{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 559757.397885727, "end_time": 563006.919563832, "total_evaluation_time_secondes": "3249.5216781049967", "model_name": "abhishek/autotrain-llama3-oh-sft-v0-2", "model_sha": "14e07850d3e1ee35f5788270ab514c2e3b3821bf", "model_dtype": "torch.float16", "model_size": "131.73 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.8597422289613343, "qem_stderr": 0.009565108281428656 }, "all": { "qem": 0.8597422289613343, "qem_stderr": 0.009565108281428656 } }, "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, "must_remove_duplicate_docs": null } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "a9c6515c2ecd2d07", "hash_input_tokens": "a2f1c23e78a778da", "hash_cont_tokens": "7783c30291d4b6b2" }, "truncated": 1319, "non_truncated": 0, "padded": 623, "non_padded": 696, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "f49691ec139bfeac", "hash_input_tokens": "df014b250093da23", "hash_cont_tokens": "d4c288a419c4c26b" }, "truncated": 1319, "non_truncated": 0, "padded": 623, "non_padded": 696, "num_truncated_few_shots": 0 } }