{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01705516920859751,
  "eval_steps": 500,
  "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": 1.6491,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5656,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5793,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5515,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5354,
      "step": 2500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5425,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5407,
      "step": 3500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5505,
      "step": 4000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5263,
      "step": 4500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5328,
      "step": 5000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5239,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5265,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5451,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5222,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5213,
      "step": 7500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5054,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5285,
      "step": 8500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5115,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5346,
      "step": 9500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5352,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.528,
      "step": 10500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5181,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5246,
      "step": 11500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5217,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5135,
      "step": 12500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.4936,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5378,
      "step": 13500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5009,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.4753,
      "step": 14500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5564,
      "step": 15000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5224,
      "step": 15500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5044,
      "step": 16000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5391,
      "step": 16500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.4972,
      "step": 17000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5071,
      "step": 17500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5166,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.496,
      "step": 18500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5299,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5151,
      "step": 19500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.526,
      "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
}