eval_results/HuggingFaceH4/starcoder2-15b-dpo/v4.1/ifeval/results_2024-03-10T19-03-37.577565.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 3568416.471836314,
    "end_time": 3569341.858482122,
    "total_evaluation_time_secondes": "925.3866458078846",
    "model_name": "HuggingFaceH4/starcoder2-15b-dpo",
    "model_sha": "3fea85086795d1c7043849eb550e631fbf8426f4",
    "model_dtype": "torch.bfloat16",
    "model_size": "30.04 GB",
    "config": null
  },
  "results": {
    "custom|ifeval|0": {
      "prompt_level_strict_acc": 0.46210720887245843,
      "prompt_level_strict_acc_stderr": 0.021454695436204697,
      "inst_level_strict_acc": 0.5731414868105515,
      "inst_level_strict_acc_stderr": 0.0005464117529822125,
      "prompt_level_loose_acc": 0.5157116451016636,
      "prompt_level_loose_acc_stderr": 0.021505948540061576,
      "inst_level_loose_acc": 0.6223021582733813,
      "inst_level_loose_acc_stderr": 0.0005356088036333955
    }
  },
  "versions": {
    "custom|ifeval|0": 0
  },
  "config_tasks": {
    "custom|ifeval": {
      "name": "ifeval",
      "prompt_function": "ifeval_prompt",
      "hf_repo": "wis-k/instruction-following-eval",
      "hf_subset": "default",
      "metric": [
        "ifeval_metric"
      ],
      "hf_avail_splits": [
        "train"
      ],
      "evaluation_splits": [
        "train"
      ],
      "few_shots_split": "train",
      "few_shots_select": "random_sampling",
      "generation_size": 1280,
      "stop_sequence": [],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "custom"
      ],
      "original_num_docs": 541,
      "effective_num_docs": 541,
      "trust_dataset": null
    }
  },
  "summary_tasks": {
    "custom|ifeval|0": {
      "hashes": {
        "hash_examples": "e99cbf567588d7c6",
        "hash_full_prompts": "7ea7bf2a8edba8f4",
        "hash_input_tokens": "dc4c9014dffc6917",
        "hash_cont_tokens": "d378f596c92ce5c8"
      },
      "truncated": 0,
      "non_truncated": 541,
      "padded": 0,
      "non_padded": 541,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "ea046ab2c6fc5928",
      "hash_full_prompts": "45f8422f6ad2da79",
      "hash_input_tokens": "5d5e6158af678a01",
      "hash_cont_tokens": "0773edd7efc4b39e"
    },
    "truncated": 0,
    "non_truncated": 541,
    "padded": 0,
    "non_padded": 541,
    "num_truncated_few_shots": 0
  }
}