{ "results": { "belebele_tur_Latn": { "name": "belebele_tur_Latn", "alias": "belebele_tur_Latn", "sample_len": 900, "acc,none": 0.8655555555555555, "acc_stderr,none": 0.011377296040197065, "acc_norm,none": 0.8655555555555555, "acc_norm_stderr,none": 0.011377296040197065 } }, "group_subtasks": {}, "configs": { "belebele_tur_Latn": { "task": "belebele_tur_Latn", "dataset_path": "facebook/belebele", "dataset_name": "tur_Latn", "test_split": "test", "fewshot_split": "test", "doc_to_text": "P: {{flores_passage}}\nQ: {{question.strip()}}\nA: {{mc_answer1}}\nB: {{mc_answer2}}\nC: {{mc_answer3}}\nD: {{mc_answer4}}\nAnswer:", "doc_to_target": "{{['1', '2', '3', '4'].index(correct_answer_num)}}", "unsafe_code": false, "doc_to_choice": [ "A", "B", "C", "D" ], "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "test", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "P: {{flores_passage}}\nQ: {{question.strip()}}\nA: {{mc_answer1}}\nB: {{mc_answer2}}\nC: {{mc_answer3}}\nD: {{mc_answer4}}\nAnswer:", "doc_to_choice": [ "A", "B", "C", "D" ], "doc_to_target": "{{['1', '2', '3', '4'].index(correct_answer_num)}}", "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "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": true, "doc_to_decontamination_query": "{{question}}", "metadata": { "version": 0.0, "pretrained": "Trendyol/Trendyol-LLM-Asure-12B", "dtype": "bfloat16", "trust_remote_code": true, "config_source": "/venv/main/lib/python3.12/site-packages/lm_eval/tasks/belebele/belebele_tur_Latn.yaml" } } }, "versions": { "belebele_tur_Latn": 0.0 }, "n-shot": { "belebele_tur_Latn": 5 }, "higher_is_better": { "belebele_tur_Latn": { "acc": true, "acc_norm": true } }, "n-samples": { "belebele_tur_Latn": { "original": 900, "effective": 900 } }, "config": { "model": "hf", "model_args": { "pretrained": "Trendyol/Trendyol-LLM-Asure-12B", "dtype": "bfloat16", "trust_remote_code": true }, "model_num_parameters": 12187325040, "model_dtype": "torch.bfloat16", "model_revision": "main", "model_sha": "df1164d37f47080ba5fbc1ff4defa0c7a1a218a5", "batch_size": "auto", "batch_sizes": [ 2 ], "device": "cuda:0", "use_cache": null, "limit": null, "bootstrap_iters": 100000, "gen_kwargs": {}, "random_seed": 42, "numpy_seed": 42, "torch_seed": 42, "fewshot_seed": 42 }, "git_hash": null, "date": 1781866108.5189137, "pretty_env_info": "PyTorch version: 2.12.0+cu130\nIs debug build: False\nCUDA used to build PyTorch: 13.0\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 24.04.4 LTS (x86_64)\nGCC version: (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0\nClang version: Could not collect\nCMake version: version 3.28.3\nLibc version: glibc-2.39\n\nPython version: 3.12.13 | packaged by conda-forge | (main, Mar 5 2026, 16:50:00) [GCC 14.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-181-generic-x86_64-with-glibc2.39\nIs CUDA available: True\nCUDA runtime version: 13.0.88\nCUDA_MODULE_LOADING set to: \nGPU models and configuration: GPU 0: NVIDIA GeForce RTX 5090\nNvidia driver version: 595.80\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.14.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.14.0\nIs XPU available: False\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\nCaching allocator config: N/A\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): 256\nOn-line CPU(s) list: 0-255\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7B13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 2\nCore(s) per socket: 64\nSocket(s): 2\nStepping: 1\nFrequency boost: enabled\nCPU(s) scaling MHz: 42%\nCPU max MHz: 3541.3679\nCPU min MHz: 1500.0000\nBogoMIPS: 4499.67\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 nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca ibpb_exit_to_user\nVirtualization: AMD-V\nL1d cache: 4 MiB (128 instances)\nL1i cache: 4 MiB (128 instances)\nL2 cache: 64 MiB (128 instances)\nL3 cache: 512 MiB (16 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-63,128-191\nNUMA node1 CPU(s): 64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Indirect target selection: 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 Reg file data sampling: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\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; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsa: Vulnerable: Clear CPU buffers attempted, no microcode\nVulnerability Tsx async abort: Not affected\nVulnerability Vmscape: Mitigation; IBPB before exit to userspace\n\nVersions of relevant libraries:\n[pip3] numpy==2.4.6\n[pip3] nvidia-cublas==13.1.1.3\n[pip3] nvidia-cuda-cupti==13.0.85\n[pip3] nvidia-cuda-nvrtc==13.0.88\n[pip3] nvidia-cuda-runtime==13.0.96\n[pip3] nvidia-cudnn-cu13==9.20.0.48\n[pip3] nvidia-cufft==12.0.0.61\n[pip3] nvidia-curand==10.4.0.35\n[pip3] nvidia-cusolver==12.0.4.66\n[pip3] nvidia-cusparse==12.6.3.3\n[pip3] nvidia-cusparselt-cu13==0.8.1\n[pip3] nvidia-nccl-cu13==2.29.7\n[pip3] nvidia-nvjitlink==13.0.88\n[pip3] nvidia-nvtx==13.0.85\n[pip3] torch==2.12.0+cu130\n[pip3] torchcodec==0.12.0+cu130\n[pip3] torchvision==0.27.0+cu130\n[pip3] triton==3.7.0\n[conda] Could not collect", "transformers_version": "5.12.1", "lm_eval_version": "0.4.12", "upper_git_hash": null, "tokenizer_pad_token": [ "", "0" ], "tokenizer_eos_token": [ "", "1" ], "tokenizer_bos_token": [ "", "2" ], "eot_token_id": 1, "max_length": 32768, "task_hashes": {}, "model_source": "hf", "model_name": "Trendyol/Trendyol-LLM-Asure-12B", "model_name_sanitized": "Trendyol__Trendyol-LLM-Asure-12B", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": true, "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\\n\\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\\n\\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n\n{%- for message in loop_messages -%}\n {# map roles so 'system' is treated like 'user' #}\n {%- if message['role'] == 'assistant' -%}\n {%- set role_out = \"model\" -%}\n {%- else -%}\n {%- set role_out = \"user\" -%}\n {%- endif -%}\n\n {{ '' + role_out + '\\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '\\n' }}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {{ 'model\\n' }}\n{%- endif -%}", "chat_template_sha": "605efb30b33f6cde07d0435456d8dc042bb2f23ec6108689e2745ef5c144a787", "total_evaluation_time_seconds": "440.93969805300003" }