File size: 8,681 Bytes
c2908a5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
{
"results": {
"lambada_openai": {
"perplexity,none": 27.470935147560528,
"perplexity_stderr,none": 1.0435144103317135,
"acc,none": 0.3526101300213468,
"acc_stderr,none": 0.006656446028047874,
"alias": "lambada_openai"
},
"hellaswag": {
"acc,none": 0.3329018123879705,
"acc_stderr,none": 0.004702886273189427,
"acc_norm,none": 0.3973312089225254,
"acc_norm_stderr,none": 0.004883455188908959,
"alias": "hellaswag"
}
},
"group_subtasks": {
"hellaswag": [],
"lambada_openai": []
},
"configs": {
"hellaswag": {
"task": "hellaswag",
"group": [
"multiple_choice"
],
"dataset_path": "hellaswag",
"training_split": "train",
"validation_split": "validation",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "{{query}}",
"doc_to_target": "{{label}}",
"doc_to_choice": "choices",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 10,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"lambada_openai": {
"task": "lambada_openai",
"group": [
"lambada"
],
"dataset_path": "EleutherAI/lambada_openai",
"dataset_name": "default",
"test_split": "test",
"doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}",
"doc_to_target": "{{' '+text.split(' ')[-1]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 10,
"metric_list": [
{
"metric": "perplexity",
"aggregation": "perplexity",
"higher_is_better": false
},
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "loglikelihood",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{text}}",
"metadata": {
"version": 1.0
}
}
},
"versions": {
"hellaswag": 1.0,
"lambada_openai": 1.0
},
"n-shot": {
"hellaswag": 10,
"lambada_openai": 10
},
"config": {
"model": "hf",
"model_args": "pretrained=/home/aiops/zhuty/tinyllama/out/tiny_LLaMA_1b_8k_cc_merged_v2_8k/iter-300000-ckpt-step-37500_hf,dtype=float,tokenizer=meta-llama/Llama-2-7b-hf",
"batch_size": "4",
"batch_sizes": [],
"device": "cuda:0",
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null
},
"git_hash": null,
"pretty_env_info": "PyTorch version: 2.1.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.26.4\nLibc version: glibc-2.31\n\nPython version: 3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.4.0-166-generic-x86_64-with-glibc2.17\nIs CUDA available: True\nCUDA runtime version: 11.8.89\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA A100-SXM4-40GB\nNvidia driver version: 535.129.03\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nByte Order: Little Endian\nAddress sizes: 43 bits physical, 48 bits virtual\nCPU(s): 256\nOn-line CPU(s) list: 0-255\nThread(s) per core: 2\nCore(s) per socket: 64\nSocket(s): 2\nNUMA node(s): 8\nVendor ID: AuthenticAMD\nCPU family: 23\nModel: 49\nModel name: AMD EPYC 7742 64-Core Processor\nStepping: 0\nFrequency boost: enabled\nCPU MHz: 2928.014\nCPU max MHz: 2250.0000\nCPU min MHz: 1500.0000\nBogoMIPS: 4491.36\nVirtualization: AMD-V\nL1d cache: 4 MiB\nL1i cache: 4 MiB\nL2 cache: 64 MiB\nL3 cache: 512 MiB\nNUMA node0 CPU(s): 0-15,128-143\nNUMA node1 CPU(s): 16-31,144-159\nNUMA node2 CPU(s): 32-47,160-175\nNUMA node3 CPU(s): 48-63,176-191\nNUMA node4 CPU(s): 64-79,192-207\nNUMA node5 CPU(s): 80-95,208-223\nNUMA node6 CPU(s): 96-111,224-239\nNUMA node7 CPU(s): 112-127,240-255\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: Vulnerable\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca sme sev sev_es\n\nVersions of relevant libraries:\n[pip3] numpy==1.22.4\n[pip3] pytorch-lightning==2.1.3\n[pip3] torch==2.1.0\n[pip3] torchmetrics==1.3.0.post0\n[pip3] triton==2.1.0\n[conda] mkl 2024.0.0 pypi_0 pypi\n[conda] mkl-fft 1.3.1 pypi_0 pypi\n[conda] mkl-service 2.4.0 pypi_0 pypi\n[conda] numpy 1.22.4 pypi_0 pypi\n[conda] pytorch-lightning 2.1.3 pypi_0 pypi\n[conda] torch 2.1.0 pypi_0 pypi\n[conda] torchmetrics 1.3.0.post0 pypi_0 pypi\n[conda] triton 2.1.0 pypi_0 pypi",
"transformers_version": "4.34.0",
"upper_git_hash": null
} |