| { | |
| "results": { | |
| "araMath_v3": { | |
| "alias": "araMath_v3", | |
| "acc,none": 0.26611570247933886, | |
| "acc_stderr,none": 0.017981693016247826, | |
| "acc_norm,none": 0.26611570247933886, | |
| "acc_norm_stderr,none": 0.017981693016247826 | |
| } | |
| }, | |
| "group_subtasks": { | |
| "araMath_v3": [] | |
| }, | |
| "configs": { | |
| "araMath_v3": { | |
| "task": "araMath_v3", | |
| "tag": [ | |
| "multiple_choice" | |
| ], | |
| "dataset_path": "lm_eval/tasks/araMath_v3/araMath_v3.py", | |
| "dataset_name": "araMath_v3", | |
| "dataset_kwargs": { | |
| "trust_remote_code": true | |
| }, | |
| "validation_split": "validation", | |
| "test_split": "test", | |
| "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_docs(doc):\n def remove_prefix(choice):\n prefixes = [\"(A)\", \"(B)\", \"(C)\", \"(D)\"]\n for prefix in prefixes:\n if choice.startswith(prefix + \" \"):\n return choice[len(prefix) + 1:] \n return choice \n\n def format_example(doc, keys):\n question = doc[\"question\"].strip()\n choices = \"\".join(\n [f\"{key}. {remove_prefix(choice)}\\n\" for key, choice in zip(keys, doc[\"options\"])]\n )\n\n prompt = f\"\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices}\\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n keys_en = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys_en),\n \"choices\": keys_en,\n \"gold\": keys_en.index(doc[\"label\"]),\n }\n return out_doc\n \n return dataset.map(_process_docs)\n", | |
| "doc_to_text": "query", | |
| "doc_to_target": "gold", | |
| "doc_to_choice": "{{choices}}", | |
| "description": "\u0645\u0646 \u0641\u0636\u0644\u0643 \u0627\u062e\u062a\u0631 \u0625\u062c\u0627\u0628\u0629 \u0648\u0627\u062d\u062f\u0629 \u0645\u0646 \u0628\u064a\u0646 'A\u060c B\u060c C\u060c D' \u062f\u0648\u0646 \u0634\u0631\u062d", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| }, | |
| { | |
| "metric": "acc_norm", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "multiple_choice", | |
| "repeats": 1, | |
| "should_decontaminate": true, | |
| "doc_to_decontamination_query": "query", | |
| "metadata": { | |
| "version": 0.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "araMath_v3": 0.0 | |
| }, | |
| "n-shot": { | |
| "araMath_v3": 5 | |
| }, | |
| "higher_is_better": { | |
| "araMath_v3": { | |
| "acc": true, | |
| "acc_norm": true | |
| } | |
| }, | |
| "n-samples": { | |
| "araMath_v3": { | |
| "original": 605, | |
| "effective": 605 | |
| } | |
| }, | |
| "config": { | |
| "model": "vllm", | |
| "model_args": "pretrained=inceptionai/jais-family-13b-chat,tensor_parallel_size=1,data_parallel_size=8,download_dir=/tmp,enforce_eager=False", | |
| "batch_size": 1, | |
| "batch_sizes": [], | |
| "device": null, | |
| "use_cache": null, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null, | |
| "random_seed": 0, | |
| "numpy_seed": 1234, | |
| "torch_seed": 1234, | |
| "fewshot_seed": 1234 | |
| }, | |
| "git_hash": "788a3672", | |
| "date": 1738675314.717633, | |
| "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.86\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect", | |
| "transformers_version": "4.48.2", | |
| "upper_git_hash": null, | |
| "tokenizer_pad_token": [ | |
| "<|endoftext|>", | |
| "0" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "<|endoftext|>", | |
| "0" | |
| ], | |
| "tokenizer_bos_token": [ | |
| "<|endoftext|>", | |
| "0" | |
| ], | |
| "eot_token_id": 0, | |
| "max_length": 2048, | |
| "task_hashes": { | |
| "araMath_v3": "b3fe722cebee19d37f6462a65a71854be30c8fada0a636e26fe49e070b49d07e" | |
| }, | |
| "model_source": "vllm", | |
| "model_name": "inceptionai/jais-family-13b-chat", | |
| "model_name_sanitized": "inceptionai__jais-family-13b-chat", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = '### Instruction: ' + messages[0]['content'] + '\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input:'%}{% else %}{% set loop_messages = messages %}{% set system_message = '### Instruction: Your name is \\'Jais\\', and you are named after Jebel Jais, the highest mountain in UAE. You were made by \\'Inception\\' in the UAE. You are a helpful, respectful, and honest assistant. Always answer as helpfully as possible, while being safe. Complete the conversation below between [|Human|] and [|AI|]:\n### Input:' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = system_message %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 %}{{ content + ' [|Human|] ' + message['content'] }}{% else %}{{ '\n[|Human|] ' + content.strip() }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n[|AI|] ' + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %} {{'\n[|AI|]\n### Response:'}}{% endif %}", | |
| "chat_template_sha": "83450a8b1d37090d808e836876679b8a0580f207e268605c01a54c91aac5346a", | |
| "start_time": 529237.504818623, | |
| "end_time": 529350.764209511, | |
| "total_evaluation_time_seconds": "113.25939088803716" | |
| } |