{
  "best_metric": 0.16061067581176758,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/cola/checkpoint-120",
  "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": 6.6687,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 4.879603385925293,
      "eval_runtime": 2.9872,
      "eval_samples_per_second": 33.476,
      "eval_steps_per_second": 4.352,
      "step": 12
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.733333333333333e-05,
      "loss": 4.1857,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6735175251960754,
      "eval_runtime": 2.9786,
      "eval_samples_per_second": 33.573,
      "eval_steps_per_second": 4.364,
      "step": 25
    },
    {
      "epoch": 2.4,
      "learning_rate": 6.0666666666666666e-05,
      "loss": 1.1578,
      "step": 30
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.22044576704502106,
      "eval_runtime": 2.9802,
      "eval_samples_per_second": 33.554,
      "eval_steps_per_second": 4.362,
      "step": 37
    },
    {
      "epoch": 3.2,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.2691,
      "step": 40
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.7333333333333336e-05,
      "loss": 0.2011,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.18446393311023712,
      "eval_runtime": 2.9788,
      "eval_samples_per_second": 33.571,
      "eval_steps_per_second": 4.364,
      "step": 50
    },
    {
      "epoch": 4.8,
      "learning_rate": 4.066666666666667e-05,
      "loss": 0.1782,
      "step": 60
    },
    {
      "epoch": 4.96,
      "eval_loss": 0.17961610853672028,
      "eval_runtime": 2.9749,
      "eval_samples_per_second": 33.615,
      "eval_steps_per_second": 4.37,
      "step": 62
    },
    {
      "epoch": 5.6,
      "learning_rate": 3.4e-05,
      "loss": 0.1609,
      "step": 70
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.1864309310913086,
      "eval_runtime": 2.9806,
      "eval_samples_per_second": 33.55,
      "eval_steps_per_second": 4.362,
      "step": 75
    },
    {
      "epoch": 6.4,
      "learning_rate": 2.7333333333333335e-05,
      "loss": 0.1644,
      "step": 80
    },
    {
      "epoch": 6.96,
      "eval_loss": 0.16424360871315002,
      "eval_runtime": 2.9883,
      "eval_samples_per_second": 33.464,
      "eval_steps_per_second": 4.35,
      "step": 87
    },
    {
      "epoch": 7.2,
      "learning_rate": 2.066666666666667e-05,
      "loss": 0.1389,
      "step": 90
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.4e-05,
      "loss": 0.1294,
      "step": 100
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.16847126185894012,
      "eval_runtime": 2.9824,
      "eval_samples_per_second": 33.53,
      "eval_steps_per_second": 4.359,
      "step": 100
    },
    {
      "epoch": 8.8,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.1189,
      "step": 110
    },
    {
      "epoch": 8.96,
      "eval_loss": 0.16718144714832306,
      "eval_runtime": 2.9865,
      "eval_samples_per_second": 33.485,
      "eval_steps_per_second": 4.353,
      "step": 112
    },
    {
      "epoch": 9.6,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.1159,
      "step": 120
    },
    {
      "epoch": 9.6,
      "eval_loss": 0.16061067581176758,
      "eval_runtime": 3.0082,
      "eval_samples_per_second": 33.243,
      "eval_steps_per_second": 4.322,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7598366896619520.0,
  "trial_name": null,
  "trial_params": null
}