Update default pretraining config [ci skip]

This commit is contained in:
Ines Montani 2020-09-15 01:12:02 +02:00
parent 154752f9c2
commit e977086a9a
1 changed files with 16 additions and 6 deletions

View File

@ -1,13 +1,23 @@
[pretraining]
max_epochs = 1000
min_length = 5
max_length = 500
dropout = 0.2
n_save_every = null
batch_size = 3000
seed = ${system.seed}
use_pytorch_for_gpu_memory = ${system.use_pytorch_for_gpu_memory}
tok2vec_model = "components.tok2vec.model"
component = "tok2vec"
layer = ""
[pretraining.batcher]
@batchers = "spacy.batch_by_words.v1"
size = 3000
discard_oversize = false
tolerance = 0.2
get_length = null
[pretraining.corpus]
@readers = "spacy.JsonlReader.v1"
path = ${paths.raw}
min_length = 5
max_length = 500
limit = 0
[pretraining.objective]
type = "characters"