ValueError: too many values to unpack (expected 2) in unsupervised.py

[csheehan10]

Hello,
I'm trying to train model using unsupervised.py with each possible pairing in the set {English, German, Spanish, French, Italian, Portuguese}. The line of code I'm running each time is
python unsupervised.py --src_lang en --tgt_lang es --src_emb data/wiki.en.vec --tgt_emb data/wiki.es.vec --n_refinement 5 --export pth
(obviously changing the parameters for language and embeddings each time)
This has worked fine for 12 of the pairings, and I have saved 12 fitted models, but for some reason when training French-Italian, French-Portuguese, or Italian-Portuguese, I get the following error at the end of the first Adversarial Training epoch:

Traceback (most recent call last):
File "unsupervised.py", line 139, in
evaluator.all_eval(to_log)
File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/cbs11/code/Users/cbs1/muse/src/evaluation/evaluator.py", line 217, in all_eval
self.word_translation(to_log)
File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/cbs11/code/Users/cbs1/muse/src/evaluation/evaluator.py", line 116, in word_translation
results = get_word_translation_accuracy(
File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/cbs11/code/Users/cbs1/muse/src/evaluation/word_translation.py", line 96, in get_word_translation_accuracy
dico = load_dictionary(path, word2id1, word2id2)
File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/cbs11/code/Users/cbs1/muse/src/evaluation/word_translation.py", line 63, in load_dictionary
word1, word2 = parts
ValueError: too many values to unpack (expected 2)

I've gone through it multiple times and can't see why this only occurs for these language pairs.