lanawwas/ALLaM-7B-Instruct-preview
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lanawwas/ALLaM-7B-Instruct-preview
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 10:54:04 +08:00
commit 3e4c694337
466 changed files with 259661 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1108
evaluations/en/Allam-7b-instruct-preview/agieval_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff

117
evaluations/en/Allam-7b-instruct-preview/arc_challenge_0_shot.json Normal file
View File

@@ -0,0 +1,117 @@
{
"results": {
"arc_challenge": {
"alias": "arc_challenge",
"acc,none": 0.5127986348122867,
"acc_stderr,none": 0.014606603181012541,
"acc_norm,none": 0.5127986348122867,
"acc_norm_stderr,none": 0.014606603181012538
}
},
"group_subtasks": {
"arc_challenge": []
},
"configs": {
"arc_challenge": {
"task": "arc_challenge",
"tag": [
"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": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
"metadata": {
"version": 1.0
}
}
},
"versions": {
"arc_challenge": 1.0
},
"n-shot": {
"arc_challenge": 0
},
"higher_is_better": {
"arc_challenge": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"arc_challenge": {
"original": 1172,
"effective": 1172
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.5,download_dir=/tmp",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "8e1bd48d",
"date": 1735958479.5122433,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.90\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.47.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 25148.877885035,
"end_time": 25235.270896756,
"total_evaluation_time_seconds": "86.39301172100022"
}

121
evaluations/en/Allam-7b-instruct-preview/gpqa_main_n_shot_0_shot.json Normal file
View File

@@ -0,0 +1,121 @@
{
"results": {
"gpqa_main_n_shot": {
"alias": "gpqa_main_n_shot",
"acc,none": 0.22767857142857142,
"acc_stderr,none": 0.0198338196436619,
"acc_norm,none": 0.22767857142857142,
"acc_norm_stderr,none": 0.0198338196436619
}
},
"group_subtasks": {
"gpqa_main_n_shot": []
},
"configs": {
"gpqa_main_n_shot": {
"task": "gpqa_main_n_shot",
"tag": "gpqa",
"dataset_path": "Idavidrein/gpqa",
"dataset_name": "gpqa_main",
"training_split": "train",
"validation_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n choices = [\n preprocess(doc[\"Incorrect Answer 1\"]),\n preprocess(doc[\"Incorrect Answer 2\"]),\n preprocess(doc[\"Incorrect Answer 3\"]),\n preprocess(doc[\"Correct Answer\"]),\n ]\n\n rng.shuffle(choices)\n correct_answer_index = choices.index(preprocess(doc[\"Correct Answer\"]))\n\n out_doc = {\n \"choice1\": choices[0],\n \"choice2\": choices[1],\n \"choice3\": choices[2],\n \"choice4\": choices[3],\n \"answer\": f\"({chr(65 + correct_answer_index)})\",\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "Question: {{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "Here are some example questions from experts. Answer the final question yourself, following the format of the previous questions exactly.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 2.0
}
}
},
"versions": {
"gpqa_main_n_shot": 2.0
},
"n-shot": {
"gpqa_main_n_shot": 0
},
"higher_is_better": {
"gpqa_main_n_shot": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"gpqa_main_n_shot": {
"original": 448,
"effective": 448
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=1,data_parallel_size=8,gpu_memory_utilization=0.8,download_dir=/tmp,enforce_eager=True",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "788a3672",
"date": 1737961176.7588274,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.89\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {
"gpqa_main_n_shot": "4a64f5415ed03d5c5fec2b22dd8bfd718011928a30847c5b126c837aaf0c0619"
},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 330039.670361117,
"end_time": 330095.888966536,
"total_evaluation_time_seconds": "56.21860541898059"
}

153
evaluations/en/Allam-7b-instruct-preview/gsm8k_5_shot.json Normal file
View File

@@ -0,0 +1,153 @@
{
"results": {
"gsm8k": {
"alias": "gsm8k",
"exact_match,strict-match": 0.6178923426838514,
"exact_match_stderr,strict-match": 0.013384173935648495,
"exact_match,flexible-extract": 0.6224412433661866,
"exact_match_stderr,flexible-extract": 0.013353150666358532
}
},
"group_subtasks": {
"gsm8k": []
},
"configs": {
"gsm8k": {
"task": "gsm8k",
"tag": [
"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": 0.0
},
"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": 3.0
}
}
},
"versions": {
"gsm8k": 3.0
},
"n-shot": {
"gsm8k": 5
},
"higher_is_better": {
"gsm8k": {
"exact_match": true
}
},
"n-samples": {
"gsm8k": {
"original": 1319,
"effective": 1319
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=1,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "788a3672",
"date": 1737546137.8667536,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 23682.650060164,
"end_time": 23828.827645231,
"total_evaluation_time_seconds": "146.1775850669983"
}

118
evaluations/en/Allam-7b-instruct-preview/hellaswag_0_shot.json Normal file
View File

@@ -0,0 +1,118 @@
{
"results": {
"hellaswag": {
"alias": "hellaswag",
"acc,none": 0.5771758613821948,
"acc_stderr,none": 0.00492998369279507,
"acc_norm,none": 0.7625970922127067,
"acc_norm_stderr,none": 0.0042462162299898715
}
},
"group_subtasks": {
"hellaswag": []
},
"configs": {
"hellaswag": {
"task": "hellaswag",
"tag": [
"multiple_choice"
],
"dataset_path": "hellaswag",
"dataset_kwargs": {
"trust_remote_code": true
},
"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": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"hellaswag": 1.0
},
"n-shot": {
"hellaswag": 0
},
"higher_is_better": {
"hellaswag": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"hellaswag": {
"original": 10042,
"effective": 10042
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.5,download_dir=/tmp",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "8e1bd48d",
"date": 1735957117.4813576,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.90\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.47.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 23786.943776673,
"end_time": 23998.958401018,
"total_evaluation_time_seconds": "212.0146243449999"
}

307
evaluations/en/Allam-7b-instruct-preview/hendrycks_ethics_0_shot.json Normal file
View File

@@ -0,0 +1,307 @@
{
"results": {
"ethics_cm": {
"alias": "ethics_cm",
"acc,none": 0.7392535392535392,
"acc_stderr,none": 0.007044761695158352
},
"ethics_deontology": {
"alias": "ethics_deontology",
"acc,none": 0.5786985539488321,
"acc_stderr,none": 0.00823518246369769
},
"ethics_justice": {
"alias": "ethics_justice",
"acc,none": 0.771819526627219,
"acc_stderr,none": 0.00807186884011459
},
"ethics_utilitarianism": {
"alias": "ethics_utilitarianism",
"acc,none": 0.6541181364392679,
"acc_stderr,none": 0.006860486742815242
},
"ethics_virtue": {
"alias": "ethics_virtue",
"acc,none": 0.9147738693467337,
"acc_stderr,none": 0.003959044383441912
}
},
"group_subtasks": {
"ethics_deontology": [],
"ethics_virtue": [],
"ethics_cm": [],
"ethics_utilitarianism": [],
"ethics_justice": []
},
"configs": {
"ethics_cm": {
"task": "ethics_cm",
"tag": [
"hendrycks_ethics"
],
"dataset_path": "EleutherAI/hendrycks_ethics",
"dataset_name": "commonsense",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"doc_to_text": "{{input}}\nQuestion: Is this wrong?\nAnswer:",
"doc_to_target": "label",
"doc_to_choice": [
"no",
"yes"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc"
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"ethics_deontology": {
"task": "ethics_deontology",
"tag": [
"hendrycks_ethics"
],
"dataset_path": "EleutherAI/hendrycks_ethics",
"dataset_name": "deontology",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"doc_to_text": "Question: Would most people believe this reasonable or unreasonable to say? \"{{scenario}} {{excuse.rstrip()}}\"\nAnswer:",
"doc_to_target": "label",
"doc_to_choice": [
"unreasonable",
"reasonable"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc"
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"ethics_justice": {
"task": "ethics_justice",
"tag": [
"hendrycks_ethics"
],
"dataset_path": "EleutherAI/hendrycks_ethics",
"dataset_name": "justice",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"doc_to_text": "Question: Would most people believe this reasonable or unreasonable to say? \"{{scenario}}\"\nAnswer:",
"doc_to_target": "label",
"doc_to_choice": [
"unreasonable",
"reasonable"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc"
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"ethics_utilitarianism": {
"task": "ethics_utilitarianism",
"tag": [
"hendrycks_ethics"
],
"dataset_path": "EleutherAI/hendrycks_ethics",
"dataset_name": "utilitarianism",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"doc_to_text": "def doc_to_text(doc) -> str:\n doc = _preproc_doc(doc)\n return f\"Scenario 1: {doc['scenarios'][0]}\\nScenario 2: {doc['scenarios'][1]}\\nQuestion: Is Scenario 1 preferable?\\nAnswer:\"\n",
"doc_to_target": "def doc_to_target(doc):\n doc = _preproc_doc(doc)\n return doc[\"label\"]\n",
"doc_to_choice": [
"no",
"yes"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc"
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"ethics_virtue": {
"task": "ethics_virtue",
"tag": [
"hendrycks_ethics"
],
"dataset_path": "EleutherAI/hendrycks_ethics",
"dataset_name": "virtue",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"doc_to_text": "Sentence: {{scenario}}\nQuestion: Does the character in this sentence exhibit the trait \"{{trait}}\"?\nAnswer:",
"doc_to_target": "label",
"doc_to_choice": [
"no",
"yes"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc"
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"ethics_cm": 1.0,
"ethics_deontology": 1.0,
"ethics_justice": 1.0,
"ethics_utilitarianism": 1.0,
"ethics_virtue": 1.0
},
"n-shot": {
"ethics_cm": 0,
"ethics_deontology": 0,
"ethics_justice": 0,
"ethics_utilitarianism": 0,
"ethics_virtue": 0
},
"higher_is_better": {
"ethics_cm": {
"acc": true
},
"ethics_deontology": {
"acc": true
},
"ethics_justice": {
"acc": true
},
"ethics_utilitarianism": {
"acc": true
},
"ethics_virtue": {
"acc": true
}
},
"n-samples": {
"ethics_justice": {
"original": 2704,
"effective": 2704
},
"ethics_utilitarianism": {
"original": 4808,
"effective": 4808
},
"ethics_cm": {
"original": 3885,
"effective": 3885
},
"ethics_virtue": {
"original": 4975,
"effective": 4975
},
"ethics_deontology": {
"original": 3596,
"effective": 3596
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.5,download_dir=/tmp",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "8e1bd48d",
"date": 1735957382.509422,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.90\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.47.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 24051.95882374,
"end_time": 24251.353762318,
"total_evaluation_time_seconds": "199.3949385779997"
}

132
evaluations/en/Allam-7b-instruct-preview/ifeval_0_shot.json Normal file
View File

@@ -0,0 +1,132 @@
{
"results": {
"ifeval": {
"alias": "ifeval",
"prompt_level_strict_acc,none": 0.3807763401109057,
"prompt_level_strict_acc_stderr,none": 0.020895937888190833,
"inst_level_strict_acc,none": 0.5,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.4214417744916821,
"prompt_level_loose_acc_stderr,none": 0.021249340085831084,
"inst_level_loose_acc,none": 0.5407673860911271,
"inst_level_loose_acc_stderr,none": "N/A"
}
},
"group_subtasks": {
"ifeval": []
},
"configs": {
"ifeval": {
"task": "ifeval",
"dataset_path": "google/IFEval",
"test_split": "train",
"doc_to_text": "prompt",
"doc_to_target": 0,
"process_results": "def process_results(doc, results):\n inp = InputExample(\n key=doc[\"key\"],\n instruction_id_list=doc[\"instruction_id_list\"],\n prompt=doc[\"prompt\"],\n kwargs=doc[\"kwargs\"],\n )\n response = results[0]\n\n out_strict = test_instruction_following_strict(inp, response)\n out_loose = test_instruction_following_loose(inp, response)\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "prompt_level_strict_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_strict_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
},
{
"metric": "prompt_level_loose_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_loose_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1280
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 4.0
}
}
},
"versions": {
"ifeval": 4.0
},
"n-shot": {
"ifeval": 0
},
"higher_is_better": {
"ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
}
},
"n-samples": {
"ifeval": {
"original": 541,
"effective": 541
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=1,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "788a3672",
"date": 1737545156.5536008,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 22701.50615791,
"end_time": 22785.243168339,
"total_evaluation_time_seconds": "83.73701042899847"
}

521
evaluations/en/Allam-7b-instruct-preview/minerva_math_4_shot.json Normal file
View File

@@ -0,0 +1,521 @@
{
"results": {
"minerva_math": {
"exact_match,none": 0.173,
"exact_match_stderr,none": 0.005146622162421542,
"alias": "minerva_math"
},
"minerva_math_algebra": {
"alias": " - minerva_math_algebra",
"exact_match,none": 0.2409435551811289,
"exact_match_stderr,none": 0.012418019817467794
},
"minerva_math_counting_and_prob": {
"alias": " - minerva_math_counting_and_prob",
"exact_match,none": 0.17088607594936708,
"exact_match_stderr,none": 0.01730732195419626
},
"minerva_math_geometry": {
"alias": " - minerva_math_geometry",
"exact_match,none": 0.12108559498956159,
"exact_match_stderr,none": 0.014921262921998898
},
"minerva_math_intermediate_algebra": {
"alias": " - minerva_math_intermediate_algebra",
"exact_match,none": 0.053156146179401995,
"exact_match_stderr,none": 0.00746986334739643
},
"minerva_math_num_theory": {
"alias": " - minerva_math_num_theory",
"exact_match,none": 0.11296296296296296,
"exact_match_stderr,none": 0.013634666880074295
},
"minerva_math_prealgebra": {
"alias": " - minerva_math_prealgebra",
"exact_match,none": 0.34328358208955223,
"exact_match_stderr,none": 0.01609740338728602
},
"minerva_math_precalc": {
"alias": " - minerva_math_precalc",
"exact_match,none": 0.05860805860805861,
"exact_match_stderr,none": 0.010061567725278785
}
},
"groups": {
"minerva_math": {
"exact_match,none": 0.173,
"exact_match_stderr,none": 0.005146622162421542,
"alias": "minerva_math"
}
},
"group_subtasks": {
"minerva_math": [
"minerva_math_algebra",
"minerva_math_counting_and_prob",
"minerva_math_geometry",
"minerva_math_intermediate_algebra",
"minerva_math_num_theory",
"minerva_math_prealgebra",
"minerva_math_precalc"
]
},
"configs": {
"minerva_math_algebra": {
"task": "minerva_math_algebra",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148513aa0f70>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_counting_and_prob": {
"task": "minerva_math_counting_and_prob",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "counting_and_probability",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148510eeaef0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_geometry": {
"task": "minerva_math_geometry",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "geometry",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148510ee8ca0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_intermediate_algebra": {
"task": "minerva_math_intermediate_algebra",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "intermediate_algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148510ee17e0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_num_theory": {
"task": "minerva_math_num_theory",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "number_theory",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148510ee15a0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_prealgebra": {
"task": "minerva_math_prealgebra",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "prealgebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148510e02b90>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"minerva_math_precalc": {
"task": "minerva_math_precalc",
"tag": [
"math_word_problems"
],
"group": [
"math_word_problems"
],
"dataset_path": "EleutherAI/hendrycks_math",
"dataset_name": "precalculus",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x148516fe49d0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"minerva_math": 1.0,
"minerva_math_algebra": 1.0,
"minerva_math_counting_and_prob": 1.0,
"minerva_math_geometry": 1.0,
"minerva_math_intermediate_algebra": 1.0,
"minerva_math_num_theory": 1.0,
"minerva_math_prealgebra": 1.0,
"minerva_math_precalc": 1.0
},
"n-shot": {
"minerva_math_algebra": 4,
"minerva_math_counting_and_prob": 4,
"minerva_math_geometry": 4,
"minerva_math_intermediate_algebra": 4,
"minerva_math_num_theory": 4,
"minerva_math_prealgebra": 4,
"minerva_math_precalc": 4
},
"higher_is_better": {
"minerva_math": {
"exact_match": true
},
"minerva_math_algebra": {
"exact_match": true
},
"minerva_math_counting_and_prob": {
"exact_match": true
},
"minerva_math_geometry": {
"exact_match": true
},
"minerva_math_intermediate_algebra": {
"exact_match": true
},
"minerva_math_num_theory": {
"exact_match": true
},
"minerva_math_prealgebra": {
"exact_match": true
},
"minerva_math_precalc": {
"exact_match": true
}
},
"n-samples": {
"minerva_math_algebra": {
"original": 1187,
"effective": 1187
},
"minerva_math_counting_and_prob": {
"original": 474,
"effective": 474
},
"minerva_math_geometry": {
"original": 479,
"effective": 479
},
"minerva_math_intermediate_algebra": {
"original": 903,
"effective": 903
},
"minerva_math_num_theory": {
"original": 540,
"effective": 540
},
"minerva_math_prealgebra": {
"original": 871,
"effective": 871
},
"minerva_math_precalc": {
"original": 546,
"effective": 546
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=1,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "788a3672",
"date": 1737544396.9634442,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 21941.885116993,
"end_time": 22486.922181144,
"total_evaluation_time_seconds": "545.0370641510017"
}

3289
evaluations/en/Allam-7b-instruct-preview/mmlu_0_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff

1103
evaluations/en/Allam-7b-instruct-preview/mmlu_pro_5_shot.json Normal file
View File

File diff suppressed because it is too large Load Diff

128
evaluations/en/Allam-7b-instruct-preview/triviaqa_5_shot.json Normal file
View File

@@ -0,0 +1,128 @@
{
"results": {
"triviaqa": {
"alias": "triviaqa",
"exact_match,remove_whitespace": 0.16066651805617477,
"exact_match_stderr,remove_whitespace": 0.002741463299754975
}
},
"group_subtasks": {
"triviaqa": []
},
"configs": {
"triviaqa": {
"task": "triviaqa",
"dataset_path": "trivia_qa",
"dataset_name": "rc.nocontext",
"training_split": "train",
"validation_split": "validation",
"doc_to_text": "Question: {{question}}?\nAnswer:",
"doc_to_target": "{{answer.aliases}}",
"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": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"\n",
".",
","
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"filter_list": [
{
"name": "remove_whitespace",
"filter": [
{
"function": "remove_whitespace"
},
{
"function": "take_first"
}
]
}
],
"should_decontaminate": true,
"doc_to_decontamination_query": "question",
"metadata": {
"version": 3.0
}
}
},
"versions": {
"triviaqa": 3.0
},
"n-shot": {
"triviaqa": 5
},
"higher_is_better": {
"triviaqa": {
"exact_match": true
}
},
"n-samples": {
"triviaqa": {
"original": 17944,
"effective": 17944
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=1,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "788a3672",
"date": 1737544037.6055677,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 21582.583321473,
"end_time": 21855.449312492,
"total_evaluation_time_seconds": "272.8659910189999"
}

108
evaluations/en/Allam-7b-instruct-preview/truthfulqa_mc2_0_shot.json Normal file
View File

@@ -0,0 +1,108 @@
{
"results": {
"truthfulqa_mc2": {
"alias": "truthfulqa_mc2",
"acc,none": 0.4667466051524712,
"acc_stderr,none": 0.015605585169281691
}
},
"group_subtasks": {
"truthfulqa_mc2": []
},
"configs": {
"truthfulqa_mc2": {
"task": "truthfulqa_mc2",
"tag": [
"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": 2.0
}
}
},
"versions": {
"truthfulqa_mc2": 2.0
},
"n-shot": {
"truthfulqa_mc2": 0
},
"higher_is_better": {
"truthfulqa_mc2": {
"acc": true
}
},
"n-samples": {
"truthfulqa_mc2": {
"original": 817,
"effective": 817
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.5,download_dir=/tmp",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "8e1bd48d",
"date": 1735957764.7570622,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.90\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.47.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 24434.078025398,
"end_time": 24545.624577618,
"total_evaluation_time_seconds": "111.54655221999928"
}

108
evaluations/en/Allam-7b-instruct-preview/winogrande_0_shot.json Normal file
View File

@@ -0,0 +1,108 @@
{
"results": {
"winogrande": {
"alias": "winogrande",
"acc,none": 0.7048145224940805,
"acc_stderr,none": 0.012819410741754765
}
},
"group_subtasks": {
"winogrande": []
},
"configs": {
"winogrande": {
"task": "winogrande",
"dataset_path": "winogrande",
"dataset_name": "winogrande_xl",
"dataset_kwargs": {
"trust_remote_code": true
},
"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": 0,
"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": 1.0
}
}
},
"versions": {
"winogrande": 1.0
},
"n-shot": {
"winogrande": 0
},
"higher_is_better": {
"winogrande": {
"acc": true
}
},
"n-samples": {
"winogrande": {
"original": 1267,
"effective": 1267
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=/tmp/7b-alpha-v1.27.2.25,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.5,download_dir=/tmp",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "8e1bd48d",
"date": 1735957928.9213855,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.90\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI 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] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.47.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<unk>",
"0"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 4096,
"task_hashes": {},
"model_source": "vllm",
"model_name": "/tmp/7b-alpha-v1.27.2.25",
"model_name_sanitized": "__tmp__7b-alpha-v1.27.2.25",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 24598.479043164,
"end_time": 24674.97354231,
"total_evaluation_time_seconds": "76.49449914599973"
}