Commit History
[#7] training & fetching m-1-3 is ready
ff61478
[#7] tokenizer:t-1-1. The tokenizer with the idiom special tokens is now fetchable directly from wandb
12f548d
[#5] idioms:d-1-3 is done. Added multiple senses of the same idiom as a list
370afc1
[#5] literal2idiomatic:d-1-3 done (annotating with special tokens). Some of the data however are erroneous
fca50f9
a couple of explore scripts for: adding two special tokens (<idiom>, </idiom>)
927768a
[#2] evaluating m-1-2 works. config.yaml simplified.
642d911
[#2] Eval script added. It still needs testing
dd810eb
[#2] Support for d-1-2 done. Support for m-1-2 partially done (need to implement the testing logic with some valid metrics)
e3c7b5a
[#1] refactoring: Alpha -> Seq2Seq. We rely on git tags for versioning models.
64a6414
[#1] fetch_alpha implemented
322e083
[#1] Alpha implemented
d8d4c8d
[#1] IdiomifyDataModule implemented (srcs, tgts_r, tgts)
25e310b
[#1] SRCBuilder, TGTBuilder implemented and tested
3be6142
[#1] checkpoint before amending builders.py
e9d1a5a
saving this branch
207cddf
eubinecto
commited on
first mvp done, removing wandb
1bf3d62
eubinecto
commited on
implemented a working fetcher
cfa482d
eubinecto
commited on