File size: 8,921 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
{
"results": {
"ifeval": {
"alias": "ifeval",
"prompt_level_strict_acc,none": 0.6765249537892791,
"prompt_level_strict_acc_stderr,none": 0.02013100339211896,
"inst_level_strict_acc,none": 0.7709832134292566,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.756007393715342,
"prompt_level_loose_acc_stderr,none": 0.018482234430967866,
"inst_level_loose_acc,none": 0.8321342925659473,
"inst_level_loose_acc_stderr,none": "N/A"
}
},
"group_subtasks": {
"ifeval": []
},
"configs": {
"ifeval": {
"task": "ifeval",
"dataset_path": "google/IFEval",
"test_split": "train",
"doc_to_text": "prompt",
"doc_to_target": 0,
"process_results": "def process_results(doc, results):\n inp = InputExample(\n key=doc[\"key\"],\n instruction_id_list=doc[\"instruction_id_list\"],\n prompt=doc[\"prompt\"],\n kwargs=doc[\"kwargs\"],\n )\n response = results[0]\n\n out_strict = test_instruction_following_strict(inp, response)\n out_loose = test_instruction_following_loose(inp, response)\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "prompt_level_strict_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_strict_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
},
{
"metric": "prompt_level_loose_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_loose_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1280
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 4.0
}
}
},
"versions": {
"ifeval": 4.0
},
"n-shot": {
"ifeval": 0
},
"higher_is_better": {
"ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
}
},
"n-samples": {
"ifeval": {
"original": 541,
"effective": 541
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=Qwen/Qwen2.5-72B-Instruct,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
"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": "150ae04f",
"date": 1737582434.8072224,
"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": "4.48.1",
"upper_git_hash": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
"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": "vllm",
"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": 124455.153996255,
"end_time": 124618.982686501,
"total_evaluation_time_seconds": "163.82869024599495"
} |