{
  "best_metric": 0.042198196053504944,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/sst/checkpoint-87",
  "epoch": 6.96,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 7.466666666666667e-05,
      "loss": 7.0533,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 4.983966827392578,
      "eval_runtime": 3.24,
      "eval_samples_per_second": 30.865,
      "eval_steps_per_second": 4.012,
      "step": 12
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.866666666666666e-05,
      "loss": 4.1938,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4440341889858246,
      "eval_runtime": 3.2423,
      "eval_samples_per_second": 30.843,
      "eval_steps_per_second": 4.01,
      "step": 25
    },
    {
      "epoch": 2.4,
      "learning_rate": 6.2e-05,
      "loss": 0.6862,
      "step": 30
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.1788669228553772,
      "eval_runtime": 3.2349,
      "eval_samples_per_second": 30.913,
      "eval_steps_per_second": 4.019,
      "step": 37
    },
    {
      "epoch": 3.2,
      "learning_rate": 5.5333333333333334e-05,
      "loss": 0.2043,
      "step": 40
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.8666666666666666e-05,
      "loss": 0.1107,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.06379850953817368,
      "eval_runtime": 3.2374,
      "eval_samples_per_second": 30.889,
      "eval_steps_per_second": 4.016,
      "step": 50
    },
    {
      "epoch": 4.8,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 0.0491,
      "step": 60
    },
    {
      "epoch": 4.96,
      "eval_loss": 0.0445735827088356,
      "eval_runtime": 3.2374,
      "eval_samples_per_second": 30.889,
      "eval_steps_per_second": 4.016,
      "step": 62
    },
    {
      "epoch": 5.6,
      "learning_rate": 3.5333333333333336e-05,
      "loss": 0.0273,
      "step": 70
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.04596562311053276,
      "eval_runtime": 3.2388,
      "eval_samples_per_second": 30.876,
      "eval_steps_per_second": 4.014,
      "step": 75
    },
    {
      "epoch": 6.4,
      "learning_rate": 2.8666666666666668e-05,
      "loss": 0.0222,
      "step": 80
    },
    {
      "epoch": 6.96,
      "eval_loss": 0.042198196053504944,
      "eval_runtime": 3.2385,
      "eval_samples_per_second": 30.879,
      "eval_steps_per_second": 4.014,
      "step": 87
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7054390093086720.0,
  "trial_name": null,
  "trial_params": null
}