "loss": 0.0226,
      "step": 950
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.145540653310018e-05,
      "loss": 0.0042,
      "step": 960
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.128730617345084e-05,
      "loss": 0.0078,
      "step": 970
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.111791652352952e-05,
      "loss": 0.0084,
      "step": 980
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.094725099208688e-05,
      "loss": 0.0044,
      "step": 990
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.077532308887141e-05,
      "loss": 0.0011,
      "step": 1000
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.01175768580287695,
      "eval_runtime": 88.0904,
      "eval_samples_per_second": 22.511,
      "eval_steps_per_second": 2.815,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3531,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 1.5022667366085427e+17,
  "trial_name": null,
  "trial_params": null
}