-
-
Notifications
You must be signed in to change notification settings - Fork 467
/
cluster.cfg
136 lines (112 loc) · 2.56 KB
/
cluster.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
[paths]
train = "data/train.spacy"
dev = "data/dev.spacy"
init_tok2vec = null
vectors = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["transformer", "coref"]
batch_size = 2
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.coref]
factory = "experimental_coref"
span_cluster_prefix = "coref_head_clusters"
[components.coref.model]
@architectures = "spacy-experimental.Coref.v1"
distance_embedding_size = 20
dropout = 0.3
hidden_size = 1024
depth = 1
antecedent_limit = 100
antecedent_batch_size = 512
[components.coref.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0.5
upstream = "transformer"
[components.coref.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
[components.coref.scorer]
@scorers = "spacy-experimental.coref_scorer.v1"
span_cluster_prefix = "${components.coref.span_cluster_prefix}"
[components.transformer]
factory = "transformer"
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "roberta-base"
tokenizer_config = {"use_fast": true}
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 400
stride = 350
[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
augmenter = null
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.3
accumulate_gradient = 1
patience = 4000
max_epochs = 20
max_steps = 200000
eval_frequency = 4000
frozen_components = []
annotating_components = []
before_to_disk = null
[training.batcher]
@batchers = "spacy.batch_by_sequence.v1"
size = 1
get_length = null
[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 = 1e-8
[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 5e-5
[training.score_weights]
coref_f = 1.0
coref_p = 0
coref_r = 0
[pretraining]
[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.tokenizer]