{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04724719469781482,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005249688299757202,
      "grad_norm": 4051.18359375,
      "learning_rate": 9e-07,
      "loss": 7.93,
      "step": 10
    },
    {
      "epoch": 0.0010499376599514404,
      "grad_norm": 111.26915740966797,
      "learning_rate": 3.899999999999999e-06,
      "loss": 7.7273,
      "step": 20
    },
    {
      "epoch": 0.0015749064899271605,
      "grad_norm": 176.40713500976562,
      "learning_rate": 6.899999999999999e-06,
      "loss": 7.5271,
      "step": 30
    },
    {
      "epoch": 0.002099875319902881,
      "grad_norm": 668.3442993164062,
      "learning_rate": 9.9e-06,
      "loss": 7.6155,
      "step": 40
    },
    {
      "epoch": 0.002624844149878601,
      "grad_norm": 171.85369873046875,
      "learning_rate": 1.2899999999999998e-05,
      "loss": 7.4873,
      "step": 50
    },
    {
      "epoch": 0.003149812979854321,
      "grad_norm": 477.1031494140625,
      "learning_rate": 1.5899999999999997e-05,
      "loss": 7.4295,
      "step": 60
    },
    {
      "epoch": 0.0036747818098300414,
      "grad_norm": 256.7841491699219,
      "learning_rate": 1.89e-05,
      "loss": 7.3037,
      "step": 70
    },
    {
      "epoch": 0.004199750639805762,
      "grad_norm": 240.86167907714844,
      "learning_rate": 2.1899999999999997e-05,
      "loss": 7.3488,
      "step": 80
    },
    {
      "epoch": 0.0047247194697814816,
      "grad_norm": 151.8752899169922,
      "learning_rate": 2.49e-05,
      "loss": 7.1664,
      "step": 90
    },
    {
      "epoch": 0.005249688299757202,
      "grad_norm": 92.41702270507812,
      "learning_rate": 2.7899999999999997e-05,
      "loss": 7.2001,
      "step": 100
    },
    {
      "epoch": 0.005774657129732922,
      "grad_norm": 125.6628189086914,
      "learning_rate": 3.09e-05,
      "loss": 7.1956,
      "step": 110
    },
    {
      "epoch": 0.006299625959708642,
      "grad_norm": 105.1700210571289,
      "learning_rate": 3.39e-05,
      "loss": 7.2136,
      "step": 120
    },
    {
      "epoch": 0.006824594789684363,
      "grad_norm": 95.49678039550781,
      "learning_rate": 3.6899999999999996e-05,
      "loss": 7.2046,
      "step": 130
    },
    {
      "epoch": 0.007349563619660083,
      "grad_norm": 70.33267974853516,
      "learning_rate": 3.99e-05,
      "loss": 7.0895,
      "step": 140
    },
    {
      "epoch": 0.007874532449635803,
      "grad_norm": 42.994972229003906,
      "learning_rate": 4.289999999999999e-05,
      "loss": 7.1157,
      "step": 150
    },
    {
      "epoch": 0.008399501279611523,
      "grad_norm": 87.23907470703125,
      "learning_rate": 4.59e-05,
      "loss": 7.1537,
      "step": 160
    },
    {
      "epoch": 0.008924470109587244,
      "grad_norm": 53.14045333862305,
      "learning_rate": 4.8899999999999996e-05,
      "loss": 7.0126,
      "step": 170
    },
    {
      "epoch": 0.009449438939562963,
      "grad_norm": 44.222225189208984,
      "learning_rate": 5.1899999999999994e-05,
      "loss": 7.1067,
      "step": 180
    },
    {
      "epoch": 0.009974407769538684,
      "grad_norm": 65.67877197265625,
      "learning_rate": 5.489999999999999e-05,
      "loss": 7.0359,
      "step": 190
    },
    {
      "epoch": 0.010499376599514405,
      "grad_norm": 34.80784225463867,
      "learning_rate": 5.79e-05,
      "loss": 7.0124,
      "step": 200
    },
    {
      "epoch": 0.011024345429490124,
      "grad_norm": 80.05706024169922,
      "learning_rate": 6.0899999999999996e-05,
      "loss": 6.9882,
      "step": 210
    },
    {
      "epoch": 0.011549314259465844,
      "grad_norm": 18.072044372558594,
      "learning_rate": 6.39e-05,
      "loss": 7.082,
      "step": 220
    },
    {
      "epoch": 0.012074283089441565,
      "grad_norm": 27.460533142089844,
      "learning_rate": 6.69e-05,
      "loss": 7.0056,
      "step": 230
    },
    {
      "epoch": 0.012599251919417284,
      "grad_norm": 20.942256927490234,
      "learning_rate": 6.989999999999999e-05,
      "loss": 7.0385,
      "step": 240
    },
    {
      "epoch": 0.013124220749393005,
      "grad_norm": 21.205760955810547,
      "learning_rate": 7.29e-05,
      "loss": 6.9065,
      "step": 250
    },
    {
      "epoch": 0.013649189579368726,
      "grad_norm": 30.357505798339844,
      "learning_rate": 7.589999999999999e-05,
      "loss": 6.9887,
      "step": 260
    },
    {
      "epoch": 0.014174158409344445,
      "grad_norm": 21.6142520904541,
      "learning_rate": 7.89e-05,
      "loss": 7.0671,
      "step": 270
    },
    {
      "epoch": 0.014699127239320165,
      "grad_norm": 34.31865310668945,
      "learning_rate": 8.19e-05,
      "loss": 6.9352,
      "step": 280
    },
    {
      "epoch": 0.015224096069295886,
      "grad_norm": 31.643892288208008,
      "learning_rate": 8.489999999999999e-05,
      "loss": 7.0615,
      "step": 290
    },
    {
      "epoch": 0.015749064899271605,
      "grad_norm": 21.246601104736328,
      "learning_rate": 8.789999999999998e-05,
      "loss": 6.8747,
      "step": 300
    },
    {
      "epoch": 0.016274033729247326,
      "grad_norm": 17.99869155883789,
      "learning_rate": 9.089999999999999e-05,
      "loss": 6.9325,
      "step": 310
    },
    {
      "epoch": 0.016799002559223047,
      "grad_norm": 10.438518524169922,
      "learning_rate": 9.389999999999999e-05,
      "loss": 6.975,
      "step": 320
    },
    {
      "epoch": 0.017323971389198767,
      "grad_norm": 38.324283599853516,
      "learning_rate": 9.69e-05,
      "loss": 6.8833,
      "step": 330
    },
    {
      "epoch": 0.017848940219174488,
      "grad_norm": 25.789045333862305,
      "learning_rate": 9.99e-05,
      "loss": 6.869,
      "step": 340
    },
    {
      "epoch": 0.018373909049150206,
      "grad_norm": 26.649545669555664,
      "learning_rate": 0.0001029,
      "loss": 6.8773,
      "step": 350
    },
    {
      "epoch": 0.018898877879125926,
      "grad_norm": 24.452266693115234,
      "learning_rate": 0.00010589999999999999,
      "loss": 6.7558,
      "step": 360
    },
    {
      "epoch": 0.019423846709101647,
      "grad_norm": 14.234713554382324,
      "learning_rate": 0.00010889999999999999,
      "loss": 6.9624,
      "step": 370
    },
    {
      "epoch": 0.019948815539077368,
      "grad_norm": 16.222957611083984,
      "learning_rate": 0.0001119,
      "loss": 6.9116,
      "step": 380
    },
    {
      "epoch": 0.02047378436905309,
      "grad_norm": 14.955327033996582,
      "learning_rate": 0.00011489999999999999,
      "loss": 6.8227,
      "step": 390
    },
    {
      "epoch": 0.02099875319902881,
      "grad_norm": 13.272610664367676,
      "learning_rate": 0.00011789999999999999,
      "loss": 6.8292,
      "step": 400
    },
    {
      "epoch": 0.021523722029004527,
      "grad_norm": 14.966605186462402,
      "learning_rate": 0.0001209,
      "loss": 6.8364,
      "step": 410
    },
    {
      "epoch": 0.022048690858980247,
      "grad_norm": 11.822840690612793,
      "learning_rate": 0.00012389999999999998,
      "loss": 6.668,
      "step": 420
    },
    {
      "epoch": 0.022573659688955968,
      "grad_norm": 12.50557804107666,
      "learning_rate": 0.0001269,
      "loss": 6.6604,
      "step": 430
    },
    {
      "epoch": 0.02309862851893169,
      "grad_norm": 13.769299507141113,
      "learning_rate": 0.00012989999999999999,
      "loss": 6.6969,
      "step": 440
    },
    {
      "epoch": 0.02362359734890741,
      "grad_norm": 9.62465763092041,
      "learning_rate": 0.00013289999999999998,
      "loss": 6.7391,
      "step": 450
    },
    {
      "epoch": 0.02414856617888313,
      "grad_norm": 8.241267204284668,
      "learning_rate": 0.0001359,
      "loss": 6.7064,
      "step": 460
    },
    {
      "epoch": 0.024673535008858848,
      "grad_norm": 14.394071578979492,
      "learning_rate": 0.0001389,
      "loss": 6.7164,
      "step": 470
    },
    {
      "epoch": 0.02519850383883457,
      "grad_norm": 8.198172569274902,
      "learning_rate": 0.00014189999999999998,
      "loss": 6.7228,
      "step": 480
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 17.51156997680664,
      "learning_rate": 0.00014489999999999997,
      "loss": 6.6933,
      "step": 490
    },
    {
      "epoch": 0.02624844149878601,
      "grad_norm": 14.444514274597168,
      "learning_rate": 0.0001479,
      "loss": 6.5789,
      "step": 500
    },
    {
      "epoch": 0.02677341032876173,
      "grad_norm": 8.710993766784668,
      "learning_rate": 0.00015089999999999998,
      "loss": 6.6053,
      "step": 510
    },
    {
      "epoch": 0.02729837915873745,
      "grad_norm": 11.155731201171875,
      "learning_rate": 0.0001539,
      "loss": 6.6003,
      "step": 520
    },
    {
      "epoch": 0.02782334798871317,
      "grad_norm": 9.0637845993042,
      "learning_rate": 0.0001569,
      "loss": 6.5253,
      "step": 530
    },
    {
      "epoch": 0.02834831681868889,
      "grad_norm": 7.813695907592773,
      "learning_rate": 0.00015989999999999998,
      "loss": 6.5777,
      "step": 540
    },
    {
      "epoch": 0.02887328564866461,
      "grad_norm": 9.640409469604492,
      "learning_rate": 0.0001629,
      "loss": 6.5582,
      "step": 550
    },
    {
      "epoch": 0.02939825447864033,
      "grad_norm": 10.287951469421387,
      "learning_rate": 0.0001659,
      "loss": 6.5429,
      "step": 560
    },
    {
      "epoch": 0.02992322330861605,
      "grad_norm": 8.388657569885254,
      "learning_rate": 0.00016889999999999996,
      "loss": 6.4797,
      "step": 570
    },
    {
      "epoch": 0.030448192138591772,
      "grad_norm": 6.651219844818115,
      "learning_rate": 0.00017189999999999998,
      "loss": 6.472,
      "step": 580
    },
    {
      "epoch": 0.03097316096856749,
      "grad_norm": 6.32115364074707,
      "learning_rate": 0.00017489999999999997,
      "loss": 6.4754,
      "step": 590
    },
    {
      "epoch": 0.03149812979854321,
      "grad_norm": 10.339417457580566,
      "learning_rate": 0.0001779,
      "loss": 6.4067,
      "step": 600
    },
    {
      "epoch": 0.03202309862851893,
      "grad_norm": 7.705801963806152,
      "learning_rate": 0.00018089999999999998,
      "loss": 6.4035,
      "step": 610
    },
    {
      "epoch": 0.03254806745849465,
      "grad_norm": 6.596720218658447,
      "learning_rate": 0.00018389999999999997,
      "loss": 6.3301,
      "step": 620
    },
    {
      "epoch": 0.03307303628847037,
      "grad_norm": 10.351055145263672,
      "learning_rate": 0.0001869,
      "loss": 6.3362,
      "step": 630
    },
    {
      "epoch": 0.03359800511844609,
      "grad_norm": 8.058084487915039,
      "learning_rate": 0.00018989999999999998,
      "loss": 6.4833,
      "step": 640
    },
    {
      "epoch": 0.034122973948421814,
      "grad_norm": 8.515560150146484,
      "learning_rate": 0.0001929,
      "loss": 6.2454,
      "step": 650
    },
    {
      "epoch": 0.034647942778397535,
      "grad_norm": 7.069362640380859,
      "learning_rate": 0.0001959,
      "loss": 6.2539,
      "step": 660
    },
    {
      "epoch": 0.035172911608373256,
      "grad_norm": 6.835115909576416,
      "learning_rate": 0.00019889999999999998,
      "loss": 6.2121,
      "step": 670
    },
    {
      "epoch": 0.035697880438348976,
      "grad_norm": 9.131962776184082,
      "learning_rate": 0.0002019,
      "loss": 6.1163,
      "step": 680
    },
    {
      "epoch": 0.03622284926832469,
      "grad_norm": 6.500721454620361,
      "learning_rate": 0.0002049,
      "loss": 6.2233,
      "step": 690
    },
    {
      "epoch": 0.03674781809830041,
      "grad_norm": 6.955876350402832,
      "learning_rate": 0.00020789999999999996,
      "loss": 6.2746,
      "step": 700
    },
    {
      "epoch": 0.03727278692827613,
      "grad_norm": 12.63397216796875,
      "learning_rate": 0.00021089999999999998,
      "loss": 6.2639,
      "step": 710
    },
    {
      "epoch": 0.03779775575825185,
      "grad_norm": 6.766085624694824,
      "learning_rate": 0.00021389999999999997,
      "loss": 6.2185,
      "step": 720
    },
    {
      "epoch": 0.03832272458822757,
      "grad_norm": 7.125621795654297,
      "learning_rate": 0.0002169,
      "loss": 6.2077,
      "step": 730
    },
    {
      "epoch": 0.038847693418203294,
      "grad_norm": 6.098615646362305,
      "learning_rate": 0.00021989999999999998,
      "loss": 6.1988,
      "step": 740
    },
    {
      "epoch": 0.039372662248179015,
      "grad_norm": 6.724160671234131,
      "learning_rate": 0.00022289999999999997,
      "loss": 6.1645,
      "step": 750
    },
    {
      "epoch": 0.039897631078154736,
      "grad_norm": 6.864727973937988,
      "learning_rate": 0.0002259,
      "loss": 5.9853,
      "step": 760
    },
    {
      "epoch": 0.040422599908130456,
      "grad_norm": 7.888518810272217,
      "learning_rate": 0.00022889999999999998,
      "loss": 6.0459,
      "step": 770
    },
    {
      "epoch": 0.04094756873810618,
      "grad_norm": 5.348147392272949,
      "learning_rate": 0.0002319,
      "loss": 6.0306,
      "step": 780
    },
    {
      "epoch": 0.0414725375680819,
      "grad_norm": 7.666118621826172,
      "learning_rate": 0.0002349,
      "loss": 6.0464,
      "step": 790
    },
    {
      "epoch": 0.04199750639805762,
      "grad_norm": 12.02874755859375,
      "learning_rate": 0.00023789999999999998,
      "loss": 5.9991,
      "step": 800
    },
    {
      "epoch": 0.04252247522803333,
      "grad_norm": 6.495911598205566,
      "learning_rate": 0.0002409,
      "loss": 5.9451,
      "step": 810
    },
    {
      "epoch": 0.04304744405800905,
      "grad_norm": 9.461275100708008,
      "learning_rate": 0.00024389999999999997,
      "loss": 5.9558,
      "step": 820
    },
    {
      "epoch": 0.043572412887984774,
      "grad_norm": 6.616198539733887,
      "learning_rate": 0.0002469,
      "loss": 5.9853,
      "step": 830
    },
    {
      "epoch": 0.044097381717960495,
      "grad_norm": 6.1858086585998535,
      "learning_rate": 0.00024989999999999995,
      "loss": 5.9692,
      "step": 840
    },
    {
      "epoch": 0.044622350547936215,
      "grad_norm": 5.398629188537598,
      "learning_rate": 0.00025289999999999997,
      "loss": 5.9193,
      "step": 850
    },
    {
      "epoch": 0.045147319377911936,
      "grad_norm": 7.980245113372803,
      "learning_rate": 0.0002559,
      "loss": 5.8701,
      "step": 860
    },
    {
      "epoch": 0.04567228820788766,
      "grad_norm": 6.517972946166992,
      "learning_rate": 0.00025889999999999995,
      "loss": 5.905,
      "step": 870
    },
    {
      "epoch": 0.04619725703786338,
      "grad_norm": 6.580096244812012,
      "learning_rate": 0.00026189999999999997,
      "loss": 5.7834,
      "step": 880
    },
    {
      "epoch": 0.0467222258678391,
      "grad_norm": 6.371602535247803,
      "learning_rate": 0.0002649,
      "loss": 5.8452,
      "step": 890
    },
    {
      "epoch": 0.04724719469781482,
      "grad_norm": 6.168027400970459,
      "learning_rate": 0.0002679,
      "loss": 5.6781,
      "step": 900
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 525,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3575928233984e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}