{
  "best_metric": 0.030880222097039223,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/word-sorting/checkpoint-112",
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 120,
  "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": 0.2601,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.053824424743652344,
      "eval_runtime": 8.4016,
      "eval_samples_per_second": 11.902,
      "eval_steps_per_second": 1.547,
      "step": 12
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0526,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.03642543405294418,
      "eval_runtime": 8.3694,
      "eval_samples_per_second": 11.948,
      "eval_steps_per_second": 1.553,
      "step": 25
    },
    {
      "epoch": 2.4,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0367,
      "step": 30
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.03345979005098343,
      "eval_runtime": 8.4155,
      "eval_samples_per_second": 11.883,
      "eval_steps_per_second": 1.545,
      "step": 37
    },
    {
      "epoch": 3.2,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0331,
      "step": 40
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0296,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.031256407499313354,
      "eval_runtime": 8.4766,
      "eval_samples_per_second": 11.797,
      "eval_steps_per_second": 1.534,
      "step": 50
    },
    {
      "epoch": 4.8,
      "learning_rate": 4e-05,
      "loss": 0.0262,
      "step": 60
    },
    {
      "epoch": 4.96,
      "eval_loss": 0.031165990978479385,
      "eval_runtime": 8.4029,
      "eval_samples_per_second": 11.901,
      "eval_steps_per_second": 1.547,
      "step": 62
    },
    {
      "epoch": 5.6,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0239,
      "step": 70
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.03090561181306839,
      "eval_runtime": 8.3105,
      "eval_samples_per_second": 12.033,
      "eval_steps_per_second": 1.564,
      "step": 75
    },
    {
      "epoch": 6.4,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0209,
      "step": 80
    },
    {
      "epoch": 6.96,
      "eval_loss": 0.03128715232014656,
      "eval_runtime": 8.4557,
      "eval_samples_per_second": 11.826,
      "eval_steps_per_second": 1.537,
      "step": 87
    },
    {
      "epoch": 7.2,
      "learning_rate": 2e-05,
      "loss": 0.0187,
      "step": 90
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0171,
      "step": 100
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.030982598662376404,
      "eval_runtime": 8.4433,
      "eval_samples_per_second": 11.844,
      "eval_steps_per_second": 1.54,
      "step": 100
    },
    {
      "epoch": 8.8,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0171,
      "step": 110
    },
    {
      "epoch": 8.96,
      "eval_loss": 0.030880222097039223,
      "eval_runtime": 8.4894,
      "eval_samples_per_second": 11.779,
      "eval_steps_per_second": 1.531,
      "step": 112
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.0,
      "loss": 0.0155,
      "step": 120
    },
    {
      "epoch": 9.6,
      "eval_loss": 0.031018836423754692,
      "eval_runtime": 8.4634,
      "eval_samples_per_second": 11.816,
      "eval_steps_per_second": 1.536,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 4.874279421837312e+16,
  "trial_name": null,
  "trial_params": null
}