{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017340338830220743,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034680677660441485,
      "grad_norm": 8.286304473876953,
      "learning_rate": 2.6999999999999996e-06,
      "loss": 36.023321533203124,
      "step": 10
    },
    {
      "epoch": 0.0006936135532088297,
      "grad_norm": 5.303624153137207,
      "learning_rate": 5.7e-06,
      "loss": 35.81325988769531,
      "step": 20
    },
    {
      "epoch": 0.0010404203298132447,
      "grad_norm": 14.0803861618042,
      "learning_rate": 8.7e-06,
      "loss": 35.61415100097656,
      "step": 30
    },
    {
      "epoch": 0.0013872271064176594,
      "grad_norm": 42.10546875,
      "learning_rate": 1.17e-05,
      "loss": 35.36910400390625,
      "step": 40
    },
    {
      "epoch": 0.0017340338830220744,
      "grad_norm": 43.37276840209961,
      "learning_rate": 1.47e-05,
      "loss": 34.86077880859375,
      "step": 50
    },
    {
      "epoch": 0.0020808406596264893,
      "grad_norm": Infinity,
      "learning_rate": 1.7699999999999997e-05,
      "loss": 34.67452697753906,
      "step": 60
    },
    {
      "epoch": 0.002427647436230904,
      "grad_norm": 86.09446716308594,
      "learning_rate": 2.04e-05,
      "loss": 34.29078979492188,
      "step": 70
    },
    {
      "epoch": 0.002774454212835319,
      "grad_norm": 43.50123977661133,
      "learning_rate": 2.34e-05,
      "loss": 33.816766357421876,
      "step": 80
    },
    {
      "epoch": 0.0031212609894397335,
      "grad_norm": 104.7258529663086,
      "learning_rate": 2.6399999999999995e-05,
      "loss": 33.36159057617188,
      "step": 90
    },
    {
      "epoch": 0.0034680677660441487,
      "grad_norm": 66.46515655517578,
      "learning_rate": 2.91e-05,
      "loss": 33.181732177734375,
      "step": 100
    },
    {
      "epoch": 0.0038148745426485635,
      "grad_norm": 127.66901397705078,
      "learning_rate": 3.2099999999999994e-05,
      "loss": 32.83320007324219,
      "step": 110
    },
    {
      "epoch": 0.004161681319252979,
      "grad_norm": 71.67156982421875,
      "learning_rate": 3.51e-05,
      "loss": 32.48929138183594,
      "step": 120
    },
    {
      "epoch": 0.004508488095857393,
      "grad_norm": 76.15655517578125,
      "learning_rate": 3.81e-05,
      "loss": 32.10602722167969,
      "step": 130
    },
    {
      "epoch": 0.004855294872461808,
      "grad_norm": 38.65349578857422,
      "learning_rate": 4.11e-05,
      "loss": 31.449526977539062,
      "step": 140
    },
    {
      "epoch": 0.005202101649066222,
      "grad_norm": 59.55622863769531,
      "learning_rate": 4.4099999999999995e-05,
      "loss": 31.01339111328125,
      "step": 150
    },
    {
      "epoch": 0.005548908425670638,
      "grad_norm": 130.26136779785156,
      "learning_rate": 4.709999999999999e-05,
      "loss": 30.92586669921875,
      "step": 160
    },
    {
      "epoch": 0.005895715202275053,
      "grad_norm": 77.2778549194336,
      "learning_rate": 5.01e-05,
      "loss": 30.492510986328124,
      "step": 170
    },
    {
      "epoch": 0.006242521978879467,
      "grad_norm": 29.711563110351562,
      "learning_rate": 5.309999999999999e-05,
      "loss": 29.836746215820312,
      "step": 180
    },
    {
      "epoch": 0.006589328755483882,
      "grad_norm": 29.891956329345703,
      "learning_rate": 5.6099999999999995e-05,
      "loss": 29.291275024414062,
      "step": 190
    },
    {
      "epoch": 0.006936135532088297,
      "grad_norm": 30.56305503845215,
      "learning_rate": 5.91e-05,
      "loss": 29.14805908203125,
      "step": 200
    },
    {
      "epoch": 0.007282942308692712,
      "grad_norm": 29.489208221435547,
      "learning_rate": 6.209999999999999e-05,
      "loss": 28.80553283691406,
      "step": 210
    },
    {
      "epoch": 0.007629749085297127,
      "grad_norm": 37.147377014160156,
      "learning_rate": 6.51e-05,
      "loss": 28.694085693359376,
      "step": 220
    },
    {
      "epoch": 0.007976555861901541,
      "grad_norm": 28.496992111206055,
      "learning_rate": 6.81e-05,
      "loss": 28.166943359375,
      "step": 230
    },
    {
      "epoch": 0.008323362638505957,
      "grad_norm": 29.42328453063965,
      "learning_rate": 7.11e-05,
      "loss": 27.878482055664062,
      "step": 240
    },
    {
      "epoch": 0.008670169415110372,
      "grad_norm": 27.867637634277344,
      "learning_rate": 7.41e-05,
      "loss": 26.99749755859375,
      "step": 250
    },
    {
      "epoch": 0.009016976191714786,
      "grad_norm": 29.695758819580078,
      "learning_rate": 7.709999999999999e-05,
      "loss": 27.208102416992187,
      "step": 260
    },
    {
      "epoch": 0.0093637829683192,
      "grad_norm": 34.605934143066406,
      "learning_rate": 8.01e-05,
      "loss": 26.798681640625,
      "step": 270
    },
    {
      "epoch": 0.009710589744923616,
      "grad_norm": 35.05394744873047,
      "learning_rate": 8.31e-05,
      "loss": 27.192486572265626,
      "step": 280
    },
    {
      "epoch": 0.01005739652152803,
      "grad_norm": 19.137067794799805,
      "learning_rate": 8.609999999999999e-05,
      "loss": 26.89140930175781,
      "step": 290
    },
    {
      "epoch": 0.010404203298132445,
      "grad_norm": 24.543006896972656,
      "learning_rate": 8.879999999999999e-05,
      "loss": 26.167477416992188,
      "step": 300
    },
    {
      "epoch": 0.010751010074736861,
      "grad_norm": 18.849651336669922,
      "learning_rate": 9.18e-05,
      "loss": 26.41388854980469,
      "step": 310
    },
    {
      "epoch": 0.011097816851341275,
      "grad_norm": 21.179908752441406,
      "learning_rate": 9.479999999999999e-05,
      "loss": 26.003546142578124,
      "step": 320
    },
    {
      "epoch": 0.01144462362794569,
      "grad_norm": 19.344528198242188,
      "learning_rate": 9.779999999999999e-05,
      "loss": 26.271051025390626,
      "step": 330
    },
    {
      "epoch": 0.011791430404550106,
      "grad_norm": 19.74913215637207,
      "learning_rate": 0.0001008,
      "loss": 26.064590454101562,
      "step": 340
    },
    {
      "epoch": 0.01213823718115452,
      "grad_norm": 17.638103485107422,
      "learning_rate": 0.00010379999999999999,
      "loss": 25.863119506835936,
      "step": 350
    },
    {
      "epoch": 0.012485043957758934,
      "grad_norm": 24.873981475830078,
      "learning_rate": 0.00010679999999999998,
      "loss": 26.28948059082031,
      "step": 360
    },
    {
      "epoch": 0.01283185073436335,
      "grad_norm": 17.048828125,
      "learning_rate": 0.00010979999999999999,
      "loss": 26.215179443359375,
      "step": 370
    },
    {
      "epoch": 0.013178657510967764,
      "grad_norm": 21.703975677490234,
      "learning_rate": 0.00011279999999999999,
      "loss": 26.152392578125,
      "step": 380
    },
    {
      "epoch": 0.013525464287572179,
      "grad_norm": 22.66498565673828,
      "learning_rate": 0.0001158,
      "loss": 26.0640625,
      "step": 390
    },
    {
      "epoch": 0.013872271064176595,
      "grad_norm": 16.945016860961914,
      "learning_rate": 0.0001188,
      "loss": 26.023715209960937,
      "step": 400
    },
    {
      "epoch": 0.01421907784078101,
      "grad_norm": 27.866268157958984,
      "learning_rate": 0.00012179999999999999,
      "loss": 25.43433380126953,
      "step": 410
    },
    {
      "epoch": 0.014565884617385423,
      "grad_norm": 22.481279373168945,
      "learning_rate": 0.00012479999999999997,
      "loss": 25.464639282226564,
      "step": 420
    },
    {
      "epoch": 0.014912691393989838,
      "grad_norm": 14.993969917297363,
      "learning_rate": 0.0001278,
      "loss": 25.218385314941408,
      "step": 430
    },
    {
      "epoch": 0.015259498170594254,
      "grad_norm": 14.426427841186523,
      "learning_rate": 0.00013079999999999998,
      "loss": 24.94810333251953,
      "step": 440
    },
    {
      "epoch": 0.015606304947198668,
      "grad_norm": 15.592818260192871,
      "learning_rate": 0.0001338,
      "loss": 25.38585662841797,
      "step": 450
    },
    {
      "epoch": 0.015953111723803082,
      "grad_norm": 14.709174156188965,
      "learning_rate": 0.0001368,
      "loss": 24.31098175048828,
      "step": 460
    },
    {
      "epoch": 0.016299918500407497,
      "grad_norm": 13.651994705200195,
      "learning_rate": 0.00013979999999999998,
      "loss": 24.82652893066406,
      "step": 470
    },
    {
      "epoch": 0.016646725277011915,
      "grad_norm": 17.521072387695312,
      "learning_rate": 0.00014279999999999997,
      "loss": 25.121923828125,
      "step": 480
    },
    {
      "epoch": 0.01699353205361633,
      "grad_norm": 13.458234786987305,
      "learning_rate": 0.0001458,
      "loss": 24.447775268554686,
      "step": 490
    },
    {
      "epoch": 0.017340338830220743,
      "grad_norm": 13.57589340209961,
      "learning_rate": 0.00014879999999999998,
      "loss": 24.76665802001953,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3109956747264000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}