{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 1.2292424440383911,
      "learning_rate": 9.949748743718594e-05,
      "loss": 2.6316,
      "step": 100
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.361342191696167,
      "learning_rate": 9.84924623115578e-05,
      "loss": 1.9567,
      "step": 200
    },
    {
      "epoch": 0.048,
      "grad_norm": 1.3794206380844116,
      "learning_rate": 9.748743718592965e-05,
      "loss": 1.8415,
      "step": 300
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.2263352870941162,
      "learning_rate": 9.64824120603015e-05,
      "loss": 1.8072,
      "step": 400
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.1767858266830444,
      "learning_rate": 9.547738693467337e-05,
      "loss": 1.7898,
      "step": 500
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.173898696899414,
      "learning_rate": 9.447236180904523e-05,
      "loss": 1.7314,
      "step": 600
    },
    {
      "epoch": 0.112,
      "grad_norm": 1.2088936567306519,
      "learning_rate": 9.34673366834171e-05,
      "loss": 1.7011,
      "step": 700
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.9866878986358643,
      "learning_rate": 9.246231155778895e-05,
      "loss": 1.6663,
      "step": 800
    },
    {
      "epoch": 0.144,
      "grad_norm": 1.2384347915649414,
      "learning_rate": 9.14572864321608e-05,
      "loss": 1.6507,
      "step": 900
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.065297245979309,
      "learning_rate": 9.045226130653267e-05,
      "loss": 1.6705,
      "step": 1000
    },
    {
      "epoch": 0.176,
      "grad_norm": 1.1226449012756348,
      "learning_rate": 8.944723618090453e-05,
      "loss": 1.6577,
      "step": 1100
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.9142518639564514,
      "learning_rate": 8.84422110552764e-05,
      "loss": 1.612,
      "step": 1200
    },
    {
      "epoch": 0.208,
      "grad_norm": 1.1804460287094116,
      "learning_rate": 8.743718592964825e-05,
      "loss": 1.6083,
      "step": 1300
    },
    {
      "epoch": 0.224,
      "grad_norm": 1.1100006103515625,
      "learning_rate": 8.64321608040201e-05,
      "loss": 1.6242,
      "step": 1400
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.1566694974899292,
      "learning_rate": 8.542713567839196e-05,
      "loss": 1.6111,
      "step": 1500
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.094859004020691,
      "learning_rate": 8.442211055276383e-05,
      "loss": 1.5816,
      "step": 1600
    },
    {
      "epoch": 0.272,
      "grad_norm": 1.2286021709442139,
      "learning_rate": 8.341708542713568e-05,
      "loss": 1.578,
      "step": 1700
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.0682488679885864,
      "learning_rate": 8.241206030150754e-05,
      "loss": 1.5795,
      "step": 1800
    },
    {
      "epoch": 0.304,
      "grad_norm": 1.1403608322143555,
      "learning_rate": 8.14070351758794e-05,
      "loss": 1.5676,
      "step": 1900
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0942330360412598,
      "learning_rate": 8.040201005025126e-05,
      "loss": 1.5749,
      "step": 2000
    },
    {
      "epoch": 0.336,
      "grad_norm": 1.060088872909546,
      "learning_rate": 7.939698492462313e-05,
      "loss": 1.5184,
      "step": 2100
    },
    {
      "epoch": 0.352,
      "grad_norm": 1.085312008857727,
      "learning_rate": 7.839195979899498e-05,
      "loss": 1.5339,
      "step": 2200
    },
    {
      "epoch": 0.368,
      "grad_norm": 1.303536295890808,
      "learning_rate": 7.738693467336684e-05,
      "loss": 1.515,
      "step": 2300
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.9337490797042847,
      "learning_rate": 7.638190954773869e-05,
      "loss": 1.5243,
      "step": 2400
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2959569692611694,
      "learning_rate": 7.537688442211056e-05,
      "loss": 1.4846,
      "step": 2500
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.1419408321380615,
      "learning_rate": 7.437185929648241e-05,
      "loss": 1.5158,
      "step": 2600
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.9983295202255249,
      "learning_rate": 7.336683417085427e-05,
      "loss": 1.4873,
      "step": 2700
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.1773889064788818,
      "learning_rate": 7.236180904522614e-05,
      "loss": 1.4894,
      "step": 2800
    },
    {
      "epoch": 0.464,
      "grad_norm": 1.2258810997009277,
      "learning_rate": 7.135678391959799e-05,
      "loss": 1.5015,
      "step": 2900
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1287764310836792,
      "learning_rate": 7.035175879396985e-05,
      "loss": 1.5166,
      "step": 3000
    },
    {
      "epoch": 0.496,
      "grad_norm": 1.1293085813522339,
      "learning_rate": 6.93467336683417e-05,
      "loss": 1.5117,
      "step": 3100
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.0602566003799438,
      "learning_rate": 6.834170854271357e-05,
      "loss": 1.455,
      "step": 3200
    },
    {
      "epoch": 0.528,
      "grad_norm": 1.2482367753982544,
      "learning_rate": 6.733668341708544e-05,
      "loss": 1.4356,
      "step": 3300
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.35064697265625,
      "learning_rate": 6.633165829145729e-05,
      "loss": 1.4528,
      "step": 3400
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.065523386001587,
      "learning_rate": 6.532663316582915e-05,
      "loss": 1.4706,
      "step": 3500
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.4030505418777466,
      "learning_rate": 6.4321608040201e-05,
      "loss": 1.4325,
      "step": 3600
    },
    {
      "epoch": 0.592,
      "grad_norm": 1.1023573875427246,
      "learning_rate": 6.331658291457287e-05,
      "loss": 1.455,
      "step": 3700
    },
    {
      "epoch": 0.608,
      "grad_norm": 1.179084062576294,
      "learning_rate": 6.231155778894473e-05,
      "loss": 1.4552,
      "step": 3800
    },
    {
      "epoch": 0.624,
      "grad_norm": 1.0885223150253296,
      "learning_rate": 6.130653266331658e-05,
      "loss": 1.4178,
      "step": 3900
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3725833892822266,
      "learning_rate": 6.030150753768844e-05,
      "loss": 1.456,
      "step": 4000
    },
    {
      "epoch": 0.656,
      "grad_norm": 1.1671427488327026,
      "learning_rate": 5.929648241206031e-05,
      "loss": 1.4552,
      "step": 4100
    },
    {
      "epoch": 0.672,
      "grad_norm": 1.0521718263626099,
      "learning_rate": 5.829145728643216e-05,
      "loss": 1.4236,
      "step": 4200
    },
    {
      "epoch": 0.688,
      "grad_norm": 1.1262151002883911,
      "learning_rate": 5.728643216080403e-05,
      "loss": 1.456,
      "step": 4300
    },
    {
      "epoch": 0.704,
      "grad_norm": 1.090331792831421,
      "learning_rate": 5.628140703517588e-05,
      "loss": 1.4021,
      "step": 4400
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1581507921218872,
      "learning_rate": 5.527638190954774e-05,
      "loss": 1.4708,
      "step": 4500
    },
    {
      "epoch": 0.736,
      "grad_norm": 1.1916351318359375,
      "learning_rate": 5.4271356783919604e-05,
      "loss": 1.4283,
      "step": 4600
    },
    {
      "epoch": 0.752,
      "grad_norm": 1.2623261213302612,
      "learning_rate": 5.3266331658291455e-05,
      "loss": 1.4593,
      "step": 4700
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.2002214193344116,
      "learning_rate": 5.226130653266332e-05,
      "loss": 1.4387,
      "step": 4800
    },
    {
      "epoch": 0.784,
      "grad_norm": 1.0627392530441284,
      "learning_rate": 5.125628140703518e-05,
      "loss": 1.4313,
      "step": 4900
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.2739390134811401,
      "learning_rate": 5.0251256281407036e-05,
      "loss": 1.4024,
      "step": 5000
    },
    {
      "epoch": 0.816,
      "grad_norm": 1.3108317852020264,
      "learning_rate": 4.92462311557789e-05,
      "loss": 1.4385,
      "step": 5100
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.4682525396347046,
      "learning_rate": 4.824120603015075e-05,
      "loss": 1.4015,
      "step": 5200
    },
    {
      "epoch": 0.848,
      "grad_norm": 1.301832675933838,
      "learning_rate": 4.723618090452262e-05,
      "loss": 1.3995,
      "step": 5300
    },
    {
      "epoch": 0.864,
      "grad_norm": 1.3100578784942627,
      "learning_rate": 4.6231155778894475e-05,
      "loss": 1.4203,
      "step": 5400
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.2472883462905884,
      "learning_rate": 4.522613065326633e-05,
      "loss": 1.3984,
      "step": 5500
    },
    {
      "epoch": 0.896,
      "grad_norm": 1.1501699686050415,
      "learning_rate": 4.42211055276382e-05,
      "loss": 1.4177,
      "step": 5600
    },
    {
      "epoch": 0.912,
      "grad_norm": 1.306634783744812,
      "learning_rate": 4.321608040201005e-05,
      "loss": 1.4013,
      "step": 5700
    },
    {
      "epoch": 0.928,
      "grad_norm": 1.199546217918396,
      "learning_rate": 4.2211055276381914e-05,
      "loss": 1.3998,
      "step": 5800
    },
    {
      "epoch": 0.944,
      "grad_norm": 1.4669443368911743,
      "learning_rate": 4.120603015075377e-05,
      "loss": 1.3858,
      "step": 5900
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.1618568897247314,
      "learning_rate": 4.020100502512563e-05,
      "loss": 1.3952,
      "step": 6000
    },
    {
      "epoch": 0.976,
      "grad_norm": 1.3658894300460815,
      "learning_rate": 3.919597989949749e-05,
      "loss": 1.34,
      "step": 6100
    },
    {
      "epoch": 0.992,
      "grad_norm": 1.1548917293548584,
      "learning_rate": 3.8190954773869346e-05,
      "loss": 1.3753,
      "step": 6200
    },
    {
      "epoch": 1.008,
      "grad_norm": 1.250981092453003,
      "learning_rate": 3.7185929648241204e-05,
      "loss": 1.363,
      "step": 6300
    },
    {
      "epoch": 1.024,
      "grad_norm": 1.1988142728805542,
      "learning_rate": 3.618090452261307e-05,
      "loss": 1.2739,
      "step": 6400
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.3094350099563599,
      "learning_rate": 3.517587939698493e-05,
      "loss": 1.3268,
      "step": 6500
    },
    {
      "epoch": 1.056,
      "grad_norm": 1.4513778686523438,
      "learning_rate": 3.4170854271356785e-05,
      "loss": 1.3114,
      "step": 6600
    },
    {
      "epoch": 1.072,
      "grad_norm": 1.2981783151626587,
      "learning_rate": 3.3165829145728643e-05,
      "loss": 1.2866,
      "step": 6700
    },
    {
      "epoch": 1.088,
      "grad_norm": 1.350372314453125,
      "learning_rate": 3.21608040201005e-05,
      "loss": 1.2909,
      "step": 6800
    },
    {
      "epoch": 1.104,
      "grad_norm": 1.1077184677124023,
      "learning_rate": 3.1155778894472366e-05,
      "loss": 1.2278,
      "step": 6900
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.3056607246398926,
      "learning_rate": 3.015075376884422e-05,
      "loss": 1.2573,
      "step": 7000
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 1.38368558883667,
      "learning_rate": 2.914572864321608e-05,
      "loss": 1.3041,
      "step": 7100
    },
    {
      "epoch": 1.152,
      "grad_norm": 1.7526077032089233,
      "learning_rate": 2.814070351758794e-05,
      "loss": 1.3056,
      "step": 7200
    },
    {
      "epoch": 1.168,
      "grad_norm": 1.1916877031326294,
      "learning_rate": 2.7135678391959802e-05,
      "loss": 1.2359,
      "step": 7300
    },
    {
      "epoch": 1.184,
      "grad_norm": 1.326968789100647,
      "learning_rate": 2.613065326633166e-05,
      "loss": 1.2529,
      "step": 7400
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.502866506576538,
      "learning_rate": 2.5125628140703518e-05,
      "loss": 1.3043,
      "step": 7500
    },
    {
      "epoch": 1.216,
      "grad_norm": 1.7037489414215088,
      "learning_rate": 2.4120603015075376e-05,
      "loss": 1.3254,
      "step": 7600
    },
    {
      "epoch": 1.232,
      "grad_norm": 1.3369475603103638,
      "learning_rate": 2.3115577889447238e-05,
      "loss": 1.3274,
      "step": 7700
    },
    {
      "epoch": 1.248,
      "grad_norm": 1.3407210111618042,
      "learning_rate": 2.21105527638191e-05,
      "loss": 1.2879,
      "step": 7800
    },
    {
      "epoch": 1.264,
      "grad_norm": 1.5996978282928467,
      "learning_rate": 2.1105527638190957e-05,
      "loss": 1.2853,
      "step": 7900
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.3061344623565674,
      "learning_rate": 2.0100502512562815e-05,
      "loss": 1.274,
      "step": 8000
    },
    {
      "epoch": 1.296,
      "grad_norm": 1.335577130317688,
      "learning_rate": 1.9105527638190956e-05,
      "loss": 1.2482,
      "step": 8100
    },
    {
      "epoch": 1.312,
      "grad_norm": 1.632110834121704,
      "learning_rate": 1.8100502512562814e-05,
      "loss": 1.2849,
      "step": 8200
    },
    {
      "epoch": 1.328,
      "grad_norm": 1.457372784614563,
      "learning_rate": 1.7095477386934675e-05,
      "loss": 1.27,
      "step": 8300
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 1.3104965686798096,
      "learning_rate": 1.6090452261306533e-05,
      "loss": 1.2698,
      "step": 8400
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.350401520729065,
      "learning_rate": 1.5085427135678393e-05,
      "loss": 1.2337,
      "step": 8500
    },
    {
      "epoch": 1.376,
      "grad_norm": 1.3079415559768677,
      "learning_rate": 1.4080402010050253e-05,
      "loss": 1.2904,
      "step": 8600
    },
    {
      "epoch": 1.392,
      "grad_norm": 1.3506203889846802,
      "learning_rate": 1.3075376884422111e-05,
      "loss": 1.2847,
      "step": 8700
    },
    {
      "epoch": 1.408,
      "grad_norm": 1.4178451299667358,
      "learning_rate": 1.2070351758793969e-05,
      "loss": 1.2713,
      "step": 8800
    },
    {
      "epoch": 1.424,
      "grad_norm": 1.2672168016433716,
      "learning_rate": 1.106532663316583e-05,
      "loss": 1.2634,
      "step": 8900
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.4467307329177856,
      "learning_rate": 1.0070351758793971e-05,
      "loss": 1.2868,
      "step": 9000
    },
    {
      "epoch": 1.456,
      "grad_norm": 1.5032036304473877,
      "learning_rate": 9.06532663316583e-06,
      "loss": 1.2323,
      "step": 9100
    },
    {
      "epoch": 1.472,
      "grad_norm": 1.1872940063476562,
      "learning_rate": 8.060301507537689e-06,
      "loss": 1.2868,
      "step": 9200
    },
    {
      "epoch": 1.488,
      "grad_norm": 1.6626771688461304,
      "learning_rate": 7.055276381909548e-06,
      "loss": 1.27,
      "step": 9300
    },
    {
      "epoch": 1.504,
      "grad_norm": 1.3130452632904053,
      "learning_rate": 6.050251256281407e-06,
      "loss": 1.2542,
      "step": 9400
    },
    {
      "epoch": 1.52,
      "grad_norm": 1.4746296405792236,
      "learning_rate": 5.045226130653267e-06,
      "loss": 1.257,
      "step": 9500
    },
    {
      "epoch": 1.536,
      "grad_norm": 1.3648103475570679,
      "learning_rate": 4.0402010050251256e-06,
      "loss": 1.2487,
      "step": 9600
    },
    {
      "epoch": 1.552,
      "grad_norm": 1.3191380500793457,
      "learning_rate": 3.035175879396985e-06,
      "loss": 1.2557,
      "step": 9700
    },
    {
      "epoch": 1.568,
      "grad_norm": 1.806413173675537,
      "learning_rate": 2.0301507537688442e-06,
      "loss": 1.2323,
      "step": 9800
    },
    {
      "epoch": 1.584,
      "grad_norm": 1.6092606782913208,
      "learning_rate": 1.0251256281407035e-06,
      "loss": 1.2321,
      "step": 9900
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.3367202281951904,
      "learning_rate": 2.0100502512562817e-08,
      "loss": 1.2361,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.995709021001564e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}