{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.78848,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00128,
      "grad_norm": 124.84142303466797,
      "learning_rate": 0.0,
      "loss": 50.6226,
      "step": 1
    },
    {
      "epoch": 0.064,
      "grad_norm": 30.030214309692383,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 45.2344,
      "step": 50
    },
    {
      "epoch": 0.128,
      "grad_norm": 10.043575286865234,
      "learning_rate": 9.900000000000002e-06,
      "loss": 35.5641,
      "step": 100
    },
    {
      "epoch": 0.192,
      "grad_norm": 10.444650650024414,
      "learning_rate": 1.49e-05,
      "loss": 31.4328,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 10.263406753540039,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 28.4483,
      "step": 200
    },
    {
      "epoch": 0.32,
      "grad_norm": 8.500882148742676,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 25.9923,
      "step": 250
    },
    {
      "epoch": 0.384,
      "grad_norm": 6.490056991577148,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 24.0558,
      "step": 300
    },
    {
      "epoch": 0.448,
      "grad_norm": 8.583775520324707,
      "learning_rate": 3.49e-05,
      "loss": 22.5281,
      "step": 350
    },
    {
      "epoch": 0.512,
      "grad_norm": 6.110221862792969,
      "learning_rate": 3.99e-05,
      "loss": 21.284,
      "step": 400
    },
    {
      "epoch": 0.576,
      "grad_norm": 7.118725299835205,
      "learning_rate": 4.49e-05,
      "loss": 20.3992,
      "step": 450
    },
    {
      "epoch": 0.64,
      "grad_norm": 6.870495796203613,
      "learning_rate": 4.99e-05,
      "loss": 19.5314,
      "step": 500
    },
    {
      "epoch": 0.704,
      "grad_norm": 5.8247199058532715,
      "learning_rate": 5e-05,
      "loss": 18.8294,
      "step": 550
    },
    {
      "epoch": 0.768,
      "grad_norm": 5.4395976066589355,
      "learning_rate": 5e-05,
      "loss": 18.1875,
      "step": 600
    },
    {
      "epoch": 0.832,
      "grad_norm": 5.808921813964844,
      "learning_rate": 5e-05,
      "loss": 17.6979,
      "step": 650
    },
    {
      "epoch": 0.896,
      "grad_norm": 6.455477714538574,
      "learning_rate": 5e-05,
      "loss": 17.2457,
      "step": 700
    },
    {
      "epoch": 0.96,
      "grad_norm": 5.533267498016357,
      "learning_rate": 5e-05,
      "loss": 16.8943,
      "step": 750
    },
    {
      "epoch": 1.02304,
      "grad_norm": 5.2249627113342285,
      "learning_rate": 5e-05,
      "loss": 16.3087,
      "step": 800
    },
    {
      "epoch": 1.08704,
      "grad_norm": 6.235313892364502,
      "learning_rate": 5e-05,
      "loss": 16.2019,
      "step": 850
    },
    {
      "epoch": 1.15104,
      "grad_norm": 5.434008598327637,
      "learning_rate": 5e-05,
      "loss": 15.9518,
      "step": 900
    },
    {
      "epoch": 1.2150400000000001,
      "grad_norm": 5.614853382110596,
      "learning_rate": 5e-05,
      "loss": 15.6954,
      "step": 950
    },
    {
      "epoch": 1.27904,
      "grad_norm": 5.3290228843688965,
      "learning_rate": 5e-05,
      "loss": 15.4492,
      "step": 1000
    },
    {
      "epoch": 1.34304,
      "grad_norm": 5.4282002449035645,
      "learning_rate": 5e-05,
      "loss": 15.2972,
      "step": 1050
    },
    {
      "epoch": 1.40704,
      "grad_norm": 5.166767120361328,
      "learning_rate": 5e-05,
      "loss": 15.1285,
      "step": 1100
    },
    {
      "epoch": 1.47104,
      "grad_norm": 5.257447242736816,
      "learning_rate": 5e-05,
      "loss": 14.8849,
      "step": 1150
    },
    {
      "epoch": 1.53504,
      "grad_norm": 5.6656670570373535,
      "learning_rate": 5e-05,
      "loss": 14.8345,
      "step": 1200
    },
    {
      "epoch": 1.59904,
      "grad_norm": 5.475069999694824,
      "learning_rate": 5e-05,
      "loss": 14.7075,
      "step": 1250
    },
    {
      "epoch": 1.66304,
      "grad_norm": 4.779252052307129,
      "learning_rate": 5e-05,
      "loss": 14.5323,
      "step": 1300
    },
    {
      "epoch": 1.7270400000000001,
      "grad_norm": 4.642063617706299,
      "learning_rate": 5e-05,
      "loss": 14.4632,
      "step": 1350
    },
    {
      "epoch": 1.79104,
      "grad_norm": 5.737455368041992,
      "learning_rate": 5e-05,
      "loss": 14.4578,
      "step": 1400
    },
    {
      "epoch": 1.85504,
      "grad_norm": 4.789783477783203,
      "learning_rate": 5e-05,
      "loss": 14.3061,
      "step": 1450
    },
    {
      "epoch": 1.9190399999999999,
      "grad_norm": 5.107880592346191,
      "learning_rate": 5e-05,
      "loss": 14.2063,
      "step": 1500
    },
    {
      "epoch": 1.98304,
      "grad_norm": 4.595057010650635,
      "learning_rate": 5e-05,
      "loss": 14.0943,
      "step": 1550
    },
    {
      "epoch": 2.04608,
      "grad_norm": 5.374480247497559,
      "learning_rate": 5e-05,
      "loss": 13.7554,
      "step": 1600
    },
    {
      "epoch": 2.11008,
      "grad_norm": 4.878725528717041,
      "learning_rate": 5e-05,
      "loss": 13.9512,
      "step": 1650
    },
    {
      "epoch": 2.17408,
      "grad_norm": 4.454578399658203,
      "learning_rate": 5e-05,
      "loss": 13.8451,
      "step": 1700
    },
    {
      "epoch": 2.23808,
      "grad_norm": 4.899575233459473,
      "learning_rate": 5e-05,
      "loss": 13.7621,
      "step": 1750
    },
    {
      "epoch": 2.30208,
      "grad_norm": 5.0458831787109375,
      "learning_rate": 5e-05,
      "loss": 13.7162,
      "step": 1800
    },
    {
      "epoch": 2.36608,
      "grad_norm": 4.963306903839111,
      "learning_rate": 5e-05,
      "loss": 13.6693,
      "step": 1850
    },
    {
      "epoch": 2.4300800000000002,
      "grad_norm": 5.5411601066589355,
      "learning_rate": 5e-05,
      "loss": 13.5797,
      "step": 1900
    },
    {
      "epoch": 2.49408,
      "grad_norm": 5.190772533416748,
      "learning_rate": 5e-05,
      "loss": 13.5055,
      "step": 1950
    },
    {
      "epoch": 2.55808,
      "grad_norm": 5.136147499084473,
      "learning_rate": 5e-05,
      "loss": 13.5095,
      "step": 2000
    },
    {
      "epoch": 2.62208,
      "grad_norm": 4.439064979553223,
      "learning_rate": 5e-05,
      "loss": 13.4366,
      "step": 2050
    },
    {
      "epoch": 2.68608,
      "grad_norm": 5.025708198547363,
      "learning_rate": 5e-05,
      "loss": 13.3976,
      "step": 2100
    },
    {
      "epoch": 2.75008,
      "grad_norm": 4.6007843017578125,
      "learning_rate": 5e-05,
      "loss": 13.365,
      "step": 2150
    },
    {
      "epoch": 2.81408,
      "grad_norm": 5.0573859214782715,
      "learning_rate": 5e-05,
      "loss": 13.389,
      "step": 2200
    },
    {
      "epoch": 2.8780799999999997,
      "grad_norm": 5.002612590789795,
      "learning_rate": 5e-05,
      "loss": 13.3038,
      "step": 2250
    },
    {
      "epoch": 2.94208,
      "grad_norm": 4.932233810424805,
      "learning_rate": 5e-05,
      "loss": 13.2322,
      "step": 2300
    },
    {
      "epoch": 3.00512,
      "grad_norm": 4.270575523376465,
      "learning_rate": 5e-05,
      "loss": 12.9527,
      "step": 2350
    },
    {
      "epoch": 3.06912,
      "grad_norm": 4.515242099761963,
      "learning_rate": 5e-05,
      "loss": 13.0987,
      "step": 2400
    },
    {
      "epoch": 3.13312,
      "grad_norm": 4.7221784591674805,
      "learning_rate": 5e-05,
      "loss": 13.0785,
      "step": 2450
    },
    {
      "epoch": 3.19712,
      "grad_norm": 4.813047409057617,
      "learning_rate": 5e-05,
      "loss": 13.0252,
      "step": 2500
    },
    {
      "epoch": 3.26112,
      "grad_norm": 4.778804779052734,
      "learning_rate": 5e-05,
      "loss": 13.0106,
      "step": 2550
    },
    {
      "epoch": 3.32512,
      "grad_norm": 4.780041694641113,
      "learning_rate": 5e-05,
      "loss": 12.9763,
      "step": 2600
    },
    {
      "epoch": 3.38912,
      "grad_norm": 5.2179741859436035,
      "learning_rate": 5e-05,
      "loss": 12.9663,
      "step": 2650
    },
    {
      "epoch": 3.45312,
      "grad_norm": 4.695342540740967,
      "learning_rate": 5e-05,
      "loss": 12.8774,
      "step": 2700
    },
    {
      "epoch": 3.5171200000000002,
      "grad_norm": 4.264077186584473,
      "learning_rate": 5e-05,
      "loss": 12.8656,
      "step": 2750
    },
    {
      "epoch": 3.58112,
      "grad_norm": 4.794581890106201,
      "learning_rate": 5e-05,
      "loss": 12.8512,
      "step": 2800
    },
    {
      "epoch": 3.64512,
      "grad_norm": 4.6235785484313965,
      "learning_rate": 5e-05,
      "loss": 12.7996,
      "step": 2850
    },
    {
      "epoch": 3.70912,
      "grad_norm": 4.2501959800720215,
      "learning_rate": 5e-05,
      "loss": 12.8353,
      "step": 2900
    },
    {
      "epoch": 3.77312,
      "grad_norm": 4.735867977142334,
      "learning_rate": 5e-05,
      "loss": 12.8402,
      "step": 2950
    },
    {
      "epoch": 3.83712,
      "grad_norm": 4.440035343170166,
      "learning_rate": 5e-05,
      "loss": 12.7597,
      "step": 3000
    },
    {
      "epoch": 3.90112,
      "grad_norm": 4.967970848083496,
      "learning_rate": 5e-05,
      "loss": 12.7294,
      "step": 3050
    },
    {
      "epoch": 3.9651199999999998,
      "grad_norm": 4.764186382293701,
      "learning_rate": 5e-05,
      "loss": 12.6673,
      "step": 3100
    },
    {
      "epoch": 4.02816,
      "grad_norm": 4.685766220092773,
      "learning_rate": 5e-05,
      "loss": 12.5239,
      "step": 3150
    },
    {
      "epoch": 4.09216,
      "grad_norm": 4.735346794128418,
      "learning_rate": 5e-05,
      "loss": 12.6292,
      "step": 3200
    },
    {
      "epoch": 4.15616,
      "grad_norm": 4.99775505065918,
      "learning_rate": 5e-05,
      "loss": 12.5879,
      "step": 3250
    },
    {
      "epoch": 4.22016,
      "grad_norm": 4.544851779937744,
      "learning_rate": 5e-05,
      "loss": 12.5355,
      "step": 3300
    },
    {
      "epoch": 4.28416,
      "grad_norm": 4.653088092803955,
      "learning_rate": 5e-05,
      "loss": 12.5443,
      "step": 3350
    },
    {
      "epoch": 4.34816,
      "grad_norm": 4.788982391357422,
      "learning_rate": 5e-05,
      "loss": 12.5729,
      "step": 3400
    },
    {
      "epoch": 4.41216,
      "grad_norm": 4.569639682769775,
      "learning_rate": 5e-05,
      "loss": 12.4854,
      "step": 3450
    },
    {
      "epoch": 4.47616,
      "grad_norm": 4.246921062469482,
      "learning_rate": 5e-05,
      "loss": 12.4362,
      "step": 3500
    },
    {
      "epoch": 4.54016,
      "grad_norm": 5.053426742553711,
      "learning_rate": 5e-05,
      "loss": 12.4905,
      "step": 3550
    },
    {
      "epoch": 4.60416,
      "grad_norm": 4.5404462814331055,
      "learning_rate": 5e-05,
      "loss": 12.4385,
      "step": 3600
    },
    {
      "epoch": 4.66816,
      "grad_norm": 4.662599086761475,
      "learning_rate": 5e-05,
      "loss": 12.3962,
      "step": 3650
    },
    {
      "epoch": 4.73216,
      "grad_norm": 4.601826190948486,
      "learning_rate": 5e-05,
      "loss": 12.4388,
      "step": 3700
    },
    {
      "epoch": 4.79616,
      "grad_norm": 4.657986164093018,
      "learning_rate": 5e-05,
      "loss": 12.4563,
      "step": 3750
    },
    {
      "epoch": 4.8601600000000005,
      "grad_norm": 4.391824722290039,
      "learning_rate": 5e-05,
      "loss": 12.4336,
      "step": 3800
    },
    {
      "epoch": 4.92416,
      "grad_norm": 4.814956188201904,
      "learning_rate": 5e-05,
      "loss": 12.3431,
      "step": 3850
    },
    {
      "epoch": 4.98816,
      "grad_norm": 4.372463703155518,
      "learning_rate": 5e-05,
      "loss": 12.3271,
      "step": 3900
    },
    {
      "epoch": 5.0512,
      "grad_norm": 4.827542781829834,
      "learning_rate": 5e-05,
      "loss": 12.1285,
      "step": 3950
    },
    {
      "epoch": 5.1152,
      "grad_norm": 4.689800262451172,
      "learning_rate": 5e-05,
      "loss": 12.322,
      "step": 4000
    },
    {
      "epoch": 5.1792,
      "grad_norm": 4.257835865020752,
      "learning_rate": 5e-05,
      "loss": 12.2307,
      "step": 4050
    },
    {
      "epoch": 5.2432,
      "grad_norm": 4.622791290283203,
      "learning_rate": 5e-05,
      "loss": 12.2289,
      "step": 4100
    },
    {
      "epoch": 5.3072,
      "grad_norm": 4.387765407562256,
      "learning_rate": 5e-05,
      "loss": 12.2121,
      "step": 4150
    },
    {
      "epoch": 5.3712,
      "grad_norm": 4.921295166015625,
      "learning_rate": 5e-05,
      "loss": 12.2374,
      "step": 4200
    },
    {
      "epoch": 5.4352,
      "grad_norm": 4.769687652587891,
      "learning_rate": 5e-05,
      "loss": 12.2007,
      "step": 4250
    },
    {
      "epoch": 5.4992,
      "grad_norm": 4.531981468200684,
      "learning_rate": 5e-05,
      "loss": 12.1711,
      "step": 4300
    },
    {
      "epoch": 5.5632,
      "grad_norm": 4.955589294433594,
      "learning_rate": 5e-05,
      "loss": 12.1988,
      "step": 4350
    },
    {
      "epoch": 5.6272,
      "grad_norm": 4.507243633270264,
      "learning_rate": 5e-05,
      "loss": 12.1362,
      "step": 4400
    },
    {
      "epoch": 5.6912,
      "grad_norm": 4.393710613250732,
      "learning_rate": 5e-05,
      "loss": 12.1713,
      "step": 4450
    },
    {
      "epoch": 5.7552,
      "grad_norm": 4.817514896392822,
      "learning_rate": 5e-05,
      "loss": 12.1741,
      "step": 4500
    },
    {
      "epoch": 5.8192,
      "grad_norm": 4.759428024291992,
      "learning_rate": 5e-05,
      "loss": 12.1548,
      "step": 4550
    },
    {
      "epoch": 5.8832,
      "grad_norm": 4.597761154174805,
      "learning_rate": 5e-05,
      "loss": 12.1451,
      "step": 4600
    },
    {
      "epoch": 5.9472000000000005,
      "grad_norm": 4.568916320800781,
      "learning_rate": 5e-05,
      "loss": 12.1225,
      "step": 4650
    },
    {
      "epoch": 6.01024,
      "grad_norm": 4.772891521453857,
      "learning_rate": 5e-05,
      "loss": 11.8941,
      "step": 4700
    },
    {
      "epoch": 6.07424,
      "grad_norm": 4.3502726554870605,
      "learning_rate": 5e-05,
      "loss": 12.0509,
      "step": 4750
    },
    {
      "epoch": 6.13824,
      "grad_norm": 4.469036102294922,
      "learning_rate": 5e-05,
      "loss": 12.0197,
      "step": 4800
    },
    {
      "epoch": 6.20224,
      "grad_norm": 4.737427711486816,
      "learning_rate": 5e-05,
      "loss": 11.9855,
      "step": 4850
    },
    {
      "epoch": 6.26624,
      "grad_norm": 4.228313446044922,
      "learning_rate": 5e-05,
      "loss": 11.9786,
      "step": 4900
    },
    {
      "epoch": 6.33024,
      "grad_norm": 4.898065567016602,
      "learning_rate": 5e-05,
      "loss": 11.9912,
      "step": 4950
    },
    {
      "epoch": 6.39424,
      "grad_norm": 4.382214069366455,
      "learning_rate": 5e-05,
      "loss": 11.9851,
      "step": 5000
    },
    {
      "epoch": 6.45824,
      "grad_norm": 4.450319766998291,
      "learning_rate": 5e-05,
      "loss": 11.9646,
      "step": 5050
    },
    {
      "epoch": 6.52224,
      "grad_norm": 4.843242168426514,
      "learning_rate": 5e-05,
      "loss": 11.9278,
      "step": 5100
    },
    {
      "epoch": 6.58624,
      "grad_norm": 4.468452453613281,
      "learning_rate": 5e-05,
      "loss": 11.9302,
      "step": 5150
    },
    {
      "epoch": 6.65024,
      "grad_norm": 4.9095659255981445,
      "learning_rate": 5e-05,
      "loss": 11.9382,
      "step": 5200
    },
    {
      "epoch": 6.71424,
      "grad_norm": 4.60357666015625,
      "learning_rate": 5e-05,
      "loss": 11.9377,
      "step": 5250
    },
    {
      "epoch": 6.77824,
      "grad_norm": 4.428177833557129,
      "learning_rate": 5e-05,
      "loss": 12.0138,
      "step": 5300
    },
    {
      "epoch": 6.84224,
      "grad_norm": 4.415019989013672,
      "learning_rate": 5e-05,
      "loss": 11.9257,
      "step": 5350
    },
    {
      "epoch": 6.90624,
      "grad_norm": 4.805417537689209,
      "learning_rate": 5e-05,
      "loss": 11.9079,
      "step": 5400
    },
    {
      "epoch": 6.97024,
      "grad_norm": 4.389927387237549,
      "learning_rate": 5e-05,
      "loss": 11.8902,
      "step": 5450
    },
    {
      "epoch": 7.03328,
      "grad_norm": 4.605067729949951,
      "learning_rate": 5e-05,
      "loss": 11.7215,
      "step": 5500
    },
    {
      "epoch": 7.09728,
      "grad_norm": 4.859168529510498,
      "learning_rate": 5e-05,
      "loss": 11.821,
      "step": 5550
    },
    {
      "epoch": 7.16128,
      "grad_norm": 4.175893783569336,
      "learning_rate": 5e-05,
      "loss": 11.8544,
      "step": 5600
    },
    {
      "epoch": 7.22528,
      "grad_norm": 4.370295524597168,
      "learning_rate": 5e-05,
      "loss": 11.7556,
      "step": 5650
    },
    {
      "epoch": 7.28928,
      "grad_norm": 4.433261394500732,
      "learning_rate": 5e-05,
      "loss": 11.8327,
      "step": 5700
    },
    {
      "epoch": 7.35328,
      "grad_norm": 4.436588764190674,
      "learning_rate": 5e-05,
      "loss": 11.8167,
      "step": 5750
    },
    {
      "epoch": 7.41728,
      "grad_norm": 4.90534782409668,
      "learning_rate": 5e-05,
      "loss": 11.7696,
      "step": 5800
    },
    {
      "epoch": 7.48128,
      "grad_norm": 4.609787940979004,
      "learning_rate": 5e-05,
      "loss": 11.7597,
      "step": 5850
    },
    {
      "epoch": 7.54528,
      "grad_norm": 3.9833970069885254,
      "learning_rate": 5e-05,
      "loss": 11.7864,
      "step": 5900
    },
    {
      "epoch": 7.60928,
      "grad_norm": 4.3542585372924805,
      "learning_rate": 5e-05,
      "loss": 11.767,
      "step": 5950
    },
    {
      "epoch": 7.67328,
      "grad_norm": 4.913259029388428,
      "learning_rate": 5e-05,
      "loss": 11.7791,
      "step": 6000
    },
    {
      "epoch": 7.73728,
      "grad_norm": 4.446979999542236,
      "learning_rate": 5e-05,
      "loss": 11.7494,
      "step": 6050
    },
    {
      "epoch": 7.80128,
      "grad_norm": 4.355462074279785,
      "learning_rate": 5e-05,
      "loss": 11.7801,
      "step": 6100
    },
    {
      "epoch": 7.86528,
      "grad_norm": 4.641010284423828,
      "learning_rate": 5e-05,
      "loss": 11.7589,
      "step": 6150
    },
    {
      "epoch": 7.92928,
      "grad_norm": 4.6447248458862305,
      "learning_rate": 5e-05,
      "loss": 11.7506,
      "step": 6200
    },
    {
      "epoch": 7.99328,
      "grad_norm": 4.449138164520264,
      "learning_rate": 5e-05,
      "loss": 11.7076,
      "step": 6250
    },
    {
      "epoch": 8.05632,
      "grad_norm": 4.435295104980469,
      "learning_rate": 5e-05,
      "loss": 11.5159,
      "step": 6300
    },
    {
      "epoch": 8.12032,
      "grad_norm": 4.4568915367126465,
      "learning_rate": 5e-05,
      "loss": 11.6926,
      "step": 6350
    },
    {
      "epoch": 8.18432,
      "grad_norm": 4.2205071449279785,
      "learning_rate": 5e-05,
      "loss": 11.665,
      "step": 6400
    },
    {
      "epoch": 8.24832,
      "grad_norm": 4.864633083343506,
      "learning_rate": 5e-05,
      "loss": 11.6492,
      "step": 6450
    },
    {
      "epoch": 8.31232,
      "grad_norm": 4.315229415893555,
      "learning_rate": 5e-05,
      "loss": 11.6751,
      "step": 6500
    },
    {
      "epoch": 8.37632,
      "grad_norm": 4.400087833404541,
      "learning_rate": 5e-05,
      "loss": 11.6541,
      "step": 6550
    },
    {
      "epoch": 8.44032,
      "grad_norm": 4.432553291320801,
      "learning_rate": 5e-05,
      "loss": 11.5929,
      "step": 6600
    },
    {
      "epoch": 8.50432,
      "grad_norm": 4.299822807312012,
      "learning_rate": 5e-05,
      "loss": 11.6211,
      "step": 6650
    },
    {
      "epoch": 8.56832,
      "grad_norm": 4.2836384773254395,
      "learning_rate": 5e-05,
      "loss": 11.6478,
      "step": 6700
    },
    {
      "epoch": 8.63232,
      "grad_norm": 4.207751750946045,
      "learning_rate": 5e-05,
      "loss": 11.6221,
      "step": 6750
    },
    {
      "epoch": 8.69632,
      "grad_norm": 4.13890266418457,
      "learning_rate": 5e-05,
      "loss": 11.6692,
      "step": 6800
    },
    {
      "epoch": 8.76032,
      "grad_norm": 4.304453372955322,
      "learning_rate": 5e-05,
      "loss": 11.6674,
      "step": 6850
    },
    {
      "epoch": 8.82432,
      "grad_norm": 4.5917158126831055,
      "learning_rate": 5e-05,
      "loss": 11.5839,
      "step": 6900
    },
    {
      "epoch": 8.88832,
      "grad_norm": 4.252579689025879,
      "learning_rate": 5e-05,
      "loss": 11.6418,
      "step": 6950
    },
    {
      "epoch": 8.95232,
      "grad_norm": 4.376040935516357,
      "learning_rate": 5e-05,
      "loss": 11.5668,
      "step": 7000
    },
    {
      "epoch": 9.01536,
      "grad_norm": 4.671627998352051,
      "learning_rate": 5e-05,
      "loss": 11.423,
      "step": 7050
    },
    {
      "epoch": 9.07936,
      "grad_norm": 4.279914379119873,
      "learning_rate": 5e-05,
      "loss": 11.5243,
      "step": 7100
    },
    {
      "epoch": 9.14336,
      "grad_norm": 4.423830032348633,
      "learning_rate": 5e-05,
      "loss": 11.5668,
      "step": 7150
    },
    {
      "epoch": 9.20736,
      "grad_norm": 4.2553510665893555,
      "learning_rate": 5e-05,
      "loss": 11.5078,
      "step": 7200
    },
    {
      "epoch": 9.27136,
      "grad_norm": 4.191752910614014,
      "learning_rate": 5e-05,
      "loss": 11.5188,
      "step": 7250
    },
    {
      "epoch": 9.33536,
      "grad_norm": 4.666179180145264,
      "learning_rate": 5e-05,
      "loss": 11.5491,
      "step": 7300
    },
    {
      "epoch": 9.39936,
      "grad_norm": 4.520998477935791,
      "learning_rate": 5e-05,
      "loss": 11.5122,
      "step": 7350
    },
    {
      "epoch": 9.46336,
      "grad_norm": 4.648169040679932,
      "learning_rate": 5e-05,
      "loss": 11.4606,
      "step": 7400
    },
    {
      "epoch": 9.52736,
      "grad_norm": 4.56096076965332,
      "learning_rate": 5e-05,
      "loss": 11.494,
      "step": 7450
    },
    {
      "epoch": 9.59136,
      "grad_norm": 4.470357418060303,
      "learning_rate": 5e-05,
      "loss": 11.5279,
      "step": 7500
    },
    {
      "epoch": 9.65536,
      "grad_norm": 4.499948978424072,
      "learning_rate": 5e-05,
      "loss": 11.4673,
      "step": 7550
    },
    {
      "epoch": 9.71936,
      "grad_norm": 4.4818267822265625,
      "learning_rate": 5e-05,
      "loss": 11.4931,
      "step": 7600
    },
    {
      "epoch": 9.78336,
      "grad_norm": 4.303125381469727,
      "learning_rate": 5e-05,
      "loss": 11.549,
      "step": 7650
    },
    {
      "epoch": 9.84736,
      "grad_norm": 4.314548969268799,
      "learning_rate": 5e-05,
      "loss": 11.4885,
      "step": 7700
    },
    {
      "epoch": 9.91136,
      "grad_norm": 4.4232096672058105,
      "learning_rate": 5e-05,
      "loss": 11.4826,
      "step": 7750
    },
    {
      "epoch": 9.97536,
      "grad_norm": 4.130805492401123,
      "learning_rate": 5e-05,
      "loss": 11.4844,
      "step": 7800
    },
    {
      "epoch": 10.0384,
      "grad_norm": 4.30977201461792,
      "learning_rate": 5e-05,
      "loss": 11.2989,
      "step": 7850
    },
    {
      "epoch": 10.1024,
      "grad_norm": 4.516940116882324,
      "learning_rate": 5e-05,
      "loss": 11.4604,
      "step": 7900
    },
    {
      "epoch": 10.1664,
      "grad_norm": 4.455264568328857,
      "learning_rate": 5e-05,
      "loss": 11.4321,
      "step": 7950
    },
    {
      "epoch": 10.2304,
      "grad_norm": 4.4683837890625,
      "learning_rate": 5e-05,
      "loss": 11.4184,
      "step": 8000
    },
    {
      "epoch": 10.2944,
      "grad_norm": 4.433289051055908,
      "learning_rate": 5e-05,
      "loss": 11.3861,
      "step": 8050
    },
    {
      "epoch": 10.3584,
      "grad_norm": 4.2703471183776855,
      "learning_rate": 5e-05,
      "loss": 11.4155,
      "step": 8100
    },
    {
      "epoch": 10.4224,
      "grad_norm": 4.401028633117676,
      "learning_rate": 5e-05,
      "loss": 11.413,
      "step": 8150
    },
    {
      "epoch": 10.4864,
      "grad_norm": 4.2924041748046875,
      "learning_rate": 5e-05,
      "loss": 11.358,
      "step": 8200
    },
    {
      "epoch": 10.5504,
      "grad_norm": 4.781132221221924,
      "learning_rate": 5e-05,
      "loss": 11.4427,
      "step": 8250
    },
    {
      "epoch": 10.6144,
      "grad_norm": 4.259821891784668,
      "learning_rate": 5e-05,
      "loss": 11.3798,
      "step": 8300
    },
    {
      "epoch": 10.6784,
      "grad_norm": 4.416878700256348,
      "learning_rate": 5e-05,
      "loss": 11.4045,
      "step": 8350
    },
    {
      "epoch": 10.7424,
      "grad_norm": 4.32927131652832,
      "learning_rate": 5e-05,
      "loss": 11.3996,
      "step": 8400
    },
    {
      "epoch": 10.8064,
      "grad_norm": 4.208673477172852,
      "learning_rate": 5e-05,
      "loss": 11.4286,
      "step": 8450
    },
    {
      "epoch": 10.8704,
      "grad_norm": 4.228538990020752,
      "learning_rate": 5e-05,
      "loss": 11.4395,
      "step": 8500
    },
    {
      "epoch": 10.9344,
      "grad_norm": 4.326662063598633,
      "learning_rate": 5e-05,
      "loss": 11.3725,
      "step": 8550
    },
    {
      "epoch": 10.9984,
      "grad_norm": 4.363870143890381,
      "learning_rate": 5e-05,
      "loss": 11.3425,
      "step": 8600
    },
    {
      "epoch": 11.06144,
      "grad_norm": 4.202701568603516,
      "learning_rate": 5e-05,
      "loss": 11.178,
      "step": 8650
    },
    {
      "epoch": 11.12544,
      "grad_norm": 4.387879371643066,
      "learning_rate": 5e-05,
      "loss": 11.3641,
      "step": 8700
    },
    {
      "epoch": 11.18944,
      "grad_norm": 4.673325538635254,
      "learning_rate": 5e-05,
      "loss": 11.2878,
      "step": 8750
    },
    {
      "epoch": 11.25344,
      "grad_norm": 4.567498683929443,
      "learning_rate": 5e-05,
      "loss": 11.279,
      "step": 8800
    },
    {
      "epoch": 11.31744,
      "grad_norm": 4.406512260437012,
      "learning_rate": 5e-05,
      "loss": 11.3242,
      "step": 8850
    },
    {
      "epoch": 11.38144,
      "grad_norm": 4.452656269073486,
      "learning_rate": 5e-05,
      "loss": 11.2941,
      "step": 8900
    },
    {
      "epoch": 11.44544,
      "grad_norm": 4.4073967933654785,
      "learning_rate": 5e-05,
      "loss": 11.2963,
      "step": 8950
    },
    {
      "epoch": 11.50944,
      "grad_norm": 4.032774448394775,
      "learning_rate": 5e-05,
      "loss": 11.2393,
      "step": 9000
    },
    {
      "epoch": 11.57344,
      "grad_norm": 4.203061580657959,
      "learning_rate": 4.003882537046961e-05,
      "loss": 11.3253,
      "step": 9050
    },
    {
      "epoch": 11.63744,
      "grad_norm": 3.976717710494995,
      "learning_rate": 3.584108054970295e-05,
      "loss": 11.254,
      "step": 9100
    },
    {
      "epoch": 11.70144,
      "grad_norm": 4.107513904571533,
      "learning_rate": 3.2629766840943096e-05,
      "loss": 11.2916,
      "step": 9150
    },
    {
      "epoch": 11.76544,
      "grad_norm": 4.054017066955566,
      "learning_rate": 2.9925762779124083e-05,
      "loss": 11.2804,
      "step": 9200
    },
    {
      "epoch": 11.82944,
      "grad_norm": 4.212456226348877,
      "learning_rate": 2.754504509022563e-05,
      "loss": 11.273,
      "step": 9250
    },
    {
      "epoch": 11.89344,
      "grad_norm": 4.274267196655273,
      "learning_rate": 2.5393598393913832e-05,
      "loss": 11.2994,
      "step": 9300
    },
    {
      "epoch": 11.95744,
      "grad_norm": 4.036962509155273,
      "learning_rate": 2.3415700122064532e-05,
      "loss": 11.2251,
      "step": 9350
    },
    {
      "epoch": 12.02048,
      "grad_norm": 4.221673965454102,
      "learning_rate": 2.157509894476324e-05,
      "loss": 11.0618,
      "step": 9400
    },
    {
      "epoch": 12.08448,
      "grad_norm": 3.9704296588897705,
      "learning_rate": 1.9846641978048286e-05,
      "loss": 11.1525,
      "step": 9450
    },
    {
      "epoch": 12.14848,
      "grad_norm": 4.236766338348389,
      "learning_rate": 1.8212030577591153e-05,
      "loss": 11.1664,
      "step": 9500
    },
    {
      "epoch": 12.21248,
      "grad_norm": 4.454754829406738,
      "learning_rate": 1.665745960488313e-05,
      "loss": 11.1714,
      "step": 9550
    },
    {
      "epoch": 12.27648,
      "grad_norm": 4.187366962432861,
      "learning_rate": 1.5172209372399177e-05,
      "loss": 11.1293,
      "step": 9600
    },
    {
      "epoch": 12.34048,
      "grad_norm": 3.8712446689605713,
      "learning_rate": 1.3747758689978906e-05,
      "loss": 11.1417,
      "step": 9650
    },
    {
      "epoch": 12.40448,
      "grad_norm": 3.7524523735046387,
      "learning_rate": 1.2377201061058736e-05,
      "loss": 11.134,
      "step": 9700
    },
    {
      "epoch": 12.46848,
      "grad_norm": 3.8904426097869873,
      "learning_rate": 1.1054846257846152e-05,
      "loss": 11.0973,
      "step": 9750
    },
    {
      "epoch": 12.53248,
      "grad_norm": 4.037586688995361,
      "learning_rate": 9.775940035844219e-06,
      "loss": 11.0743,
      "step": 9800
    },
    {
      "epoch": 12.59648,
      "grad_norm": 4.056551933288574,
      "learning_rate": 8.536461800758008e-06,
      "loss": 11.1361,
      "step": 9850
    },
    {
      "epoch": 12.66048,
      "grad_norm": 4.02345085144043,
      "learning_rate": 7.332975261919188e-06,
      "loss": 11.1224,
      "step": 9900
    },
    {
      "epoch": 12.72448,
      "grad_norm": 3.7386345863342285,
      "learning_rate": 6.162516039352809e-06,
      "loss": 11.1529,
      "step": 9950
    },
    {
      "epoch": 12.78848,
      "grad_norm": 3.9756412506103516,
      "learning_rate": 5.022505627814258e-06,
      "loss": 11.2208,
      "step": 10000
    },
    {
      "epoch": 12.78848,
      "step": 10000,
      "total_flos": 3.4083642457613926e+17,
      "train_loss": 13.154044556808472,
      "train_runtime": 50106.2685,
      "train_samples_per_second": 25.546,
      "train_steps_per_second": 0.2
    }
  ],
  "logging_steps": 50,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 13,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4083642457613926e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}