orca_mini_v6_8b
/
open-llm-lb-2-evals-log
/leaderboard_mmlu_pro
/results_2024-07-09T17-41-22.805410.json
| { | |
| "results": { | |
| "leaderboard_mmlu_pro": { | |
| "alias": "leaderboard_mmlu_pro", | |
| "acc,none": 0.35638297872340424, | |
| "acc_stderr,none": 0.004366378439456917 | |
| } | |
| }, | |
| "group_subtasks": { | |
| "leaderboard_mmlu_pro": [] | |
| }, | |
| "configs": { | |
| "leaderboard_mmlu_pro": { | |
| "task": "leaderboard_mmlu_pro", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "doc_to_text": "def doc_to_text(doc):\n doc_to_text = f\"{doc['question']}\\n\"\n\n for i in range(len(doc[\"options\"])):\n doc_to_text += f\"{string.ascii_uppercase[i]}. {doc['options'][i]}\\n\"\n\n doc_to_text += \"Answer:\"\n return doc_to_text\n", | |
| "doc_to_target": "answer", | |
| "doc_to_choice": "def doc_to_choice(doc):\n return [string.ascii_uppercase[i] for i in range(len(doc[\"options\"]))]\n", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "multiple_choice", | |
| "repeats": 1, | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 0.1 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "leaderboard_mmlu_pro": 0.1 | |
| }, | |
| "n-shot": { | |
| "leaderboard_mmlu_pro": 5 | |
| }, | |
| "higher_is_better": { | |
| "leaderboard_mmlu_pro": { | |
| "acc": true | |
| } | |
| }, | |
| "n-samples": { | |
| "leaderboard_mmlu_pro": { | |
| "original": 12032, | |
| "effective": 12032 | |
| } | |
| }, | |
| "config": { | |
| "model": "hf", | |
| "model_args": "pretrained=pankajmathur/orca_mini_v6_8b,dtype=bfloat16", | |
| "batch_size": "auto", | |
| "batch_sizes": [ | |
| 16 | |
| ], | |
| "device": "cuda:0", | |
| "use_cache": "cache_pankajmathur/orca_mini_v6_8b/leaderboard_mmlu_pro", | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null, | |
| "random_seed": 0, | |
| "numpy_seed": 1234, | |
| "torch_seed": 1234, | |
| "fewshot_seed": 1234 | |
| }, | |
| "git_hash": "773209c", | |
| "date": 1720545511.667663, | |
| "pretty_env_info": "PyTorch version: 2.2.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-60-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA A100-SXM4-80GB\nNvidia driver version: 535.104.05\ncuDNN version: Could not collect\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): 256\nOn-line CPU(s) list: 0-255\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7763 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 max MHz: 3529.0520\nCPU min MHz: 1500.0000\nBogoMIPS: 4900.18\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\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): 8\nNUMA node0 CPU(s): 0-15,128-143\nNUMA node1 CPU(s): 16-31,144-159\nNUMA node2 CPU(s): 32-47,160-175\nNUMA node3 CPU(s): 48-63,176-191\nNUMA node4 CPU(s): 64-79,192-207\nNUMA node5 CPU(s): 80-95,208-223\nNUMA node6 CPU(s): 96-111,224-239\nNUMA node7 CPU(s): 112-127,240-255\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: 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; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.3\n[pip3] torch==2.2.0\n[pip3] torchaudio==2.2.0\n[pip3] torchvision==0.17.0\n[pip3] triton==2.2.0\n[conda] Could not collect", | |
| "transformers_version": "4.42.3", | |
| "upper_git_hash": "be01651cf6b611c09f088c336db74ea625227716", | |
| "tokenizer_pad_token": [ | |
| "<|end_of_text|>", | |
| "128001" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "<|im_end|>", | |
| "128256" | |
| ], | |
| "tokenizer_bos_token": [ | |
| "<|begin_of_text|>", | |
| "128000" | |
| ], | |
| "eot_token_id": 128256, | |
| "max_length": 8192, | |
| "task_hashes": {}, | |
| "model_source": "hf", | |
| "model_name": "pankajmathur/orca_mini_v6_8b", | |
| "model_name_sanitized": "pankajmathur__orca_mini_v6_8b", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": null, | |
| "chat_template_sha": null, | |
| "start_time": 25392799.258005407, | |
| "end_time": 25394178.190460667, | |
| "total_evaluation_time_seconds": "1378.9324552603066" | |
| } |