{ "humaneval": { "pass@1": 0.14682926829268292, "pass@10": 0.1950433350182723 }, "config": { "prefix": "", "do_sample": true, "temperature": 0.2, "top_k": 0, "top_p": 0.95, "n_samples": 50, "eos": "<|endoftext|>", "seed": 0, "model": "/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint/", "modeltype": "causal", "peft_model": null, "revision": null, "use_auth_token": false, "trust_remote_code": false, "tasks": "humaneval", "instruction_tokens": null, "batch_size": 32, "max_length_generation": 512, "precision": "fp16", "load_in_8bit": false, "load_in_4bit": false, "left_padding": false, "limit": null, "limit_start": 0, "save_every_k_tasks": -1, "postprocess": true, "allow_code_execution": true, "generation_only": false, "load_generations_path": null, "load_data_path": null, "metric_output_path": "/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint//humaneval_fp16.json", "save_generations": true, "load_generations_intermediate_paths": null, "save_generations_path": "generations.json", "save_references": false, "save_references_path": "references.json", "prompt": "prompt", "max_memory_per_gpu": "auto", "check_references": false } }