From b5bbfec591b9cb659bf51add783e0935fbee452b Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Wed, 29 Jul 2020 14:26:44 +0200
Subject: [PATCH] Update config

---
 examples/experiments/onto-joint/defaults.cfg | 83 +++++++++++---------
 1 file changed, 44 insertions(+), 39 deletions(-)

diff --git a/examples/experiments/onto-joint/defaults.cfg b/examples/experiments/onto-joint/defaults.cfg
index 95c2f28bd..d37929ff1 100644
--- a/examples/experiments/onto-joint/defaults.cfg
+++ b/examples/experiments/onto-joint/defaults.cfg
@@ -20,20 +20,20 @@ seed = 0
 accumulate_gradient = 1
 use_pytorch_for_gpu_memory = false
 # Control how scores are printed and checkpoints are evaluated.
-scores = ["speed", "tags_acc", "uas", "las", "ents_f"]
+eval_batch_size = 128
 score_weights = {"las": 0.4, "ents_f": 0.4, "tags_acc": 0.2}
-# These settings are invalid for the transformer models.
 init_tok2vec = null
 discard_oversize = false
-omit_extra_lookups = false
 batch_by = "words"
-use_gpu = -1
 raw_text = null
 tag_map = null
+vectors = null
+base_model = null
+morph_rules = null
 
 [training.batch_size]
 @schedules = "compounding.v1"
-start = 1000
+start = 100
 stop = 1000
 compound = 1.001
 
@@ -46,74 +46,79 @@ L2 = 0.01
 grad_clip = 1.0
 use_averages = false
 eps = 1e-8
-#learn_rate = 0.001
-
-[training.optimizer.learn_rate]
-@schedules = "warmup_linear.v1"
-warmup_steps = 250
-total_steps = 20000
-initial_rate = 0.001
+learn_rate = 0.001
 
 [nlp]
 lang = "en"
-base_model = null
-vectors = null
+load_vocab_data = false
+pipeline = ["tok2vec", "ner", "tagger", "parser"]
 
-[nlp.pipeline]
+[nlp.tokenizer]
+@tokenizers = "spacy.Tokenizer.v1"
 
-[nlp.pipeline.tok2vec]
+[nlp.lemmatizer]
+@lemmatizers = "spacy.Lemmatizer.v1"
+
+[components]
+
+[components.tok2vec]
 factory = "tok2vec"
 
-
-[nlp.pipeline.ner]
+[components.ner]
 factory = "ner"
 learn_tokens = false
 min_action_freq = 1
 
-[nlp.pipeline.tagger]
+[components.tagger]
 factory = "tagger"
 
-[nlp.pipeline.parser]
+[components.parser]
 factory = "parser"
 learn_tokens = false
 min_action_freq = 30
 
-[nlp.pipeline.tagger.model]
+[components.tagger.model]
 @architectures = "spacy.Tagger.v1"
 
-[nlp.pipeline.tagger.model.tok2vec]
-@architectures = "spacy.Tok2VecTensors.v1"
-width = ${nlp.pipeline.tok2vec.model:width}
+[components.tagger.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode:width}
 
-[nlp.pipeline.parser.model]
+[components.parser.model]
 @architectures = "spacy.TransitionBasedParser.v1"
 nr_feature_tokens = 8
 hidden_width = 128
 maxout_pieces = 2
 use_upper = true
 
-[nlp.pipeline.parser.model.tok2vec]
-@architectures = "spacy.Tok2VecTensors.v1"
-width = ${nlp.pipeline.tok2vec.model:width}
+[components.parser.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode:width}
 
-[nlp.pipeline.ner.model]
+[components.ner.model]
 @architectures = "spacy.TransitionBasedParser.v1"
 nr_feature_tokens = 3
 hidden_width = 128
 maxout_pieces = 2
 use_upper = true
 
-[nlp.pipeline.ner.model.tok2vec]
-@architectures = "spacy.Tok2VecTensors.v1"
-width = ${nlp.pipeline.tok2vec.model:width}
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode:width}
 
-[nlp.pipeline.tok2vec.model]
-@architectures = "spacy.HashEmbedCNN.v1"
-pretrained_vectors = ${nlp:vectors}
-width = 128
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v1"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v1"
+width = ${components.tok2vec.model.encode:width}
+rows = 2000
+also_embed_subwords = true
+also_use_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v1"
+width = 96
 depth = 4
 window_size = 1
-embed_size = 7000
 maxout_pieces = 3
-subword_features = true
-dropout = ${training:dropout}