mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
fb7f018ded
* Add the configuration schema for distillation This also adds the default configuration and some tests. The schema will be used by the training loop and `distill` subcommand. * Format * Change distillation shortopt to -d * Fix descripion of max_epochs * Rename distillation flag to -dt * Rename `pipe_map` to `student_to_teacher`
35 lines
559 B
INI
35 lines
559 B
INI
[paths]
|
|
raw_text = null
|
|
|
|
[distillation]
|
|
corpus = "corpora.distillation"
|
|
dropout = 0.1
|
|
max_epochs = 1
|
|
max_steps = 0
|
|
student_to_teacher = {}
|
|
|
|
[distillation.batcher]
|
|
@batchers = "spacy.batch_by_words.v1"
|
|
size = 3000
|
|
discard_oversize = false
|
|
tolerance = 0.2
|
|
|
|
[distillation.optimizer]
|
|
@optimizers = "Adam.v1"
|
|
beta1 = 0.9
|
|
beta2 = 0.999
|
|
L2_is_weight_decay = true
|
|
L2 = 0.01
|
|
grad_clip = 1.0
|
|
use_averages = true
|
|
eps = 1e-8
|
|
learn_rate = 1e-4
|
|
|
|
[corpora]
|
|
|
|
[corpora.distillation]
|
|
@readers = "spacy.PlainTextCorpus.v1"
|
|
path = ${paths.raw_text}
|
|
min_length = 0
|
|
max_length = 0
|