初始化项目，由ModelHub XC社区提供模型
Model: lanawwas/ALLaM-7B-Instruct-preview Source: Original Platform
This commit is contained in:
ModelHub XC
1108
evaluations/en/Llama-3.3-70B-Instruct/agieval_0_shot.json
Normal file
1108
evaluations/en/Llama-3.3-70B-Instruct/agieval_0_shot.json
Normal file
File diff suppressed because it is too large
Load Diff
117
evaluations/en/Llama-3.3-70B-Instruct/arc_challenge_0_shot.json
Normal file
117
evaluations/en/Llama-3.3-70B-Instruct/arc_challenge_0_shot.json
Normal file
@@ -0,0 +1,117 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"alias": "arc_challenge",
|
||||
"acc,none": 0.6117747440273038,
|
||||
"acc_stderr,none": 0.014241614207414047,
|
||||
"acc_norm,none": 0.6339590443686007,
|
||||
"acc_norm_stderr,none": 0.014077223108470134
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737581843.4494154,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 123864.353343428,
|
||||
"end_time": 123962.742418921,
|
||||
"total_evaluation_time_seconds": "98.38907549300347"
|
||||
}
|
||||
@@ -0,0 +1,119 @@
|
||||
{
|
||||
"results": {
|
||||
"gpqa_main_n_shot": {
|
||||
"alias": "gpqa_main_n_shot",
|
||||
"acc,none": 0.25892857142857145,
|
||||
"acc_stderr,none": 0.020718879324472143,
|
||||
"acc_norm,none": 0.25892857142857145,
|
||||
"acc_norm_stderr,none": 0.020718879324472143
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737587163.2574375,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 129184.190027017,
|
||||
"end_time": 129313.238046962,
|
||||
"total_evaluation_time_seconds": "129.04801994499576"
|
||||
}
|
||||
153
evaluations/en/Llama-3.3-70B-Instruct/gsm8k_5_shot.json
Normal file
153
evaluations/en/Llama-3.3-70B-Instruct/gsm8k_5_shot.json
Normal file
@@ -0,0 +1,153 @@
|
||||
{
|
||||
"results": {
|
||||
"gsm8k": {
|
||||
"alias": "gsm8k",
|
||||
"exact_match,strict-match": 0.9082638362395754,
|
||||
"exact_match_stderr,strict-match": 0.00795094214833935,
|
||||
"exact_match,flexible-extract": 0.935557240333586,
|
||||
"exact_match_stderr,flexible-extract": 0.0067633917284882555
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737587329.0756748,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 129350.110628712,
|
||||
"end_time": 129590.582331698,
|
||||
"total_evaluation_time_seconds": "240.4717029859894"
|
||||
}
|
||||
118
evaluations/en/Llama-3.3-70B-Instruct/hellaswag_0_shot.json
Normal file
118
evaluations/en/Llama-3.3-70B-Instruct/hellaswag_0_shot.json
Normal file
@@ -0,0 +1,118 @@
|
||||
{
|
||||
"results": {
|
||||
"hellaswag": {
|
||||
"alias": "hellaswag",
|
||||
"acc,none": 0.657239593706433,
|
||||
"acc_stderr,none": 0.004736621698861193,
|
||||
"acc_norm,none": 0.843855805616411,
|
||||
"acc_norm_stderr,none": 0.003622501370331856
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737582214.4104311,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 124235.149145965,
|
||||
"end_time": 124763.573958303,
|
||||
"total_evaluation_time_seconds": "528.4248123379948"
|
||||
}
|
||||
@@ -0,0 +1,307 @@
|
||||
{
|
||||
"results": {
|
||||
"ethics_cm": {
|
||||
"alias": "ethics_cm",
|
||||
"acc,none": 0.8023166023166023,
|
||||
"acc_stderr,none": 0.006390257774878015
|
||||
},
|
||||
"ethics_deontology": {
|
||||
"alias": "ethics_deontology",
|
||||
"acc,none": 0.6298665183537263,
|
||||
"acc_stderr,none": 0.008052931418172102
|
||||
},
|
||||
"ethics_justice": {
|
||||
"alias": "ethics_justice",
|
||||
"acc,none": 0.8557692307692307,
|
||||
"acc_stderr,none": 0.006757472246675016
|
||||
},
|
||||
"ethics_utilitarianism": {
|
||||
"alias": "ethics_utilitarianism",
|
||||
"acc,none": 0.8148918469217971,
|
||||
"acc_stderr,none": 0.005601775490890298
|
||||
},
|
||||
"ethics_virtue": {
|
||||
"alias": "ethics_virtue",
|
||||
"acc,none": 0.9495477386934673,
|
||||
"acc_stderr,none": 0.003103457695116678
|
||||
}
|
||||
},
|
||||
"group_subtasks": {
|
||||
"ethics_deontology": [],
|
||||
"ethics_justice": [],
|
||||
"ethics_cm": [],
|
||||
"ethics_utilitarianism": [],
|
||||
"ethics_virtue": []
|
||||
},
|
||||
"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_virtue": {
|
||||
"original": 4975,
|
||||
"effective": 4975
|
||||
},
|
||||
"ethics_utilitarianism": {
|
||||
"original": 4808,
|
||||
"effective": 4808
|
||||
},
|
||||
"ethics_cm": {
|
||||
"original": 3885,
|
||||
"effective": 3885
|
||||
},
|
||||
"ethics_justice": {
|
||||
"original": 2704,
|
||||
"effective": 2704
|
||||
},
|
||||
"ethics_deontology": {
|
||||
"original": 3596,
|
||||
"effective": 3596
|
||||
}
|
||||
},
|
||||
"config": {
|
||||
"model": "vllm",
|
||||
"model_args": "pretrained=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737580554.1132338,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 122574.978636081,
|
||||
"end_time": 123057.366655506,
|
||||
"total_evaluation_time_seconds": "482.3880194250087"
|
||||
}
|
||||
132
evaluations/en/Llama-3.3-70B-Instruct/ifeval_0_shot.json
Normal file
132
evaluations/en/Llama-3.3-70B-Instruct/ifeval_0_shot.json
Normal file
@@ -0,0 +1,132 @@
|
||||
{
|
||||
"results": {
|
||||
"ifeval": {
|
||||
"alias": "ifeval",
|
||||
"prompt_level_strict_acc,none": 0.6321626617375231,
|
||||
"prompt_level_strict_acc_stderr,none": 0.02075130655602969,
|
||||
"inst_level_strict_acc,none": 0.7278177458033573,
|
||||
"inst_level_strict_acc_stderr,none": "N/A",
|
||||
"prompt_level_loose_acc,none": 0.7005545286506469,
|
||||
"prompt_level_loose_acc_stderr,none": 0.019709834029672916,
|
||||
"inst_level_loose_acc,none": 0.7781774580335732,
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737584656.560232,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 126677.523972637,
|
||||
"end_time": 126852.930489088,
|
||||
"total_evaluation_time_seconds": "175.4065164509957"
|
||||
}
|
||||
521
evaluations/en/Llama-3.3-70B-Instruct/minerva_math_4_shot.json
Normal file
521
evaluations/en/Llama-3.3-70B-Instruct/minerva_math_4_shot.json
Normal file
@@ -0,0 +1,521 @@
|
||||
{
|
||||
"results": {
|
||||
"minerva_math": {
|
||||
"exact_match,none": 0.4642,
|
||||
"exact_match_stderr,none": 0.006628889249601153,
|
||||
"alias": "minerva_math"
|
||||
},
|
||||
"minerva_math_algebra": {
|
||||
"alias": " - minerva_math_algebra",
|
||||
"exact_match,none": 0.6293176074136478,
|
||||
"exact_match_stderr,none": 0.01402469985709588
|
||||
},
|
||||
"minerva_math_counting_and_prob": {
|
||||
"alias": " - minerva_math_counting_and_prob",
|
||||
"exact_match,none": 0.5253164556962026,
|
||||
"exact_match_stderr,none": 0.02296053591387607
|
||||
},
|
||||
"minerva_math_geometry": {
|
||||
"alias": " - minerva_math_geometry",
|
||||
"exact_match,none": 0.4154488517745303,
|
||||
"exact_match_stderr,none": 0.022540113165977028
|
||||
},
|
||||
"minerva_math_intermediate_algebra": {
|
||||
"alias": " - minerva_math_intermediate_algebra",
|
||||
"exact_match,none": 0.22591362126245848,
|
||||
"exact_match_stderr,none": 0.013923956329164374
|
||||
},
|
||||
"minerva_math_num_theory": {
|
||||
"alias": " - minerva_math_num_theory",
|
||||
"exact_match,none": 0.45925925925925926,
|
||||
"exact_match_stderr,none": 0.021464912562702897
|
||||
},
|
||||
"minerva_math_prealgebra": {
|
||||
"alias": " - minerva_math_prealgebra",
|
||||
"exact_match,none": 0.6383467278989667,
|
||||
"exact_match_stderr,none": 0.016289767709994334
|
||||
},
|
||||
"minerva_math_precalc": {
|
||||
"alias": " - minerva_math_precalc",
|
||||
"exact_match,none": 0.21611721611721613,
|
||||
"exact_match_stderr,none": 0.017630799001234886
|
||||
}
|
||||
},
|
||||
"groups": {
|
||||
"minerva_math": {
|
||||
"exact_match,none": 0.4642,
|
||||
"exact_match_stderr,none": 0.006628889249601153,
|
||||
"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 0x14a39a518a60>"
|
||||
},
|
||||
"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 0x14a39a4ae9e0>"
|
||||
},
|
||||
"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 0x14a39a4ac8b0>"
|
||||
},
|
||||
"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 0x14a39b2a4d30>"
|
||||
},
|
||||
"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 0x14a39b2a57e0>"
|
||||
},
|
||||
"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 0x14a39b229d80>"
|
||||
},
|
||||
"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 0x14a39b958670>"
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737583466.5454865,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 125487.461297843,
|
||||
"end_time": 126234.645678455,
|
||||
"total_evaluation_time_seconds": "747.1843806120014"
|
||||
}
|
||||
3283
evaluations/en/Llama-3.3-70B-Instruct/mmlu_0_shot.json
Normal file
3283
evaluations/en/Llama-3.3-70B-Instruct/mmlu_0_shot.json
Normal file
File diff suppressed because it is too large
Load Diff
1103
evaluations/en/Llama-3.3-70B-Instruct/mmlu_pro_5_shot.json
Normal file
1103
evaluations/en/Llama-3.3-70B-Instruct/mmlu_pro_5_shot.json
Normal file
File diff suppressed because it is too large
Load Diff
128
evaluations/en/Llama-3.3-70B-Instruct/triviaqa_5_shot.json
Normal file
128
evaluations/en/Llama-3.3-70B-Instruct/triviaqa_5_shot.json
Normal file
@@ -0,0 +1,128 @@
|
||||
{
|
||||
"results": {
|
||||
"triviaqa": {
|
||||
"alias": "triviaqa",
|
||||
"exact_match,remove_whitespace": 0.817041908158716,
|
||||
"exact_match_stderr,remove_whitespace": 0.0028863596794662027
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737582778.909245,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 124799.725543077,
|
||||
"end_time": 125319.396698907,
|
||||
"total_evaluation_time_seconds": "519.6711558300012"
|
||||
}
|
||||
108
evaluations/en/Llama-3.3-70B-Instruct/truthfulqa_mc2_0_shot.json
Normal file
108
evaluations/en/Llama-3.3-70B-Instruct/truthfulqa_mc2_0_shot.json
Normal file
@@ -0,0 +1,108 @@
|
||||
{
|
||||
"results": {
|
||||
"truthfulqa_mc2": {
|
||||
"alias": "truthfulqa_mc2",
|
||||
"acc,none": 0.6090721533173807,
|
||||
"acc_stderr,none": 0.014847067973697343
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737581194.728857,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 123215.544564302,
|
||||
"end_time": 123421.64257545,
|
||||
"total_evaluation_time_seconds": "206.09801114798756"
|
||||
}
|
||||
108
evaluations/en/Llama-3.3-70B-Instruct/winogrande_0_shot.json
Normal file
108
evaluations/en/Llama-3.3-70B-Instruct/winogrande_0_shot.json
Normal file
@@ -0,0 +1,108 @@
|
||||
{
|
||||
"results": {
|
||||
"winogrande": {
|
||||
"alias": "winogrande",
|
||||
"acc,none": 0.7924230465666929,
|
||||
"acc_stderr,none": 0.011398593419386783
|
||||
}
|
||||
},
|
||||
"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=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,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": "150ae04f",
|
||||
"date": 1737581074.38925,
|
||||
"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: 4890.87\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
|
||||
"tokenizer_pad_token": [
|
||||
"<|finetune_right_pad_id|>",
|
||||
"128004"
|
||||
],
|
||||
"tokenizer_eos_token": [
|
||||
"<|eot_id|>",
|
||||
"128009"
|
||||
],
|
||||
"tokenizer_bos_token": [
|
||||
"<|begin_of_text|>",
|
||||
"128000"
|
||||
],
|
||||
"eot_token_id": 128009,
|
||||
"max_length": 131072,
|
||||
"task_hashes": {},
|
||||
"model_source": "vllm",
|
||||
"model_name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct",
|
||||
"system_instruction": null,
|
||||
"system_instruction_sha": null,
|
||||
"fewshot_as_multiturn": false,
|
||||
"chat_template": null,
|
||||
"chat_template_sha": null,
|
||||
"start_time": 123095.348423816,
|
||||
"end_time": 123177.388886054,
|
||||
"total_evaluation_time_seconds": "82.04046223800106"
|
||||
}
|
||||
Reference in New Issue
Block a user