{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 4.078213691711426,
      "learning_rate": 0.0002,
      "loss": 7.9129,
      "step": 1
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.97159481048584,
      "learning_rate": 0.00019800000000000002,
      "loss": 7.6134,
      "step": 2
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.7602293491363525,
      "learning_rate": 0.000196,
      "loss": 7.8455,
      "step": 3
    },
    {
      "epoch": 0.04,
      "grad_norm": 4.0464582443237305,
      "learning_rate": 0.000194,
      "loss": 7.8158,
      "step": 4
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.8224234580993652,
      "learning_rate": 0.000192,
      "loss": 7.9859,
      "step": 5
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.202148675918579,
      "learning_rate": 0.00019,
      "loss": 7.5316,
      "step": 6
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.851012706756592,
      "learning_rate": 0.000188,
      "loss": 7.2205,
      "step": 7
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.0483713150024414,
      "learning_rate": 0.00018600000000000002,
      "loss": 7.8461,
      "step": 8
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.13923716545105,
      "learning_rate": 0.00018400000000000003,
      "loss": 7.2227,
      "step": 9
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.680180072784424,
      "learning_rate": 0.000182,
      "loss": 7.4933,
      "step": 10
    },
    {
      "epoch": 0.11,
      "grad_norm": 3.260732650756836,
      "learning_rate": 0.00018,
      "loss": 7.6958,
      "step": 11
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.8471994400024414,
      "learning_rate": 0.00017800000000000002,
      "loss": 7.6344,
      "step": 12
    },
    {
      "epoch": 0.13,
      "grad_norm": 2.6308438777923584,
      "learning_rate": 0.00017600000000000002,
      "loss": 7.4863,
      "step": 13
    },
    {
      "epoch": 0.14,
      "grad_norm": 2.4808456897735596,
      "learning_rate": 0.000174,
      "loss": 7.3214,
      "step": 14
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.461528778076172,
      "learning_rate": 0.000172,
      "loss": 7.1394,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.1280977725982666,
      "learning_rate": 0.00017,
      "loss": 7.043,
      "step": 16
    },
    {
      "epoch": 0.17,
      "grad_norm": 2.5462498664855957,
      "learning_rate": 0.000168,
      "loss": 7.5148,
      "step": 17
    },
    {
      "epoch": 0.18,
      "grad_norm": 2.8547370433807373,
      "learning_rate": 0.000166,
      "loss": 7.4716,
      "step": 18
    },
    {
      "epoch": 0.19,
      "grad_norm": 2.2861642837524414,
      "learning_rate": 0.000164,
      "loss": 7.1729,
      "step": 19
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.3367812633514404,
      "learning_rate": 0.000162,
      "loss": 7.0268,
      "step": 20
    },
    {
      "epoch": 0.21,
      "grad_norm": 2.690157413482666,
      "learning_rate": 0.00016,
      "loss": 7.0476,
      "step": 21
    },
    {
      "epoch": 0.22,
      "grad_norm": 2.565459728240967,
      "learning_rate": 0.00015800000000000002,
      "loss": 7.2141,
      "step": 22
    },
    {
      "epoch": 0.23,
      "grad_norm": 2.4736032485961914,
      "learning_rate": 0.00015600000000000002,
      "loss": 7.0999,
      "step": 23
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.2865843772888184,
      "learning_rate": 0.000154,
      "loss": 6.9753,
      "step": 24
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.2901926040649414,
      "learning_rate": 0.000152,
      "loss": 7.0139,
      "step": 25
    },
    {
      "epoch": 0.26,
      "grad_norm": 2.3267297744750977,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.9557,
      "step": 26
    },
    {
      "epoch": 0.27,
      "grad_norm": 2.325007200241089,
      "learning_rate": 0.000148,
      "loss": 6.8993,
      "step": 27
    },
    {
      "epoch": 0.28,
      "grad_norm": 2.1269795894622803,
      "learning_rate": 0.000146,
      "loss": 7.0971,
      "step": 28
    },
    {
      "epoch": 0.29,
      "grad_norm": 2.5330810546875,
      "learning_rate": 0.000144,
      "loss": 6.6721,
      "step": 29
    },
    {
      "epoch": 0.3,
      "grad_norm": 2.2944796085357666,
      "learning_rate": 0.000142,
      "loss": 6.883,
      "step": 30
    },
    {
      "epoch": 0.31,
      "grad_norm": 2.663357973098755,
      "learning_rate": 0.00014,
      "loss": 6.7511,
      "step": 31
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.83375883102417,
      "learning_rate": 0.000138,
      "loss": 6.9667,
      "step": 32
    },
    {
      "epoch": 0.33,
      "grad_norm": 2.613729476928711,
      "learning_rate": 0.00013600000000000003,
      "loss": 6.5078,
      "step": 33
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.977636456489563,
      "learning_rate": 0.000134,
      "loss": 6.8069,
      "step": 34
    },
    {
      "epoch": 0.35,
      "grad_norm": 2.582000970840454,
      "learning_rate": 0.000132,
      "loss": 7.0432,
      "step": 35
    },
    {
      "epoch": 0.36,
      "grad_norm": 2.213886022567749,
      "learning_rate": 0.00013000000000000002,
      "loss": 6.7972,
      "step": 36
    },
    {
      "epoch": 0.37,
      "grad_norm": 2.0590531826019287,
      "learning_rate": 0.00012800000000000002,
      "loss": 6.8204,
      "step": 37
    },
    {
      "epoch": 0.38,
      "grad_norm": 2.1140480041503906,
      "learning_rate": 0.000126,
      "loss": 7.0744,
      "step": 38
    },
    {
      "epoch": 0.39,
      "grad_norm": 2.0761420726776123,
      "learning_rate": 0.000124,
      "loss": 6.8748,
      "step": 39
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.073491096496582,
      "learning_rate": 0.000122,
      "loss": 6.7299,
      "step": 40
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.8805994987487793,
      "learning_rate": 0.00012,
      "loss": 6.9304,
      "step": 41
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.9433634281158447,
      "learning_rate": 0.000118,
      "loss": 6.8906,
      "step": 42
    },
    {
      "epoch": 0.43,
      "grad_norm": 2.2443718910217285,
      "learning_rate": 0.000116,
      "loss": 7.0239,
      "step": 43
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.9340946674346924,
      "learning_rate": 0.00011399999999999999,
      "loss": 6.9923,
      "step": 44
    },
    {
      "epoch": 0.45,
      "grad_norm": 2.704198122024536,
      "learning_rate": 0.00011200000000000001,
      "loss": 6.5122,
      "step": 45
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.9237380027770996,
      "learning_rate": 0.00011000000000000002,
      "loss": 6.5666,
      "step": 46
    },
    {
      "epoch": 0.47,
      "grad_norm": 2.3720009326934814,
      "learning_rate": 0.00010800000000000001,
      "loss": 6.3787,
      "step": 47
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.01981782913208,
      "learning_rate": 0.00010600000000000002,
      "loss": 6.7743,
      "step": 48
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.8788270950317383,
      "learning_rate": 0.00010400000000000001,
      "loss": 6.8256,
      "step": 49
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.6647967100143433,
      "learning_rate": 0.00010200000000000001,
      "loss": 6.7689,
      "step": 50
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.0098962783813477,
      "learning_rate": 0.0001,
      "loss": 6.8299,
      "step": 51
    },
    {
      "epoch": 0.52,
      "grad_norm": 2.0713934898376465,
      "learning_rate": 9.8e-05,
      "loss": 6.7025,
      "step": 52
    },
    {
      "epoch": 0.53,
      "grad_norm": 2.398433208465576,
      "learning_rate": 9.6e-05,
      "loss": 6.7398,
      "step": 53
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.6726354360580444,
      "learning_rate": 9.4e-05,
      "loss": 6.5412,
      "step": 54
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.8346298933029175,
      "learning_rate": 9.200000000000001e-05,
      "loss": 6.7592,
      "step": 55
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.9056272506713867,
      "learning_rate": 9e-05,
      "loss": 6.6956,
      "step": 56
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.801260232925415,
      "learning_rate": 8.800000000000001e-05,
      "loss": 6.5269,
      "step": 57
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.8898510932922363,
      "learning_rate": 8.6e-05,
      "loss": 6.7459,
      "step": 58
    },
    {
      "epoch": 0.59,
      "grad_norm": 2.074327230453491,
      "learning_rate": 8.4e-05,
      "loss": 6.7297,
      "step": 59
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8296312093734741,
      "learning_rate": 8.2e-05,
      "loss": 6.5726,
      "step": 60
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.098116636276245,
      "learning_rate": 8e-05,
      "loss": 6.8952,
      "step": 61
    },
    {
      "epoch": 0.62,
      "grad_norm": 2.026061534881592,
      "learning_rate": 7.800000000000001e-05,
      "loss": 6.4499,
      "step": 62
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.9384962320327759,
      "learning_rate": 7.6e-05,
      "loss": 6.6644,
      "step": 63
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.031684160232544,
      "learning_rate": 7.4e-05,
      "loss": 6.5497,
      "step": 64
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.384727716445923,
      "learning_rate": 7.2e-05,
      "loss": 6.7444,
      "step": 65
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.8046963214874268,
      "learning_rate": 7e-05,
      "loss": 6.732,
      "step": 66
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.729483962059021,
      "learning_rate": 6.800000000000001e-05,
      "loss": 6.7472,
      "step": 67
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.7570774555206299,
      "learning_rate": 6.6e-05,
      "loss": 6.8116,
      "step": 68
    },
    {
      "epoch": 0.69,
      "grad_norm": 2.2705280780792236,
      "learning_rate": 6.400000000000001e-05,
      "loss": 6.5579,
      "step": 69
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.9317717552185059,
      "learning_rate": 6.2e-05,
      "loss": 6.5143,
      "step": 70
    },
    {
      "epoch": 0.71,
      "grad_norm": 2.614461660385132,
      "learning_rate": 6e-05,
      "loss": 7.002,
      "step": 71
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.696247935295105,
      "learning_rate": 5.8e-05,
      "loss": 6.6007,
      "step": 72
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.7958284616470337,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 6.7074,
      "step": 73
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.9168063402175903,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 6.4209,
      "step": 74
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.9771013259887695,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 6.5363,
      "step": 75
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.7233262062072754,
      "learning_rate": 5e-05,
      "loss": 6.59,
      "step": 76
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.9168037176132202,
      "learning_rate": 4.8e-05,
      "loss": 6.3178,
      "step": 77
    },
    {
      "epoch": 0.78,
      "grad_norm": 2.4024784564971924,
      "learning_rate": 4.600000000000001e-05,
      "loss": 6.5254,
      "step": 78
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.8796895742416382,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 6.4418,
      "step": 79
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.9695855379104614,
      "learning_rate": 4.2e-05,
      "loss": 6.559,
      "step": 80
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.81187903881073,
      "learning_rate": 4e-05,
      "loss": 6.7848,
      "step": 81
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.9385106563568115,
      "learning_rate": 3.8e-05,
      "loss": 6.7478,
      "step": 82
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.6835720539093018,
      "learning_rate": 3.6e-05,
      "loss": 6.6711,
      "step": 83
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.6492624282836914,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 6.3784,
      "step": 84
    },
    {
      "epoch": 0.85,
      "grad_norm": 2.062317132949829,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 6.8674,
      "step": 85
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.8025001287460327,
      "learning_rate": 3e-05,
      "loss": 6.7674,
      "step": 86
    },
    {
      "epoch": 0.87,
      "grad_norm": 2.0063161849975586,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 6.6614,
      "step": 87
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.8531196117401123,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 6.5318,
      "step": 88
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.6739861965179443,
      "learning_rate": 2.4e-05,
      "loss": 6.4156,
      "step": 89
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.7740029096603394,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 6.3604,
      "step": 90
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.8241342306137085,
      "learning_rate": 2e-05,
      "loss": 6.5298,
      "step": 91
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.9504824876785278,
      "learning_rate": 1.8e-05,
      "loss": 6.4742,
      "step": 92
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.7933169603347778,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 6.6833,
      "step": 93
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.8611327409744263,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 6.7714,
      "step": 94
    },
    {
      "epoch": 0.95,
      "grad_norm": 4.733095645904541,
      "learning_rate": 1.2e-05,
      "loss": 6.3956,
      "step": 95
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.52779483795166,
      "learning_rate": 1e-05,
      "loss": 6.2473,
      "step": 96
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.936763882637024,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.4085,
      "step": 97
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.458106517791748,
      "learning_rate": 6e-06,
      "loss": 6.4266,
      "step": 98
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.7914412021636963,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.288,
      "step": 99
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7982107400894165,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 6.6815,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1385791608576.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}