{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 410627.375267444, "end_time": 411970.638759163, "total_evaluation_time_secondes": "1343.2634917189716", "model_name": "deepseek-ai/deepseek-coder-6.7b-instruct", "model_sha": "e5d64addd26a6a1db0f9b863abf6ee3141936807", "model_dtype": "torch.bfloat16", "model_size": "12.84 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.2979529946929492, "qem_stderr": 0.012597932232914513 } }, "versions": { "lighteval|gsm8k|5": 0 }, "config_tasks": { "lighteval|gsm8k": { "name": "gsm8k", "prompt_function": "gsm8k", "hf_repo": "gsm8k", "hf_subset": "main", "metric": [ "quasi_exact_match_gsm8k" ], "hf_avail_splits": [ "train", "test" ], "evaluation_splits": [ "test" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": 256, "stop_sequence": [ "Question:" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 1319, "effective_num_docs": 1319, "trust_dataset": true } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "640a54a3af4acf7d", "hash_input_tokens": "36ae76ed497ee9a2", "hash_cont_tokens": "69a62569afb555b5" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "63edc7243f4f9070", "hash_input_tokens": "6984c91bf3bf1c79", "hash_cont_tokens": "588bef232a1571c6" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "num_truncated_few_shots": 0 } }