| { |
| "results": { |
| "hellaswag": { |
| "alias": "hellaswag", |
| "acc,none": 0.6032662816172077, |
| "acc_stderr,none": 0.004882200364432369, |
| "acc_norm,none": 0.7843059151563434, |
| "acc_norm_stderr,none": 0.004104623991846364 |
| } |
| }, |
| "group_subtasks": { |
| "hellaswag": [] |
| }, |
| "configs": { |
| "hellaswag": { |
| "task": "hellaswag", |
| "tag": [ |
| "multiple_choice" |
| ], |
| "dataset_path": "hellaswag", |
| "dataset_kwargs": { |
| "trust_remote_code": true |
| }, |
| "training_split": "train", |
| "validation_split": "validation", |
| "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n", |
| "doc_to_text": "{{query}}", |
| "doc_to_target": "{{label}}", |
| "doc_to_choice": "choices", |
| "description": "", |
| "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": 1.0 |
| } |
| } |
| }, |
| "versions": { |
| "hellaswag": 1.0 |
| }, |
| "n-shot": { |
| "hellaswag": 0 |
| }, |
| "higher_is_better": { |
| "hellaswag": { |
| "acc": true, |
| "acc_norm": true |
| } |
| }, |
| "n-samples": { |
| "hellaswag": { |
| "original": 10042, |
| "effective": 10042 |
| } |
| }, |
| "config": { |
| "model": "hf", |
| "model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True", |
| "model_num_parameters": 7455550464, |
| "model_dtype": "torch.bfloat16", |
| "model_revision": "main", |
| "model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6", |
| "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": "5e10e017", |
| "date": 1736907020.9520104, |
| "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": "4.48.0", |
| "upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711", |
| "tokenizer_pad_token": [ |
| "<|pad|>", |
| "2023" |
| ], |
| "tokenizer_eos_token": [ |
| "<|endoftext|>", |
| "11" |
| ], |
| "tokenizer_bos_token": [ |
| null, |
| "None" |
| ], |
| "eot_token_id": 11, |
| "max_length": 32768, |
| "task_hashes": { |
| "hellaswag": "745f36a5a7a36e5192c010e2b43818ea1ff49739a6078fa6edbcf3bda680e5d7" |
| }, |
| "model_source": "hf", |
| "model_name": "tiiuae/Falcon3-7B-Instruct", |
| "model_name_sanitized": "tiiuae__Falcon3-7B-Instruct", |
| "system_instruction": null, |
| "system_instruction_sha": null, |
| "fewshot_as_multiturn": false, |
| "chat_template": null, |
| "chat_template_sha": null, |
| "start_time": 617271.261912427, |
| "end_time": 617483.451207438, |
| "total_evaluation_time_seconds": "212.18929501099046" |
| } |
