{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 22.986753463745117,
      "learning_rate": 0.00198,
      "loss": 1.7003,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 8.073963165283203,
      "learning_rate": 0.00196,
      "loss": 1.9785,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 7.6197099685668945,
      "learning_rate": 0.0019399999999999999,
      "loss": 1.9353,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.2731146812438965,
      "learning_rate": 0.00192,
      "loss": 1.5962,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.425559043884277,
      "learning_rate": 0.0019,
      "loss": 1.389,
      "step": 50
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.872774600982666,
      "learning_rate": 0.00188,
      "loss": 1.4156,
      "step": 60
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.199490070343018,
      "learning_rate": 0.00186,
      "loss": 1.6583,
      "step": 70
    },
    {
      "epoch": 0.02,
      "grad_norm": 4.413191318511963,
      "learning_rate": 0.00184,
      "loss": 1.4334,
      "step": 80
    },
    {
      "epoch": 0.02,
      "grad_norm": 5.90674352645874,
      "learning_rate": 0.00182,
      "loss": 1.6046,
      "step": 90
    },
    {
      "epoch": 0.02,
      "grad_norm": 6.410930633544922,
      "learning_rate": 0.0018000000000000002,
      "loss": 1.5504,
      "step": 100
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.529223680496216,
      "learning_rate": 0.0017800000000000001,
      "loss": 1.6463,
      "step": 110
    },
    {
      "epoch": 0.02,
      "grad_norm": 4.781284332275391,
      "learning_rate": 0.00176,
      "loss": 1.6136,
      "step": 120
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.6382951736450195,
      "learning_rate": 0.00174,
      "loss": 1.5105,
      "step": 130
    },
    {
      "epoch": 0.03,
      "grad_norm": 4.392839431762695,
      "learning_rate": 0.00172,
      "loss": 1.6061,
      "step": 140
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.9011926651000977,
      "learning_rate": 0.0017,
      "loss": 1.6188,
      "step": 150
    },
    {
      "epoch": 0.03,
      "grad_norm": 4.002920627593994,
      "learning_rate": 0.00168,
      "loss": 1.4177,
      "step": 160
    },
    {
      "epoch": 0.03,
      "grad_norm": 4.34838342666626,
      "learning_rate": 0.00166,
      "loss": 1.5689,
      "step": 170
    },
    {
      "epoch": 0.04,
      "grad_norm": 8.142854690551758,
      "learning_rate": 0.00164,
      "loss": 1.5804,
      "step": 180
    },
    {
      "epoch": 0.04,
      "grad_norm": 5.837989330291748,
      "learning_rate": 0.0016200000000000001,
      "loss": 1.5981,
      "step": 190
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.33852219581604,
      "learning_rate": 0.0016,
      "loss": 1.4347,
      "step": 200
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.069826602935791,
      "learning_rate": 0.00158,
      "loss": 1.4809,
      "step": 210
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.71095609664917,
      "learning_rate": 0.0015600000000000002,
      "loss": 1.388,
      "step": 220
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.450407981872559,
      "learning_rate": 0.0015400000000000001,
      "loss": 1.603,
      "step": 230
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.475738048553467,
      "learning_rate": 0.00152,
      "loss": 1.5731,
      "step": 240
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.051819086074829,
      "learning_rate": 0.0015,
      "loss": 1.5133,
      "step": 250
    },
    {
      "epoch": 0.05,
      "grad_norm": 5.014269828796387,
      "learning_rate": 0.00148,
      "loss": 1.5458,
      "step": 260
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.558957815170288,
      "learning_rate": 0.00146,
      "loss": 1.4918,
      "step": 270
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.6234660148620605,
      "learning_rate": 0.0014399999999999999,
      "loss": 1.5247,
      "step": 280
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.9923095703125,
      "learning_rate": 0.00142,
      "loss": 1.6671,
      "step": 290
    },
    {
      "epoch": 0.06,
      "grad_norm": 7.883978366851807,
      "learning_rate": 0.0014,
      "loss": 1.5732,
      "step": 300
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.3218066692352295,
      "learning_rate": 0.00138,
      "loss": 1.6297,
      "step": 310
    },
    {
      "epoch": 0.06,
      "grad_norm": 9.045559883117676,
      "learning_rate": 0.00136,
      "loss": 1.6581,
      "step": 320
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.832301139831543,
      "learning_rate": 0.00134,
      "loss": 1.6966,
      "step": 330
    },
    {
      "epoch": 0.07,
      "grad_norm": 3.6719107627868652,
      "learning_rate": 0.00132,
      "loss": 1.5904,
      "step": 340
    },
    {
      "epoch": 0.07,
      "grad_norm": 5.4335455894470215,
      "learning_rate": 0.0013000000000000002,
      "loss": 1.6643,
      "step": 350
    },
    {
      "epoch": 0.07,
      "grad_norm": 3.2848339080810547,
      "learning_rate": 0.00128,
      "loss": 1.4174,
      "step": 360
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.8206841945648193,
      "learning_rate": 0.00126,
      "loss": 1.7362,
      "step": 370
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.389599084854126,
      "learning_rate": 0.00124,
      "loss": 1.6058,
      "step": 380
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.887266159057617,
      "learning_rate": 0.00122,
      "loss": 1.4604,
      "step": 390
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.9653384685516357,
      "learning_rate": 0.0012,
      "loss": 1.5152,
      "step": 400
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.5362136363983154,
      "learning_rate": 0.00118,
      "loss": 1.469,
      "step": 410
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.7318670749664307,
      "learning_rate": 0.00116,
      "loss": 1.4136,
      "step": 420
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.6364078521728516,
      "learning_rate": 0.00114,
      "loss": 1.6937,
      "step": 430
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.9428081512451172,
      "learning_rate": 0.0011200000000000001,
      "loss": 1.4825,
      "step": 440
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.1813700199127197,
      "learning_rate": 0.0011,
      "loss": 1.4593,
      "step": 450
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.612652778625488,
      "learning_rate": 0.00108,
      "loss": 1.389,
      "step": 460
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.5145719051361084,
      "learning_rate": 0.0010600000000000002,
      "loss": 1.3896,
      "step": 470
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.4980382919311523,
      "learning_rate": 0.0010400000000000001,
      "loss": 1.3725,
      "step": 480
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.6995227336883545,
      "learning_rate": 0.00102,
      "loss": 1.4769,
      "step": 490
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.1483154296875,
      "learning_rate": 0.001,
      "loss": 1.5983,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 4.0788232684018176e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}