{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.997333333333333,
  "eval_steps": 500,
  "global_step": 562,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.53,
      "learning_rate": 3e-05,
      "loss": 2.0369,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6128205128205129,
      "eval_loss": 1.2953312397003174,
      "eval_runtime": 4.1114,
      "eval_samples_per_second": 121.614,
      "eval_steps_per_second": 15.323,
      "step": 187
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 27.2,
      "eval_f1": 37.44218938149973,
      "step": 187
    },
    {
      "epoch": 1.07,
      "learning_rate": 3e-05,
      "loss": 1.3264,
      "step": 200
    },
    {
      "epoch": 1.6,
      "learning_rate": 3e-05,
      "loss": 1.2821,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6146153846153846,
      "eval_loss": 1.2741013765335083,
      "eval_runtime": 4.8302,
      "eval_samples_per_second": 103.516,
      "eval_steps_per_second": 13.043,
      "step": 375
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 25.6,
      "eval_f1": 38.026666666666664,
      "step": 375
    },
    {
      "epoch": 2.13,
      "learning_rate": 3e-05,
      "loss": 1.2348,
      "step": 400
    },
    {
      "epoch": 2.67,
      "learning_rate": 3e-05,
      "loss": 1.1987,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6161538461538462,
      "eval_loss": 1.2714948654174805,
      "eval_runtime": 4.868,
      "eval_samples_per_second": 102.712,
      "eval_steps_per_second": 12.942,
      "step": 562
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 28.0,
      "eval_f1": 40.6962091503268,
      "step": 562
    }
  ],
  "logging_steps": 100,
  "max_steps": 9350,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 2.0994404860821504e+16,
  "trial_name": null,
  "trial_params": null
}