File size: 13,060 Bytes
6f25beb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 |
{
"results": {
"araMath_v3": {
"alias": "araMath_v3",
"acc,none": 0.27107438016528923,
"acc_stderr,none": 0.01808703482553977,
"acc_norm,none": 0.27107438016528923,
"acc_norm_stderr,none": 0.01808703482553977
}
},
"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=mistralai/Mistral-7B-Instruct-v0.3,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7248023552,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db",
"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": 1739618557.9082067,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.3",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 32768,
"task_hashes": {
"araMath_v3": "fc6325d1e91d814a9212e7cd3d01a2ea0128526a5ff5a12b13029293c7b85a14"
},
"model_source": "hf",
"model_name": "mistralai/Mistral-7B-Instruct-v0.3",
"model_name_sanitized": "mistralai__Mistral-7B-Instruct-v0.3",
"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\"]|trim + 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 optional system message!\") }}\n {%- endif %}\n{%- endfor %}\n",
"chat_template_sha": "e16746b40344d6c5b5265988e0328a0bf7277be86f1c335156eae07e29c82826",
"start_time": 1583844.288660905,
"end_time": 1583895.209942275,
"total_evaluation_time_seconds": "50.921281369868666"
} |