Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
| { | |
| "results": { | |
| "polish_psc_regex": { | |
| "exact_match,score-first": 0.961038961038961, | |
| "exact_match_stderr,score-first": 0.005896277440445261, | |
| "f1,score-first": 0.9725490196078431, | |
| "f1_stderr,score-first": "N/A", | |
| "alias": "polish_psc_regex" | |
| } | |
| }, | |
| "group_subtasks": { | |
| "polish_psc_regex": [] | |
| }, | |
| "configs": { | |
| "polish_psc_regex": { | |
| "task": "polish_psc_regex", | |
| "dataset_path": "allegro/klej-psc", | |
| "training_split": "train", | |
| "test_split": "test", | |
| "doc_to_text": "Fragment 1: \"{{extract_text}}\"\nFragment 2: \"{{summary_text}}\"\nPytanie: jaka jest zale偶no艣膰 mi臋dzy fragmentami 1 i 2?\nMo偶liwe odpowiedzi:\nA - wszystkie odpowiedzi poprawne\nB - dotycz膮 tego samego artyku艂u\nC - dotycz膮 r贸偶nych artyku艂贸w\nD - brak poprawnej odpowiedzi\nPrawid艂owa odpowied藕:", | |
| "doc_to_target": "{{{0: 'A', 1: 'C', 2: 'B', 3: 'D'}.get(label|int + 1)}}", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| }, | |
| { | |
| "metric": "def f1(predictions, references):\n _prediction = predictions[0]\n _reference = references[0]\n string_label = [\"B\", \"C\"]\n reference = string_label.index(_reference)\n prediction = (\n string_label.index(_prediction)\n if _prediction in string_label\n else 0\n )\n\n return (prediction, reference)\n", | |
| "aggregation": "def agg_f1(items):\n predictions, references = zip(*items)\n references, predictions = np.asarray(references), np.asarray(predictions)\n\n return sklearn.metrics.f1_score(references, predictions)\n", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| ".", | |
| "," | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0, | |
| "max_gen_toks": 50 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "score-first", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "(\\b[ABCD]\\b)" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": true, | |
| "doc_to_decontamination_query": "{{extract_text}} {{summary_text}}" | |
| } | |
| }, | |
| "versions": { | |
| "polish_psc_regex": "Yaml" | |
| }, | |
| "n-shot": { | |
| "polish_psc_regex": 5 | |
| }, | |
| "higher_is_better": { | |
| "polish_psc_regex": { | |
| "exact_match": true, | |
| "f1": true | |
| } | |
| }, | |
| "n-samples": { | |
| "polish_psc_regex": { | |
| "original": 1078, | |
| "effective": 1078 | |
| } | |
| }, | |
| "config": { | |
| "model": "local-completions", | |
| "model_args": "model=meta-llama/Meta-Llama-3.1-405B-Instruct-FP8,base_url=http://149.156.182.180:9096/c02/v1/,tokenizer_backend=huggingface", | |
| "batch_size": 1, | |
| "batch_sizes": [], | |
| "device": null, | |
| "use_cache": "openai_cache_llama405", | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null, | |
| "random_seed": 0, | |
| "numpy_seed": 1234, | |
| "torch_seed": 1234, | |
| "fewshot_seed": 1234 | |
| }, | |
| "git_hash": "fe6ba240", | |
| "date": 1722332415.5031052, | |
| "pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 24.04 LTS (x86_64)\nGCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.39\n\nPython version: 3.12.4 (main, Jun 12 2024, 15:54:43) [GCC 13.2.0] (64-bit runtime)\nPython platform: Linux-6.8.0-31-generic-x86_64-with-glibc2.39\nIs CUDA available: False\nCUDA runtime version: No CUDA\nCUDA_MODULE_LOADING set to: N/A\nGPU models and configuration: No CUDA\nNvidia driver version: No CUDA\ncuDNN version: No CUDA\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: 39 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 8\nOn-line CPU(s) list: 0-7\nVendor ID: GenuineIntel\nModel name: Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz\nCPU family: 6\nModel: 158\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 1\nStepping: 9\nCPU(s) scaling MHz: 91%\nCPU max MHz: 3800.0000\nCPU min MHz: 800.0000\nBogoMIPS: 5599.85\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 vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault pti ssbd ibrs ibpb stibp tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx rdseed adx smap clflushopt intel_pt xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp vnmi md_clear flush_l1d arch_capabilities\nVirtualization: VT-x\nL1d cache: 128 KiB (4 instances)\nL1i cache: 128 KiB (4 instances)\nL2 cache: 1 MiB (4 instances)\nL3 cache: 6 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0-7\nVulnerability Gather data sampling: Mitigation; Microcode\nVulnerability Itlb multihit: KVM: Mitigation: VMX disabled\nVulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable\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\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: Mitigation; Microcode\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.1\n[conda] Could not collect", | |
| "transformers_version": "4.42.3", | |
| "upper_git_hash": null, | |
| "task_hashes": { | |
| "polish_psc_regex": "62e1c0c7b4494ec1f99bb0c7eeaad898f5b3e48f9263f8212e2a9759d5499045" | |
| }, | |
| "model_source": "local-completions", | |
| "model_name": "meta-llama/Meta-Llama-3.1-405B-Instruct-FP8", | |
| "model_name_sanitized": "meta-llama__Meta-Llama-3.1-405B-Instruct-FP8", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "chat_template": null, | |
| "chat_template_sha": null, | |
| "start_time": 333995.290451213, | |
| "end_time": 365863.372666725, | |
| "total_evaluation_time_seconds": "31868.082215511997" | |
| } |