zhouxh19
commented
11 months ago Thanks for your feedback. We have fixed the problem.
https://github.com/TsinghuaDatabaseGroup/DB-GPT/commit/1547d02a18debc4d3f3ac4d00ca8cf1d963f5cdb
Closed yangyongguang closed 11 months ago
zhouxh19
commented
11 months ago Thanks for your feedback. We have fixed the problem.
https://github.com/TsinghuaDatabaseGroup/DB-GPT/commit/1547d02a18debc4d3f3ac4d00ca8cf1d963f5cdb
import sys; print('Python %s on %s' % (sys.version, sys.platform)) /root/miniconda3/envs/D-Bot/bin/python /root/.pycharm_helpers/pydev/pydevd.py --multiprocess --qt-support=auto --client localhost --port 37745 --file /home/workspace/YYG/FromS/DB-GPT/main.py Connected to pydev debugger (build 232.8660.197) 系统启动java的jvm虚拟环境成功 12/14/2023 19:25:09 - ERROR - root - obtain_historical_queries_statistics Fails! 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} 12/14/2023 19:25:09 - WARNING - root - Unused arguments: {'model': 'diag-llama'} Report Initialization! 0%| | 0/1====================== Initialization ====================== rank : 0 local_rank : 0 world_size : 1 local_size : 1 master : localhost:10010 device : 0 cpus : [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 1 3, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 2 4, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 3 5, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 4 6, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 5 7, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 6 8, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 7 9, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 9 0, 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, 117, 118 , 119, 120, 121, 122, 123, 124, 125, 126, 12 7, 128, 129, 130, 131, 132, 133, 134, 135, 1 36, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162 , 163, 164, 165, 166, 167, 168, 169, 170, 17 1, 172, 173, 174, 175] /root/miniconda3/envs/D-Bot/lib/python3.10/site-packages/bmtrain/synchronize.py:15: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage() nccl.allReduce(barrier.storage(), barrier.storage(), 'sum', config['comm']) args.load is not None, start to load checkpoints /home/workspace/YYG/YYG/D-Bot/DiagLlama/DiagLlama.pt [INFO][2023-12-14 19:25:39][jeeves-hpc-gpu00][inference.py:33:105510] - load model in 21.73s You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the
legacy(previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, setlegacy=False. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 [INFO][2023-12-14 19:25:40][jeeves-hpc-gpu00][inference.py:38:105510] - load tokenizer in 1.27s finish loading 100%|██████████████████████████████████████████████████████████████████████| 1/1 Role Assignment! 100%|██████████████████████████████████████████████████████████████████████| 1/1 12/14/2023 19:26:07 - INFO - sentence_transformers.SentenceTransformer - Load pretrained SentenceTransformer: ./localized_llms/sentence_embedding/sentence-transformer/ 12/14/2023 19:26:10 - INFO - sentence_transformers.SentenceTransformer - Use pytorch device: cuda Batches: 100%|████████████████████████████████████| 1/1 [00:00<00:00, 1.46it/s] CpuExpert Diagnosis!insert into table1 select generate_series...was identified as potentially problematic due to its large scale data insertion within a short timeframe. This type of operations is resource-intensive and could significantly impact system performance. Understanding this knowledge allows us to better diagnose and find solutions for such issues in the future.