{ "results": { "exams_ar": { "alias": "exams_ar", "acc,none": 0.4506517690875233, "acc_stderr,none": 0.021491266540407467, "acc_norm,none": 0.4506517690875233, "acc_norm_stderr,none": 0.021491266540407467 } }, "group_subtasks": { "exams_ar": [] }, "configs": { "exams_ar": { "task": "exams_ar", "tag": [ "multiple_choice" ], "dataset_path": "lm_eval/tasks/exams_ar", "dataset_name": "exams_ar", "dataset_kwargs": { "trust_remote_code": true }, "validation_split": "validation", "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n\n def _process_docs(doc):\n def format_example(doc, keys):\n \"\"\"\n \n \u0633\u0624\u0627\u0644:\n A. \n B. \n C. \n D. \n \u0627\u062c\u0627\u0628\u0629:\n \"\"\"\n \n question = doc[\"question\"].strip()\n \n choices = \"\".join(\n [f\"{key}. {choice}\\n\" for key, choice in zip(keys, doc[\"choices\"])]\n )\n prompt = f\"\u0627\u0644\u0633\u0624\u0627\u0644: {question}\\n{choices} \\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n def _format_subject(subject):\n arabic_words = subtasks_ar[subtasks.index(subject)]\n return arabic_words\n\n keys = [\"A\", \"B\", \"C\", \"D\"]\n \n subject = doc['id'].split(\"-\")[0]\n description = f\"\ufed2\ufef4\ufee3\ufe8d \ufef2\ufee0\ufef3 \ufe84\ufeb4\ufe8c\ufedf\ufe93 \ufe8d\ufefc\ufea8\ufe98\ufef3\ufe8d\ufead \ufee2\ufee7 \ufee2\ufe98\ufecb\ufea9\ufea9 (\ufee2\ufecb \ufe8d\ufefa\ufe9f\ufe8e\ufe91\ufe8e\ufe97) \ufea1\ufeee\ufedf {_format_subject(subject)} \\n\" #\ufee2\ufee7 \ufed2\ufec0\ufee0\ufedb \ufe8e\ufea8\ufe97\ufead \ufe88\ufe9f\ufe8e\ufe91\ufe93 \ufeed\ufe8e\ufea3\ufea9\ufe93 \ufee2\ufee7 \ufe90\ufef4\ufee7 'A\u060c B\u060c C\u060c D' \ufea9\ufeee\ufee7 \ufeb5\ufeae\ufea3\\n\"\n\n out_doc = {\n \"idx\": doc[\"idx\"],\n \"id\": doc[\"id\"],\n 'dsecription': description,\n \"query\": format_example(doc, keys), # \"Question: \" + doc[\"question\"]['stem'] + \"\\nAnswer:\",\n \"choices\": keys,\n \"gold\": [\"A\", \"B\", \"C\", \"D\"].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": "description", "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": 1.0 } } }, "versions": { "exams_ar": 1.0 }, "n-shot": { "exams_ar": 5 }, "higher_is_better": { "exams_ar": { "acc": true, "acc_norm": true } }, "n-samples": { "exams_ar": { "original": 537, "effective": 537 } }, "config": { "model": "hf", "model_args": "pretrained=inceptionai/jais-family-13b-chat,trust_remote_code=True,cache_dir=/tmp,parallelize=False", "model_num_parameters": 13027571240, "model_dtype": "torch.float32", "model_revision": "main", "model_sha": "0ef8b4f80429609890816d912b331d3b95864707", "batch_size": "auto", "batch_sizes": [ 8 ], "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": "150ae04f", "date": 1737023418.5168922, "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 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\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): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.87\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\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: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\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": "4.48.0", "upper_git_hash": "2e5cd5395faf76fea1afc96dd0f7161a9d3aa145", "tokenizer_pad_token": [ "<|endoftext|>", "0" ], "tokenizer_eos_token": [ "<|endoftext|>", "0" ], "tokenizer_bos_token": [ "<|endoftext|>", "0" ], "eot_token_id": 0, "max_length": 2048, "task_hashes": {}, "model_source": "hf", "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": null, "chat_template_sha": null, "start_time": 3042.082462715, "end_time": 4392.50396786, "total_evaluation_time_seconds": "1350.4215051449996" }