{
  "best_metric": 0.8249552249908447,
  "best_model_checkpoint": "./output/training_results/C017_random_sample_Meta-Llama-3-8B_instruct_20240729_013421/checkpoint-10",
  "epoch": 0.20833333333333334,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.0256,
      "step": 1
    },
    {
      "epoch": 0.0625,
      "grad_norm": 12.686407811650787,
      "learning_rate": 7.5e-07,
      "loss": 0.9401,
      "step": 3
    },
    {
      "epoch": 0.10416666666666667,
      "eval_loss": 1.0273184776306152,
      "eval_runtime": 0.9514,
      "eval_samples_per_second": 357.354,
      "eval_steps_per_second": 3.153,
      "step": 5
    },
    {
      "epoch": 0.125,
      "grad_norm": 12.806299862704327,
      "learning_rate": 2.25e-06,
      "loss": 1.0723,
      "step": 6
    },
    {
      "epoch": 0.1875,
      "grad_norm": 5.72001023912609,
      "learning_rate": 2.865909090909091e-06,
      "loss": 0.8986,
      "step": 9
    },
    {
      "epoch": 0.20833333333333334,
      "eval_loss": 0.8249552249908447,
      "eval_runtime": 0.8717,
      "eval_samples_per_second": 390.025,
      "eval_steps_per_second": 3.441,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 204983500800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}