{ "results": { "agieval_nous": { "acc_norm,none": 0.5357423409269442, "acc_norm_stderr,none": 0.00952110343229611, "acc,none": 0.6233307148468186, "acc_stderr,none": 0.009151821236525831, "alias": "agieval_nous" }, "agieval_aqua_rat": { "acc,none": 0.5511811023622047, "acc_stderr,none": 0.03126961011656295, "acc_norm,none": 0.5118110236220472, "acc_norm_stderr,none": 0.031425959141896394, "alias": " - agieval_aqua_rat" }, "agieval_logiqa_en": { "acc,none": 0.554531490015361, "acc_stderr,none": 0.019494627133439985, "acc_norm,none": 0.46236559139784944, "acc_norm_stderr,none": 0.019555980839597826, "alias": " - agieval_logiqa_en" }, "agieval_lsat_ar": { "acc,none": 0.26956521739130435, "acc_stderr,none": 0.02932276422894952, "acc_norm,none": 0.2565217391304348, "acc_norm_stderr,none": 0.028858814315305643, "alias": " - agieval_lsat_ar" }, "agieval_lsat_lr": { "acc,none": 0.7, "acc_stderr,none": 0.020311909655921973, "acc_norm,none": 0.5764705882352941, "acc_norm_stderr,none": 0.021901379648792133, "alias": " - agieval_lsat_lr" }, "agieval_lsat_rc": { "acc,none": 0.7881040892193308, "acc_stderr,none": 0.02496236224822418, "acc_norm,none": 0.6765799256505576, "acc_norm_stderr,none": 0.028574302844503813, "alias": " - agieval_lsat_rc" }, "agieval_sat_en": { "acc,none": 0.8689320388349514, "acc_stderr,none": 0.02357025313368066, "acc_norm,none": 0.8446601941747572, "acc_norm_stderr,none": 0.02529912276040303, "alias": " - agieval_sat_en" }, "agieval_sat_en_without_passage": { "acc,none": 0.616504854368932, "acc_stderr,none": 0.033960279445866416, "acc_norm,none": 0.5194174757281553, "acc_norm_stderr,none": 0.03489517135066013, "alias": " - agieval_sat_en_without_passage" }, "agieval_sat_math": { "acc,none": 0.6772727272727272, "acc_stderr,none": 0.03159203270502094, "acc_norm,none": 0.5318181818181819, "acc_norm_stderr,none": 0.03371838809107287, "alias": " - agieval_sat_math" } }, "groups": { "agieval_nous": { "acc_norm,none": 0.5357423409269442, "acc_norm_stderr,none": 0.00952110343229611, "acc,none": 0.6233307148468186, "acc_stderr,none": 0.009151821236525831, "alias": "agieval_nous" } }, "group_subtasks": { "agieval_nous": [ "agieval_sat_en", "agieval_lsat_ar", "agieval_sat_en_without_passage", "agieval_aqua_rat", "agieval_logiqa_en", "agieval_sat_math", "agieval_lsat_rc", "agieval_lsat_lr" ] }, "configs": { "agieval_aqua_rat": { "task": "agieval_aqua_rat", "group": [ "agieval", "agieval_en", "agieval_nous" ], "dataset_path": "hails/agieval-aqua-rat", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_logiqa_en": { "task": "agieval_logiqa_en", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-logiqa-en", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_lsat_ar": { "task": "agieval_lsat_ar", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-lsat-ar", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_lsat_lr": { "task": "agieval_lsat_lr", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-lsat-lr", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_lsat_rc": { "task": "agieval_lsat_rc", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-lsat-rc", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_sat_en": { "task": "agieval_sat_en", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-sat-en", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_sat_en_without_passage": { "task": "agieval_sat_en_without_passage", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-sat-en-without-passage", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } }, "agieval_sat_math": { "task": "agieval_sat_math", "group": [ "agieval", "agieval_nous", "agieval_en" ], "dataset_path": "hails/agieval-sat-math", "test_split": "test", "doc_to_text": "{{query}}", "doc_to_target": "{{gold}}", "doc_to_choice": "{{choices}}", "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "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": 1.0 } } }, "versions": { "agieval_aqua_rat": 1.0, "agieval_logiqa_en": 1.0, "agieval_lsat_ar": 1.0, "agieval_lsat_lr": 1.0, "agieval_lsat_rc": 1.0, "agieval_sat_en": 1.0, "agieval_sat_en_without_passage": 1.0, "agieval_sat_math": 1.0 }, "n-shot": { "agieval_aqua_rat": 0, "agieval_logiqa_en": 0, "agieval_lsat_ar": 0, "agieval_lsat_lr": 0, "agieval_lsat_rc": 0, "agieval_nous": 0, "agieval_sat_en": 0, "agieval_sat_en_without_passage": 0, "agieval_sat_math": 0 }, "higher_is_better": { "agieval_aqua_rat": { "acc": true, "acc_norm": true }, "agieval_logiqa_en": { "acc": true, "acc_norm": true }, "agieval_lsat_ar": { "acc": true, "acc_norm": true }, "agieval_lsat_lr": { "acc": true, "acc_norm": true }, "agieval_lsat_rc": { "acc": true, "acc_norm": true }, "agieval_nous": { "acc": true, "acc_norm": true }, "agieval_sat_en": { "acc": true, "acc_norm": true }, "agieval_sat_en_without_passage": { "acc": true, "acc_norm": true }, "agieval_sat_math": { "acc": true, "acc_norm": true } }, "n-samples": { "agieval_sat_en": { "original": 206, "effective": 206 }, "agieval_lsat_ar": { "original": 230, "effective": 230 }, "agieval_sat_en_without_passage": { "original": 206, "effective": 206 }, "agieval_aqua_rat": { "original": 254, "effective": 254 }, "agieval_logiqa_en": { "original": 651, "effective": 651 }, "agieval_sat_math": { "original": 220, "effective": 220 }, "agieval_lsat_rc": { "original": 269, "effective": 269 }, "agieval_lsat_lr": { "original": 510, "effective": 510 } }, "config": { "model": "hf", "model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True", "model_num_parameters": 72706203648, "model_dtype": "torch.float16", "model_revision": "main", "model_sha": "", "batch_size": "16", "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": "b3e4c49a", "date": 1718163625.5715299, "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\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 3.29.3\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, Apr 6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1050-azure-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 530.30.02\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\nByte Order: Little Endian\nAddress sizes: 48 bits physical, 48 bits virtual\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nNUMA node(s): 4\nVendor ID: AuthenticAMD\nCPU family: 25\nModel: 1\nModel name: AMD EPYC 7V13 64-Core Processor\nStepping: 1\nCPU MHz: 2445.435\nBogoMIPS: 4890.87\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB\nL1i cache: 3 MiB\nL2 cache: 48 MiB\nL3 cache: 384 MiB\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: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] magma-cuda117 2.6.1 1 pytorch\n[conda] mkl 2022.2.1 pypi_0 pypi\n[conda] mkl-include 2022.2.1 pypi_0 pypi\n[conda] numpy 1.24.4 pypi_0 pypi\n[conda] pytorch-lightning 1.9.5 pypi_0 pypi\n[conda] torch 2.0.1 pypi_0 pypi\n[conda] torch-nebula 0.16.10 pypi_0 pypi\n[conda] torch-ort 1.17.0 pypi_0 pypi\n[conda] torchaudio 2.0.2+cu117 pypi_0 pypi\n[conda] torchdata 0.6.1 pypi_0 pypi\n[conda] torchmetrics 1.2.0 pypi_0 pypi\n[conda] torchsnapshot 0.1.0 pypi_0 pypi\n[conda] torchvision 0.15.2+cu117 pypi_0 pypi\n[conda] triton 2.0.0 pypi_0 pypi", "transformers_version": "4.41.1", "upper_git_hash": null, "task_hashes": {}, "model_source": "hf", "model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors", "model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors", "system_instruction": null, "system_instruction_sha": null, "chat_template": null, "chat_template_sha": null, "start_time": 377200.61189737, "end_time": 380116.891366629, "total_evaluation_time_seconds": "2916.279469258967" }