FedML-AI/FedNLP

Issues

• fednlp disappeared in the new url. can you restore it?

  #37 opened a year ago by springfall2018
  0

• Come up problems in Running Text Classification model with No module named transformers

  #36 opened 2 years ago by QIJIAHAO-6
  0

• Hanging after last round of training

  #23 opened 2 years ago by bangawayoo
  1

• when run "bash run_simulation.sh 5" , error "MPI_ABORT was invoked on......."

  #35 opened 2 years ago by hdmimang
  0

• Issue when running centralized/bilstm_exps/main_text_classification.py

  #30 opened 3 years ago by aayush9753
  1

• Bugs

  #14 opened 4 years ago by vicMio
  1

• Come up problems in Running Text Classification model with distilbert

  #20 opened 3 years ago by MuleiOnline
  2

• KeyError: 'Unable to open object (bad heap free list)'

  #29 opened 3 years ago by ysgncss
  3

• 怎么体现联邦学习？我怎么得到每个节点学习过程中的loss情况呢

  #32 opened 3 years ago by ysgncss
  1

• No protocol specified | Open MPI not enough slots available in the system

  #33 opened 3 years ago by selfcontrol7
  2

• when running “sh run_text_classification.sh” fedavg_main_tc.py: error: argument --client_num_per_round: expected one argument

  #34 opened 3 years ago by hdmimang
  1

• 怎么生成partition.h5文件？

  #31 opened 3 years ago by ysgncss
  0

• object doesn't exist for text classification script

  #15 opened 3 years ago by ayanflow
  5

• how to change the number of client

  #25 opened 3 years ago by haohaoer
  2

• Hyperparameters for reproducing the results of the paper?

  #27 opened 3 years ago by bangawayoo
  1

• Accuracy and loss didn't improve for FedAvg on 20news

  #19 opened 3 years ago by haofuml
  7

• [IMPORTANT]Client Sampling Frozen

  #28 opened 3 years ago by zjc664656505
  20

• Could you support knowledge distillation-based FL algorithms like FedED, Fedmd, or FedDF

  #26 opened 3 years ago by Barry-Menglong-Yao
  0

• Error running uniform partition for text classification

  #24 opened 3 years ago by bangawayoo
  1

• Windows 10 support

  #18 opened 3 years ago by shubham-malaviya
  1

• About large model

  #22 opened 3 years ago by xiang-xiang-zhu
  1

• lstm experiment data loader files missing

  #21 opened 3 years ago by Grancis
  0

• No such file or directory: 'cache_dir/distilbert_distilbert-base-uncased_cached_256_ClassificationModel_20news_niid_label_clients=100_alpha=5.0_-1'

  #16 opened 4 years ago by ayanflow
  2

• No dataloader in data_preprocessing

  #13 opened 4 years ago by ziqi-zhang
  12

• Data Parallelism (DP) during training does not meet expectation (only 3 processes are working, should be FOUR), I will optimize it after ICML deadline.

  #6 opened 4 years ago by chaoyanghe
  2

• Some suggestions/issues in "XXXModel" class

  #9 opened 4 years ago by chaoyanghe
  2

• Optimizer suggestion for federated learning experiments

  #1 opened 4 years ago by chaoyanghe
  0

• change FL dataset file name to "--data_file data/data_loaders/${DATA_NAME}_data.pkl"

  #2 opened 4 years ago by chaoyanghe
  0

• Too many unused configuration/functionalities in the model trainer class (e.g., model/fed_transformers/classification/classification_model.py

  #3 opened 4 years ago by chaoyanghe
  4

• (Distributed Data Loader)The data loading time for sentment140 is too long. I waited for more than half an hour.

  #4 opened 4 years ago by chaoyanghe
  27

• QA does not calculate F1 score result , may I know how to fix it?

  #10 opened 4 years ago by chaoyanghe
  2

• [SQuAD] crashed when doing official evaluation

  #11 opened 4 years ago by chaoyanghe
  5

• Refactor Model class to Trainer class

  #8 opened 4 years ago by chaoyanghe
  1

• The client side learning rate warm up and scheduler may be an issue for FL.

  #5 opened 4 years ago by chaoyanghe
  1

• Pretraining v.s. Fine-tuning

  #7 opened 4 years ago by chaoyanghe
  1