Update spaCy pipeline
Browse files- .gitattributes +3 -0
- README.md +9 -9
- config.cfg +5 -5
- en_t1_pipeline-any-py3-none-any.whl +2 -2
- meta.json +21 -21
- ner/model +0 -0
- tok2vec/model +2 -2
- vocab/key2row +3 -1
- vocab/strings.json +0 -0
- vocab/vectors +0 -0
.gitattributes
CHANGED
@@ -35,3 +35,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
en_t1_pipeline-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
37 |
tok2vec/model filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
en_t1_pipeline-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
37 |
tok2vec/model filter=lfs diff=lfs merge=lfs -text
|
38 |
+
vocab/key2row filter=lfs diff=lfs merge=lfs -text
|
39 |
+
vocab/strings.json filter=lfs diff=lfs merge=lfs -text
|
40 |
+
vocab/vectors filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -13,13 +13,13 @@ model-index:
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
-
value: 0.
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
-
value: 0.
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
-
value: 0.
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
@@ -28,7 +28,7 @@ model-index:
|
|
28 |
| **spaCy** | `>=3.7.2,<3.8.0` |
|
29 |
| **Default Pipeline** | `tok2vec`, `ner` |
|
30 |
| **Components** | `tok2vec`, `ner` |
|
31 |
-
| **Vectors** |
|
32 |
| **Sources** | n/a |
|
33 |
| **License** | n/a |
|
34 |
| **Author** | [n/a]() |
|
@@ -49,8 +49,8 @@ model-index:
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
-
| `ENTS_F` | 98.
|
53 |
-
| `ENTS_P` | 98.
|
54 |
-
| `ENTS_R` | 98.
|
55 |
-
| `TOK2VEC_LOSS` |
|
56 |
-
| `NER_LOSS` |
|
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
+
value: 0.9862148436
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
+
value: 0.9863411303
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
+
value: 0.9862779829
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
|
|
28 |
| **spaCy** | `>=3.7.2,<3.8.0` |
|
29 |
| **Default Pipeline** | `tok2vec`, `ner` |
|
30 |
| **Components** | `tok2vec`, `ner` |
|
31 |
+
| **Vectors** | 514157 keys, 514157 unique vectors (300 dimensions) |
|
32 |
| **Sources** | n/a |
|
33 |
| **License** | n/a |
|
34 |
| **Author** | [n/a]() |
|
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
+
| `ENTS_F` | 98.63 |
|
53 |
+
| `ENTS_P` | 98.62 |
|
54 |
+
| `ENTS_R` | 98.63 |
|
55 |
+
| `TOK2VEC_LOSS` | 55320.69 |
|
56 |
+
| `NER_LOSS` | 237842.15 |
|
config.cfg
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
[paths]
|
2 |
train = "./train.spacy"
|
3 |
dev = "./train.spacy"
|
4 |
-
vectors =
|
5 |
init_tok2vec = null
|
6 |
|
7 |
[system]
|
@@ -53,12 +53,12 @@ factory = "tok2vec"
|
|
53 |
width = ${components.tok2vec.model.encode.width}
|
54 |
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
55 |
rows = [5000,1000,2500,2500]
|
56 |
-
include_static_vectors =
|
57 |
|
58 |
[components.tok2vec.model.encode]
|
59 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
60 |
-
width =
|
61 |
-
depth =
|
62 |
window_size = 1
|
63 |
maxout_pieces = 3
|
64 |
|
@@ -88,7 +88,7 @@ gpu_allocator = ${system.gpu_allocator}
|
|
88 |
dropout = 0.1
|
89 |
accumulate_gradient = 1
|
90 |
patience = 1600
|
91 |
-
max_epochs =
|
92 |
max_steps = 20000
|
93 |
eval_frequency = 200
|
94 |
frozen_components = []
|
|
|
1 |
[paths]
|
2 |
train = "./train.spacy"
|
3 |
dev = "./train.spacy"
|
4 |
+
vectors = "en_core_web_lg"
|
5 |
init_tok2vec = null
|
6 |
|
7 |
[system]
|
|
|
53 |
width = ${components.tok2vec.model.encode.width}
|
54 |
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
55 |
rows = [5000,1000,2500,2500]
|
56 |
+
include_static_vectors = true
|
57 |
|
58 |
[components.tok2vec.model.encode]
|
59 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
60 |
+
width = 256
|
61 |
+
depth = 8
|
62 |
window_size = 1
|
63 |
maxout_pieces = 3
|
64 |
|
|
|
88 |
dropout = 0.1
|
89 |
accumulate_gradient = 1
|
90 |
patience = 1600
|
91 |
+
max_epochs = 50
|
92 |
max_steps = 20000
|
93 |
eval_frequency = 200
|
94 |
frozen_components = []
|
en_t1_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 sha256:08b701abd9509917a23b0561f3233da191089229bec72911e8e67dc195af31f5
|
3 |
+
size 606866597
|
meta.json
CHANGED
@@ -10,10 +10,10 @@
|
|
10 |
"spacy_version":">=3.7.2,<3.8.0",
|
11 |
"spacy_git_version":"a89eae928",
|
12 |
"vectors":{
|
13 |
-
"width":
|
14 |
-
"vectors":
|
15 |
-
"keys":
|
16 |
-
"name":
|
17 |
},
|
18 |
"labels":{
|
19 |
"tok2vec":[
|
@@ -39,29 +39,29 @@
|
|
39 |
|
40 |
],
|
41 |
"performance":{
|
42 |
-
"ents_f":0.
|
43 |
-
"ents_p":0.
|
44 |
-
"ents_r":0.
|
45 |
"ents_per_type":{
|
46 |
"Other":{
|
47 |
-
"p":0.
|
48 |
-
"r":0.
|
49 |
-
"f":0.
|
50 |
},
|
51 |
"treatment":{
|
52 |
-
"p":0.
|
53 |
-
"r":0.
|
54 |
-
"f":0.
|
55 |
},
|
56 |
"chronic_disease":{
|
57 |
-
"p":0.
|
58 |
-
"r":0.
|
59 |
-
"f":0.
|
60 |
},
|
61 |
"cancer":{
|
62 |
-
"p":0.
|
63 |
-
"r":0.
|
64 |
-
"f":0.
|
65 |
},
|
66 |
"allergy_name":{
|
67 |
"p":0.984375,
|
@@ -69,8 +69,8 @@
|
|
69 |
"f":0.9882352941
|
70 |
}
|
71 |
},
|
72 |
-
"tok2vec_loss":
|
73 |
-
"ner_loss":
|
74 |
},
|
75 |
"requirements":[
|
76 |
|
|
|
10 |
"spacy_version":">=3.7.2,<3.8.0",
|
11 |
"spacy_git_version":"a89eae928",
|
12 |
"vectors":{
|
13 |
+
"width":300,
|
14 |
+
"vectors":514157,
|
15 |
+
"keys":514157,
|
16 |
+
"name":"en_vectors"
|
17 |
},
|
18 |
"labels":{
|
19 |
"tok2vec":[
|
|
|
39 |
|
40 |
],
|
41 |
"performance":{
|
42 |
+
"ents_f":0.9862779829,
|
43 |
+
"ents_p":0.9862148436,
|
44 |
+
"ents_r":0.9863411303,
|
45 |
"ents_per_type":{
|
46 |
"Other":{
|
47 |
+
"p":0.9879058979,
|
48 |
+
"r":0.9845620408,
|
49 |
+
"f":0.986231135
|
50 |
},
|
51 |
"treatment":{
|
52 |
+
"p":0.9826889786,
|
53 |
+
"r":0.9906922629,
|
54 |
+
"f":0.9866743917
|
55 |
},
|
56 |
"chronic_disease":{
|
57 |
+
"p":0.9868540345,
|
58 |
+
"r":0.9855138072,
|
59 |
+
"f":0.9861834655
|
60 |
},
|
61 |
"cancer":{
|
62 |
+
"p":0.9832439678,
|
63 |
+
"r":0.9872139973,
|
64 |
+
"f":0.9852249832
|
65 |
},
|
66 |
"allergy_name":{
|
67 |
"p":0.984375,
|
|
|
69 |
"f":0.9882352941
|
70 |
}
|
71 |
},
|
72 |
+
"tok2vec_loss":553.2069168486,
|
73 |
+
"ner_loss":2378.4214779778
|
74 |
},
|
75 |
"requirements":[
|
76 |
|
ner/model
CHANGED
Binary files a/ner/model and b/ner/model differ
|
|
tok2vec/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:b96f8a465acf9dc750817a669b65bf3a827deb95893e8a6ae4303b4d03c0dbb2
|
3 |
+
size 34434008
|
vocab/key2row
CHANGED
@@ -1 +1,3 @@
|
|
1 |
-
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31566ae010da3d399eb1d930ae142757afd2601034a4be3bdb00d18881c8c06a
|
3 |
+
size 7066303
|
vocab/strings.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
vocab/vectors
CHANGED
Binary files a/vocab/vectors and b/vocab/vectors differ
|
|