libing125
libing125
I run your code with python kgcvae_swda.py on cpu, and get the output: Avg recall BLEU 0.358250, avg precision BLEU 0.124279 and F1 0.184540 (only 1 reference response. Not final...
I encountered this error when I run `sh scripts/DailyDialog/multi_gpu_train.sh` my environment: paddlepaddle==1.6.0 via `pip install paddlepaddle-gpu==1.6.0` cuda 10 cudnn 7.6 thanks!
in https://github.com/alexa/dialoglue/blob/42737dac04d8c922c524a51fd451ea4c0b932bf2/data_utils/process_slot.py#L47-L49 Slot BIO labels are stored in a python `set`, then saved into a python `list` using a for loop. But `set` is unordered. In my experiment, `vocab.txt` is...
I run your code with CUDA_VISIBLE_DEVICES=0,1,2,3 python3 run_classifier_TABSA.py --task_name semeval_QA_B --data_dir data/semeval2014/bert-pair --vocab_file uncased_L-12_H-768_A-12/vocab.txt --bert_config_file uncased_L-12_H-768_A-12/bert_config.json --init_checkpoint uncased_L-12_H-768_A-12/pytorch_model.bin --eval_test --do_lower_case --max_seq_length 512 --train_batch_size 24 --learning_rate 2e-5 --num_train_epochs 12.0 --output_dir results_v2/semeval_result/QA_B...
ValueError: setting an array element with a sequence. global step 0 learning rate 0.1000 step-time 0.00 perplexity [1.00] kl_loss [0.00] dec_loss [0.00] dis_loss [0.00] Traceback (most recent call last): File...
Hi, can you release your `DST-UBAR` checkpoint for Multiwoz2.1? There are some bugs running the DST code and I'm not sure how to fix the bugs to reproduce the joint...
bugs everywhere.
**Description:** **Reference Issues:** #XX (XX is the issue number you work on)