From e977086a9a7c0e15c459610fae084b251a435ec1 Mon Sep 17 00:00:00 2001
From: Ines Montani <ines@ines.io>
Date: Tue, 15 Sep 2020 01:12:02 +0200
Subject: [PATCH] Update default pretraining config [ci skip]

---
 spacy/default_config_pretraining.cfg | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/spacy/default_config_pretraining.cfg b/spacy/default_config_pretraining.cfg
index 7032eac03..9120db338 100644
--- a/spacy/default_config_pretraining.cfg
+++ b/spacy/default_config_pretraining.cfg
@@ -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"