LysandreJik
commited on
Commit
•
0057c8b
1
Parent(s):
857b9d3
Initial commit
Browse files
.gitattributes
CHANGED
@@ -14,3 +14,5 @@
|
|
14 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
14 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
+
serialization/model.tar.gz filter=lfs diff=lfs merge=lfs -text
|
18 |
+
serialization/best.th filter=lfs diff=lfs merge=lfs -text
|
experiment.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_reader": {
|
3 |
+
"type": "conll2003",
|
4 |
+
"tag_label": "ner",
|
5 |
+
"token_indexers": {
|
6 |
+
"tokens": {
|
7 |
+
"type": "single_id",
|
8 |
+
"lowercase_tokens": true
|
9 |
+
}
|
10 |
+
}
|
11 |
+
},
|
12 |
+
"validation_dataset_reader": {
|
13 |
+
"type": "conll2003",
|
14 |
+
"tag_label": "ner",
|
15 |
+
"token_indexers": {
|
16 |
+
"tokens": {
|
17 |
+
"type": "single_id",
|
18 |
+
"namespace": "test_tokens",
|
19 |
+
"lowercase_tokens": true
|
20 |
+
}
|
21 |
+
}
|
22 |
+
},
|
23 |
+
"train_data_path": "test_fixtures/data/conll2003.txt",
|
24 |
+
"validation_data_path": "test_fixtures/data/conll2003.txt",
|
25 |
+
"model": {
|
26 |
+
"type": "simple_tagger",
|
27 |
+
"calculate_span_f1": true,
|
28 |
+
"label_encoding": "IOB1",
|
29 |
+
"text_field_embedder": {
|
30 |
+
"token_embedders": {
|
31 |
+
"tokens": {
|
32 |
+
"type": "embedding",
|
33 |
+
"projection_dim": 2,
|
34 |
+
"pretrained_file": "test_fixtures/embeddings/glove.6B.100d.sample.txt.gz",
|
35 |
+
"embedding_dim": 100,
|
36 |
+
"trainable": true
|
37 |
+
}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"encoder": {
|
41 |
+
"type": "lstm",
|
42 |
+
"input_size": 2,
|
43 |
+
"hidden_size": 4,
|
44 |
+
"num_layers": 1
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"data_loader": {
|
48 |
+
"batch_sampler":{
|
49 |
+
"type": "bucket",
|
50 |
+
"padding_noise": 0.0,
|
51 |
+
"batch_size" : 80
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"trainer": {
|
55 |
+
"num_epochs": 1,
|
56 |
+
"grad_norm": 1.0,
|
57 |
+
"patience": 500,
|
58 |
+
"cuda_device": -1,
|
59 |
+
"optimizer": {
|
60 |
+
"type": "adadelta",
|
61 |
+
"lr": 0.000001,
|
62 |
+
"rho": 0.95
|
63 |
+
}
|
64 |
+
}
|
65 |
+
}
|
serialization/best.th
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7138c889aebcfadc4d9c82b2df0958c52d7abbab2f3d2d9caff64b30a1d362d
|
3 |
+
size 9270
|
serialization/model.tar.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c281875582a0dd7c9bdf2af74f0316536fc38651bc5cabf3395c6df67d737085
|
3 |
+
size 9015
|
serialization/vocabulary/labels.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
O
|
2 |
+
I-ORG
|
3 |
+
I-PER
|
4 |
+
I-LOC
|
serialization/vocabulary/non_padded_namespaces.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
*labels
|
2 |
+
*tags
|
serialization/vocabulary/test_tokens.txt
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
@@UNKNOWN@@
|
2 |
+
.
|
3 |
+
u.n.
|
4 |
+
official
|
5 |
+
ekeus
|
6 |
+
heads
|
7 |
+
for
|
8 |
+
baghdad
|
9 |
+
ai2
|
10 |
+
engineer
|
11 |
+
joel
|
12 |
+
lives
|
13 |
+
in
|
14 |
+
seattle
|
serialization/vocabulary/tokens.txt
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
@@UNKNOWN@@
|
2 |
+
.
|
3 |
+
u.n.
|
4 |
+
official
|
5 |
+
ekeus
|
6 |
+
heads
|
7 |
+
for
|
8 |
+
baghdad
|
9 |
+
ai2
|
10 |
+
engineer
|
11 |
+
joel
|
12 |
+
lives
|
13 |
+
in
|
14 |
+
seattle
|