Reproduction Issues of Code Llama about bigcode-evaluation-harness HOT 3 CLOSED

{
  "humaneval": {
    "pass@1": 0.4024390243902439
  },
  "config": {
    "prefix": "",
    "do_sample": false,
    "temperature": 0.2,
    "top_k": 0,
    "top_p": 0.95,
    "n_samples": 1,
    "eos": "<|endoftext|>",
    "seed": 0,
    "model": "/mnt/models/CodeLlama-7b-Python",
    "modeltype": "causal",
    "peft_model": null,
    "revision": null,
    "use_auth_token": true,
    "trust_remote_code": true,
    "tasks": "humaneval",
    "instruction_tokens": null,
    "batch_size": 1,
    "max_length_generation": 512,
    "precision": "bf16",
    "load_in_8bit": false,
    "load_in_4bit": false,
    "limit": null,
    "limit_start": 0,
    "postprocess": true,
    "allow_code_execution": true,
    "generation_only": false,
    "load_generations_path": null,
    "load_data_path": null,
    "metric_output_path": "/root/ch/bigcode-evaluation-harness/outputs/metrics/humaneval_codellama_7b_python.json",
    "save_generations": true,
    "save_generations_path": "/root/ch/bigcode-evaluation-harness/outputs/generations/humaneval_codellama_7b_python.json",
    "save_references": false,
    "prompt": "prompt",
    "max_memory_per_gpu": "auto",
    "check_references": false
  }
}

--load_generations_path /root/ch/bigcode-evaluation-harness/outputs/generations/humaneval_codellama_7b_python.json