{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 69.39678453228684,
      "learning_rate": 0.0,
      "loss": 1.3331,
      "step": 1
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 67.38445293131373,
      "learning_rate": 6.666666666666667e-07,
      "loss": 1.3643,
      "step": 2
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 75.47532102004956,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.5724,
      "step": 3
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 88.43266413230059,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.6266,
      "step": 4
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 66.45735433388617,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.2792,
      "step": 5
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 61.241729619029876,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.4816,
      "step": 6
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 10.626273805566337,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3891,
      "step": 7
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 11.032016541103701,
      "learning_rate": 4.666666666666667e-06,
      "loss": 1.3277,
      "step": 8
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 5.963070703878128,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.2359,
      "step": 9
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 5.9867830825436235,
      "learning_rate": 6e-06,
      "loss": 1.2556,
      "step": 10
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 5.011550731011978,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.2716,
      "step": 11
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3.119689148793926,
      "learning_rate": 7.333333333333333e-06,
      "loss": 1.0509,
      "step": 12
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 2.2486859393512884,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0621,
      "step": 13
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.957333617490225,
      "learning_rate": 8.666666666666668e-06,
      "loss": 1.0376,
      "step": 14
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.5927107620763485,
      "learning_rate": 9.333333333333334e-06,
      "loss": 1.0835,
      "step": 15
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.413595616015281,
      "learning_rate": 1e-05,
      "loss": 1.0093,
      "step": 16
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 1.7152584076806776,
      "learning_rate": 9.999661540018812e-06,
      "loss": 1.1138,
      "step": 17
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.263855919335494,
      "learning_rate": 9.99864620589731e-06,
      "loss": 0.9737,
      "step": 18
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.047848774505768,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.9921,
      "step": 19
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.8887062238237249,
      "learning_rate": 9.994585556692624e-06,
      "loss": 1.0203,
      "step": 20
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.8425520202008281,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.9464,
      "step": 21
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.8680785364483358,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.8086,
      "step": 22
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 0.8497370461821104,
      "learning_rate": 9.98342444022253e-06,
      "loss": 0.9445,
      "step": 23
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.7848403971451252,
      "learning_rate": 9.978353953249023e-06,
      "loss": 0.8393,
      "step": 24
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.7597746715658343,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.9696,
      "step": 25
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.7757103740660095,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.933,
      "step": 26
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.7213051350341784,
      "learning_rate": 9.959101757706308e-06,
      "loss": 0.8427,
      "step": 27
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.7079728637936245,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.9152,
      "step": 28
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 0.6211768276119314,
      "learning_rate": 9.942908597485558e-06,
      "loss": 0.9322,
      "step": 29
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5522226534532197,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.813,
      "step": 30
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 0.5630006106015307,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.8706,
      "step": 31
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.5352757347740947,
      "learning_rate": 9.913603233532067e-06,
      "loss": 0.7991,
      "step": 32
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.673310596153775,
      "learning_rate": 9.902502478779897e-06,
      "loss": 0.8998,
      "step": 33
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.5963616670991083,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.9978,
      "step": 34
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.5319897525225635,
      "learning_rate": 9.878311400921072e-06,
      "loss": 0.8363,
      "step": 35
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.5184635787874254,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.8537,
      "step": 36
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 0.5735639478428182,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8904,
      "step": 37
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.593750559378217,
      "learning_rate": 9.83707609731432e-06,
      "loss": 0.9007,
      "step": 38
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.6152374747553514,
      "learning_rate": 9.822018700574696e-06,
      "loss": 0.9218,
      "step": 39
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.5038903863782735,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8847,
      "step": 40
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 0.552343181392342,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.8914,
      "step": 41
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.5082716376107524,
      "learning_rate": 9.77293816123866e-06,
      "loss": 0.8235,
      "step": 42
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 0.5375428052966806,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8565,
      "step": 43
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.5032705712745359,
      "learning_rate": 9.736983212571646e-06,
      "loss": 0.7708,
      "step": 44
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.5135414965386772,
      "learning_rate": 9.718042531967918e-06,
      "loss": 0.8892,
      "step": 45
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.5633975111716812,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8632,
      "step": 46
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 0.5688397873746105,
      "learning_rate": 9.678247579197658e-06,
      "loss": 0.8725,
      "step": 47
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.4837668112332736,
      "learning_rate": 9.657398694630713e-06,
      "loss": 0.8518,
      "step": 48
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 0.5432246392160757,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.9468,
      "step": 49
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.4577395130749343,
      "learning_rate": 9.613812221777212e-06,
      "loss": 0.6808,
      "step": 50
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.553508289659992,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.9131,
      "step": 51
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.5685339741146429,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8839,
      "step": 52
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 0.45501841733607706,
      "learning_rate": 9.543755644867823e-06,
      "loss": 0.8332,
      "step": 53
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.5890488116966353,
      "learning_rate": 9.519168849742603e-06,
      "loss": 0.7853,
      "step": 54
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.5568914271970364,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8263,
      "step": 55
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.477804022916267,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.8375,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5256821529934272,
      "learning_rate": 9.441751253965022e-06,
      "loss": 0.7701,
      "step": 57
    }
  ],
  "logging_steps": 1,
  "max_steps": 285,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 13124895178752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}