lanawwas/ALLaM-7B-Instruct-preview
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lanawwas/ALLaM-7B-Instruct-preview
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 10:54:04 +08:00
commit 3e4c694337
466 changed files with 259661 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
evaluations/ar/Qwen2.5-7B-Instruct/acva_5_shot.json Normal file
View File

@@ -0,0 +1,123 @@
{
"results": {
"acva": {
"alias": "acva",
"acc,none": 0.7839265212399541,
"acc_stderr,none": 0.004410159183412007,
"acc_norm,none": 0.7817451205510907,
"acc_norm_stderr,none": 0.004426193797299392
}
},
"group_subtasks": {
"acva": []
},
"configs": {
"acva": {
"task": "acva",
"tag": [
"multiple_choice"
],
"dataset_path": "FreedomIntelligence/ACVA-Arabic-Cultural-Value-Alignment",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _format_subject(subject):\n \n arabic_words = subtasks_ar[subtasks.index(subject)]\n return arabic_words\n \n def _generate_subject(doc):\n subject = _format_subject(doc[\"id\"].split(\"-\")[0])\n\n return subject\n \n def _process_docs(doc):\n keys = [\"\u0635\u062d\",\n \"\u062e\u0637\u0623\"]\n subject = _generate_subject(doc)\n gold = keys.index(doc['answer'])\n out_doc = {\n \"id\": doc[\"id\"],\n \"query\": \"\\n\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644:\" + doc[\"question\"]+\"\\n\u0625\u062c\u0627\u0628\u0629:'\",\n \"choices\": keys,\n \"gold\": gold,\n \"subject\": subject,\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 \u0639\u0628\u0627\u0631\u0627\u062a \u0625\u0645\u0627 \u0635\u062d\u064a\u062d\u0629 \u0623\u0648 \u062e\u0627\u0637\u0626\u0629 \u062d\u0648\u0644 {{subject}}\n \u0627\u0644\u0631\u062c\u0627\u0621 \u062a\u0635\u0646\u064a\u0641 \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0625\u0644\u0649 '\u0635\u062d' \u0623\u0648 '\u062e\u0637\u0623' \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": false,
"metadata": {
"version": 0.0
}
}
},
"versions": {
"acva": 0.0
},
"n-shot": {
"acva": 5
},
"higher_is_better": {
"acva": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"acva": {
"original": 8710,
"effective": 8710
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"batch_size": "auto",
"batch_sizes": [
64
],
"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": "5e10e017",
"date": 1736969210.259454,
"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: 4890.86\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 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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 3831.319873887,
"end_time": 4381.143410904,
"total_evaluation_time_seconds": "549.823537017"
}

142
evaluations/ar/Qwen2.5-7B-Instruct/ar_ifeval_0_shot.json Normal file
View File

@@ -0,0 +1,142 @@
{
"results": {
"ar_ifeval": {
"alias": "ar_ifeval",
"prompt_level_strict_acc,none": 0.28171641791044777,
"prompt_level_strict_acc_stderr,none": 0.019448099048933045,
"inst_level_strict_acc,none": 0.6518771331058021,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.332089552238806,
"prompt_level_loose_acc_stderr,none": 0.020361503053631682,
"inst_level_loose_acc,none": 0.6805460750853243,
"inst_level_loose_acc_stderr,none": "N/A"
}
},
"group_subtasks": {
"ar_ifeval": []
},
"configs": {
"ar_ifeval": {
"task": "ar_ifeval",
"dataset_path": "lm_eval/tasks/ar_ifeval/ar_ifeval.py",
"dataset_name": "ar_ifeval",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"doc_to_text": "prompt",
"doc_to_target": 0,
"process_results": "def process_results(doc, results):\n\n response = results[0]\n out_strict = process_sample(doc, response, 'strict')\n out_loose = process_sample(doc, response, 'loose')\n\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "prompt_level_strict_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_strict_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
},
{
"metric": "prompt_level_loose_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_loose_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1280
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 4.0
}
}
},
"versions": {
"ar_ifeval": 4.0
},
"n-shot": {
"ar_ifeval": 0
},
"higher_is_better": {
"ar_ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
}
},
"n-samples": {
"ar_ifeval": {
"original": 536,
"effective": 536
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738576311.7497714,
"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: 4890.87\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 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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"ar_ifeval": "e94d7ab29bcea6c517c784b2aa65ffd558e3b4c84901ed8e147df9bd1f71c35c"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 1344856.801255893,
"end_time": 1348853.74844184,
"total_evaluation_time_seconds": "3996.947185947094"
}

126
evaluations/ar/Qwen2.5-7B-Instruct/araMath_v3_5_shot.json Normal file
View File

@@ -0,0 +1,126 @@
{
"results": {
"araMath_v3": {
"alias": "araMath_v3",
"acc,none": 0.7173553719008264,
"acc_stderr,none": 0.01832183956763465,
"acc_norm,none": 0.7173553719008264,
"acc_norm_stderr,none": 0.01832183956763465
}
},
"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": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738675616.0209072,
"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": "4.48.2",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|endoftext|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"araMath_v3": "4afa6622c31e4fb937d7ad0da2119b52cd56b8bedea0f95cc12cc332c35e09f6"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 674736.742411863,
"end_time": 674788.659606429,
"total_evaluation_time_seconds": "51.917194566107355"
}

130
evaluations/ar/Qwen2.5-7B-Instruct/araPro_0_shot.json Normal file
View File

@@ -0,0 +1,130 @@
{
"results": {
"araPro": {
"alias": "araPro",
"acc,none": 0.6462707458508299,
"acc_stderr,none": 0.006761728608991266,
"acc_norm,none": 0.6462707458508299,
"acc_norm_stderr,none": 0.006761728608991266
}
},
"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=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738745497.0234828,
"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: 4890.87\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 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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"araPro": "59a5e15442970296d6c76ad4c1ea628b774166211f664b5c0f3eb594d33d6eb2"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 1109114.192296206,
"end_time": 1109669.826812652,
"total_evaluation_time_seconds": "555.6345164459199"
}

2049
evaluations/ar/Qwen2.5-7B-Instruct/arabicmmlu_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff

126
evaluations/ar/Qwen2.5-7B-Instruct/etec_v2_0_shot.json Normal file
View File

@@ -0,0 +1,126 @@
{
"results": {
"etec_v2": {
"alias": "etec_v2",
"acc,none": 0.6412294647588765,
"acc_stderr,none": 0.011044454621265165,
"acc_norm,none": 0.6412294647588765,
"acc_norm_stderr,none": 0.011044454621265165
}
},
"group_subtasks": {
"etec_v2": []
},
"configs": {
"etec_v2": {
"task": "etec_v2",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/etec_v2/etec.py",
"dataset_name": "etec_v2",
"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 format_example(doc, keys):\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 print(doc[\"label\"])\n keys_ar = [\"\u0623\", \"\u0628\", \"\u062c\", \"\u062f\"]\n keys_en = [\"A\", \"B\", \"C\", \"D\"]\n out_doc = {\n \"query\": format_example(doc, keys_en),\n \"choices\": keys_en,\n \"gold\": int(doc[\"label\"])-1,\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\n ",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"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": "query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"etec_v2": 0.0
},
"n-shot": {
"etec_v2": 0
},
"higher_is_better": {
"etec_v2": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"etec_v2": {
"original": 1887,
"effective": 1887
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738682237.6531827,
"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: 4890.89\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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"etec_v2": "ccf52ad4d1e05dccde272349596fb8819b25302b4afaa8ddefdc7288f9965839"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 1057097.582369473,
"end_time": 1057186.664077031,
"total_evaluation_time_seconds": "89.08170755789615"
}

127
evaluations/ar/Qwen2.5-7B-Instruct/exams_ar_5_shot.json Normal file
View File

@@ -0,0 +1,127 @@
{
"results": {
"exams_ar": {
"alias": "exams_ar",
"acc,none": 0.5065176908752328,
"acc_stderr,none": 0.02159487569233192,
"acc_norm,none": 0.5065176908752328,
"acc_norm_stderr,none": 0.02159487569233192
}
},
"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 <prompt>\n \u0633\u0624\u0627\u0644:\n A. <choice1>\n B. <choice2>\n C. <choice3>\n D. <choice4>\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=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"batch_size": "auto",
"batch_sizes": [
64
],
"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": 1737022505.297799,
"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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 101438.818449475,
"end_time": 101848.977613468,
"total_evaluation_time_seconds": "410.1591639929975"
}

543
evaluations/ar/Qwen2.5-7B-Instruct/gat_0_shot.json Normal file
View File

@@ -0,0 +1,543 @@
{
"results": {
"gat": {
"acc,none": 0.4142104603035244,
"acc_stderr,none": 0.0038397567806533668,
"alias": "gat"
},
"gat_algebra": {
"alias": " - gat_algebra",
"acc,none": 0.3888682745825603,
"acc_stderr,none": 0.009392255011265211
},
"gat_analogy": {
"alias": " - gat_analogy",
"acc,none": 0.3493624772313297,
"acc_stderr,none": 0.009101555643753388
},
"gat_arithmetic": {
"alias": " - gat_arithmetic",
"acc,none": 0.36474052263525947,
"acc_stderr,none": 0.009236399342894993
},
"gat_association": {
"alias": " - gat_association",
"acc,none": 0.5023923444976076,
"acc_stderr,none": 0.0154744343816748
},
"gat_comparisons": {
"alias": " - gat_comparisons",
"acc,none": 0.30901639344262294,
"acc_stderr,none": 0.013234964445015209
},
"gat_completion": {
"alias": " - gat_completion",
"acc,none": 0.5462809917355372,
"acc_stderr,none": 0.01431819857472042
},
"gat_contextual": {
"alias": " - gat_contextual",
"acc,none": 0.32745398773006135,
"acc_stderr,none": 0.013000616127135718
},
"gat_geometry": {
"alias": " - gat_geometry",
"acc,none": 0.43561643835616437,
"acc_stderr,none": 0.025988942967463693
},
"gat_reading": {
"alias": " - gat_reading",
"acc,none": 0.5512287334593573,
"acc_stderr,none": 0.00967270003130818
}
},
"groups": {
"gat": {
"acc,none": 0.4142104603035244,
"acc_stderr,none": 0.0038397567806533668,
"alias": "gat"
}
},
"group_subtasks": {
"gat": [
"gat_analogy",
"gat_association",
"gat_completion",
"gat_reading",
"gat_algebra",
"gat_arithmetic",
"gat_comparisons",
"gat_contextual",
"gat_geometry"
]
},
"configs": {
"gat_algebra": {
"task": "gat_algebra",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_analogy": {
"task": "gat_analogy",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "analogy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_arithmetic": {
"task": "gat_arithmetic",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "arithmetic",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_association": {
"task": "gat_association",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "association",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_comparisons": {
"task": "gat_comparisons",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "comparisons",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_completion": {
"task": "gat_completion",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "completion",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_contextual": {
"task": "gat_contextual",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "contextual",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "\u0627\u0648\u062c\u062f \u0627\u0644\u062e\u0637\u0623 \u0627\u0644\u0633\u064a\u0627\u0642\u064a \u0641\u064a \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0645\u0646 \u0628\u064a\u0646 \u0627\u0644\u062e\u064a\u0627\u0631\u0627\u062a:",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_geometry": {
"task": "gat_geometry",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "geometry",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"gat_reading": {
"task": "gat_reading",
"dataset_path": "lm_eval/tasks/gat/gat_data/gat.py",
"dataset_name": "reading",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n",
"doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:",
"doc_to_target": "{{label}}",
"doc_to_choice": [
"\u0623",
"\u0628",
"\u062c",
"\u062f"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
}
},
"versions": {
"gat": 0,
"gat_algebra": 0.0,
"gat_analogy": 0.0,
"gat_arithmetic": 0.0,
"gat_association": 0.0,
"gat_comparisons": 0.0,
"gat_completion": 0.0,
"gat_contextual": 0.0,
"gat_geometry": 0.0,
"gat_reading": 0.0
},
"n-shot": {
"gat_algebra": 0,
"gat_analogy": 0,
"gat_arithmetic": 0,
"gat_association": 0,
"gat_comparisons": 0,
"gat_completion": 0,
"gat_contextual": 0,
"gat_geometry": 0,
"gat_reading": 0
},
"higher_is_better": {
"gat": {
"acc": true
},
"gat_algebra": {
"acc": true
},
"gat_analogy": {
"acc": true
},
"gat_arithmetic": {
"acc": true
},
"gat_association": {
"acc": true
},
"gat_comparisons": {
"acc": true
},
"gat_completion": {
"acc": true
},
"gat_contextual": {
"acc": true
},
"gat_geometry": {
"acc": true
},
"gat_reading": {
"acc": true
}
},
"n-samples": {
"gat_analogy": {
"original": 2745,
"effective": 2745
},
"gat_association": {
"original": 1045,
"effective": 1045
},
"gat_completion": {
"original": 1210,
"effective": 1210
},
"gat_reading": {
"original": 2645,
"effective": 2645
},
"gat_algebra": {
"original": 2695,
"effective": 2695
},
"gat_arithmetic": {
"original": 2717,
"effective": 2717
},
"gat_comparisons": {
"original": 1220,
"effective": 1220
},
"gat_contextual": {
"original": 1304,
"effective": 1304
},
"gat_geometry": {
"original": 365,
"effective": 365
}
},
"config": {
"model": "hf",
"model_args": "parallelize=False,pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,mm=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75",
"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": "3127d82f",
"date": 1730951149.5236645,
"pretty_env_info": "PyTorch version: 2.1.0a0+29c30b1\nIs debug build: False\nCUDA used to build PyTorch: 12.2\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==1.22.2\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.1.0a0+29c30b1\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==0.16.0a0\n[pip3] triton==2.0.0.dev20221202\n[conda] Could not collect",
"transformers_version": "4.38.2",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|endoftext|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 8058.842983944,
"end_time": 9035.124412401,
"total_evaluation_time_seconds": "976.2814284570013"
}

127
evaluations/ar/Qwen2.5-7B-Instruct/moe_ien_mcq_0_shot.json Normal file
View File

@@ -0,0 +1,127 @@
{
"results": {
"moe_ien_mcq": {
"alias": "moe_ien_mcq",
"acc,none": 0.6637637637637638,
"acc_stderr,none": 0.004726808644291313,
"acc_norm,none": 0.6637637637637638,
"acc_norm_stderr,none": 0.004726808644291313
}
},
"group_subtasks": {
"moe_ien_mcq": []
},
"configs": {
"moe_ien_mcq": {
"task": "moe_ien_mcq",
"dataset_path": "lm_eval/tasks/moe_ien_mcq/ien_moe_mcq.py",
"dataset_name": "moe_ien_mcq",
"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.split(\". \", 1)[1] if \". \" in choice else choice\n\n def format_example(doc, keys):\n question = doc[\"Question\"].strip()\n \n choices = \"\".join(\n [f\"{key}. {remove_prefix(choice)}\\n\" for key, choice in zip(keys, doc[\"Choices\"])]\n \n )\n prompt = f\"\\n\\n\u0633\u0624\u0627\u0644: {question}\\n{choices} \\n\u0627\u062c\u0627\u0628\u0629:\"\n return prompt\n\n keys = [\"A\", \"B\", \"C\", \"D\", \"E\", \"F\"][0:len(doc[\"Choices\"])]\n out_doc = {\n \"Query\": format_example(doc, keys), \n \"Choices\": keys,\n \"gold\": int(doc[\"Answer\"])-1, ## \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\u202f\u064a\u0644\u064a\u202f\u0623\u0633\u0626\u0644\u0629\u202f\u0627\u0644\u0627\u062e\u062a\u064a\u0627\u0631\u202f\u0645\u0646\u202f\u0645\u062a\u0639\u062f\u062f\u202f(\u0645\u0639\u202f\u0627\u0644\u0625\u062c\u0627\u0628\u0627\u062a)\u202f\u0641\u064a\u202f{{Subject}}",
"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": "Query",
"metadata": {
"version": 0.0
}
}
},
"versions": {
"moe_ien_mcq": 0.0
},
"n-shot": {
"moe_ien_mcq": 0
},
"higher_is_better": {
"moe_ien_mcq": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"moe_ien_mcq": {
"original": 9990,
"effective": 9990
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738674600.0544074,
"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": "4.48.2",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|endoftext|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"moe_ien_mcq": "ce48b9a14bd92b18b8dc937edb46c180c4856590e207dc535b0ed1f5e8d9a7a5"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 673720.647842419,
"end_time": 674046.632315245,
"total_evaluation_time_seconds": "325.9844728260068"
}

129
evaluations/ar/Qwen2.5-7B-Instruct/moe_ien_tf_0_shot.json Normal file
View File

@@ -0,0 +1,129 @@
{
"results": {
"moe_ien_tf": {
"alias": "moe_ien_tf",
"acc,none": 0.7846470891293148,
"acc_stderr,none": 0.005387365696365709,
"acc_norm,none": 0.7846470891293148,
"acc_norm_stderr,none": 0.005387365696365709
}
},
"group_subtasks": {
"moe_ien_tf": []
},
"configs": {
"moe_ien_tf": {
"task": "moe_ien_tf",
"tag": [
"multiple_choice"
],
"dataset_path": "lm_eval/tasks/moe_ien_tf/moe_ien_tf.py",
"dataset_name": "moe_ien_tf",
"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 keys=[\"\u0635\u062d\u064a\u062d\u0629\",\n \"\u062e\u0627\u0637\u0626\u0629\"\n ]\n #keys =[\"\u0635\u0648\u0627\u0628\",\n # \"\u062e\u0637\u0623\"]\n target_key = int(doc[\"Answer\"])-1\n\n out_doc = {\n \"query\": \"\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644:\" +doc[\"Question\"]+\"\\n\u0625\u062c\u0627\u0628\u0629:'\", \n \"choices\": keys,\n \"gold\": target_key,\n }\n return out_doc\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 \u0639\u0628\u0627\u0631\u0627\u062a \u0625\u0645\u0627 \u0635\u062d\u064a\u062d\u0629 \u0623\u0648 \u062e\u0627\u0637\u0626\u0629 \u062d\u0648\u0644 {{Subject}}\n \u0627\u0644\u0631\u062c\u0627\u0621 \u062a\u0635\u0646\u064a\u0641 \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0625\u0644\u0649 '\u0635\u062d\u064a\u062d\u0629' \u0623\u0648 '\u062e\u0627\u0637\u0626\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": false,
"metadata": {
"version": 2.0
}
}
},
"versions": {
"moe_ien_tf": 2.0
},
"n-shot": {
"moe_ien_tf": 0
},
"higher_is_better": {
"moe_ien_tf": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"moe_ien_tf": {
"original": 5823,
"effective": 5823
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
"model_num_parameters": 7615616512,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "a09a35458c702b33eeacc393d103063234e8bc28",
"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": 1738682461.636686,
"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: 4890.89\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|>",
"151643"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 151645,
"max_length": 32768,
"task_hashes": {
"moe_ien_tf": "f4ddc3d519c912c82ff8c20b8732077ac9136d725beb5ceddd9896a9640d070e"
},
"model_source": "hf",
"model_name": "Qwen/Qwen2.5-7B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"chat_template_sha": "cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f",
"start_time": 1057321.504482153,
"end_time": 1057680.019318038,
"total_evaluation_time_seconds": "358.5148358847946"
}

2662
evaluations/ar/Qwen2.5-7B-Instruct/openaimmlu_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff