140 lines
11 KiB
JSON
140 lines
11 KiB
JSON
|
{
|
||
|
|
"results": {
|
||
|
|
"ar_ifeval": {
|
||
|
|
"alias": "ar_ifeval",
|
||
|
|
"prompt_level_strict_acc,none": 0.6865671641791045,
|
||
|
|
"prompt_level_strict_acc_stderr,none": 0.020055655889994813,
|
||
|
|
"inst_level_strict_acc,none": 0.8675767918088737,
|
||
|
|
"inst_level_strict_acc_stderr,none": "N/A",
|
||
|
|
"prompt_level_loose_acc,none": 0.7798507462686567,
|
||
|
|
"prompt_level_loose_acc_stderr,none": 0.017913789384648014,
|
||
|
|
"inst_level_loose_acc,none": 0.9078498293515358,
|
||
|
|
"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/Qwen2.5-14B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
|
||
|
|
"model_num_parameters": 14770033664,
|
||
|
|
"model_dtype": "torch.bfloat16",
|
||
|
|
"model_revision": "main",
|
||
|
|
"model_sha": "cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8",
|
||
|
|
"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": "150ae04f",
|
||
|
|
"date": 1737366501.2749803,
|
||
|
|
"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 3.27.9\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [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: 12.3.107\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: 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.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.7\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.7\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 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\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: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (12 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: 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==1.15.0rc2\n[pip3] open_clip_torch==2.26.1\n[pip3] optree==0.10.0\n[p
|
||
|
|
"transformers_version": "4.48.0",
|
||
|
|
"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/Qwen2.5-14B-Instruct",
|
||
|
|
"model_name_sanitized": "Qwen__Qwen2.5-14B-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": 1222795.529793559,
|
||
|
|
"end_time": 1224741.388765624,
|
||
|
|
"total_evaluation_time_seconds": "1945.858972064918"
|
||
|
|
}
|