File size: 857 Bytes
12f548d 642d911 ff61478 64a6414 59df933 ff61478 59df933 642d911 e3c7b5a 08409ff e3c7b5a 642d911 370afc1 642d911 fca50f9 642d911 fca50f9 12f548d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 |
# for training an idiomifier
idiomifier:
ver: m-1-3
desc: Just overfitting on PIE dataset, but now with <idiom> & </idiom> special tokens.
bart: facebook/bart-base
lr: 0.00005
literal2idiomatic_ver: d-1-3
idioms_ver: d-1-3
tokenizer_ver: t-1-1
max_epochs: 8
batch_size: 40
shuffle: true
seed: 104
# for building & uploading datasets or tokenizer
idioms:
ver: d-1-3
description: the set of idioms in the traning set of literal2idiomatic_d-1-3. Definitions of them are added as well.
literal2idiomatic:
ver: d-1-3
description: The idioms are annotated with <idiom> & </idiom>.
train_ratio: 0.8
seed: 104
boi_token: <idiom>
eoi_token: </idiom>
tokenizer:
ver: t-1-1
description: A pretrained BartTokenizer. The idiom special tokens are pre-added.
bart: facebook/bart-base
boi_token: <idiom>
eoi_token: </idiom>
|