{
"results": {
"winogrande": {
"alias": "winogrande",
"acc,none": 0.7371744277821626,
"acc_stderr,none": 0.012370922527262008
}
},
"group_subtasks": {
"winogrande": []
},
"configs": {
"winogrande": {
"task": "winogrande",
"dataset_path": "winogrande",
"dataset_name": "winogrande_xl",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"validation_split": "validation",
"doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n",
"doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n",
"doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
"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": true,
"doc_to_decontamination_query": "sentence",
"metadata": {
"version": 1.0
}
}
},
"versions": {
"winogrande": 1.0
},
"n-shot": {
"winogrande": 0
},
"higher_is_better": {
"winogrande": {
"acc": true
}
},
"n-samples": {
"winogrande": {
"original": 1267,
"effective": 1267
}
},
"config": {
"model": "hf",
"model_args": "parallelize=True,pretrained=FreedomIntelligence/AceGPT-v2-8B-Chat,trust_remote_code=True,mm=False,trust_remote_code=True",
"model_num_parameters": 8030261248,
"model_dtype": "torch.float16",
"model_revision": "main",
"model_sha": "562d0998c03c02d315e346f81650a43955711901",
"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": 1732457295.7930105,
"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": "4.46.3",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|end_of_text|>",
"128001"
],
"tokenizer_eos_token": [
"<|end_of_text|>",
"128001"
],
"tokenizer_bos_token": [
"<|begin_of_text|>",
"128000"
],
"eot_token_id": 128001,
"max_length": 8192,
"task_hashes": {},
"model_source": "hf",
"model_name": "FreedomIntelligence/AceGPT-v2-8B-Chat",
"model_name_sanitized": "FreedomIntelligence__AceGPT-v2-8B-Chat",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 934783.15582321,
"end_time": 935295.980413407,
"total_evaluation_time_seconds": "512.8245901969494"
}