{
  "best_metric": 0.0313660129904747,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/sst/checkpoint-75",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "learning_rate": 4.2e-05,
      "loss": 7.604,
      "step": 10
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000102,
      "loss": 6.408,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.78858482837677,
      "eval_runtime": 6.2379,
      "eval_samples_per_second": 32.062,
      "eval_steps_per_second": 4.008,
      "step": 25
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.000162,
      "loss": 1.6353,
      "step": 30
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00022199999999999998,
      "loss": 0.1518,
      "step": 40
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00028199999999999997,
      "loss": 0.0807,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.06099913269281387,
      "eval_runtime": 6.2244,
      "eval_samples_per_second": 32.132,
      "eval_steps_per_second": 4.016,
      "step": 50
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002895,
      "loss": 0.0667,
      "step": 60
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0002745,
      "loss": 0.0418,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0313660129904747,
      "eval_runtime": 6.2691,
      "eval_samples_per_second": 31.902,
      "eval_steps_per_second": 3.988,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6295295189975040.0,
  "trial_name": null,
  "trial_params": null
}