129 lines
8.6 KiB
JSON
129 lines
8.6 KiB
JSON
|
{
|
||
|
|
"results": {
|
||
|
|
"moe_ien_tf": {
|
||
|
|
"alias": "moe_ien_tf",
|
||
|
|
"acc,none": 0.7590589043448395,
|
||
|
|
"acc_stderr,none": 0.00560476076159517,
|
||
|
|
"acc_norm,none": 0.7590589043448395,
|
||
|
|
"acc_norm_stderr,none": 0.00560476076159517
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"group_subtasks": {
|
||
|
|
"moe_ien_tf": []
|
||
|
|
},
|
||
|
|
"configs": {
|
||
|
|
"moe_ien_tf": {
|
||
|
|
"task": "moe_ien_tf",
|
||
|
|
"tag": [
|
||
|
|
"multiple_choice"
|
||
|
|
],
|
||
|
|
"dataset_path": "lm_eval/tasks/moe_ien_tf/moe_ien_tf.py",
|
||
|
|
"dataset_name": "moe_ien_tf",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"trust_remote_code": true
|
||
|
|
},
|
||
|
|
"validation_split": "validation",
|
||
|
|
"test_split": "test",
|
||
|
|
"fewshot_split": "validation",
|
||
|
|
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_docs(doc):\n keys=[\"\u0635\u062d\u064a\u062d\u0629\",\n \"\u062e\u0627\u0637\u0626\u0629\"\n ]\n #keys =[\"\u0635\u0648\u0627\u0628\",\n # \"\u062e\u0637\u0623\"]\n target_key = int(doc[\"Answer\"])-1\n\n out_doc = {\n \"query\": \"\\n\\n\u0627\u0644\u0633\u0624\u0627\u0644:\" +doc[\"Question\"]+\"\\n\u0625\u062c\u0627\u0628\u0629:'\", \n \"choices\": keys,\n \"gold\": target_key,\n }\n return out_doc\n return dataset.map(_process_docs)\n",
|
||
|
|
"doc_to_text": "query",
|
||
|
|
"doc_to_target": "gold",
|
||
|
|
"doc_to_choice": "choices",
|
||
|
|
"description": "\u0641\u064a\u0645\u0627 \u064a\u0644\u064a \u0639\u0628\u0627\u0631\u0627\u062a \u0625\u0645\u0627 \u0635\u062d\u064a\u062d\u0629 \u0623\u0648 \u062e\u0627\u0637\u0626\u0629 \u062d\u0648\u0644 {{Subject}}\n \u0627\u0644\u0631\u062c\u0627\u0621 \u062a\u0635\u0646\u064a\u0641 \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0625\u0644\u0649 '\u0635\u062d\u064a\u062d\u0629' \u0623\u0648 '\u062e\u0627\u0637\u0626\u0629' \u062f\u0648\u0646 \u0634\u0631\u062d ",
|
||
|
|
"target_delimiter": " ",
|
||
|
|
"fewshot_delimiter": "\n\n",
|
||
|
|
"fewshot_config": {
|
||
|
|
"sampler": "balanced_cat"
|
||
|
|
},
|
||
|
|
"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": {
|
||
|
|
"moe_ien_tf": 2.0
|
||
|
|
},
|
||
|
|
"n-shot": {
|
||
|
|
"moe_ien_tf": 0
|
||
|
|
},
|
||
|
|
"higher_is_better": {
|
||
|
|
"moe_ien_tf": {
|
||
|
|
"acc": true,
|
||
|
|
"acc_norm": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"n-samples": {
|
||
|
|
"moe_ien_tf": {
|
||
|
|
"original": 5823,
|
||
|
|
"effective": 5823
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"model": "hf",
|
||
|
|
"model_args": "pretrained=FreedomIntelligence/AceGPT-v2-8B-Chat,trust_remote_code=True,cache_dir=/tmp,parallelize=False",
|
||
|
|
"model_num_parameters": 8030261248,
|
||
|
|
"model_dtype": "torch.float16",
|
||
|
|
"model_revision": "main",
|
||
|
|
"model_sha": "562d0998c03c02d315e346f81650a43955711901",
|
||
|
|
"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": "b955b2950",
|
||
|
|
"date": 1739783594.7150183,
|
||
|
|
"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: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 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:
|
||
|
|
"transformers_version": "4.48.3",
|
||
|
|
"upper_git_hash": null,
|
||
|
|
"tokenizer_pad_token": [
|
||
|
|
"<|end_of_text|>",
|
||
|
|
"128001"
|
||
|
|
],
|
||
|
|
"tokenizer_eos_token": [
|
||
|
|
"<|end_of_text|>",
|
||
|
|
"128001"
|
||
|
|
],
|
||
|
|
"tokenizer_bos_token": [
|
||
|
|
"<|begin_of_text|>",
|
||
|
|
"128000"
|
||
|
|
],
|
||
|
|
"eot_token_id": 128001,
|
||
|
|
"max_length": 8192,
|
||
|
|
"task_hashes": {
|
||
|
|
"moe_ien_tf": "a8315c59ec304a82f04395ff5e7728d6586b1b0b5f569486840b7d29d76a8dd8"
|
||
|
|
},
|
||
|
|
"model_source": "hf",
|
||
|
|
"model_name": "FreedomIntelligence/AceGPT-v2-8B-Chat",
|
||
|
|
"model_name_sanitized": "FreedomIntelligence__AceGPT-v2-8B-Chat",
|
||
|
|
"system_instruction": null,
|
||
|
|
"system_instruction_sha": null,
|
||
|
|
"fewshot_as_multiturn": false,
|
||
|
|
"chat_template": null,
|
||
|
|
"chat_template_sha": null,
|
||
|
|
"start_time": 61508.598662402,
|
||
|
|
"end_time": 61883.458017876,
|
||
|
|
"total_evaluation_time_seconds": "374.85935547400004"
|
||
|
|
}
|