{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.538160469667319,
  "eval_steps": 1000,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009784735812133072,
      "grad_norm": 165951.1875,
      "learning_rate": 4.411764705882353e-08,
      "loss": 0.8416,
      "step": 10
    },
    {
      "epoch": 0.019569471624266144,
      "grad_norm": 206132.796875,
      "learning_rate": 9.313725490196079e-08,
      "loss": 0.8378,
      "step": 20
    },
    {
      "epoch": 0.029354207436399216,
      "grad_norm": 171197.53125,
      "learning_rate": 1.4215686274509803e-07,
      "loss": 0.8388,
      "step": 30
    },
    {
      "epoch": 0.03913894324853229,
      "grad_norm": 206661.828125,
      "learning_rate": 1.9117647058823527e-07,
      "loss": 0.847,
      "step": 40
    },
    {
      "epoch": 0.04892367906066536,
      "grad_norm": 230268.96875,
      "learning_rate": 2.4019607843137255e-07,
      "loss": 0.8411,
      "step": 50
    },
    {
      "epoch": 0.05870841487279843,
      "grad_norm": 133248.28125,
      "learning_rate": 2.8921568627450984e-07,
      "loss": 0.8412,
      "step": 60
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 147768.828125,
      "learning_rate": 3.3823529411764707e-07,
      "loss": 0.8431,
      "step": 70
    },
    {
      "epoch": 0.07827788649706457,
      "grad_norm": 167327.53125,
      "learning_rate": 3.872549019607843e-07,
      "loss": 0.8431,
      "step": 80
    },
    {
      "epoch": 0.08806262230919765,
      "grad_norm": 151943.75,
      "learning_rate": 4.3627450980392154e-07,
      "loss": 0.8311,
      "step": 90
    },
    {
      "epoch": 0.09784735812133072,
      "grad_norm": 149971.59375,
      "learning_rate": 4.852941176470588e-07,
      "loss": 0.8412,
      "step": 100
    },
    {
      "epoch": 0.10763209393346379,
      "grad_norm": 162329.40625,
      "learning_rate": 5.34313725490196e-07,
      "loss": 0.8356,
      "step": 110
    },
    {
      "epoch": 0.11741682974559686,
      "grad_norm": 158769.765625,
      "learning_rate": 5.833333333333334e-07,
      "loss": 0.8351,
      "step": 120
    },
    {
      "epoch": 0.12720156555772993,
      "grad_norm": 157725.59375,
      "learning_rate": 6.323529411764706e-07,
      "loss": 0.8331,
      "step": 130
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 205733.0,
      "learning_rate": 6.813725490196079e-07,
      "loss": 0.8366,
      "step": 140
    },
    {
      "epoch": 0.14677103718199608,
      "grad_norm": 172581.328125,
      "learning_rate": 7.30392156862745e-07,
      "loss": 0.831,
      "step": 150
    },
    {
      "epoch": 0.15655577299412915,
      "grad_norm": 137428.0,
      "learning_rate": 7.794117647058823e-07,
      "loss": 0.8326,
      "step": 160
    },
    {
      "epoch": 0.16634050880626222,
      "grad_norm": 151189.203125,
      "learning_rate": 8.284313725490196e-07,
      "loss": 0.8281,
      "step": 170
    },
    {
      "epoch": 0.1761252446183953,
      "grad_norm": 145620.625,
      "learning_rate": 8.774509803921568e-07,
      "loss": 0.8252,
      "step": 180
    },
    {
      "epoch": 0.18590998043052837,
      "grad_norm": 169938.84375,
      "learning_rate": 9.264705882352941e-07,
      "loss": 0.8308,
      "step": 190
    },
    {
      "epoch": 0.19569471624266144,
      "grad_norm": 138760.015625,
      "learning_rate": 9.754901960784313e-07,
      "loss": 0.824,
      "step": 200
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 107872.125,
      "learning_rate": 9.99631294374483e-07,
      "loss": 0.8254,
      "step": 210
    },
    {
      "epoch": 0.21526418786692758,
      "grad_norm": 113610.8359375,
      "learning_rate": 9.966849112204936e-07,
      "loss": 0.8267,
      "step": 220
    },
    {
      "epoch": 0.22504892367906065,
      "grad_norm": 172441.515625,
      "learning_rate": 9.908095200725339e-07,
      "loss": 0.8198,
      "step": 230
    },
    {
      "epoch": 0.23483365949119372,
      "grad_norm": 128079.9140625,
      "learning_rate": 9.82039768787326e-07,
      "loss": 0.8143,
      "step": 240
    },
    {
      "epoch": 0.2446183953033268,
      "grad_norm": 98149.8984375,
      "learning_rate": 9.70427373595903e-07,
      "loss": 0.8191,
      "step": 250
    },
    {
      "epoch": 0.25440313111545987,
      "grad_norm": 147377.4375,
      "learning_rate": 9.560408141270531e-07,
      "loss": 0.8178,
      "step": 260
    },
    {
      "epoch": 0.26418786692759294,
      "grad_norm": 156439.40625,
      "learning_rate": 9.389649295750781e-07,
      "loss": 0.8085,
      "step": 270
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 131892.015625,
      "learning_rate": 9.193004183933174e-07,
      "loss": 0.8172,
      "step": 280
    },
    {
      "epoch": 0.2837573385518591,
      "grad_norm": 132474.5,
      "learning_rate": 8.971632444637971e-07,
      "loss": 0.8136,
      "step": 290
    },
    {
      "epoch": 0.29354207436399216,
      "grad_norm": 112619.109375,
      "learning_rate": 8.726839532448928e-07,
      "loss": 0.8065,
      "step": 300
    },
    {
      "epoch": 0.30332681017612523,
      "grad_norm": 94225.5703125,
      "learning_rate": 8.460069019297606e-07,
      "loss": 0.813,
      "step": 310
    },
    {
      "epoch": 0.3131115459882583,
      "grad_norm": 117812.8203125,
      "learning_rate": 8.172894081553822e-07,
      "loss": 0.8022,
      "step": 320
    },
    {
      "epoch": 0.32289628180039137,
      "grad_norm": 143287.125,
      "learning_rate": 7.86700822282382e-07,
      "loss": 0.8061,
      "step": 330
    },
    {
      "epoch": 0.33268101761252444,
      "grad_norm": 107456.25,
      "learning_rate": 7.544215287164917e-07,
      "loss": 0.8006,
      "step": 340
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 101521.171875,
      "learning_rate": 7.206418821609812e-07,
      "loss": 0.8055,
      "step": 350
    },
    {
      "epoch": 0.3522504892367906,
      "grad_norm": 118311.5234375,
      "learning_rate": 6.855610850731017e-07,
      "loss": 0.8081,
      "step": 360
    },
    {
      "epoch": 0.36203522504892366,
      "grad_norm": 89621.828125,
      "learning_rate": 6.493860129443046e-07,
      "loss": 0.8058,
      "step": 370
    },
    {
      "epoch": 0.37181996086105673,
      "grad_norm": 143168.65625,
      "learning_rate": 6.123299943316975e-07,
      "loss": 0.8028,
      "step": 380
    },
    {
      "epoch": 0.3816046966731898,
      "grad_norm": 118598.2890625,
      "learning_rate": 5.746115528350295e-07,
      "loss": 0.8032,
      "step": 390
    },
    {
      "epoch": 0.3913894324853229,
      "grad_norm": 111807.8203125,
      "learning_rate": 5.364531184379139e-07,
      "loss": 0.8014,
      "step": 400
    },
    {
      "epoch": 0.40117416829745595,
      "grad_norm": 124106.1328125,
      "learning_rate": 4.980797158126566e-07,
      "loss": 0.8045,
      "step": 410
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 102746.4765625,
      "learning_rate": 4.597176373239061e-07,
      "loss": 0.7996,
      "step": 420
    },
    {
      "epoch": 0.4207436399217221,
      "grad_norm": 108317.5859375,
      "learning_rate": 4.215931085565761e-07,
      "loss": 0.8037,
      "step": 430
    },
    {
      "epoch": 0.43052837573385516,
      "grad_norm": 113342.515625,
      "learning_rate": 3.8393095423757764e-07,
      "loss": 0.8047,
      "step": 440
    },
    {
      "epoch": 0.44031311154598823,
      "grad_norm": 111908.90625,
      "learning_rate": 3.469532724185699e-07,
      "loss": 0.8021,
      "step": 450
    },
    {
      "epoch": 0.4500978473581213,
      "grad_norm": 85004.15625,
      "learning_rate": 3.1087812473822845e-07,
      "loss": 0.8012,
      "step": 460
    },
    {
      "epoch": 0.4598825831702544,
      "grad_norm": 98335.1796875,
      "learning_rate": 2.7591825048770643e-07,
      "loss": 0.7977,
      "step": 470
    },
    {
      "epoch": 0.46966731898238745,
      "grad_norm": 110674.03125,
      "learning_rate": 2.422798120625886e-07,
      "loss": 0.7979,
      "step": 480
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 114861.5390625,
      "learning_rate": 2.1016117919955512e-07,
      "loss": 0.8014,
      "step": 490
    },
    {
      "epoch": 0.4892367906066536,
      "grad_norm": 130109.5703125,
      "learning_rate": 1.7975175916725031e-07,
      "loss": 0.7994,
      "step": 500
    },
    {
      "epoch": 0.49902152641878667,
      "grad_norm": 100678.8671875,
      "learning_rate": 1.5123087980985606e-07,
      "loss": 0.802,
      "step": 510
    },
    {
      "epoch": 0.5088062622309197,
      "grad_norm": 115718.078125,
      "learning_rate": 1.2476673203018728e-07,
      "loss": 0.7971,
      "step": 520
    },
    {
      "epoch": 0.5185909980430529,
      "grad_norm": 94845.9453125,
      "learning_rate": 1.0051537794861287e-07,
      "loss": 0.7952,
      "step": 530
    },
    {
      "epoch": 0.5283757338551859,
      "grad_norm": 106283.5703125,
      "learning_rate": 7.861983058679871e-08,
      "loss": 0.8013,
      "step": 540
    },
    {
      "epoch": 0.538160469667319,
      "grad_norm": 93847.1640625,
      "learning_rate": 5.920921050348626e-08,
      "loss": 0.7968,
      "step": 550
    }
  ],
  "logging_steps": 10,
  "max_steps": 1022,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.4092073189376e+16,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}