{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2455795677799607,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.999464304375242e-06,
      "loss": 0.7019,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.997857345043108e-06,
      "loss": 0.6739,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.99517950459963e-06,
      "loss": 0.6677,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.99143142060366e-06,
      "loss": 0.6625,
      "step": 200
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.98661398542506e-06,
      "loss": 0.6649,
      "step": 250
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.980728346032255e-06,
      "loss": 0.6528,
      "step": 300
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.973775903719142e-06,
      "loss": 0.6442,
      "step": 350
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.965758313771466e-06,
      "loss": 0.6375,
      "step": 400
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.956677485072722e-06,
      "loss": 0.6303,
      "step": 450
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.946535579649664e-06,
      "loss": 0.634,
      "step": 500
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.0,
      "eval_loss": 0.6457224488258362,
      "eval_runtime": 154.2695,
      "eval_samples_per_second": 87.989,
      "eval_steps_per_second": 14.669,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 10180,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}