{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01705516920859751,
  "eval_steps": 2500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 4.05,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 3.3945,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 3.2271,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 3.0742,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.8783,
      "step": 2500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.8391,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.7742,
      "step": 3500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.7115,
      "step": 4000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.6343,
      "step": 4500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.6073,
      "step": 5000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.5515,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.4989,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.481,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.4226,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3769,
      "step": 7500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3274,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3547,
      "step": 8500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3042,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3047,
      "step": 9500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.285,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.263,
      "step": 10500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1968,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1975,
      "step": 11500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.176,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1405,
      "step": 12500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1032,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.126,
      "step": 13500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0626,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0201,
      "step": 14500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0958,
      "step": 15000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0517,
      "step": 15500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0233,
      "step": 16000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0422,
      "step": 16500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9729,
      "step": 17000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9913,
      "step": 17500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9862,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9559,
      "step": 18500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9739,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9574,
      "step": 19500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9771,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20000,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "total_flos": 9.652535293088563e+16,
  "trial_name": null,
  "trial_params": null
}