When training the model, the code reports an error

[yanpinlu]

When I run:
python3 predictor/run_tcrconv.py --name b_small
--dataset training_data/vdjdb-b-small.csv
--mode cv
--h_cdr31 CDR3B --h_long1 LongB
--folds training_data/folds_vdjdb-b-small. npy
--fold_num 5
--epitope_labels training_data/unique_epitopes_vdjdb-b-small. npy --chains B --embedfile1 check_embs.bin
What should I do if the following error occurs

Traceback (most recent call last):
File "predictor/run_tcrconv.py", line 19, in
loader, n_categories, n_feat = utils.get_dataloaders(p,device=device,usetypes=usetypes)
File "/home/luyanping/data/TCR_epitope_prediction/Compare_models_same_data/tcrconv/tcrconv/predictor/utils.py", line 509, in get_datalo
embeddings = get_embeddings(tcr_emb_dict,cdr3s,cdr3s,maxlen(cdr3s),append_onehot=p['append_oh'],device=device)
File "/home/luyanping/data/TCR_epitope_prediction/Compare_models_same_data/tcrconv/tcrconv/predictor/utils.py", line 451, in get_embedd
nfeat=tcr_emb_dict[longs[0]].shape[0]
TypeError: list indices must be integers or slices, not str

@emmijokinen @Dumitrescu-Alexandru