3338 lines
135 KiB
JSON
3338 lines
135 KiB
JSON
|
[
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"arc_challenge": {
|
||
|
|
"acc,none": 0.5921501706484642,
|
||
|
|
"acc_stderr,none": 0.014361097288449701,
|
||
|
|
"acc_norm,none": 0.6339590443686007,
|
||
|
|
"acc_norm_stderr,none": 0.014077223108470139,
|
||
|
|
"alias": "arc_challenge"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"arc_challenge": []
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"arc_challenge": {
|
||
|
|
"task": "arc_challenge",
|
||
|
|
"group": [
|
||
|
|
"ai2_arc"
|
||
|
|
],
|
||
|
|
"dataset_path": "allenai/ai2_arc",
|
||
|
|
"dataset_name": "ARC-Challenge",
|
||
|
|
"training_split": "train",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"test_split": "test",
|
||
|
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||
|
|
"doc_to_target": "{{choices.label.index(answerKey)}}",
|
||
|
|
"doc_to_choice": "{{choices.text}}",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 25,
|
||
|
|
"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: {{question}}\nAnswer:",
|
||
|
|
"metadata": {
|
||
|
|
"version": 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"arc_challenge": 1
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"arc_challenge": 25
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711787477.9239457,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"gsm8k": {
|
||
|
|
"exact_match,strict-match": 0.4783927217589083,
|
||
|
|
"exact_match_stderr,strict-match": 0.013759618667051773,
|
||
|
|
"exact_match,flexible-extract": 0.5367702805155421,
|
||
|
|
"exact_match_stderr,flexible-extract": 0.013735191956468648,
|
||
|
|
"alias": "gsm8k"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"gsm8k": []
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"gsm8k": {
|
||
|
|
"task": "gsm8k",
|
||
|
|
"group": [
|
||
|
|
"math_word_problems"
|
||
|
|
],
|
||
|
|
"dataset_path": "gsm8k",
|
||
|
|
"dataset_name": "main",
|
||
|
|
"training_split": "train",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "train",
|
||
|
|
"doc_to_text": "Question: {{question}}\nAnswer:",
|
||
|
|
"doc_to_target": "{{answer}}",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 5,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "exact_match",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true,
|
||
|
|
"ignore_case": true,
|
||
|
|
"ignore_punctuation": false,
|
||
|
|
"regexes_to_ignore": [
|
||
|
|
",",
|
||
|
|
"\\$",
|
||
|
|
"(?s).*#### ",
|
||
|
|
"\\.$"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "generate_until",
|
||
|
|
"generation_kwargs": {
|
||
|
|
"until": [
|
||
|
|
"Question:",
|
||
|
|
"</s>",
|
||
|
|
"<|im_end|>"
|
||
|
|
],
|
||
|
|
"do_sample": false,
|
||
|
|
"temperature": 0
|
||
|
|
},
|
||
|
|
"repeats": 1,
|
||
|
|
"filter_list": [
|
||
|
|
{
|
||
|
|
"name": "strict-match",
|
||
|
|
"filter": [
|
||
|
|
{
|
||
|
|
"function": "regex",
|
||
|
|
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"function": "take_first"
|
||
|
|
}
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "flexible-extract",
|
||
|
|
"filter": [
|
||
|
|
{
|
||
|
|
"function": "regex",
|
||
|
|
"group_select": -1,
|
||
|
|
"regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"function": "take_first"
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"should_decontaminate": false,
|
||
|
|
"metadata": {
|
||
|
|
"version": 3
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"gsm8k": 3
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"gsm8k": 5
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711781684.2771027,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"hellaswag": {
|
||
|
|
"acc,none": 0.6389165504879506,
|
||
|
|
"acc_stderr,none": 0.004793330525656218,
|
||
|
|
"acc_norm,none": 0.8338976299541924,
|
||
|
|
"acc_norm_stderr,none": 0.00371411888431746,
|
||
|
|
"alias": "hellaswag"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"hellaswag": []
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"hellaswag": {
|
||
|
|
"task": "hellaswag",
|
||
|
|
"group": [
|
||
|
|
"multiple_choice"
|
||
|
|
],
|
||
|
|
"dataset_path": "hellaswag",
|
||
|
|
"training_split": "train",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
|
||
|
|
"doc_to_text": "{{query}}",
|
||
|
|
"doc_to_target": "{{label}}",
|
||
|
|
"doc_to_choice": "choices",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 10,
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"hellaswag": 1
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"hellaswag": 10
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711783556.4633062,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"mmlu": {
|
||
|
|
"acc,none": 0.6122347243982339,
|
||
|
|
"acc_stderr,none": 0.003893774654142997,
|
||
|
|
"alias": "mmlu"
|
||
|
|
},
|
||
|
|
"mmlu_humanities": {
|
||
|
|
"alias": " - humanities",
|
||
|
|
"acc,none": 0.5713071200850159,
|
||
|
|
"acc_stderr,none": 0.0068534756048584345
|
||
|
|
},
|
||
|
|
"mmlu_formal_logic": {
|
||
|
|
"alias": " - formal_logic",
|
||
|
|
"acc,none": 0.42063492063492064,
|
||
|
|
"acc_stderr,none": 0.04415438226743744
|
||
|
|
},
|
||
|
|
"mmlu_high_school_european_history": {
|
||
|
|
"alias": " - high_school_european_history",
|
||
|
|
"acc,none": 0.7757575757575758,
|
||
|
|
"acc_stderr,none": 0.032568666616811015
|
||
|
|
},
|
||
|
|
"mmlu_high_school_us_history": {
|
||
|
|
"alias": " - high_school_us_history",
|
||
|
|
"acc,none": 0.7745098039215687,
|
||
|
|
"acc_stderr,none": 0.029331162294251728
|
||
|
|
},
|
||
|
|
"mmlu_high_school_world_history": {
|
||
|
|
"alias": " - high_school_world_history",
|
||
|
|
"acc,none": 0.7848101265822784,
|
||
|
|
"acc_stderr,none": 0.02675082699467616
|
||
|
|
},
|
||
|
|
"mmlu_international_law": {
|
||
|
|
"alias": " - international_law",
|
||
|
|
"acc,none": 0.743801652892562,
|
||
|
|
"acc_stderr,none": 0.03984979653302872
|
||
|
|
},
|
||
|
|
"mmlu_jurisprudence": {
|
||
|
|
"alias": " - jurisprudence",
|
||
|
|
"acc,none": 0.7962962962962963,
|
||
|
|
"acc_stderr,none": 0.03893542518824846
|
||
|
|
},
|
||
|
|
"mmlu_logical_fallacies": {
|
||
|
|
"alias": " - logical_fallacies",
|
||
|
|
"acc,none": 0.7423312883435583,
|
||
|
|
"acc_stderr,none": 0.03436150827846917
|
||
|
|
},
|
||
|
|
"mmlu_moral_disputes": {
|
||
|
|
"alias": " - moral_disputes",
|
||
|
|
"acc,none": 0.6936416184971098,
|
||
|
|
"acc_stderr,none": 0.024818350129436593
|
||
|
|
},
|
||
|
|
"mmlu_moral_scenarios": {
|
||
|
|
"alias": " - moral_scenarios",
|
||
|
|
"acc,none": 0.3877094972067039,
|
||
|
|
"acc_stderr,none": 0.016295332328155814
|
||
|
|
},
|
||
|
|
"mmlu_philosophy": {
|
||
|
|
"alias": " - philosophy",
|
||
|
|
"acc,none": 0.6945337620578779,
|
||
|
|
"acc_stderr,none": 0.026160584450140453
|
||
|
|
},
|
||
|
|
"mmlu_prehistory": {
|
||
|
|
"alias": " - prehistory",
|
||
|
|
"acc,none": 0.6697530864197531,
|
||
|
|
"acc_stderr,none": 0.026168298456732846
|
||
|
|
},
|
||
|
|
"mmlu_professional_law": {
|
||
|
|
"alias": " - professional_law",
|
||
|
|
"acc,none": 0.4602346805736636,
|
||
|
|
"acc_stderr,none": 0.012729785386598563
|
||
|
|
},
|
||
|
|
"mmlu_world_religions": {
|
||
|
|
"alias": " - world_religions",
|
||
|
|
"acc,none": 0.8187134502923976,
|
||
|
|
"acc_stderr,none": 0.029547741687640038
|
||
|
|
},
|
||
|
|
"mmlu_other": {
|
||
|
|
"alias": " - other",
|
||
|
|
"acc,none": 0.6765368522690698,
|
||
|
|
"acc_stderr,none": 0.008076844905366993
|
||
|
|
},
|
||
|
|
"mmlu_business_ethics": {
|
||
|
|
"alias": " - business_ethics",
|
||
|
|
"acc,none": 0.6,
|
||
|
|
"acc_stderr,none": 0.049236596391733084
|
||
|
|
},
|
||
|
|
"mmlu_clinical_knowledge": {
|
||
|
|
"alias": " - clinical_knowledge",
|
||
|
|
"acc,none": 0.6490566037735849,
|
||
|
|
"acc_stderr,none": 0.02937364625323469
|
||
|
|
},
|
||
|
|
"mmlu_college_medicine": {
|
||
|
|
"alias": " - college_medicine",
|
||
|
|
"acc,none": 0.6127167630057804,
|
||
|
|
"acc_stderr,none": 0.03714325906302065
|
||
|
|
},
|
||
|
|
"mmlu_global_facts": {
|
||
|
|
"alias": " - global_facts",
|
||
|
|
"acc,none": 0.35,
|
||
|
|
"acc_stderr,none": 0.047937248544110196
|
||
|
|
},
|
||
|
|
"mmlu_human_aging": {
|
||
|
|
"alias": " - human_aging",
|
||
|
|
"acc,none": 0.6636771300448431,
|
||
|
|
"acc_stderr,none": 0.031708824268455
|
||
|
|
},
|
||
|
|
"mmlu_management": {
|
||
|
|
"alias": " - management",
|
||
|
|
"acc,none": 0.7864077669902912,
|
||
|
|
"acc_stderr,none": 0.040580420156460344
|
||
|
|
},
|
||
|
|
"mmlu_marketing": {
|
||
|
|
"alias": " - marketing",
|
||
|
|
"acc,none": 0.8846153846153846,
|
||
|
|
"acc_stderr,none": 0.020930193185179323
|
||
|
|
},
|
||
|
|
"mmlu_medical_genetics": {
|
||
|
|
"alias": " - medical_genetics",
|
||
|
|
"acc,none": 0.7,
|
||
|
|
"acc_stderr,none": 0.046056618647183814
|
||
|
|
},
|
||
|
|
"mmlu_miscellaneous": {
|
||
|
|
"alias": " - miscellaneous",
|
||
|
|
"acc,none": 0.7956577266922095,
|
||
|
|
"acc_stderr,none": 0.0144191239809319
|
||
|
|
},
|
||
|
|
"mmlu_nutrition": {
|
||
|
|
"alias": " - nutrition",
|
||
|
|
"acc,none": 0.7091503267973857,
|
||
|
|
"acc_stderr,none": 0.02600480036395213
|
||
|
|
},
|
||
|
|
"mmlu_professional_accounting": {
|
||
|
|
"alias": " - professional_accounting",
|
||
|
|
"acc,none": 0.46808510638297873,
|
||
|
|
"acc_stderr,none": 0.029766675075873866
|
||
|
|
},
|
||
|
|
"mmlu_professional_medicine": {
|
||
|
|
"alias": " - professional_medicine",
|
||
|
|
"acc,none": 0.6066176470588235,
|
||
|
|
"acc_stderr,none": 0.02967428828131116
|
||
|
|
},
|
||
|
|
"mmlu_virology": {
|
||
|
|
"alias": " - virology",
|
||
|
|
"acc,none": 0.5180722891566265,
|
||
|
|
"acc_stderr,none": 0.038899512528272166
|
||
|
|
},
|
||
|
|
"mmlu_social_sciences": {
|
||
|
|
"alias": " - social_sciences",
|
||
|
|
"acc,none": 0.7175820604484888,
|
||
|
|
"acc_stderr,none": 0.007942844244396587
|
||
|
|
},
|
||
|
|
"mmlu_econometrics": {
|
||
|
|
"alias": " - econometrics",
|
||
|
|
"acc,none": 0.4473684210526316,
|
||
|
|
"acc_stderr,none": 0.04677473004491199
|
||
|
|
},
|
||
|
|
"mmlu_high_school_geography": {
|
||
|
|
"alias": " - high_school_geography",
|
||
|
|
"acc,none": 0.7777777777777778,
|
||
|
|
"acc_stderr,none": 0.02962022787479047
|
||
|
|
},
|
||
|
|
"mmlu_high_school_government_and_politics": {
|
||
|
|
"alias": " - high_school_government_and_politics",
|
||
|
|
"acc,none": 0.8652849740932642,
|
||
|
|
"acc_stderr,none": 0.02463978909770944
|
||
|
|
},
|
||
|
|
"mmlu_high_school_macroeconomics": {
|
||
|
|
"alias": " - high_school_macroeconomics",
|
||
|
|
"acc,none": 0.6333333333333333,
|
||
|
|
"acc_stderr,none": 0.024433016466052455
|
||
|
|
},
|
||
|
|
"mmlu_high_school_microeconomics": {
|
||
|
|
"alias": " - high_school_microeconomics",
|
||
|
|
"acc,none": 0.6302521008403361,
|
||
|
|
"acc_stderr,none": 0.03135709599613591
|
||
|
|
},
|
||
|
|
"mmlu_high_school_psychology": {
|
||
|
|
"alias": " - high_school_psychology",
|
||
|
|
"acc,none": 0.8036697247706422,
|
||
|
|
"acc_stderr,none": 0.017030719339154354
|
||
|
|
},
|
||
|
|
"mmlu_human_sexuality": {
|
||
|
|
"alias": " - human_sexuality",
|
||
|
|
"acc,none": 0.7633587786259542,
|
||
|
|
"acc_stderr,none": 0.03727673575596914
|
||
|
|
},
|
||
|
|
"mmlu_professional_psychology": {
|
||
|
|
"alias": " - professional_psychology",
|
||
|
|
"acc,none": 0.6519607843137255,
|
||
|
|
"acc_stderr,none": 0.019270998708223974
|
||
|
|
},
|
||
|
|
"mmlu_public_relations": {
|
||
|
|
"alias": " - public_relations",
|
||
|
|
"acc,none": 0.6818181818181818,
|
||
|
|
"acc_stderr,none": 0.04461272175910508
|
||
|
|
},
|
||
|
|
"mmlu_security_studies": {
|
||
|
|
"alias": " - security_studies",
|
||
|
|
"acc,none": 0.726530612244898,
|
||
|
|
"acc_stderr,none": 0.028535560337128445
|
||
|
|
},
|
||
|
|
"mmlu_sociology": {
|
||
|
|
"alias": " - sociology",
|
||
|
|
"acc,none": 0.8208955223880597,
|
||
|
|
"acc_stderr,none": 0.027113286753111837
|
||
|
|
},
|
||
|
|
"mmlu_us_foreign_policy": {
|
||
|
|
"alias": " - us_foreign_policy",
|
||
|
|
"acc,none": 0.84,
|
||
|
|
"acc_stderr,none": 0.03684529491774709
|
||
|
|
},
|
||
|
|
"mmlu_stem": {
|
||
|
|
"alias": " - stem",
|
||
|
|
"acc,none": 0.5071360608943863,
|
||
|
|
"acc_stderr,none": 0.008525934831521783
|
||
|
|
},
|
||
|
|
"mmlu_abstract_algebra": {
|
||
|
|
"alias": " - abstract_algebra",
|
||
|
|
"acc,none": 0.36,
|
||
|
|
"acc_stderr,none": 0.048241815132442176
|
||
|
|
},
|
||
|
|
"mmlu_anatomy": {
|
||
|
|
"alias": " - anatomy",
|
||
|
|
"acc,none": 0.6074074074074074,
|
||
|
|
"acc_stderr,none": 0.04218506215368879
|
||
|
|
},
|
||
|
|
"mmlu_astronomy": {
|
||
|
|
"alias": " - astronomy",
|
||
|
|
"acc,none": 0.6578947368421053,
|
||
|
|
"acc_stderr,none": 0.03860731599316091
|
||
|
|
},
|
||
|
|
"mmlu_college_biology": {
|
||
|
|
"alias": " - college_biology",
|
||
|
|
"acc,none": 0.7083333333333334,
|
||
|
|
"acc_stderr,none": 0.03800968060554858
|
||
|
|
},
|
||
|
|
"mmlu_college_chemistry": {
|
||
|
|
"alias": " - college_chemistry",
|
||
|
|
"acc,none": 0.43,
|
||
|
|
"acc_stderr,none": 0.049756985195624284
|
||
|
|
},
|
||
|
|
"mmlu_college_computer_science": {
|
||
|
|
"alias": " - college_computer_science",
|
||
|
|
"acc,none": 0.45,
|
||
|
|
"acc_stderr,none": 0.05
|
||
|
|
},
|
||
|
|
"mmlu_college_mathematics": {
|
||
|
|
"alias": " - college_mathematics",
|
||
|
|
"acc,none": 0.36,
|
||
|
|
"acc_stderr,none": 0.048241815132442176
|
||
|
|
},
|
||
|
|
"mmlu_college_physics": {
|
||
|
|
"alias": " - college_physics",
|
||
|
|
"acc,none": 0.3431372549019608,
|
||
|
|
"acc_stderr,none": 0.04724007352383888
|
||
|
|
},
|
||
|
|
"mmlu_computer_security": {
|
||
|
|
"alias": " - computer_security",
|
||
|
|
"acc,none": 0.74,
|
||
|
|
"acc_stderr,none": 0.0440844002276808
|
||
|
|
},
|
||
|
|
"mmlu_conceptual_physics": {
|
||
|
|
"alias": " - conceptual_physics",
|
||
|
|
"acc,none": 0.5531914893617021,
|
||
|
|
"acc_stderr,none": 0.0325005368436584
|
||
|
|
},
|
||
|
|
"mmlu_electrical_engineering": {
|
||
|
|
"alias": " - electrical_engineering",
|
||
|
|
"acc,none": 0.5379310344827586,
|
||
|
|
"acc_stderr,none": 0.04154659671707548
|
||
|
|
},
|
||
|
|
"mmlu_elementary_mathematics": {
|
||
|
|
"alias": " - elementary_mathematics",
|
||
|
|
"acc,none": 0.40476190476190477,
|
||
|
|
"acc_stderr,none": 0.025279850397404907
|
||
|
|
},
|
||
|
|
"mmlu_high_school_biology": {
|
||
|
|
"alias": " - high_school_biology",
|
||
|
|
"acc,none": 0.7612903225806451,
|
||
|
|
"acc_stderr,none": 0.024251071262208837
|
||
|
|
},
|
||
|
|
"mmlu_high_school_chemistry": {
|
||
|
|
"alias": " - high_school_chemistry",
|
||
|
|
"acc,none": 0.458128078817734,
|
||
|
|
"acc_stderr,none": 0.03505630140785742
|
||
|
|
},
|
||
|
|
"mmlu_high_school_computer_science": {
|
||
|
|
"alias": " - high_school_computer_science",
|
||
|
|
"acc,none": 0.7,
|
||
|
|
"acc_stderr,none": 0.046056618647183814
|
||
|
|
},
|
||
|
|
"mmlu_high_school_mathematics": {
|
||
|
|
"alias": " - high_school_mathematics",
|
||
|
|
"acc,none": 0.3111111111111111,
|
||
|
|
"acc_stderr,none": 0.028226446749683515
|
||
|
|
},
|
||
|
|
"mmlu_high_school_physics": {
|
||
|
|
"alias": " - high_school_physics",
|
||
|
|
"acc,none": 0.304635761589404,
|
||
|
|
"acc_stderr,none": 0.03757949922943342
|
||
|
|
},
|
||
|
|
"mmlu_high_school_statistics": {
|
||
|
|
"alias": " - high_school_statistics",
|
||
|
|
"acc,none": 0.4722222222222222,
|
||
|
|
"acc_stderr,none": 0.0340470532865388
|
||
|
|
},
|
||
|
|
"mmlu_machine_learning": {
|
||
|
|
"alias": " - machine_learning",
|
||
|
|
"acc,none": 0.48214285714285715,
|
||
|
|
"acc_stderr,none": 0.047427623612430116
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"groups": {
|
||
|
|
"mmlu": {
|
||
|
|
"acc,none": 0.6122347243982339,
|
||
|
|
"acc_stderr,none": 0.003893774654142997,
|
||
|
|
"alias": "mmlu"
|
||
|
|
},
|
||
|
|
"mmlu_humanities": {
|
||
|
|
"alias": " - humanities",
|
||
|
|
"acc,none": 0.5713071200850159,
|
||
|
|
"acc_stderr,none": 0.0068534756048584345
|
||
|
|
},
|
||
|
|
"mmlu_other": {
|
||
|
|
"alias": " - other",
|
||
|
|
"acc,none": 0.6765368522690698,
|
||
|
|
"acc_stderr,none": 0.008076844905366993
|
||
|
|
},
|
||
|
|
"mmlu_social_sciences": {
|
||
|
|
"alias": " - social_sciences",
|
||
|
|
"acc,none": 0.7175820604484888,
|
||
|
|
"acc_stderr,none": 0.007942844244396587
|
||
|
|
},
|
||
|
|
"mmlu_stem": {
|
||
|
|
"alias": " - stem",
|
||
|
|
"acc,none": 0.5071360608943863,
|
||
|
|
"acc_stderr,none": 0.008525934831521783
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"mmlu_stem": [
|
||
|
|
"mmlu_high_school_chemistry",
|
||
|
|
"mmlu_machine_learning",
|
||
|
|
"mmlu_high_school_biology",
|
||
|
|
"mmlu_college_biology",
|
||
|
|
"mmlu_astronomy",
|
||
|
|
"mmlu_abstract_algebra",
|
||
|
|
"mmlu_high_school_computer_science",
|
||
|
|
"mmlu_electrical_engineering",
|
||
|
|
"mmlu_college_mathematics",
|
||
|
|
"mmlu_college_physics",
|
||
|
|
"mmlu_high_school_statistics",
|
||
|
|
"mmlu_high_school_physics",
|
||
|
|
"mmlu_elementary_mathematics",
|
||
|
|
"mmlu_high_school_mathematics",
|
||
|
|
"mmlu_anatomy",
|
||
|
|
"mmlu_computer_security",
|
||
|
|
"mmlu_college_chemistry",
|
||
|
|
"mmlu_college_computer_science",
|
||
|
|
"mmlu_conceptual_physics"
|
||
|
|
],
|
||
|
|
"mmlu_other": [
|
||
|
|
"mmlu_professional_medicine",
|
||
|
|
"mmlu_nutrition",
|
||
|
|
"mmlu_human_aging",
|
||
|
|
"mmlu_clinical_knowledge",
|
||
|
|
"mmlu_professional_accounting",
|
||
|
|
"mmlu_marketing",
|
||
|
|
"mmlu_global_facts",
|
||
|
|
"mmlu_miscellaneous",
|
||
|
|
"mmlu_college_medicine",
|
||
|
|
"mmlu_management",
|
||
|
|
"mmlu_virology",
|
||
|
|
"mmlu_medical_genetics",
|
||
|
|
"mmlu_business_ethics"
|
||
|
|
],
|
||
|
|
"mmlu_social_sciences": [
|
||
|
|
"mmlu_us_foreign_policy",
|
||
|
|
"mmlu_high_school_macroeconomics",
|
||
|
|
"mmlu_high_school_geography",
|
||
|
|
"mmlu_security_studies",
|
||
|
|
"mmlu_professional_psychology",
|
||
|
|
"mmlu_sociology",
|
||
|
|
"mmlu_econometrics",
|
||
|
|
"mmlu_high_school_psychology",
|
||
|
|
"mmlu_high_school_microeconomics",
|
||
|
|
"mmlu_human_sexuality",
|
||
|
|
"mmlu_high_school_government_and_politics",
|
||
|
|
"mmlu_public_relations"
|
||
|
|
],
|
||
|
|
"mmlu_humanities": [
|
||
|
|
"mmlu_logical_fallacies",
|
||
|
|
"mmlu_moral_scenarios",
|
||
|
|
"mmlu_high_school_european_history",
|
||
|
|
"mmlu_high_school_world_history",
|
||
|
|
"mmlu_jurisprudence",
|
||
|
|
"mmlu_formal_logic",
|
||
|
|
"mmlu_prehistory",
|
||
|
|
"mmlu_international_law",
|
||
|
|
"mmlu_high_school_us_history",
|
||
|
|
"mmlu_professional_law",
|
||
|
|
"mmlu_world_religions",
|
||
|
|
"mmlu_moral_disputes",
|
||
|
|
"mmlu_philosophy"
|
||
|
|
],
|
||
|
|
"mmlu": [
|
||
|
|
"mmlu_humanities",
|
||
|
|
"mmlu_social_sciences",
|
||
|
|
"mmlu_other",
|
||
|
|
"mmlu_stem"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"mmlu_abstract_algebra": {
|
||
|
|
"task": "mmlu_abstract_algebra",
|
||
|
|
"task_alias": "abstract_algebra",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "abstract_algebra",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_anatomy": {
|
||
|
|
"task": "mmlu_anatomy",
|
||
|
|
"task_alias": "anatomy",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "anatomy",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about anatomy.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_astronomy": {
|
||
|
|
"task": "mmlu_astronomy",
|
||
|
|
"task_alias": "astronomy",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "astronomy",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about astronomy.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_business_ethics": {
|
||
|
|
"task": "mmlu_business_ethics",
|
||
|
|
"task_alias": "business_ethics",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "business_ethics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about business ethics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_clinical_knowledge": {
|
||
|
|
"task": "mmlu_clinical_knowledge",
|
||
|
|
"task_alias": "clinical_knowledge",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "clinical_knowledge",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_biology": {
|
||
|
|
"task": "mmlu_college_biology",
|
||
|
|
"task_alias": "college_biology",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_biology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college biology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_chemistry": {
|
||
|
|
"task": "mmlu_college_chemistry",
|
||
|
|
"task_alias": "college_chemistry",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_chemistry",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college chemistry.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_computer_science": {
|
||
|
|
"task": "mmlu_college_computer_science",
|
||
|
|
"task_alias": "college_computer_science",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_computer_science",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college computer science.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_mathematics": {
|
||
|
|
"task": "mmlu_college_mathematics",
|
||
|
|
"task_alias": "college_mathematics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_mathematics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college mathematics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_medicine": {
|
||
|
|
"task": "mmlu_college_medicine",
|
||
|
|
"task_alias": "college_medicine",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_medicine",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college medicine.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_college_physics": {
|
||
|
|
"task": "mmlu_college_physics",
|
||
|
|
"task_alias": "college_physics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "college_physics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about college physics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_computer_security": {
|
||
|
|
"task": "mmlu_computer_security",
|
||
|
|
"task_alias": "computer_security",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "computer_security",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about computer security.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_conceptual_physics": {
|
||
|
|
"task": "mmlu_conceptual_physics",
|
||
|
|
"task_alias": "conceptual_physics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "conceptual_physics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_econometrics": {
|
||
|
|
"task": "mmlu_econometrics",
|
||
|
|
"task_alias": "econometrics",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "econometrics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about econometrics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_electrical_engineering": {
|
||
|
|
"task": "mmlu_electrical_engineering",
|
||
|
|
"task_alias": "electrical_engineering",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "electrical_engineering",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_elementary_mathematics": {
|
||
|
|
"task": "mmlu_elementary_mathematics",
|
||
|
|
"task_alias": "elementary_mathematics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "elementary_mathematics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_formal_logic": {
|
||
|
|
"task": "mmlu_formal_logic",
|
||
|
|
"task_alias": "formal_logic",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "formal_logic",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about formal logic.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_global_facts": {
|
||
|
|
"task": "mmlu_global_facts",
|
||
|
|
"task_alias": "global_facts",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "global_facts",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about global facts.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_biology": {
|
||
|
|
"task": "mmlu_high_school_biology",
|
||
|
|
"task_alias": "high_school_biology",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_biology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school biology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_chemistry": {
|
||
|
|
"task": "mmlu_high_school_chemistry",
|
||
|
|
"task_alias": "high_school_chemistry",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_chemistry",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_computer_science": {
|
||
|
|
"task": "mmlu_high_school_computer_science",
|
||
|
|
"task_alias": "high_school_computer_science",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_computer_science",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school computer science.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_european_history": {
|
||
|
|
"task": "mmlu_high_school_european_history",
|
||
|
|
"task_alias": "high_school_european_history",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_european_history",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school european history.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_geography": {
|
||
|
|
"task": "mmlu_high_school_geography",
|
||
|
|
"task_alias": "high_school_geography",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_geography",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school geography.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_government_and_politics": {
|
||
|
|
"task": "mmlu_high_school_government_and_politics",
|
||
|
|
"task_alias": "high_school_government_and_politics",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_government_and_politics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_macroeconomics": {
|
||
|
|
"task": "mmlu_high_school_macroeconomics",
|
||
|
|
"task_alias": "high_school_macroeconomics",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_macroeconomics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_mathematics": {
|
||
|
|
"task": "mmlu_high_school_mathematics",
|
||
|
|
"task_alias": "high_school_mathematics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_mathematics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_microeconomics": {
|
||
|
|
"task": "mmlu_high_school_microeconomics",
|
||
|
|
"task_alias": "high_school_microeconomics",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_microeconomics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_physics": {
|
||
|
|
"task": "mmlu_high_school_physics",
|
||
|
|
"task_alias": "high_school_physics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_physics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school physics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_psychology": {
|
||
|
|
"task": "mmlu_high_school_psychology",
|
||
|
|
"task_alias": "high_school_psychology",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_psychology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school psychology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_statistics": {
|
||
|
|
"task": "mmlu_high_school_statistics",
|
||
|
|
"task_alias": "high_school_statistics",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_statistics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school statistics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_us_history": {
|
||
|
|
"task": "mmlu_high_school_us_history",
|
||
|
|
"task_alias": "high_school_us_history",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_us_history",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school us history.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_high_school_world_history": {
|
||
|
|
"task": "mmlu_high_school_world_history",
|
||
|
|
"task_alias": "high_school_world_history",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "high_school_world_history",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about high school world history.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_human_aging": {
|
||
|
|
"task": "mmlu_human_aging",
|
||
|
|
"task_alias": "human_aging",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "human_aging",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about human aging.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_human_sexuality": {
|
||
|
|
"task": "mmlu_human_sexuality",
|
||
|
|
"task_alias": "human_sexuality",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "human_sexuality",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about human sexuality.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_international_law": {
|
||
|
|
"task": "mmlu_international_law",
|
||
|
|
"task_alias": "international_law",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "international_law",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about international law.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_jurisprudence": {
|
||
|
|
"task": "mmlu_jurisprudence",
|
||
|
|
"task_alias": "jurisprudence",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "jurisprudence",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_logical_fallacies": {
|
||
|
|
"task": "mmlu_logical_fallacies",
|
||
|
|
"task_alias": "logical_fallacies",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "logical_fallacies",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_machine_learning": {
|
||
|
|
"task": "mmlu_machine_learning",
|
||
|
|
"task_alias": "machine_learning",
|
||
|
|
"group": "mmlu_stem",
|
||
|
|
"group_alias": "stem",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "machine_learning",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about machine learning.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_management": {
|
||
|
|
"task": "mmlu_management",
|
||
|
|
"task_alias": "management",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "management",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about management.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_marketing": {
|
||
|
|
"task": "mmlu_marketing",
|
||
|
|
"task_alias": "marketing",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "marketing",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about marketing.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_medical_genetics": {
|
||
|
|
"task": "mmlu_medical_genetics",
|
||
|
|
"task_alias": "medical_genetics",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "medical_genetics",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about medical genetics.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_miscellaneous": {
|
||
|
|
"task": "mmlu_miscellaneous",
|
||
|
|
"task_alias": "miscellaneous",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "miscellaneous",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_moral_disputes": {
|
||
|
|
"task": "mmlu_moral_disputes",
|
||
|
|
"task_alias": "moral_disputes",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "moral_disputes",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about moral disputes.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_moral_scenarios": {
|
||
|
|
"task": "mmlu_moral_scenarios",
|
||
|
|
"task_alias": "moral_scenarios",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "moral_scenarios",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_nutrition": {
|
||
|
|
"task": "mmlu_nutrition",
|
||
|
|
"task_alias": "nutrition",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "nutrition",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about nutrition.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_philosophy": {
|
||
|
|
"task": "mmlu_philosophy",
|
||
|
|
"task_alias": "philosophy",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "philosophy",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about philosophy.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_prehistory": {
|
||
|
|
"task": "mmlu_prehistory",
|
||
|
|
"task_alias": "prehistory",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "prehistory",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about prehistory.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_professional_accounting": {
|
||
|
|
"task": "mmlu_professional_accounting",
|
||
|
|
"task_alias": "professional_accounting",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "professional_accounting",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about professional accounting.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_professional_law": {
|
||
|
|
"task": "mmlu_professional_law",
|
||
|
|
"task_alias": "professional_law",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "professional_law",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about professional law.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_professional_medicine": {
|
||
|
|
"task": "mmlu_professional_medicine",
|
||
|
|
"task_alias": "professional_medicine",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "professional_medicine",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about professional medicine.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_professional_psychology": {
|
||
|
|
"task": "mmlu_professional_psychology",
|
||
|
|
"task_alias": "professional_psychology",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "professional_psychology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about professional psychology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_public_relations": {
|
||
|
|
"task": "mmlu_public_relations",
|
||
|
|
"task_alias": "public_relations",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "public_relations",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about public relations.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_security_studies": {
|
||
|
|
"task": "mmlu_security_studies",
|
||
|
|
"task_alias": "security_studies",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "security_studies",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about security studies.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_sociology": {
|
||
|
|
"task": "mmlu_sociology",
|
||
|
|
"task_alias": "sociology",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "sociology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about sociology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_us_foreign_policy": {
|
||
|
|
"task": "mmlu_us_foreign_policy",
|
||
|
|
"task_alias": "us_foreign_policy",
|
||
|
|
"group": "mmlu_social_sciences",
|
||
|
|
"group_alias": "social_sciences",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "us_foreign_policy",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_virology": {
|
||
|
|
"task": "mmlu_virology",
|
||
|
|
"task_alias": "virology",
|
||
|
|
"group": "mmlu_other",
|
||
|
|
"group_alias": "other",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "virology",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about virology.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"mmlu_world_religions": {
|
||
|
|
"task": "mmlu_world_religions",
|
||
|
|
"task_alias": "world_religions",
|
||
|
|
"group": "mmlu_humanities",
|
||
|
|
"group_alias": "humanities",
|
||
|
|
"dataset_path": "hails/mmlu_no_train",
|
||
|
|
"dataset_name": "world_religions",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "dev",
|
||
|
|
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
|
||
|
|
"doc_to_target": "answer",
|
||
|
|
"doc_to_choice": [
|
||
|
|
"A",
|
||
|
|
"B",
|
||
|
|
"C",
|
||
|
|
"D"
|
||
|
|
],
|
||
|
|
"description": "The following are multiple choice questions (with answers) about world religions.\n\n",
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"mmlu_abstract_algebra": 0,
|
||
|
|
"mmlu_anatomy": 0,
|
||
|
|
"mmlu_astronomy": 0,
|
||
|
|
"mmlu_business_ethics": 0,
|
||
|
|
"mmlu_clinical_knowledge": 0,
|
||
|
|
"mmlu_college_biology": 0,
|
||
|
|
"mmlu_college_chemistry": 0,
|
||
|
|
"mmlu_college_computer_science": 0,
|
||
|
|
"mmlu_college_mathematics": 0,
|
||
|
|
"mmlu_college_medicine": 0,
|
||
|
|
"mmlu_college_physics": 0,
|
||
|
|
"mmlu_computer_security": 0,
|
||
|
|
"mmlu_conceptual_physics": 0,
|
||
|
|
"mmlu_econometrics": 0,
|
||
|
|
"mmlu_electrical_engineering": 0,
|
||
|
|
"mmlu_elementary_mathematics": 0,
|
||
|
|
"mmlu_formal_logic": 0,
|
||
|
|
"mmlu_global_facts": 0,
|
||
|
|
"mmlu_high_school_biology": 0,
|
||
|
|
"mmlu_high_school_chemistry": 0,
|
||
|
|
"mmlu_high_school_computer_science": 0,
|
||
|
|
"mmlu_high_school_european_history": 0,
|
||
|
|
"mmlu_high_school_geography": 0,
|
||
|
|
"mmlu_high_school_government_and_politics": 0,
|
||
|
|
"mmlu_high_school_macroeconomics": 0,
|
||
|
|
"mmlu_high_school_mathematics": 0,
|
||
|
|
"mmlu_high_school_microeconomics": 0,
|
||
|
|
"mmlu_high_school_physics": 0,
|
||
|
|
"mmlu_high_school_psychology": 0,
|
||
|
|
"mmlu_high_school_statistics": 0,
|
||
|
|
"mmlu_high_school_us_history": 0,
|
||
|
|
"mmlu_high_school_world_history": 0,
|
||
|
|
"mmlu_human_aging": 0,
|
||
|
|
"mmlu_human_sexuality": 0,
|
||
|
|
"mmlu_international_law": 0,
|
||
|
|
"mmlu_jurisprudence": 0,
|
||
|
|
"mmlu_logical_fallacies": 0,
|
||
|
|
"mmlu_machine_learning": 0,
|
||
|
|
"mmlu_management": 0,
|
||
|
|
"mmlu_marketing": 0,
|
||
|
|
"mmlu_medical_genetics": 0,
|
||
|
|
"mmlu_miscellaneous": 0,
|
||
|
|
"mmlu_moral_disputes": 0,
|
||
|
|
"mmlu_moral_scenarios": 0,
|
||
|
|
"mmlu_nutrition": 0,
|
||
|
|
"mmlu_philosophy": 0,
|
||
|
|
"mmlu_prehistory": 0,
|
||
|
|
"mmlu_professional_accounting": 0,
|
||
|
|
"mmlu_professional_law": 0,
|
||
|
|
"mmlu_professional_medicine": 0,
|
||
|
|
"mmlu_professional_psychology": 0,
|
||
|
|
"mmlu_public_relations": 0,
|
||
|
|
"mmlu_security_studies": 0,
|
||
|
|
"mmlu_sociology": 0,
|
||
|
|
"mmlu_us_foreign_policy": 0,
|
||
|
|
"mmlu_virology": 0,
|
||
|
|
"mmlu_world_religions": 0
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"mmlu": 0,
|
||
|
|
"mmlu_abstract_algebra": 5,
|
||
|
|
"mmlu_anatomy": 5,
|
||
|
|
"mmlu_astronomy": 5,
|
||
|
|
"mmlu_business_ethics": 5,
|
||
|
|
"mmlu_clinical_knowledge": 5,
|
||
|
|
"mmlu_college_biology": 5,
|
||
|
|
"mmlu_college_chemistry": 5,
|
||
|
|
"mmlu_college_computer_science": 5,
|
||
|
|
"mmlu_college_mathematics": 5,
|
||
|
|
"mmlu_college_medicine": 5,
|
||
|
|
"mmlu_college_physics": 5,
|
||
|
|
"mmlu_computer_security": 5,
|
||
|
|
"mmlu_conceptual_physics": 5,
|
||
|
|
"mmlu_econometrics": 5,
|
||
|
|
"mmlu_electrical_engineering": 5,
|
||
|
|
"mmlu_elementary_mathematics": 5,
|
||
|
|
"mmlu_formal_logic": 5,
|
||
|
|
"mmlu_global_facts": 5,
|
||
|
|
"mmlu_high_school_biology": 5,
|
||
|
|
"mmlu_high_school_chemistry": 5,
|
||
|
|
"mmlu_high_school_computer_science": 5,
|
||
|
|
"mmlu_high_school_european_history": 5,
|
||
|
|
"mmlu_high_school_geography": 5,
|
||
|
|
"mmlu_high_school_government_and_politics": 5,
|
||
|
|
"mmlu_high_school_macroeconomics": 5,
|
||
|
|
"mmlu_high_school_mathematics": 5,
|
||
|
|
"mmlu_high_school_microeconomics": 5,
|
||
|
|
"mmlu_high_school_physics": 5,
|
||
|
|
"mmlu_high_school_psychology": 5,
|
||
|
|
"mmlu_high_school_statistics": 5,
|
||
|
|
"mmlu_high_school_us_history": 5,
|
||
|
|
"mmlu_high_school_world_history": 5,
|
||
|
|
"mmlu_human_aging": 5,
|
||
|
|
"mmlu_human_sexuality": 5,
|
||
|
|
"mmlu_humanities": 5,
|
||
|
|
"mmlu_international_law": 5,
|
||
|
|
"mmlu_jurisprudence": 5,
|
||
|
|
"mmlu_logical_fallacies": 5,
|
||
|
|
"mmlu_machine_learning": 5,
|
||
|
|
"mmlu_management": 5,
|
||
|
|
"mmlu_marketing": 5,
|
||
|
|
"mmlu_medical_genetics": 5,
|
||
|
|
"mmlu_miscellaneous": 5,
|
||
|
|
"mmlu_moral_disputes": 5,
|
||
|
|
"mmlu_moral_scenarios": 5,
|
||
|
|
"mmlu_nutrition": 5,
|
||
|
|
"mmlu_other": 5,
|
||
|
|
"mmlu_philosophy": 5,
|
||
|
|
"mmlu_prehistory": 5,
|
||
|
|
"mmlu_professional_accounting": 5,
|
||
|
|
"mmlu_professional_law": 5,
|
||
|
|
"mmlu_professional_medicine": 5,
|
||
|
|
"mmlu_professional_psychology": 5,
|
||
|
|
"mmlu_public_relations": 5,
|
||
|
|
"mmlu_security_studies": 5,
|
||
|
|
"mmlu_social_sciences": 5,
|
||
|
|
"mmlu_sociology": 5,
|
||
|
|
"mmlu_stem": 5,
|
||
|
|
"mmlu_us_foreign_policy": 5,
|
||
|
|
"mmlu_virology": 5,
|
||
|
|
"mmlu_world_religions": 5
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711788028.1817935,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"truthfulqa": {
|
||
|
|
"rouge2_diff,none": 8.67940525480841,
|
||
|
|
"rouge2_diff_stderr,none": 1.4198080901104466,
|
||
|
|
"rougeL_acc,none": 0.5006119951040392,
|
||
|
|
"rougeL_acc_stderr,none": 0.01750348793889251,
|
||
|
|
"bleu_diff,none": 6.113558118723995,
|
||
|
|
"bleu_diff_stderr,none": 0.9835911873788621,
|
||
|
|
"bleu_max,none": 31.58553386517857,
|
||
|
|
"bleu_max_stderr,none": 0.8624877973356571,
|
||
|
|
"rougeL_diff,none": 8.01633158328263,
|
||
|
|
"rougeL_diff_stderr,none": 1.3219926011549958,
|
||
|
|
"rouge1_acc,none": 0.5201958384332925,
|
||
|
|
"rouge1_acc_stderr,none": 0.017489216849737043,
|
||
|
|
"rouge1_max,none": 58.02723518350246,
|
||
|
|
"rouge1_max_stderr,none": 0.888784126120325,
|
||
|
|
"rouge2_max,none": 44.60344255474271,
|
||
|
|
"rouge2_max_stderr,none": 1.0820687663065565,
|
||
|
|
"acc,none": 0.4345242323941256,
|
||
|
|
"acc_stderr,none": 0.011190008265641689,
|
||
|
|
"rouge1_diff,none": 8.368475511958406,
|
||
|
|
"rouge1_diff_stderr,none": 1.3027365232348227,
|
||
|
|
"rougeL_max,none": 54.8884498682059,
|
||
|
|
"rougeL_max_stderr,none": 0.9253643022959754,
|
||
|
|
"bleu_acc,none": 0.5091799265605875,
|
||
|
|
"bleu_acc_stderr,none": 0.017500550724819743,
|
||
|
|
"rouge2_acc,none": 0.4638922888616891,
|
||
|
|
"rouge2_acc_stderr,none": 0.017457800422268615,
|
||
|
|
"alias": "truthfulqa"
|
||
|
|
},
|
||
|
|
"truthfulqa_gen": {
|
||
|
|
"bleu_max,none": 31.58553386517857,
|
||
|
|
"bleu_max_stderr,none": 0.862487797335657,
|
||
|
|
"bleu_acc,none": 0.5091799265605875,
|
||
|
|
"bleu_acc_stderr,none": 0.017500550724819743,
|
||
|
|
"bleu_diff,none": 6.113558118723995,
|
||
|
|
"bleu_diff_stderr,none": 0.9835911873788621,
|
||
|
|
"rouge1_max,none": 58.02723518350246,
|
||
|
|
"rouge1_max_stderr,none": 0.888784126120325,
|
||
|
|
"rouge1_acc,none": 0.5201958384332925,
|
||
|
|
"rouge1_acc_stderr,none": 0.01748921684973704,
|
||
|
|
"rouge1_diff,none": 8.368475511958406,
|
||
|
|
"rouge1_diff_stderr,none": 1.3027365232348225,
|
||
|
|
"rouge2_max,none": 44.60344255474271,
|
||
|
|
"rouge2_max_stderr,none": 1.0820687663065565,
|
||
|
|
"rouge2_acc,none": 0.4638922888616891,
|
||
|
|
"rouge2_acc_stderr,none": 0.01745780042226862,
|
||
|
|
"rouge2_diff,none": 8.67940525480841,
|
||
|
|
"rouge2_diff_stderr,none": 1.4198080901104464,
|
||
|
|
"rougeL_max,none": 54.8884498682059,
|
||
|
|
"rougeL_max_stderr,none": 0.9253643022959754,
|
||
|
|
"rougeL_acc,none": 0.5006119951040392,
|
||
|
|
"rougeL_acc_stderr,none": 0.01750348793889251,
|
||
|
|
"rougeL_diff,none": 8.01633158328263,
|
||
|
|
"rougeL_diff_stderr,none": 1.3219926011549958,
|
||
|
|
"alias": " - truthfulqa_gen"
|
||
|
|
},
|
||
|
|
"truthfulqa_mc1": {
|
||
|
|
"acc,none": 0.35006119951040393,
|
||
|
|
"acc_stderr,none": 0.016697949420151025,
|
||
|
|
"alias": " - truthfulqa_mc1"
|
||
|
|
},
|
||
|
|
"truthfulqa_mc2": {
|
||
|
|
"acc,none": 0.5189872652778472,
|
||
|
|
"acc_stderr,none": 0.014901128316426086,
|
||
|
|
"alias": " - truthfulqa_mc2"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"groups": {
|
||
|
|
"truthfulqa": {
|
||
|
|
"rouge2_diff,none": 8.67940525480841,
|
||
|
|
"rouge2_diff_stderr,none": 1.4198080901104466,
|
||
|
|
"rougeL_acc,none": 0.5006119951040392,
|
||
|
|
"rougeL_acc_stderr,none": 0.01750348793889251,
|
||
|
|
"bleu_diff,none": 6.113558118723995,
|
||
|
|
"bleu_diff_stderr,none": 0.9835911873788621,
|
||
|
|
"bleu_max,none": 31.58553386517857,
|
||
|
|
"bleu_max_stderr,none": 0.8624877973356571,
|
||
|
|
"rougeL_diff,none": 8.01633158328263,
|
||
|
|
"rougeL_diff_stderr,none": 1.3219926011549958,
|
||
|
|
"rouge1_acc,none": 0.5201958384332925,
|
||
|
|
"rouge1_acc_stderr,none": 0.017489216849737043,
|
||
|
|
"rouge1_max,none": 58.02723518350246,
|
||
|
|
"rouge1_max_stderr,none": 0.888784126120325,
|
||
|
|
"rouge2_max,none": 44.60344255474271,
|
||
|
|
"rouge2_max_stderr,none": 1.0820687663065565,
|
||
|
|
"acc,none": 0.4345242323941256,
|
||
|
|
"acc_stderr,none": 0.011190008265641689,
|
||
|
|
"rouge1_diff,none": 8.368475511958406,
|
||
|
|
"rouge1_diff_stderr,none": 1.3027365232348227,
|
||
|
|
"rougeL_max,none": 54.8884498682059,
|
||
|
|
"rougeL_max_stderr,none": 0.9253643022959754,
|
||
|
|
"bleu_acc,none": 0.5091799265605875,
|
||
|
|
"bleu_acc_stderr,none": 0.017500550724819743,
|
||
|
|
"rouge2_acc,none": 0.4638922888616891,
|
||
|
|
"rouge2_acc_stderr,none": 0.017457800422268615,
|
||
|
|
"alias": "truthfulqa"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"truthfulqa": [
|
||
|
|
"truthfulqa_mc1",
|
||
|
|
"truthfulqa_gen",
|
||
|
|
"truthfulqa_mc2"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"truthfulqa_gen": {
|
||
|
|
"task": "truthfulqa_gen",
|
||
|
|
"group": [
|
||
|
|
"truthfulqa"
|
||
|
|
],
|
||
|
|
"dataset_path": "truthful_qa",
|
||
|
|
"dataset_name": "generation",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n return dataset.map(preprocess_function)\n",
|
||
|
|
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}",
|
||
|
|
"doc_to_target": " ",
|
||
|
|
"process_results": "def process_results_gen(doc, results):\n completion = results[0]\n true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n all_refs = true_refs + false_refs\n\n # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n # # BLEURT\n # bleurt_scores_true = self.bleurt.compute(\n # predictions=[completion] * len(true_refs), references=true_refs\n # )[\"scores\"]\n # bleurt_scores_false = self.bleurt.compute(\n # predictions=[completion] * len(false_refs), references=false_refs\n # )[\"scores\"]\n # bleurt_correct = max(bleurt_scores_true)\n # bleurt_incorrect = max(bleurt_scores_false)\n # bleurt_max = bleurt_correct\n # bleurt_diff = bleurt_correct - bleurt_incorrect\n # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n # BLEU\n bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n bleu_max = bleu_correct\n bleu_diff = bleu_correct - bleu_incorrect\n bleu_acc = int(bleu_correct > bleu_incorrect)\n\n # ROUGE-N\n rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n # ROUGE-1\n rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n rouge1_max = rouge1_correct\n rouge1_diff = rouge1_correct - rouge1_incorrect\n rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n # ROUGE-2\n rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n rouge2_max = rouge2_correct\n rouge2_diff = rouge2_correct - rouge2_incorrect\n rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n # ROUGE-L\n rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n rougeL_max = rougeL_correct\n rougeL_diff = rougeL_correct - rougeL_incorrect\n rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n return {\n # \"bleurt_max\": bleurt_max,\n # \"bleurt_acc\": bleurt_acc,\n # \"bleurt_diff\": bleurt_diff,\n \"bleu_max\": bleu_max,\n \"bleu_acc\": bleu_acc,\n \"bleu_diff\": bleu_diff,\n \"rouge1_max\": rouge1_max,\n \"rouge1_acc\": rouge1_acc,\n \"rouge1_diff\": rouge1_diff,\n \"rouge2_max\": rouge2_max,\n \"rouge2_acc\": rouge2_acc,\n \"rouge2_diff\": rouge2_diff,\n \"rougeL_max\": rougeL_max,\n \"rougeL_acc\": rougeL_acc,\n \"rougeL_diff\": rougeL_diff,\n }\n",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "bleu_max",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "bleu_acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "bleu_diff",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge1_max",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge1_acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge1_diff",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge2_max",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge2_acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rouge2_diff",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rougeL_max",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rougeL_acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"metric": "rougeL_diff",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "generate_until",
|
||
|
|
"generation_kwargs": {
|
||
|
|
"until": [
|
||
|
|
"\n\n"
|
||
|
|
],
|
||
|
|
"do_sample": false
|
||
|
|
},
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": true,
|
||
|
|
"doc_to_decontamination_query": "question",
|
||
|
|
"metadata": {
|
||
|
|
"version": 3
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"truthfulqa_mc1": {
|
||
|
|
"task": "truthfulqa_mc1",
|
||
|
|
"group": [
|
||
|
|
"truthfulqa"
|
||
|
|
],
|
||
|
|
"dataset_path": "truthful_qa",
|
||
|
|
"dataset_name": "multiple_choice",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
|
||
|
|
"doc_to_target": 0,
|
||
|
|
"doc_to_choice": "{{mc1_targets.choices}}",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": true,
|
||
|
|
"doc_to_decontamination_query": "question",
|
||
|
|
"metadata": {
|
||
|
|
"version": 2
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"truthfulqa_mc2": {
|
||
|
|
"task": "truthfulqa_mc2",
|
||
|
|
"group": [
|
||
|
|
"truthfulqa"
|
||
|
|
],
|
||
|
|
"dataset_path": "truthful_qa",
|
||
|
|
"dataset_name": "multiple_choice",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
|
||
|
|
"doc_to_target": 0,
|
||
|
|
"doc_to_choice": "{{mc2_targets.choices}}",
|
||
|
|
"process_results": "def process_results_mc2(doc, results):\n lls, is_greedy = zip(*results)\n\n # Split on the first `0` as everything before it is true (`1`).\n split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n # Compute the normalized probability mass for the correct answer.\n ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n p_true = p_true / (sum(p_true) + sum(p_false))\n\n return {\"acc\": sum(p_true)}\n",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 0,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": true,
|
||
|
|
"doc_to_decontamination_query": "question",
|
||
|
|
"metadata": {
|
||
|
|
"version": 2
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"truthfulqa_gen": 3,
|
||
|
|
"truthfulqa_mc1": 2,
|
||
|
|
"truthfulqa_mc2": 2
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"truthfulqa": 0,
|
||
|
|
"truthfulqa_gen": 0,
|
||
|
|
"truthfulqa_mc1": 0,
|
||
|
|
"truthfulqa_mc2": 0
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711780604.5790782,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"results": {
|
||
|
|
"winogrande": {
|
||
|
|
"acc,none": 0.7971586424625099,
|
||
|
|
"acc_stderr,none": 0.011301439925936643,
|
||
|
|
"alias": "winogrande"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"winogrande": []
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"winogrande": {
|
||
|
|
"task": "winogrande",
|
||
|
|
"dataset_path": "winogrande",
|
||
|
|
"dataset_name": "winogrande_xl",
|
||
|
|
"training_split": "train",
|
||
|
|
"validation_split": "validation",
|
||
|
|
"doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n",
|
||
|
|
"doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n",
|
||
|
|
"doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
|
||
|
|
"description": "",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"num_fewshot": 5,
|
||
|
|
"metric_list": [
|
||
|
|
{
|
||
|
|
"metric": "acc",
|
||
|
|
"aggregation": "mean",
|
||
|
|
"higher_is_better": true
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"output_type": "multiple_choice",
|
||
|
|
"repeats": 1,
|
||
|
|
"should_decontaminate": true,
|
||
|
|
"doc_to_decontamination_query": "sentence",
|
||
|
|
"metadata": {
|
||
|
|
"version": 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"versions": {
|
||
|
|
"winogrande": 1
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"winogrande": 5
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=cognitivecomputations/dolphin-2.8-mistral-7b-v02,dtype=auto",
|
||
|
|
"batch_size": "8",
|
||
|
|
"batch_sizes": [],
|
||
|
|
"device": "cuda:0",
|
||
|
|
"use_cache": null,
|
||
|
|
"limit": null,
|
||
|
|
"bootstrap_iters": 100000,
|
||
|
|
"gen_kwargs": null
|
||
|
|
},
|
||
|
|
"git_hash": "ab7cc6b1",
|
||
|
|
"date": 1711781102.7529685,
|
||
|
|
"pretty_env_info": "PyTorch version: 2.2.2+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: 3.11.8 (main, Feb 26 2024, 21:39:34) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-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: \nGPU 0: NVIDIA L40S\nGPU 1: NVIDIA L40S\nGPU 2: NVIDIA L40S\nGPU 3: NVIDIA L40S\nGPU 4: NVIDIA L40S\nGPU 5: NVIDIA L40S\nGPU 6: NVIDIA L40S\nGPU 7: NVIDIA L40S\nGPU 8: NVIDIA L40S\nGPU 9: NVIDIA L40S\n\nNvidia driver version: 550.54.15\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: 46 bits physical, 57 bits virtual\nByte Order: Little Endian\nCPU(s): 80\nOn-line CPU(s) list: 0-79\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 9254 24-Core Processor\nCPU family: 25\nModel: 17\nThread(s) per core: 2\nCore(s) per socket: 4\nSocket(s): 10\nStepping: 1\nBogoMIPS: 5800.00\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid fsrm flush_l1d arch_capabilities\nVirtualization: AMD-V\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 1.3 MiB (40 instances)\nL1i cache: 1.3 MiB (40 instances)\nL2 cache: 40 MiB (40 instances)\nL3 cache: 160 MiB (5 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-39\nNUMA node1 CPU(s): 40-79\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\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==1.26.4\n[pip3] torch==2.2.2\n[pip3] torchaudio==2.2.2\n[pip3]
|
||
|
|
"transformers_version": "4.39.2",
|
||
|
|
"upper_git_hash": null
|
||
|
|
}
|
||
|
|
]
|