{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 21930,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11399908800729594,
      "grad_norm": 1.4812531471252441,
      "learning_rate": 1.9544915640674875e-05,
      "loss": 0.1287,
      "step": 500
    },
    {
      "epoch": 0.22799817601459188,
      "grad_norm": 2.198870897293091,
      "learning_rate": 1.9088919288645692e-05,
      "loss": 0.1045,
      "step": 1000
    },
    {
      "epoch": 0.34199726402188785,
      "grad_norm": 1.3517733812332153,
      "learning_rate": 1.863292293661651e-05,
      "loss": 0.0895,
      "step": 1500
    },
    {
      "epoch": 0.45599635202918376,
      "grad_norm": 1.352580189704895,
      "learning_rate": 1.8176926584587324e-05,
      "loss": 0.0766,
      "step": 2000
    },
    {
      "epoch": 0.5699954400364797,
      "grad_norm": 1.960016131401062,
      "learning_rate": 1.772093023255814e-05,
      "loss": 0.0713,
      "step": 2500
    },
    {
      "epoch": 0.6839945280437757,
      "grad_norm": 0.5876455903053284,
      "learning_rate": 1.7264933880528958e-05,
      "loss": 0.0657,
      "step": 3000
    },
    {
      "epoch": 0.7979936160510716,
      "grad_norm": 0.9299254417419434,
      "learning_rate": 1.6808937528499772e-05,
      "loss": 0.0623,
      "step": 3500
    },
    {
      "epoch": 0.9119927040583675,
      "grad_norm": 1.3892526626586914,
      "learning_rate": 1.635294117647059e-05,
      "loss": 0.0621,
      "step": 4000
    },
    {
      "epoch": 1.0259917920656634,
      "grad_norm": 1.7030184268951416,
      "learning_rate": 1.5896944824441403e-05,
      "loss": 0.0585,
      "step": 4500
    },
    {
      "epoch": 1.1399908800729595,
      "grad_norm": 0.9616603255271912,
      "learning_rate": 1.5440948472412224e-05,
      "loss": 0.0448,
      "step": 5000
    },
    {
      "epoch": 1.2539899680802553,
      "grad_norm": 1.245125412940979,
      "learning_rate": 1.4984952120383038e-05,
      "loss": 0.0429,
      "step": 5500
    },
    {
      "epoch": 1.3679890560875512,
      "grad_norm": 1.2846943140029907,
      "learning_rate": 1.4528955768353854e-05,
      "loss": 0.0408,
      "step": 6000
    },
    {
      "epoch": 1.4819881440948472,
      "grad_norm": 1.0010948181152344,
      "learning_rate": 1.407295941632467e-05,
      "loss": 0.0386,
      "step": 6500
    },
    {
      "epoch": 1.5959872321021433,
      "grad_norm": 1.1298205852508545,
      "learning_rate": 1.3616963064295488e-05,
      "loss": 0.0364,
      "step": 7000
    },
    {
      "epoch": 1.7099863201094392,
      "grad_norm": 0.5932161211967468,
      "learning_rate": 1.3160966712266304e-05,
      "loss": 0.0344,
      "step": 7500
    },
    {
      "epoch": 1.823985408116735,
      "grad_norm": 1.195202112197876,
      "learning_rate": 1.270497036023712e-05,
      "loss": 0.033,
      "step": 8000
    },
    {
      "epoch": 1.937984496124031,
      "grad_norm": 1.2507325410842896,
      "learning_rate": 1.2248974008207935e-05,
      "loss": 0.0321,
      "step": 8500
    },
    {
      "epoch": 2.0519835841313268,
      "grad_norm": 2.5148258209228516,
      "learning_rate": 1.1792977656178753e-05,
      "loss": 0.0278,
      "step": 9000
    },
    {
      "epoch": 2.165982672138623,
      "grad_norm": 0.7329283356666565,
      "learning_rate": 1.1336981304149568e-05,
      "loss": 0.0233,
      "step": 9500
    },
    {
      "epoch": 2.279981760145919,
      "grad_norm": 0.42915332317352295,
      "learning_rate": 1.0880984952120384e-05,
      "loss": 0.0226,
      "step": 10000
    },
    {
      "epoch": 2.3939808481532148,
      "grad_norm": 0.7090346813201904,
      "learning_rate": 1.04249886000912e-05,
      "loss": 0.0223,
      "step": 10500
    },
    {
      "epoch": 2.5079799361605106,
      "grad_norm": 0.6480665802955627,
      "learning_rate": 9.968992248062017e-06,
      "loss": 0.0204,
      "step": 11000
    },
    {
      "epoch": 2.621979024167807,
      "grad_norm": 1.7029985189437866,
      "learning_rate": 9.512995896032832e-06,
      "loss": 0.0221,
      "step": 11500
    },
    {
      "epoch": 2.7359781121751023,
      "grad_norm": 0.9722331166267395,
      "learning_rate": 9.056999544003648e-06,
      "loss": 0.0208,
      "step": 12000
    },
    {
      "epoch": 2.8499772001823986,
      "grad_norm": 0.3082011938095093,
      "learning_rate": 8.601003191974465e-06,
      "loss": 0.0204,
      "step": 12500
    },
    {
      "epoch": 2.9639762881896945,
      "grad_norm": 0.33128827810287476,
      "learning_rate": 8.145006839945281e-06,
      "loss": 0.0207,
      "step": 13000
    },
    {
      "epoch": 3.0779753761969904,
      "grad_norm": 0.7698410749435425,
      "learning_rate": 7.689010487916098e-06,
      "loss": 0.0171,
      "step": 13500
    },
    {
      "epoch": 3.191974464204286,
      "grad_norm": 0.7875366806983948,
      "learning_rate": 7.233014135886913e-06,
      "loss": 0.0156,
      "step": 14000
    },
    {
      "epoch": 3.305973552211582,
      "grad_norm": 0.6971263289451599,
      "learning_rate": 6.77701778385773e-06,
      "loss": 0.0157,
      "step": 14500
    },
    {
      "epoch": 3.4199726402188784,
      "grad_norm": 0.464100182056427,
      "learning_rate": 6.321021431828546e-06,
      "loss": 0.0143,
      "step": 15000
    },
    {
      "epoch": 3.5339717282261742,
      "grad_norm": 0.5803436636924744,
      "learning_rate": 5.8650250797993626e-06,
      "loss": 0.0147,
      "step": 15500
    },
    {
      "epoch": 3.64797081623347,
      "grad_norm": 0.7879688739776611,
      "learning_rate": 5.409028727770178e-06,
      "loss": 0.0137,
      "step": 16000
    },
    {
      "epoch": 3.761969904240766,
      "grad_norm": 1.0888534784317017,
      "learning_rate": 4.953032375740995e-06,
      "loss": 0.0139,
      "step": 16500
    },
    {
      "epoch": 3.875968992248062,
      "grad_norm": 0.3893286883831024,
      "learning_rate": 4.49703602371181e-06,
      "loss": 0.0137,
      "step": 17000
    },
    {
      "epoch": 3.989968080255358,
      "grad_norm": 0.4917721748352051,
      "learning_rate": 4.041039671682627e-06,
      "loss": 0.0136,
      "step": 17500
    },
    {
      "epoch": 4.1039671682626535,
      "grad_norm": 1.25238835811615,
      "learning_rate": 3.585043319653443e-06,
      "loss": 0.0117,
      "step": 18000
    },
    {
      "epoch": 4.21796625626995,
      "grad_norm": 0.9064317941665649,
      "learning_rate": 3.129046967624259e-06,
      "loss": 0.0108,
      "step": 18500
    },
    {
      "epoch": 4.331965344277246,
      "grad_norm": 0.4522368311882019,
      "learning_rate": 2.6730506155950754e-06,
      "loss": 0.0105,
      "step": 19000
    },
    {
      "epoch": 4.4459644322845415,
      "grad_norm": 1.0190762281417847,
      "learning_rate": 2.217054263565892e-06,
      "loss": 0.0108,
      "step": 19500
    },
    {
      "epoch": 4.559963520291838,
      "grad_norm": 0.23909200727939606,
      "learning_rate": 1.7610579115367079e-06,
      "loss": 0.0114,
      "step": 20000
    },
    {
      "epoch": 4.673962608299133,
      "grad_norm": 0.8679990768432617,
      "learning_rate": 1.3050615595075241e-06,
      "loss": 0.0105,
      "step": 20500
    },
    {
      "epoch": 4.7879616963064295,
      "grad_norm": 0.4421948790550232,
      "learning_rate": 8.490652074783402e-07,
      "loss": 0.0109,
      "step": 21000
    },
    {
      "epoch": 4.901960784313726,
      "grad_norm": 1.2229384183883667,
      "learning_rate": 3.930688554491564e-07,
      "loss": 0.0103,
      "step": 21500
    }
  ],
  "logging_steps": 500,
  "max_steps": 21930,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2352410932543488.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}