{ "args": { "out": "/mnt/beegfs/yi/laoyao_2b_moe_pretraining_dataset/validation/sft_heldout_2p8k_20260611", "tokenizer": "/mnt/beegfs/yi/laoyao_moe_rebalanced/tokenizers/pretrain-mix-code40-text60-bpe-65k-20260623", "train_total": 0, "test_per_group": 400, "seed": 20260611, "hf_endpoint": "https://hf-mirror.com", "use_hf": true, "allow_shortfall": true, "upsample_train_shortfall": false, "min_prompt_tokens": 4, "min_answer_tokens": 8, "max_prompt_tokens": 1024, "max_answer_tokens": 1024, "trust_metadata_lengths": true, "max_seen_per_source": 300000, "stop_empty_source_early": false }, "train_ratios": { "chinese_exam": 0, "chinese_dialogue": 35, "code": 30, "math": 20, "logic": 5, "science_reasoning": 5, "english_dialogue": 5 }, "test_quotas": { "chinese_exam": 400, "chinese_dialogue": 400, "code": 400, "math": 400, "logic": 400, "science_reasoning": 400, "english_dialogue": 400 }, "loaders": { "test_hf": { "test:chinese_exam:ceval/ceval-exam": { "seen": 546, "accepted": 400, "too_short": 146 }, "test:chinese_dialogue:m-a-p/COIG-CQIA": { "seen": 478, "too_long": 78, "accepted": 400 }, "test:code:openai/openai_humaneval": { "seen": 164, "accepted": 159, "too_short": 3, "too_long": 2 }, "test:code:google-research-datasets/mbpp": { "seen": 241, "accepted": 241 }, "test:math:gsm8k": { "seen": 400, "accepted": 400 }, "test:logic:cais/mmlu": { "seen": 331, "accepted": 212, "too_short": 119 }, "test:logic:lighteval/bbh": { "load_error:test:logical_deduction_three_objects": 1, "error:ValueError(\"Bad split: test. Available splits: ['train']\")": 1, "seen": 246, "accepted": 188, "too_short": 58 }, "test:science_reasoning:Idavidrein/gpqa": { "load_error:train:None": 1, "error:ValueError(\"Config name is missing.\\nPlease pick one among the available configs: ['gpqa_extended', 'gpqa_main', 'gpqa_diamond', 'gpqa_experts']\\nExample of usa": 1 }, "test:science_reasoning:allenai/ai2_arc": { "seen": 567, "accepted": 400, "too_short": 167 }, "test:english_dialogue:HuggingFaceH4/ultrachat_200k": { "seen": 501, "too_long": 100, "accepted": 400, "too_short": 1 } }, "train_local": {}, "train_hf": {} }, "result": { "failed": false, "test_total": 2800, "train_total": 0, "test_counts": { "logic": 400, "chinese_dialogue": 400, "math": 400, "science_reasoning": 400, "chinese_exam": 400, "code": 400, "english_dialogue": 400 }, "train_counts": {}, "test_shortfall": {}, "train_shortfall": {}, "train_upsampled": {}, "train_quotas": { "chinese_exam": 0, "chinese_dialogue": 0, "code": 0, "math": 0, "logic": 0, "science_reasoning": 0, "english_dialogue": 0 }, "train_source_top": {}, "test_source_top": { "m-a-p/COIG-CQIA:zhihu": 400, "gsm8k:main": 400, "allenai/ai2_arc:ARC-Challenge": 400, "HuggingFaceH4/ultrachat_200k": 400, "google-research-datasets/mbpp": 241, "lighteval/bbh:logical_deduction_three_objects": 188, "openai/openai_humaneval": 159, "cais/mmlu:logical_fallacies": 113, "cais/mmlu:formal_logic": 99, "ceval/ceval-exam:college_economics": 48, "ceval/ceval-exam:accountant": 43, "ceval/ceval-exam:civil_servant": 41, "ceval/ceval-exam:business_administration": 27, "ceval/ceval-exam:college_programming": 26, "ceval/ceval-exam:education_science": 26, "ceval/ceval-exam:art_studies": 25, "ceval/ceval-exam:clinical_medicine": 25, "ceval/ceval-exam:advanced_mathematics": 22, "ceval/ceval-exam:college_chemistry": 21, "ceval/ceval-exam:basic_medicine": 21, "ceval/ceval-exam:college_physics": 18, "ceval/ceval-exam:computer_architecture": 16, "ceval/ceval-exam:chinese_language_and_literature": 16, "ceval/ceval-exam:discrete_mathematics": 13, "ceval/ceval-exam:computer_network": 11, "ceval/ceval-exam:electrical_engineer": 1 } } }