Closed zhuyachen closed 4 years ago
Hi, As it says in the paper and in the config file:
split: # sequence numbers
train:
- 0
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 9
- 10
valid:
- 8
test:
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
Hi,
Thank you for releasing the source code of this awesome work! I wonder if you could tell me which sequences did you select to train the pre-trained models, because I want to try these models for inference. Was it chose just like the paper said? Thanks!