| { | |
| "results": { | |
| "lambada_openai": { | |
| "perplexity,none": 33.885559155804046, | |
| "perplexity_stderr,none": 1.3590630677706959, | |
| "acc,none": 0.3293227246264312, | |
| "acc_stderr,none": 0.006547563491030402, | |
| "alias": "lambada_openai" | |
| }, | |
| "hellaswag": { | |
| "acc,none": 0.3211511651065525, | |
| "acc_stderr,none": 0.004659644733309563, | |
| "acc_norm,none": 0.37821151165106554, | |
| "acc_norm_stderr,none": 0.0048394970205366235, | |
| "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-200000-ckpt-step-25000_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-5.4.0-88-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: 48 bits physical, 48 bits virtual\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nThread(s) per core: 2\nCore(s) per socket: 24\nSocket(s): 2\nNUMA node(s): 8\nVendor ID: AuthenticAMD\nCPU family: 23\nModel: 49\nModel name: AMD EPYC 7352 24-Core Processor\nStepping: 0\nCPU MHz: 2888.364\nBogoMIPS: 4591.49\nVirtualization: AMD-V\nL1d cache: 1.5 MiB\nL1i cache: 1.5 MiB\nL2 cache: 24 MiB\nL3 cache: 256 MiB\nNUMA node0 CPU(s): 0-5,48-53\nNUMA node1 CPU(s): 6-11,54-59\nNUMA node2 CPU(s): 12-17,60-65\nNUMA node3 CPU(s): 18-23,66-71\nNUMA node4 CPU(s): 24-29,72-77\nNUMA node5 CPU(s): 30-35,78-83\nNUMA node6 CPU(s): 36-41,84-89\nNUMA node7 CPU(s): 42-47,90-95\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\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; Full AMD retpoline, IBPB conditional, IBRS_FW, STIBP conditional, RSB filling\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 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\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 | |
| } |