{
  "best_metric": 0.031680114567279816,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/sum/checkpoint-100",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 7.333333333333333e-05,
      "loss": 2.9796,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.8474284410476685,
      "eval_runtime": 2.9025,
      "eval_samples_per_second": 34.453,
      "eval_steps_per_second": 4.479,
      "step": 12
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6178,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.31484881043434143,
      "eval_runtime": 2.9228,
      "eval_samples_per_second": 34.214,
      "eval_steps_per_second": 4.448,
      "step": 25
    },
    {
      "epoch": 2.4,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.4051,
      "step": 30
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.13756035268306732,
      "eval_runtime": 2.9586,
      "eval_samples_per_second": 33.799,
      "eval_steps_per_second": 4.394,
      "step": 37
    },
    {
      "epoch": 3.2,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1943,
      "step": 40
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0721,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.06226326525211334,
      "eval_runtime": 2.9426,
      "eval_samples_per_second": 33.984,
      "eval_steps_per_second": 4.418,
      "step": 50
    },
    {
      "epoch": 4.8,
      "learning_rate": 4e-05,
      "loss": 0.043,
      "step": 60
    },
    {
      "epoch": 4.96,
      "eval_loss": 0.03685503825545311,
      "eval_runtime": 2.9565,
      "eval_samples_per_second": 33.823,
      "eval_steps_per_second": 4.397,
      "step": 62
    },
    {
      "epoch": 5.6,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0342,
      "step": 70
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.045043423771858215,
      "eval_runtime": 2.9492,
      "eval_samples_per_second": 33.907,
      "eval_steps_per_second": 4.408,
      "step": 75
    },
    {
      "epoch": 6.4,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0254,
      "step": 80
    },
    {
      "epoch": 6.96,
      "eval_loss": 0.04237747564911842,
      "eval_runtime": 2.9496,
      "eval_samples_per_second": 33.903,
      "eval_steps_per_second": 4.407,
      "step": 87
    },
    {
      "epoch": 7.2,
      "learning_rate": 2e-05,
      "loss": 0.0293,
      "step": 90
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0163,
      "step": 100
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.031680114567279816,
      "eval_runtime": 2.9477,
      "eval_samples_per_second": 33.925,
      "eval_steps_per_second": 4.41,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5934292402176000.0,
  "trial_name": null,
  "trial_params": null
}