File size: 2,540 Bytes
0592a76
aaf8333
 
0592a76
 
 
 
 
 
 
 
 
c004b3f
0592a76
 
 
 
 
 
353872c
0592a76
 
 
 
 
aaf8333
 
0592a76
 
aaf8333
0592a76
aaf8333
0592a76
 
 
 
 
 
 
aaf8333
 
0592a76
 
 
 
 
 
 
 
 
 
 
 
 
aaf8333
0592a76
aaf8333
 
0592a76
 
 
 
aaf8333
0592a76
aaf8333
0592a76
aaf8333
0592a76
 
 
 
 
 
 
 
aaf8333
0592a76
aaf8333
0592a76
 
 
 
3c14845
0592a76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aaf8333
 
0592a76
 
 
 
 
 
 
 
 
 
 
 
 
aaf8333
0592a76
 
aaf8333
 
 
 
 
 
0592a76
 
 
 
aaf8333
0592a76
 
 
 
 
 
 
 
 
 
 
 
 
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
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "xx"
pipeline = ["senter"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 256
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.v1"}

[components]

[components.senter]
factory = "senter"
overwrite = false
scorer = {"@scorers":"spacy.senter_scorer.v1"}

[components.senter.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.senter.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"

[components.senter.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.senter.model.tok2vec.encode:width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
rows = [1000,500,500,500,50]
include_static_vectors = false

[components.senter.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 16
depth = 2
window_size = 1
maxout_pieces = 2

[corpora]

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 10000
max_epochs = 0
max_steps = 100000
eval_frequency = 1000
frozen_components = []
before_to_disk = null
annotating_components = []
before_update = 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 = true
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
sents_f = 0.06
sents_p = 0.0
sents_r = 0.0
dep_uas = 0.0
dep_las = 0.47
ents_f = 0.47
ents_p = 0.0
ents_r = 0.0
speed = 0.0

[pretraining]

[initialize]
vocab_data = null
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
before_init = null
after_init = null

[initialize.components]

[initialize.lookups]
@misc = "spacy.LookupsDataLoader.v1"
lang = ${nlp.lang}
tables = []

[initialize.tokenizer]