{ "results": { "winogrande": { "alias": "winogrande", "acc,none": 0.4925019731649566, "acc_stderr,none": 0.014050905521228571 } }, "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": "pretrained=EleutherAI/pythia-160m,revision=step2000,dtype=float,trust_remote_code=True", "model_num_parameters": 162322944, "model_dtype": "torch.float32", "model_revision": "step2000", "model_sha": "accca40b06cfe1ecdcefd89cc45894451e2d3072", "batch_size": "8", "batch_sizes": [], "device": "cuda:0", "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": "a5b7c41", "date": 1730218964.5189857, "pretty_env_info": "PyTorch version: 2.5.0+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: 14.0.0-1ubuntu1.1\nCMake version: version 3.30.5\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.1.85+-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.140\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: Tesla T4\nNvidia driver version: 535.104.05\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.6\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: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 2\nOn-line CPU(s) list: 0,1\nVendor ID: GenuineIntel\nModel name: Intel(R) Xeon(R) CPU @ 2.20GHz\nCPU family: 6\nModel: 79\nThread(s) per core: 2\nCore(s) per socket: 1\nSocket(s): 1\nStepping: 0\nBogoMIPS: 4399.99\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt arat md_clear arch_capabilities\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 32 KiB (1 instance)\nL1i cache: 32 KiB (1 instance)\nL2 cache: 256 KiB (1 instance)\nL3 cache: 55 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0,1\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Mitigation; PTE Inversion\nVulnerability Mds: Vulnerable; SMT Host state unknown\nVulnerability Meltdown: Vulnerable\nVulnerability Mmio stale data: Vulnerable\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed: Vulnerable\nVulnerability Spec rstack overflow: Not affected\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers\nVulnerability Spectre v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Vulnerable (Syscall hardening enabled)\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Vulnerable\n\nVersions of relevant libraries:\n[pip3] mypy==1.13.0\n[pip3] mypy-extensions==1.0.0\n[pip3] numpy==1.26.4\n[pip3] optree==0.13.0\n[pip3] torch==2.5.0+cu121\n[pip3] torchaudio==2.5.0+cu121\n[pip3] torchsummary==1.5.1\n[pip3] torchvision==0.20.0+cu121\n[conda] Could not collect", "transformers_version": "4.44.2", "upper_git_hash": null, "tokenizer_pad_token": [ "<|endoftext|>", "0" ], "tokenizer_eos_token": [ "<|endoftext|>", "0" ], "tokenizer_bos_token": [ "<|endoftext|>", "0" ], "eot_token_id": 0, "max_length": 2048, "task_hashes": {}, "model_source": "hf", "model_name": "EleutherAI/pythia-160m", "model_name_sanitized": "EleutherAI__pythia-160m", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 315.567616419, "end_time": 352.637806904, "total_evaluation_time_seconds": "37.07019048500001" }