130 lines
11 KiB
JSON
130 lines
11 KiB
JSON
{
|
|
"results": {
|
|
"araPro": {
|
|
"alias": "araPro",
|
|
"acc,none": 0.41471705658868224,
|
|
"acc_stderr,none": 0.006967450316480296,
|
|
"acc_norm,none": 0.41471705658868224,
|
|
"acc_norm_stderr,none": 0.006967450316480296
|
|
}
|
|
},
|
|
"group_subtasks": {
|
|
"araPro": []
|
|
},
|
|
"configs": {
|
|
"araPro": {
|
|
"task": "araPro",
|
|
"tag": [
|
|
"multiple_choice"
|
|
],
|
|
"dataset_path": "lm_eval/tasks/araPro/araPro.py",
|
|
"dataset_name": "araPro",
|
|
"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 def _process_docs(doc): \n def remove_prefix(choice):\n return choice.replace('.', '') if '.' in choice[:2] else choice\n \n def format_example(doc, keys):\n question = doc[\"question\"].strip()\n \n choice_num = ['choice1', 'choice2', 'choice3', 'choice4']\n choices = \"\".join(\n [f\"{key}. {remove_prefix(doc[choice_num[index]])}\\n\" for index, key in enumerate(keys)]\n )\n\n prompt = f\"\\n\\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 = [\"1\", \"2\", \"3\", \"4\"]\n keys = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys), \n \"choices\": keys,\n \"gold\": doc[\"answer\"]-1,\n } \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": "\u0641\u064a\u0645\u0627 \u064a\u0644\u064a \u0623\u0633\u0626\u0644\u0629 \u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631 \u0645\u0646 \u0645\u062a\u0639\u062f\u062f (\u0645\u0639 \u0627\u0644\u0625\u062c\u0627\u0628\u0627\u062a) \u0645\u0646 \u0641\u0636\u0644\u0643 \u0627\u062e\u062a\u0631 \u0625\u062c\u0627\u0628\u0629 \u0648\u0627\u062d\u062f\u0629 \u062f\u0648\u0646 \u0634\u0631\u062d",
|
|
"target_delimiter": " ",
|
|
"fewshot_delimiter": "\n\n",
|
|
"fewshot_config": {
|
|
"sampler": "balanced_cat"
|
|
},
|
|
"num_fewshot": 0,
|
|
"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": "Question",
|
|
"metadata": {
|
|
"version": 2.0
|
|
}
|
|
}
|
|
},
|
|
"versions": {
|
|
"araPro": 2.0
|
|
},
|
|
"n-shot": {
|
|
"araPro": 0
|
|
},
|
|
"higher_is_better": {
|
|
"araPro": {
|
|
"acc": true,
|
|
"acc_norm": true
|
|
}
|
|
},
|
|
"n-samples": {
|
|
"araPro": {
|
|
"original": 5001,
|
|
"effective": 5001
|
|
}
|
|
},
|
|
"config": {
|
|
"model": "hf",
|
|
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
|
|
"model_num_parameters": 7455550464,
|
|
"model_dtype": "torch.bfloat16",
|
|
"model_revision": "main",
|
|
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
|
|
"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": "b955b2950",
|
|
"date": 1739617143.3614087,
|
|
"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: 4890.88\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": "4.48.3",
|
|
"upper_git_hash": null,
|
|
"tokenizer_pad_token": [
|
|
"<|pad|>",
|
|
"2023"
|
|
],
|
|
"tokenizer_eos_token": [
|
|
"<|endoftext|>",
|
|
"11"
|
|
],
|
|
"tokenizer_bos_token": [
|
|
null,
|
|
"None"
|
|
],
|
|
"eot_token_id": 11,
|
|
"max_length": 32768,
|
|
"task_hashes": {
|
|
"araPro": "063166ad2e52146b6a051c978bf54b1397281e222da633e81fa50357d2409ee9"
|
|
},
|
|
"model_source": "hf",
|
|
"model_name": "tiiuae/Falcon3-7B-Instruct",
|
|
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
|
|
"system_instruction": null,
|
|
"system_instruction_sha": null,
|
|
"fewshot_as_multiturn": false,
|
|
"chat_template": "{%- if tools %}\n{{- '<|system|>\\n' }}\n{%- if messages[0]['role'] == 'system' %}\n{{- messages[0]['content'] }}\n{%- set remaining_messages = messages[1:] %}\n{%- else %}\n{%- set remaining_messages = messages %}\n{%- endif %}\n{{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\\n\\n# Tools\\n\\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\\n\\n<tools>' + tools|tojson(indent=2) + '</tools>\\n\\n# Output Format\\n\\nYour response MUST follow this format when making function calls:\\n<tool_call>\\n[\\n {\"name\": \"function_name\", \"arguments\": {\"arg1\": \"value1\", \"arg2\": \"value2\"}},\\n {\"name\": \"another_function\", \"arguments\": {\"arg\": \"value\"}}\\n]\\n</tool_call>\\nIf no function calls are needed, respond normally without the tool_call tags.\\n' }}\n{%- for message in remaining_messages %}\n{%- if message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if message.content %}\n{{- '<|assistant|>\\n' + message['content'] }}\n{%- endif %}\n{%- if message.tool_calls %}\n{{- '\\n<tool_call>\\n' }}\n{{- message.tool_calls|tojson(indent=2) }}\n{{- '\\n</tool_call>' }}\n{%- endif %}\n{{- eos_token + '\\n' }}\n{%- elif message['role'] == 'tool' %}\n{{- '<|assistant|>\\n<tool_response>\\n' + message['content'] + '\\n</tool_response>\\n' }}\n{%- endif %}\n{%- endfor %}\n{{- '<|assistant|>\\n' if add_generation_prompt }}\n{%- else %}\n{%- for message in messages %}\n{%- if message['role'] == 'system' %}\n{{- '<|system|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'user' %}\n{{- '<|user|>\\n' + message['content'] + '\\n' }}\n{%- elif message['role'] == 'assistant' %}\n{%- if not loop.last %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token + '\\n' }}\n{%- else %}\n{{- '<|assistant|>\\n' + message['content'] + eos_token }}\n{%- endif %}\n{%- endif %}\n{%- if loop.last and add_generation_prompt %}\n{{- '<|assistant|>\\n' }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}",
|
|
"chat_template_sha": "914ccd80356f5822d1a50d97546e37f60c04ed831fe431aa40346574ec266901",
|
|
"start_time": 1391826.416201954,
|
|
"end_time": 1394850.089034202,
|
|
"total_evaluation_time_seconds": "3023.672832248034"
|
|
} |