File size: 8,369 Bytes
661e616 |
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 |
{
"results": {
"gpqa_main_n_shot": {
"alias": "gpqa_main_n_shot",
"acc,none": 0.25669642857142855,
"acc_stderr,none": 0.020660425491724695,
"acc_norm,none": 0.25669642857142855,
"acc_norm_stderr,none": 0.020660425491724695
}
},
"group_subtasks": {
"gpqa_main_n_shot": []
},
"configs": {
"gpqa_main_n_shot": {
"task": "gpqa_main_n_shot",
"tag": "gpqa",
"dataset_path": "Idavidrein/gpqa",
"dataset_name": "gpqa_main",
"training_split": "train",
"validation_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n choices = [\n preprocess(doc[\"Incorrect Answer 1\"]),\n preprocess(doc[\"Incorrect Answer 2\"]),\n preprocess(doc[\"Incorrect Answer 3\"]),\n preprocess(doc[\"Correct Answer\"]),\n ]\n\n rng.shuffle(choices)\n correct_answer_index = choices.index(preprocess(doc[\"Correct Answer\"]))\n\n out_doc = {\n \"choice1\": choices[0],\n \"choice2\": choices[1],\n \"choice3\": choices[2],\n \"choice4\": choices[3],\n \"answer\": f\"({chr(65 + correct_answer_index)})\",\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "Question: {{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "Here are some example questions from experts. Answer the final question yourself, following the format of the previous questions exactly.\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": false,
"metadata": {
"version": 2.0
}
}
},
"versions": {
"gpqa_main_n_shot": 2.0
},
"n-shot": {
"gpqa_main_n_shot": 0
},
"higher_is_better": {
"gpqa_main_n_shot": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"gpqa_main_n_shot": {
"original": 448,
"effective": 448
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Qwen/Qwen2.5-72B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 72706203648,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "d3d951150c1e5848237cd6a7ad11df4836aee842",
"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": "8e1bd48d",
"date": 1736546509.7547767,
"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[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.2.0a0\n[pip3] torchdata==0.7.0a0\n[pip3] torchdiffeq==0.2.4\n[pip3] torchmetrics==1.4.1\n[pip3] torchsde==0.2.6\n[pip3] torchtext==0.17.0a0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.44.0",
"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/Qwen2.5-72B-Instruct",
"model_name_sanitized": "Qwen__Qwen2.5-72B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 402807.194136229,
"end_time": 403076.721871911,
"total_evaluation_time_seconds": "269.52773568202974"
} |