-
Notifications
You must be signed in to change notification settings - Fork 3
/
config.cfg
172 lines (143 loc) · 3.16 KB
/
config.cfg
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
[paths]
train = "srp_training_data/srp_set-ud-train.spacy"
dev = "srp_training_data/srp_set-ud-dev.spacy"
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "srp"
pipeline = ["tok2vec","tagger","parser","attribute_ruler","lemmatizer"]
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
[components]
[components.attribute_ruler]
factory = "attribute_ruler"
validate = false
[components.lemmatizer]
factory = "srp_lemmatizer"
[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30
moves = null
update_with_oracle_cut_size = 100
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
tok2vec = ${components.tok2vec.model}
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = true
nO = null
[components.tagger]
factory = "tagger"
[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.tagger.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = null
width = 96
depth = 4
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = ${components.tok2vec.model.encode.width}
attrs = ["ORTH","SHAPE"]
rows = [5000,2500]
include_static_vectors = false
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = "${paths.train}"
max_length = 0
limit = 0
gold_preproc = false
augmenter = null
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
max_steps = 600
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
eval_frequency = 200
frozen_components = []
before_to_disk = null
[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null
[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0
[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false
[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001
[training.score_weights]
dep_las_per_type = null
sents_p = null
sents_r = null
tag_acc = 0.33
dep_uas = 0.17
dep_las = 0.17
sents_f = 0.0
lemma_acc = 0.33
[pretraining]
[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.components.attribute_ruler]
[initialize.components.attribute_ruler.tag_map]
@readers = "srsly.read_json.v1"
path = "srp/tag_map.json"
[initialize.tokenizer]