142 lines
13 KiB
JSON
142 lines
13 KiB
JSON
|
{
|
||
|
|
"results": {
|
||
|
|
"ar_ifeval": {
|
||
|
|
"alias": "ar_ifeval",
|
||
|
|
"prompt_level_strict_acc,none": 0.3582089552238806,
|
||
|
|
"prompt_level_strict_acc_stderr,none": 0.020729467924035978,
|
||
|
|
"inst_level_strict_acc,none": 0.70580204778157,
|
||
|
|
"inst_level_strict_acc_stderr,none": "N/A",
|
||
|
|
"prompt_level_loose_acc,none": 0.44402985074626866,
|
||
|
|
"prompt_level_loose_acc_stderr,none": 0.021481021503779226,
|
||
|
|
"inst_level_loose_acc,none": 0.7631399317406143,
|
||
|
|
"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=mistralai/Mistral-Nemo-Instruct-2407,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
|
||
|
|
"model_num_parameters": 12247782400,
|
||
|
|
"model_dtype": "torch.bfloat16",
|
||
|
|
"model_revision": "main",
|
||
|
|
"model_sha": "8aedd450f2583e9c67fae1929f6936b8fc5aef9c",
|
||
|
|
"batch_size": 1,
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": null,
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null,
|
||
|
|
"random_seed": 0,
|
||
|
|
"numpy_seed": 1234,
|
||
|
|
"torch_seed": 1234,
|
||
|
|
"fewshot_seed": 1234
|
||
|
|
},
|
||
|
|
"git_hash": "b955b2950",
|
||
|
|
"date": 1739619352.6594934,
|
||
|
|
"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:
|
||
|
|
"transformers_version": "4.48.3",
|
||
|
|
"upper_git_hash": null,
|
||
|
|
"tokenizer_pad_token": [
|
||
|
|
"<unk>",
|
||
|
|
"0"
|
||
|
|
],
|
||
|
|
"tokenizer_eos_token": [
|
||
|
|
"</s>",
|
||
|
|
"2"
|
||
|
|
],
|
||
|
|
"tokenizer_bos_token": [
|
||
|
|
"<s>",
|
||
|
|
"1"
|
||
|
|
],
|
||
|
|
"eot_token_id": 2,
|
||
|
|
"max_length": 131072,
|
||
|
|
"task_hashes": {
|
||
|
|
"ar_ifeval": "f326b8a98c506486038a589a169e687707c38c2ea33f7dd1189337e8bafb199b"
|
||
|
|
},
|
||
|
|
"model_source": "hf",
|
||
|
|
"model_name": "mistralai/Mistral-Nemo-Instruct-2407",
|
||
|
|
"model_name_sanitized": "mistralai__Mistral-Nemo-Instruct-2407",
|
||
|
|
"system_instruction": null,
|
||
|
|
"system_instruction_sha": null,
|
||
|
|
"fewshot_as_multiturn": false,
|
||
|
|
"chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}\n{%- set ns = namespace() %}\n{%- set ns.index = 0 %}\n{%- for message in loop_messages %}\n {%- if not (message.role == \"tool\" or message.role == \"tool_results\" or (message.tool_calls is defined and message.tool_calls is not none)) %}\n {%- if (message[\"role\"] == \"user\") != (ns.index % 2 == 0) %}\n {{- raise_exception(\"After the optional system message, conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif %}\n {%- set ns.index = ns.index + 1 %}\n {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if message[\"role\"] == \"user\" %}\n {%- if tools is not none and (message == user_messages[-1]) %}\n {{- \"[AVAILABLE_TOOLS][\" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- '{\"type\": \"function\", \"function\": {' }}\n {%- for key, val in tool.items() if key != \"return\" %}\n {%- if val is string %}\n {{- '\"' + key + '\": \"' + val + '\"' }}\n {%- else %}\n {{- '\"' + key + '\": ' + val|tojson }}\n {%- endif %}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \"}}\" }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" }}\n {%- endif %}\n {%- endfor %}\n {{- \"[/AVAILABLE_TOOLS]\" }}\n {%- endif %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST]\" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n {%- else %}\n {{- \"[INST]\" + message[\"content\"] + \"[/INST]\" }}\n {%- endif %}\n {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}\n {{- \"[TOOL_CALLS][\" }}\n {%- for tool_call in message.tool_calls %}\n {%- set out = tool_call.function|tojson %}\n {{- out[:-1] }}\n {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" + eos_token }}\n {%- endif %}\n {%- endfor %}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- message[\"content\"] + eos_token}}\n {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n {%- if message.content is defined and message.content.content is defined %}\n {%- set content = message.content.content %}\n {%- else %}\n {%- set content = message.content %}\n {%- endif %}\n {{- '[TOOL_RESULTS]{\"content\": ' + content|string + \", \" }}\n {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial op
|
||
|
|
"chat_template_sha": "e4676cb56dffea7782fd3e2b577cfaf1e123537e6ef49b3ec7caa6c095c62272",
|
||
|
|
"start_time": 1394036.696567707,
|
||
|
|
"end_time": 1403362.389299741,
|
||
|
|
"total_evaluation_time_seconds": "9325.692732034018"
|
||
|
|
}
|