208 lines
13 KiB
JSON
208 lines
13 KiB
JSON
{
|
|
"results": {
|
|
"sklegal": {
|
|
"name": "sklegal",
|
|
"alias": "sklegal",
|
|
"sample_len": 1334,
|
|
"acc,none": 0.2841079460269865,
|
|
"acc_stderr,none": 0.012352372689133341,
|
|
"acc_norm,none": 0.46926536731634183,
|
|
"acc_norm_stderr,none": 0.013668878751636108
|
|
},
|
|
"skquad": {
|
|
"name": "skquad",
|
|
"alias": "skquad",
|
|
"sample_len": 9583,
|
|
"exact,none": 1.9722425127830534,
|
|
"exact_stderr,none": "N/A",
|
|
"f1,none": 27.7993811825338,
|
|
"f1_stderr,none": "N/A",
|
|
"HasAns_exact,none": 2.410565457109886,
|
|
"HasAns_exact_stderr,none": "N/A",
|
|
"HasAns_f1,none": 34.145591726147124,
|
|
"HasAns_f1_stderr,none": "N/A",
|
|
"NoAns_exact,none": 0.05605381165919283,
|
|
"NoAns_exact_stderr,none": "N/A",
|
|
"NoAns_f1,none": 0.05605381165919283,
|
|
"NoAns_f1_stderr,none": "N/A",
|
|
"best_exact,none": 18.61629969738078,
|
|
"best_exact_stderr,none": "N/A",
|
|
"best_f1,none": 28.301192071377013,
|
|
"best_f1_stderr,none": "N/A"
|
|
}
|
|
},
|
|
"group_subtasks": {},
|
|
"configs": {
|
|
"sklegal": {
|
|
"task": "sklegal",
|
|
"dataset_path": "TUKE-KEMT/slovak-legal-exam",
|
|
"test_split": "test",
|
|
"doc_to_text": "{{prompt}} ",
|
|
"doc_to_target": "label",
|
|
"unsafe_code": false,
|
|
"doc_to_choice": "{{answers}}",
|
|
"description": "",
|
|
"target_delimiter": " ",
|
|
"fewshot_delimiter": "\n\n",
|
|
"fewshot_config": {
|
|
"sampler": "default",
|
|
"split": null,
|
|
"process_docs": null,
|
|
"fewshot_indices": null,
|
|
"samples": null,
|
|
"doc_to_text": "{{prompt}} ",
|
|
"doc_to_choice": "{{answers}}",
|
|
"doc_to_target": "label",
|
|
"gen_prefix": null,
|
|
"fewshot_delimiter": "\n\n",
|
|
"target_delimiter": " "
|
|
},
|
|
"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,
|
|
"pretrained": "slovak-nlp/mistral-sk-7b",
|
|
"peft": "Jakub1320/mistral-sk-7b-slovak-alpaca-qlora",
|
|
"dtype": "float16",
|
|
"config_source": "/home/schwarc/diplomovka/lmeval_missing_tasks/sklegal.yaml"
|
|
}
|
|
},
|
|
"skquad": {
|
|
"task": "skquad",
|
|
"unsafe_code": false,
|
|
"description": "",
|
|
"target_delimiter": " ",
|
|
"fewshot_delimiter": "\n\n",
|
|
"fewshot_config": {
|
|
"sampler": "default",
|
|
"split": null,
|
|
"process_docs": null,
|
|
"fewshot_indices": null,
|
|
"samples": null,
|
|
"doc_to_text": null,
|
|
"doc_to_choice": null,
|
|
"doc_to_target": null,
|
|
"gen_prefix": null,
|
|
"fewshot_delimiter": "\n\n",
|
|
"target_delimiter": " "
|
|
},
|
|
"num_fewshot": 0,
|
|
"output_type": "generate_until",
|
|
"generation_kwargs": {
|
|
"temperature": 0.0,
|
|
"do_sample": false,
|
|
"max_gen_toks": 256,
|
|
"until": [
|
|
"\n\n"
|
|
]
|
|
},
|
|
"repeats": 1,
|
|
"should_decontaminate": false,
|
|
"metadata": {
|
|
"version": 3
|
|
}
|
|
}
|
|
},
|
|
"versions": {
|
|
"sklegal": 1,
|
|
"skquad": 3
|
|
},
|
|
"n-shot": {
|
|
"sklegal": 0,
|
|
"skquad": 0
|
|
},
|
|
"higher_is_better": {
|
|
"sklegal": {
|
|
"acc": true,
|
|
"acc_norm": true
|
|
},
|
|
"skquad": {
|
|
"exact": true,
|
|
"f1": true,
|
|
"HasAns_exact": true,
|
|
"HasAns_f1": true,
|
|
"NoAns_exact": true,
|
|
"NoAns_f1": true,
|
|
"best_exact": true,
|
|
"best_f1": true
|
|
}
|
|
},
|
|
"n-samples": {
|
|
"sklegal": {
|
|
"original": 1334,
|
|
"effective": 1334
|
|
},
|
|
"skquad": {
|
|
"original": 9583,
|
|
"effective": 9583
|
|
}
|
|
},
|
|
"config": {
|
|
"model": "hf",
|
|
"model_args": {
|
|
"pretrained": "slovak-nlp/mistral-sk-7b",
|
|
"peft": "Jakub1320/mistral-sk-7b-slovak-alpaca-qlora",
|
|
"dtype": "float16"
|
|
},
|
|
"model_num_parameters": 7283675136,
|
|
"model_dtype": "torch.float16",
|
|
"model_revision": "main",
|
|
"model_sha": "089497ae0d72018e9591895c54f774bf0b4a83a4",
|
|
"peft_sha": "b7d5ba53c81f33334442196915712b5b028d4005",
|
|
"batch_size": "1",
|
|
"batch_sizes": [],
|
|
"device": "cuda:0",
|
|
"use_cache": null,
|
|
"limit": null,
|
|
"bootstrap_iters": 100000,
|
|
"gen_kwargs": {},
|
|
"random_seed": 0,
|
|
"numpy_seed": 1234,
|
|
"torch_seed": 1234,
|
|
"fewshot_seed": 1234
|
|
},
|
|
"git_hash": null,
|
|
"date": 1786998254.1614816,
|
|
"pretty_env_info": "PyTorch version: 2.6.0+cu124\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.16.3\nLibc version: glibc-2.31\n\nPython version: 3.11.15 (main, Mar 11 2026, 17:20:07) [GCC 14.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-119-generic-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 10.1.243\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA TITAN RTX\nGPU 1: NVIDIA TITAN RTX\n\nNvidia driver version: 575.57.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.10.2\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.10.2\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\nByte Order: Little Endian\nAddress sizes: 46 bits physical, 48 bits virtual\nCPU(s): 20\nOn-line CPU(s) list: 0-19\nThread(s) per core: 2\nCore(s) per socket: 10\nSocket(s): 1\nNUMA node(s): 1\nVendor ID: GenuineIntel\nCPU family: 6\nModel: 85\nModel name: Intel(R) Core(TM) i9-9820X CPU @ 3.30GHz\nStepping: 4\nCPU MHz: 3300.000\nCPU max MHz: 4200,0000\nCPU min MHz: 1200,0000\nBogoMIPS: 6599.98\nL1d cache: 320 KiB\nL1i cache: 320 KiB\nL2 cache: 10 MiB\nL3 cache: 16,5 MiB\nNUMA node0 CPU(s): 0-19\nVulnerability Gather data sampling: Mitigation; Microcode\nVulnerability Itlb multihit: KVM: Mitigation: VMX unsupported\nVulnerability L1tf: Mitigation; PTE Inversion\nVulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable\nVulnerability Meltdown: Mitigation; PTI\nVulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed: Mitigation; IBRS\nVulnerability Spec rstack overflow: Not affected\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; IBRS; IBPB conditional; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti ssbd mba ibrs ibpb stibp fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req md_clear flush_l1d arch_capabilities\n\nVersions of relevant libraries:\n[pip3] numpy==2.4.6\n[pip3] nvidia-cublas==13.1.1.3\n[pip3] nvidia-cublas-cu12==12.4.5.8\n[pip3] nvidia-cuda-cupti==13.0.85\n[pip3] nvidia-cuda-cupti-cu12==12.4.127\n[pip3] nvidia-cuda-nvrtc==13.0.88\n[pip3] nvidia-cuda-nvrtc-cu12==12.4.127\n[pip3] nvidia-cuda-runtime==13.0.96\n[pip3] nvidia-cuda-runtime-cu12==12.4.127\n[pip3] nvidia-cudnn-cu12==9.1.0.70\n[pip3] nvidia-cudnn-cu13==9.20.0.48\n[pip3] nvidia-cufft==12.0.0.61\n[pip3] nvidia-cufft-cu12==11.2.1.3\n[pip3] nvidia-curand==10.4.0.35\n[pip3] nvidia-curand-cu12==10.3.5.147\n[pip3] nvidia-cusolver==12.0.4.66\n[pip3] nvidia-cusolver-cu12==11.6.1.9\n[pip3] nvidia-cusparse==12.6.3.3\n[pip3] nvidia-cusparse-cu12==12.3.1.170\n[pip3] nvidia-cusparselt-cu12==0.6.2\n[pip3] nvidia-cusparselt-cu13==0.8.1\n[pip3] nvidia-nccl-cu12==2.21.5\n[pip3] nvidia-nccl-cu13==2.29.7\n[pip3] nvidia-nvjitlink==13.0.88\n[pip3] nvidia-nvjitlink-cu12==12.4.127\n[pip3] nvidia-nvtx==13.0.85\n[pip3] nvidia-nvtx-cu12==12.4.127\n[pip3] torch==2.6.0+cu124\n[pip3] torchaudio==2.6.0+cu124\n[pip3] torchdata==0.11.0\n[pip3] torchvision==0.21.0+cu124\n[pip3] triton==3.2.0\n[conda] numpy 2.4.6 pypi_0 pypi\n[conda] nvidia-cublas 13.1.1.3 pypi_0 pypi\n[conda] nvidia-cublas-cu12 12.4.5.8 pypi_0 pypi\n[conda] nvidia-cuda-cupti 13.0.85 pypi_0 pypi\n[conda] nvidia-cuda-cupti-cu12 12.4.127 pypi_0 pypi\n[conda] nvidia-cuda-nvrtc 13.0.88 pypi_0 pypi\n[conda] nvidia-cuda-nvrtc-cu12 12.4.127 pypi_0 pypi\n[conda] nvidia-cuda-runtime 13.0.96 pypi_0 pypi\n[conda] nvidia-cuda-runtime-cu12 12.4.127 pypi_0 pypi\n[conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi\n[conda] nvidia-cudnn-cu13 9.20.0.48 pypi_0 pypi\n[conda] nvidia-cufft 12.0.0.61 pypi_0 pypi\n[conda] nvidia-cufft-cu12 11.2.1.3 pypi_0 pypi\n[conda] nvidia-curand 10.4.0.35 pypi_0 pypi\n[conda] nvidia-curand-cu12 10.3.5.147 pypi_0 pypi\n[conda] nvidia-cusolver 12.0.4.66 pypi_0 pypi\n[conda] nvidia-cusolver-cu12 11.6.1.9 pypi_0 pypi\n[conda] nvidia-cusparse 12.6.3.3 pypi_0 pypi\n[conda] nvidia-cusparse-cu12 12.3.1.170 pypi_0 pypi\n[conda] nvidia-cusparselt-cu12 0.6.2 pypi_0 pypi\n[conda] nvidia-cusparselt-cu13 0.8.1 pypi_0 pypi\n[conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi\n[conda] nvidia-nccl-cu13 2.29.7 pypi_0 pypi\n[conda] nvidia-nvjitlink 13.0.88 pypi_0 pypi\n[conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi\n[conda] nvidia-nvtx 13.0.85 pypi_0 pypi\n[conda] nvidia-nvtx-cu12 12.4.127 pypi_0 pypi\n[conda] torch 2.6.0+cu124 pypi_0 pypi\n[conda] torchaudio 2.6.0+cu124 pypi_0 pypi\n[conda] torchdata 0.11.0 pypi_0 pypi\n[conda] torchvision 0.21.0+cu124 pypi_0 pypi\n[conda] triton 3.2.0 pypi_0 pypi",
|
|
"transformers_version": "5.5.0",
|
|
"lm_eval_version": "0.4.12",
|
|
"upper_git_hash": null,
|
|
"tokenizer_pad_token": [
|
|
"</s>",
|
|
"2"
|
|
],
|
|
"tokenizer_eos_token": [
|
|
"</s>",
|
|
"2"
|
|
],
|
|
"tokenizer_bos_token": [
|
|
"<s>",
|
|
"1"
|
|
],
|
|
"eot_token_id": 2,
|
|
"max_length": 32768,
|
|
"task_hashes": {},
|
|
"model_source": "hf",
|
|
"model_name": "Jakub1320/mistral-sk-7b-slovak-alpaca-qlora",
|
|
"model_name_sanitized": "Jakub1320__mistral-sk-7b-slovak-alpaca-qlora",
|
|
"system_instruction": null,
|
|
"system_instruction_sha": null,
|
|
"fewshot_as_multiturn": null,
|
|
"chat_template": null,
|
|
"chat_template_sha": null,
|
|
"total_evaluation_time_seconds": "58250.00474518072"
|
|
} |