File size: 4,667 Bytes
6bc2011
bca1e5f
 
6bc2011
 
 
 
 
 
bca1e5f
6bc2011
 
 
 
 
 
 
bca1e5f
6bc2011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bca1e5f
 
6bc2011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bca1e5f
6bc2011
bca1e5f
6bc2011
 
 
 
bca1e5f
6bc2011
 
bca1e5f
6bc2011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bca1e5f
6bc2011
 
 
bca1e5f
 
6bc2011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
[paths]
train = "corpus/filter-train.spacy"
dev = "corpus/filter-test.spacy"
vectors = "en_core_web_lg"
init_tok2vec = null

[variables]
wandb_project_name = "tako-query-filter"
wandb_team_name = "tako-team"
base_model = "ner/dashing-wind"

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec","ner","textcat_classify"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.v1"}

[components]

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 256
upstream = "*"

[components.textcat_classify]
factory = "weighted_textcat"
class_weights = [0.67,0.33]
scorer = {"@scorers":"spacy.textcat_scorer.v2"}
threshold = 0.0

[components.textcat_classify.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null

[components.textcat_classify.model.linear_model]
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
nO = null

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

[components.textcat_classify.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 128
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","ENT_TYPE"]
rows = [2000,500,1000,500,500]
include_static_vectors = true

[components.textcat_classify.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 128
window_size = 1
maxout_pieces = 3
depth = 4

[components.tok2vec]
factory = "tok2vec"

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

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 256
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = true

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
window_size = 1
maxout_pieces = 3
depth = 8

[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
gold_preproc = false
limit = 0

[corpora.train.augmenter]
@augmenters = "spacy.lower_case.v1"
level = 0.3

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1000
max_epochs = 0
max_steps = 20000
eval_frequency = 100
frozen_components = ["tagger","attribute_ruler","parser","tok2vec","ner"]
annotating_components = ["ner"]
before_to_disk = null
before_update = null

[training.batcher]
@batchers = "spacy.batch_by_sequence.v1"
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 2000
compound = 1.001
t = 0.0

[training.logger]
@loggers = "spacy.ChainLogger.v1"
logger3 = null
logger4 = null
logger5 = null
logger6 = null
logger7 = null
logger8 = null
logger9 = null
logger10 = null

[training.logger.logger1]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.logger.logger2]
@loggers = "spacy.WandbLogger.v5"
project_name = ${variables.wandb_project_name}
remove_config_values = []
model_log_interval = null
log_dataset_dir = null
entity = null
run_name = null
log_best_dir = null
log_latest_dir = null
log_custom_stats = null

[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]
ents_f = 0.5
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
cats_score = 0.25
cats_score_desc = null
cats_micro_p = null
cats_micro_r = 0.25
cats_micro_f = null
cats_macro_p = null
cats_macro_r = null
cats_macro_f = null
cats_macro_auc = null
cats_f_per_type = null

[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.textcat_classify]
positive_label = "ACCEPT"

[initialize.components.textcat_classify.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/filter-labels/textcat_classify.json"
require = false

[initialize.tokenizer]