Commit
•
99b3e04
1
Parent(s):
ec143d0
Update spaCy pipeline
Browse files- README.md +16 -11
- config.cfg +26 -35
- en_pipeline-any-py3-none-any.whl +2 -2
- meta.json +31 -16
- textcat/cfg +8 -0
- textcat/model +0 -0
- tokenizer +0 -0
- transformer/model +2 -2
- vocab/strings.json +0 -0
README.md
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- spacy
|
|
|
4 |
language:
|
5 |
- en
|
6 |
model-index:
|
7 |
- name: en_pipeline
|
8 |
results: []
|
9 |
-
pipeline_tag: token-classification
|
10 |
---
|
11 |
| Feature | Description |
|
12 |
| --- | --- |
|
13 |
| **Name** | `en_pipeline` |
|
14 |
| **Version** | `0.0.0` |
|
15 |
-
| **spaCy** | `>=3.
|
16 |
-
| **Default Pipeline** | `transformer`, `
|
17 |
-
| **Components** | `transformer`, `
|
18 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
19 |
| **Sources** | n/a |
|
20 |
| **License** | n/a |
|
@@ -24,11 +24,11 @@ pipeline_tag: token-classification
|
|
24 |
|
25 |
<details>
|
26 |
|
27 |
-
<summary>View label scheme (
|
28 |
|
29 |
| Component | Labels |
|
30 |
| --- | --- |
|
31 |
-
| **`
|
32 |
|
33 |
</details>
|
34 |
|
@@ -36,8 +36,13 @@ pipeline_tag: token-classification
|
|
36 |
|
37 |
| Type | Score |
|
38 |
| --- | --- |
|
39 |
-
| `
|
40 |
-
| `
|
41 |
-
| `
|
42 |
-
| `
|
43 |
-
| `
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- spacy
|
4 |
+
- text-classification
|
5 |
language:
|
6 |
- en
|
7 |
model-index:
|
8 |
- name: en_pipeline
|
9 |
results: []
|
|
|
10 |
---
|
11 |
| Feature | Description |
|
12 |
| --- | --- |
|
13 |
| **Name** | `en_pipeline` |
|
14 |
| **Version** | `0.0.0` |
|
15 |
+
| **spaCy** | `>=3.7.5,<3.8.0` |
|
16 |
+
| **Default Pipeline** | `transformer`, `textcat` |
|
17 |
+
| **Components** | `transformer`, `textcat` |
|
18 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
19 |
| **Sources** | n/a |
|
20 |
| **License** | n/a |
|
|
|
24 |
|
25 |
<details>
|
26 |
|
27 |
+
<summary>View label scheme (2 labels for 1 components)</summary>
|
28 |
|
29 |
| Component | Labels |
|
30 |
| --- | --- |
|
31 |
+
| **`textcat`** | `0.0`, `1.0` |
|
32 |
|
33 |
</details>
|
34 |
|
|
|
36 |
|
37 |
| Type | Score |
|
38 |
| --- | --- |
|
39 |
+
| `CATS_SCORE` | 92.75 |
|
40 |
+
| `CATS_MICRO_P` | 92.75 |
|
41 |
+
| `CATS_MICRO_R` | 92.75 |
|
42 |
+
| `CATS_MICRO_F` | 92.75 |
|
43 |
+
| `CATS_MACRO_P` | 92.74 |
|
44 |
+
| `CATS_MACRO_R` | 92.76 |
|
45 |
+
| `CATS_MACRO_F` | 92.75 |
|
46 |
+
| `CATS_MACRO_AUC` | 97.20 |
|
47 |
+
| `TRANSFORMER_LOSS` | 26.49 |
|
48 |
+
| `TEXTCAT_LOSS` | 4617.23 |
|
config.cfg
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
[paths]
|
2 |
-
train = "/content/
|
3 |
-
dev = "/content/
|
4 |
vectors = null
|
5 |
init_tok2vec = null
|
6 |
|
@@ -10,45 +10,33 @@ seed = 0
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "en"
|
13 |
-
pipeline = ["transformer","
|
14 |
batch_size = 128
|
15 |
disabled = []
|
16 |
before_creation = null
|
17 |
after_creation = null
|
18 |
after_pipeline_creation = null
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
|
20 |
|
21 |
[components]
|
22 |
|
23 |
-
[components.
|
24 |
-
factory = "
|
25 |
-
|
26 |
-
|
27 |
-
spans_key = "sc"
|
28 |
-
threshold = 0.5
|
29 |
|
30 |
-
[components.
|
31 |
-
@architectures = "spacy.
|
32 |
-
|
33 |
-
[components.spancat.model.reducer]
|
34 |
-
@layers = "spacy.mean_max_reducer.v1"
|
35 |
-
hidden_size = 128
|
36 |
-
|
37 |
-
[components.spancat.model.scorer]
|
38 |
-
@layers = "spacy.LinearLogistic.v1"
|
39 |
nO = null
|
40 |
-
nI = null
|
41 |
|
42 |
-
[components.
|
43 |
@architectures = "spacy-transformers.TransformerListener.v1"
|
44 |
grad_factor = 1.0
|
45 |
pooling = {"@layers":"reduce_mean.v1"}
|
46 |
upstream = "*"
|
47 |
|
48 |
-
[components.spancat.suggester]
|
49 |
-
@misc = "spacy.ngram_suggester.v1"
|
50 |
-
sizes = [1,2,3]
|
51 |
-
|
52 |
[components.transformer]
|
53 |
factory = "transformer"
|
54 |
max_batch_items = 4096
|
@@ -97,12 +85,13 @@ seed = ${system.seed}
|
|
97 |
gpu_allocator = ${system.gpu_allocator}
|
98 |
dropout = 0.1
|
99 |
patience = 1600
|
100 |
-
max_epochs =
|
101 |
max_steps = 20000
|
102 |
eval_frequency = 200
|
103 |
frozen_components = []
|
104 |
annotating_components = []
|
105 |
before_to_disk = null
|
|
|
106 |
|
107 |
[training.batcher]
|
108 |
@batchers = "spacy.batch_by_padded.v1"
|
@@ -112,13 +101,8 @@ buffer = 256
|
|
112 |
get_length = null
|
113 |
|
114 |
[training.logger]
|
115 |
-
@loggers = "spacy.
|
116 |
-
|
117 |
-
remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
|
118 |
-
model_log_interval = 1000
|
119 |
-
log_dataset_dir = null
|
120 |
-
entity = null
|
121 |
-
run_name = null
|
122 |
|
123 |
[training.optimizer]
|
124 |
@optimizers = "Adam.v1"
|
@@ -137,9 +121,16 @@ total_steps = 20000
|
|
137 |
initial_rate = 0.00005
|
138 |
|
139 |
[training.score_weights]
|
140 |
-
|
141 |
-
|
142 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
|
144 |
[pretraining]
|
145 |
|
|
|
1 |
[paths]
|
2 |
+
train = "/content/train.spacy"
|
3 |
+
dev = "/content/dev.spacy"
|
4 |
vectors = null
|
5 |
init_tok2vec = null
|
6 |
|
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "en"
|
13 |
+
pipeline = ["transformer","textcat"]
|
14 |
batch_size = 128
|
15 |
disabled = []
|
16 |
before_creation = null
|
17 |
after_creation = null
|
18 |
after_pipeline_creation = null
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
+
vectors = {"@vectors":"spacy.Vectors.v1"}
|
21 |
|
22 |
[components]
|
23 |
|
24 |
+
[components.textcat]
|
25 |
+
factory = "textcat"
|
26 |
+
scorer = {"@scorers":"spacy.textcat_scorer.v2"}
|
27 |
+
threshold = 0.0
|
|
|
|
|
28 |
|
29 |
+
[components.textcat.model]
|
30 |
+
@architectures = "spacy.TextCatCNN.v2"
|
31 |
+
exclusive_classes = true
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
nO = null
|
|
|
33 |
|
34 |
+
[components.textcat.model.tok2vec]
|
35 |
@architectures = "spacy-transformers.TransformerListener.v1"
|
36 |
grad_factor = 1.0
|
37 |
pooling = {"@layers":"reduce_mean.v1"}
|
38 |
upstream = "*"
|
39 |
|
|
|
|
|
|
|
|
|
40 |
[components.transformer]
|
41 |
factory = "transformer"
|
42 |
max_batch_items = 4096
|
|
|
85 |
gpu_allocator = ${system.gpu_allocator}
|
86 |
dropout = 0.1
|
87 |
patience = 1600
|
88 |
+
max_epochs = 0
|
89 |
max_steps = 20000
|
90 |
eval_frequency = 200
|
91 |
frozen_components = []
|
92 |
annotating_components = []
|
93 |
before_to_disk = null
|
94 |
+
before_update = null
|
95 |
|
96 |
[training.batcher]
|
97 |
@batchers = "spacy.batch_by_padded.v1"
|
|
|
101 |
get_length = null
|
102 |
|
103 |
[training.logger]
|
104 |
+
@loggers = "spacy.ConsoleLogger.v1"
|
105 |
+
progress_bar = true
|
|
|
|
|
|
|
|
|
|
|
106 |
|
107 |
[training.optimizer]
|
108 |
@optimizers = "Adam.v1"
|
|
|
121 |
initial_rate = 0.00005
|
122 |
|
123 |
[training.score_weights]
|
124 |
+
cats_score = 1.0
|
125 |
+
cats_score_desc = null
|
126 |
+
cats_micro_p = null
|
127 |
+
cats_micro_r = null
|
128 |
+
cats_micro_f = null
|
129 |
+
cats_macro_p = null
|
130 |
+
cats_macro_r = null
|
131 |
+
cats_macro_f = null
|
132 |
+
cats_macro_auc = null
|
133 |
+
cats_f_per_type = null
|
134 |
|
135 |
[pretraining]
|
136 |
|
en_pipeline-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc4b6d9fbc7f361daed941b6fe095316168d9b2e03e2f9052443da4667d93c7c
|
3 |
+
size 455652929
|
meta.json
CHANGED
@@ -7,8 +7,8 @@
|
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
@@ -19,33 +19,48 @@
|
|
19 |
"transformer":[
|
20 |
|
21 |
],
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"Transliteration",
|
26 |
-
"Synonyms",
|
27 |
-
"Tense semantics"
|
28 |
]
|
29 |
},
|
30 |
"pipeline":[
|
31 |
"transformer",
|
32 |
-
"
|
33 |
],
|
34 |
"components":[
|
35 |
"transformer",
|
36 |
-
"
|
37 |
],
|
38 |
"disabled":[
|
39 |
|
40 |
],
|
41 |
"performance":{
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
},
|
48 |
"requirements":[
|
49 |
-
"spacy-transformers>=1.
|
50 |
]
|
51 |
}
|
|
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
+
"spacy_version":">=3.7.5,<3.8.0",
|
11 |
+
"spacy_git_version":"a6d0fc360",
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
|
|
19 |
"transformer":[
|
20 |
|
21 |
],
|
22 |
+
"textcat":[
|
23 |
+
"0.0",
|
24 |
+
"1.0"
|
|
|
|
|
|
|
25 |
]
|
26 |
},
|
27 |
"pipeline":[
|
28 |
"transformer",
|
29 |
+
"textcat"
|
30 |
],
|
31 |
"components":[
|
32 |
"transformer",
|
33 |
+
"textcat"
|
34 |
],
|
35 |
"disabled":[
|
36 |
|
37 |
],
|
38 |
"performance":{
|
39 |
+
"cats_score":0.9274664714,
|
40 |
+
"cats_score_desc":"macro F",
|
41 |
+
"cats_micro_p":0.9275,
|
42 |
+
"cats_micro_r":0.9275,
|
43 |
+
"cats_micro_f":0.9275,
|
44 |
+
"cats_macro_p":0.9274025193,
|
45 |
+
"cats_macro_r":0.927568036,
|
46 |
+
"cats_macro_f":0.9274664714,
|
47 |
+
"cats_macro_auc":0.9719873134,
|
48 |
+
"cats_f_per_type":{
|
49 |
+
"0.0":{
|
50 |
+
"p":0.9331366765,
|
51 |
+
"r":0.9249512671,
|
52 |
+
"f":0.9290259422
|
53 |
+
},
|
54 |
+
"1.0":{
|
55 |
+
"p":0.9216683622,
|
56 |
+
"r":0.9301848049,
|
57 |
+
"f":0.9259070005
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"transformer_loss":0.2649244879,
|
61 |
+
"textcat_loss":46.1722830437
|
62 |
},
|
63 |
"requirements":[
|
64 |
+
"spacy-transformers>=1.3.5,<1.4.0"
|
65 |
]
|
66 |
}
|
textcat/cfg
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels":[
|
3 |
+
"0.0",
|
4 |
+
"1.0"
|
5 |
+
],
|
6 |
+
"threshold":0.0,
|
7 |
+
"positive_label":null
|
8 |
+
}
|
textcat/model
ADDED
Binary file (7.07 kB). View file
|
|
tokenizer
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
transformer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f97d21817132eac87779f4acf8dacc5a89b07a27d89bd5d6ee5d78efedad0d9f
|
3 |
+
size 502025449
|
vocab/strings.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|