{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.76923076923077,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.23,
      "learning_rate": 0.000975,
      "loss": 1.1621,
      "step": 20
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00095,
      "loss": 0.7214,
      "step": 40
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.000925,
      "loss": 0.5522,
      "step": 60
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.4059,
      "step": 80
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.000875,
      "loss": 0.3237,
      "step": 100
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.00085,
      "loss": 0.249,
      "step": 120
    },
    {
      "epoch": 8.62,
      "learning_rate": 0.000825,
      "loss": 0.1859,
      "step": 140
    },
    {
      "epoch": 9.85,
      "learning_rate": 0.0008,
      "loss": 0.1988,
      "step": 160
    },
    {
      "epoch": 11.08,
      "learning_rate": 0.0007750000000000001,
      "loss": 0.1458,
      "step": 180
    },
    {
      "epoch": 12.31,
      "learning_rate": 0.00075,
      "loss": 0.1279,
      "step": 200
    },
    {
      "epoch": 13.54,
      "learning_rate": 0.000725,
      "loss": 0.1002,
      "step": 220
    },
    {
      "epoch": 14.77,
      "learning_rate": 0.0007,
      "loss": 0.1024,
      "step": 240
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.000675,
      "loss": 0.0808,
      "step": 260
    },
    {
      "epoch": 17.23,
      "learning_rate": 0.0006500000000000001,
      "loss": 0.0743,
      "step": 280
    },
    {
      "epoch": 18.46,
      "learning_rate": 0.000625,
      "loss": 0.0638,
      "step": 300
    },
    {
      "epoch": 19.69,
      "learning_rate": 0.0006,
      "loss": 0.0444,
      "step": 320
    },
    {
      "epoch": 20.92,
      "learning_rate": 0.000575,
      "loss": 0.0441,
      "step": 340
    },
    {
      "epoch": 22.15,
      "learning_rate": 0.00055,
      "loss": 0.035,
      "step": 360
    },
    {
      "epoch": 23.38,
      "learning_rate": 0.0005250000000000001,
      "loss": 0.0305,
      "step": 380
    },
    {
      "epoch": 24.62,
      "learning_rate": 0.0005,
      "loss": 0.0272,
      "step": 400
    },
    {
      "epoch": 25.85,
      "learning_rate": 0.000475,
      "loss": 0.0252,
      "step": 420
    },
    {
      "epoch": 27.08,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.021,
      "step": 440
    },
    {
      "epoch": 28.31,
      "learning_rate": 0.000425,
      "loss": 0.0188,
      "step": 460
    },
    {
      "epoch": 29.54,
      "learning_rate": 0.0004,
      "loss": 0.0186,
      "step": 480
    },
    {
      "epoch": 30.77,
      "learning_rate": 0.000375,
      "loss": 0.0178,
      "step": 500
    }
  ],
  "max_steps": 800,
  "num_train_epochs": 50,
  "total_flos": 6.497819467776e+17,
  "trial_name": null,
  "trial_params": null
}