{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 14299,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.744067728226103e-05,
      "loss": 2.2624,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.6195,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 1.5902,
      "step": 300
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.5743,
      "step": 400
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.6174,
      "step": 500
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 1.5901,
      "step": 600
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 1.6239,
      "step": 700
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 1.5941,
      "step": 800
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 1.5958,
      "step": 900
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 1.6153,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 1.6057,
      "step": 1100
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 1.5912,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 1.5743,
      "step": 1300
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 1.5914,
      "step": 1400
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 1.5982,
      "step": 1500
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 1.6243,
      "step": 1600
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 1.5919,
      "step": 1700
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 1.6657,
      "step": 1800
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 1.5617,
      "step": 1900
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 1.6119,
      "step": 2000
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 1.6065,
      "step": 2100
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 1.6083,
      "step": 2200
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 1.5941,
      "step": 2300
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 1.5984,
      "step": 2400
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 1.6146,
      "step": 2500
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 1.5795,
      "step": 2600
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 1.6075,
      "step": 2700
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 1.5891,
      "step": 2800
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 1.6145,
      "step": 2900
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 1.6148,
      "step": 3000
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 1.5933,
      "step": 3100
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 1.5984,
      "step": 3200
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 1.5871,
      "step": 3300
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 1.5893,
      "step": 3400
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 1.6136,
      "step": 3500
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 1.5723,
      "step": 3600
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 1.5873,
      "step": 3700
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 1.5868,
      "step": 3800
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 1.6131,
      "step": 3900
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 1.5685,
      "step": 4000
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 1.6014,
      "step": 4100
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 1.5402,
      "step": 4200
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 1.577,
      "step": 4300
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.5723,
      "step": 4400
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.5432,
      "step": 4500
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 1.5987,
      "step": 4600
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 1.6015,
      "step": 4700
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.5848,
      "step": 4800
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.547,
      "step": 4900
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 1.563,
      "step": 5000
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 1.571,
      "step": 5100
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 1.5562,
      "step": 5200
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 1.5762,
      "step": 5300
    },
    {
      "epoch": 0.38,
      "learning_rate": 5e-05,
      "loss": 1.5837,
      "step": 5400
    },
    {
      "epoch": 0.38,
      "learning_rate": 5e-05,
      "loss": 1.5926,
      "step": 5500
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 1.5939,
      "step": 5600
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 1.5689,
      "step": 5700
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.5701,
      "step": 5800
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.5744,
      "step": 5900
    },
    {
      "epoch": 0.42,
      "learning_rate": 5e-05,
      "loss": 1.5617,
      "step": 6000
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 1.594,
      "step": 6100
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 1.5909,
      "step": 6200
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 1.544,
      "step": 6300
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 1.5568,
      "step": 6400
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 1.5536,
      "step": 6500
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 1.5356,
      "step": 6600
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 1.5098,
      "step": 6700
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 1.5231,
      "step": 6800
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 1.5658,
      "step": 6900
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 1.5379,
      "step": 7000
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 1.5326,
      "step": 7100
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 1.5385,
      "step": 7200
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 1.5492,
      "step": 7300
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 1.5566,
      "step": 7400
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 1.5182,
      "step": 7500
    },
    {
      "epoch": 0.53,
      "learning_rate": 5e-05,
      "loss": 1.542,
      "step": 7600
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 1.5348,
      "step": 7700
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 1.541,
      "step": 7800
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 1.545,
      "step": 7900
    },
    {
      "epoch": 0.56,
      "learning_rate": 5e-05,
      "loss": 1.5045,
      "step": 8000
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 1.4969,
      "step": 8100
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 1.517,
      "step": 8200
    },
    {
      "epoch": 0.58,
      "learning_rate": 5e-05,
      "loss": 1.5262,
      "step": 8300
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 1.5164,
      "step": 8400
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 1.5557,
      "step": 8500
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-05,
      "loss": 1.5422,
      "step": 8600
    },
    {
      "epoch": 0.61,
      "learning_rate": 5e-05,
      "loss": 1.5283,
      "step": 8700
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 1.5218,
      "step": 8800
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 1.5142,
      "step": 8900
    },
    {
      "epoch": 0.63,
      "learning_rate": 5e-05,
      "loss": 1.5171,
      "step": 9000
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 1.517,
      "step": 9100
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 1.529,
      "step": 9200
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-05,
      "loss": 1.5035,
      "step": 9300
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 1.5116,
      "step": 9400
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 1.5186,
      "step": 9500
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 1.4911,
      "step": 9600
    },
    {
      "epoch": 0.68,
      "learning_rate": 5e-05,
      "loss": 1.4649,
      "step": 9700
    },
    {
      "epoch": 0.69,
      "learning_rate": 5e-05,
      "loss": 1.4844,
      "step": 9800
    },
    {
      "epoch": 0.69,
      "learning_rate": 5e-05,
      "loss": 1.5288,
      "step": 9900
    },
    {
      "epoch": 0.7,
      "learning_rate": 5e-05,
      "loss": 1.4952,
      "step": 10000
    },
    {
      "epoch": 0.71,
      "learning_rate": 5e-05,
      "loss": 1.4732,
      "step": 10100
    },
    {
      "epoch": 0.71,
      "learning_rate": 5e-05,
      "loss": 1.5338,
      "step": 10200
    },
    {
      "epoch": 0.72,
      "learning_rate": 5e-05,
      "loss": 1.4655,
      "step": 10300
    },
    {
      "epoch": 0.73,
      "learning_rate": 5e-05,
      "loss": 1.4582,
      "step": 10400
    },
    {
      "epoch": 0.73,
      "learning_rate": 5e-05,
      "loss": 1.4788,
      "step": 10500
    },
    {
      "epoch": 0.74,
      "learning_rate": 5e-05,
      "loss": 1.4891,
      "step": 10600
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-05,
      "loss": 1.5126,
      "step": 10700
    },
    {
      "epoch": 0.76,
      "learning_rate": 5e-05,
      "loss": 1.5224,
      "step": 10800
    },
    {
      "epoch": 0.76,
      "learning_rate": 5e-05,
      "loss": 1.4811,
      "step": 10900
    },
    {
      "epoch": 0.77,
      "learning_rate": 5e-05,
      "loss": 1.4623,
      "step": 11000
    },
    {
      "epoch": 0.78,
      "learning_rate": 5e-05,
      "loss": 1.4655,
      "step": 11100
    },
    {
      "epoch": 0.78,
      "learning_rate": 5e-05,
      "loss": 1.4531,
      "step": 11200
    },
    {
      "epoch": 0.79,
      "learning_rate": 5e-05,
      "loss": 1.4616,
      "step": 11300
    },
    {
      "epoch": 0.8,
      "learning_rate": 5e-05,
      "loss": 1.4442,
      "step": 11400
    },
    {
      "epoch": 0.8,
      "learning_rate": 5e-05,
      "loss": 1.4889,
      "step": 11500
    },
    {
      "epoch": 0.81,
      "learning_rate": 5e-05,
      "loss": 1.5087,
      "step": 11600
    },
    {
      "epoch": 0.82,
      "learning_rate": 5e-05,
      "loss": 1.4804,
      "step": 11700
    },
    {
      "epoch": 0.83,
      "learning_rate": 5e-05,
      "loss": 1.4737,
      "step": 11800
    },
    {
      "epoch": 0.83,
      "learning_rate": 5e-05,
      "loss": 1.4591,
      "step": 11900
    },
    {
      "epoch": 0.84,
      "learning_rate": 5e-05,
      "loss": 1.4595,
      "step": 12000
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-05,
      "loss": 1.4909,
      "step": 12100
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-05,
      "loss": 1.4742,
      "step": 12200
    },
    {
      "epoch": 0.86,
      "learning_rate": 5e-05,
      "loss": 1.4383,
      "step": 12300
    },
    {
      "epoch": 0.87,
      "learning_rate": 5e-05,
      "loss": 1.4517,
      "step": 12400
    },
    {
      "epoch": 0.87,
      "learning_rate": 5e-05,
      "loss": 1.448,
      "step": 12500
    },
    {
      "epoch": 0.88,
      "learning_rate": 5e-05,
      "loss": 1.4438,
      "step": 12600
    },
    {
      "epoch": 0.89,
      "learning_rate": 5e-05,
      "loss": 1.4533,
      "step": 12700
    },
    {
      "epoch": 0.9,
      "learning_rate": 5e-05,
      "loss": 1.4606,
      "step": 12800
    },
    {
      "epoch": 0.9,
      "learning_rate": 5e-05,
      "loss": 1.4629,
      "step": 12900
    },
    {
      "epoch": 0.91,
      "learning_rate": 5e-05,
      "loss": 1.451,
      "step": 13000
    },
    {
      "epoch": 0.92,
      "learning_rate": 5e-05,
      "loss": 1.4366,
      "step": 13100
    },
    {
      "epoch": 0.92,
      "learning_rate": 5e-05,
      "loss": 1.459,
      "step": 13200
    },
    {
      "epoch": 0.93,
      "learning_rate": 5e-05,
      "loss": 1.4358,
      "step": 13300
    },
    {
      "epoch": 0.94,
      "learning_rate": 5e-05,
      "loss": 1.4735,
      "step": 13400
    },
    {
      "epoch": 0.94,
      "learning_rate": 5e-05,
      "loss": 1.4474,
      "step": 13500
    },
    {
      "epoch": 0.95,
      "learning_rate": 5e-05,
      "loss": 1.4368,
      "step": 13600
    },
    {
      "epoch": 0.96,
      "learning_rate": 5e-05,
      "loss": 1.4134,
      "step": 13700
    },
    {
      "epoch": 0.97,
      "learning_rate": 5e-05,
      "loss": 1.455,
      "step": 13800
    },
    {
      "epoch": 0.97,
      "learning_rate": 5e-05,
      "loss": 1.4479,
      "step": 13900
    },
    {
      "epoch": 0.98,
      "learning_rate": 5e-05,
      "loss": 1.4398,
      "step": 14000
    },
    {
      "epoch": 0.99,
      "learning_rate": 5e-05,
      "loss": 1.433,
      "step": 14100
    },
    {
      "epoch": 0.99,
      "learning_rate": 5e-05,
      "loss": 1.4429,
      "step": 14200
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4375,
      "eval_runtime": 19.8133,
      "eval_samples_per_second": 117.85,
      "eval_steps_per_second": 14.738,
      "step": 14299
    }
  ],
  "max_steps": 14299,
  "num_train_epochs": 1,
  "total_flos": 2.6064687168162365e+18,
  "trial_name": null,
  "trial_params": null
}