Upload folder using huggingface_hub
Browse files- 1_Pooling/config.json +1 -3
- README.md +5 -5
- config.json +1 -1
- dev-metrics.json +5 -0
- log.csv +66 -0
- sts-metrics.json +6 -0
1_Pooling/config.json
CHANGED
@@ -3,7 +3,5 @@
|
|
3 |
"pooling_mode_cls_token": true,
|
4 |
"pooling_mode_mean_tokens": false,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
-
"pooling_mode_mean_sqrt_len_tokens": false
|
7 |
-
"pooling_mode_weightedmean_tokens": false,
|
8 |
-
"pooling_mode_lasttoken": false
|
9 |
}
|
|
|
3 |
"pooling_mode_cls_token": true,
|
4 |
"pooling_mode_mean_tokens": false,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
|
|
|
|
7 |
}
|
README.md
CHANGED
@@ -9,7 +9,7 @@ datasets:
|
|
9 |
- shunk031/jsnli
|
10 |
---
|
11 |
|
12 |
-
#
|
13 |
|
14 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
15 |
|
@@ -29,7 +29,7 @@ Then you can use the model like this:
|
|
29 |
from sentence_transformers import SentenceTransformer
|
30 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
31 |
|
32 |
-
model = SentenceTransformer('
|
33 |
embeddings = model.encode(sentences)
|
34 |
print(embeddings)
|
35 |
```
|
@@ -52,8 +52,8 @@ def cls_pooling(model_output, attention_mask):
|
|
52 |
sentences = ['This is an example sentence', 'Each sentence is converted']
|
53 |
|
54 |
# Load model from HuggingFace Hub
|
55 |
-
tokenizer = AutoTokenizer.from_pretrained('
|
56 |
-
model = AutoModel.from_pretrained('
|
57 |
|
58 |
# Tokenize sentences
|
59 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
@@ -75,7 +75,7 @@ print(sentence_embeddings)
|
|
75 |
|
76 |
<!--- Describe how your model was evaluated -->
|
77 |
|
78 |
-
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=
|
79 |
|
80 |
|
81 |
|
|
|
9 |
- shunk031/jsnli
|
10 |
---
|
11 |
|
12 |
+
# {MODEL_NAME}
|
13 |
|
14 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
15 |
|
|
|
29 |
from sentence_transformers import SentenceTransformer
|
30 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
31 |
|
32 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
33 |
embeddings = model.encode(sentences)
|
34 |
print(embeddings)
|
35 |
```
|
|
|
52 |
sentences = ['This is an example sentence', 'Each sentence is converted']
|
53 |
|
54 |
# Load model from HuggingFace Hub
|
55 |
+
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
|
56 |
+
model = AutoModel.from_pretrained('{MODEL_NAME}')
|
57 |
|
58 |
# Tokenize sentences
|
59 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
|
|
75 |
|
76 |
<!--- Describe how your model was evaluated -->
|
77 |
|
78 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
79 |
|
80 |
|
81 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "cl-tohoku/bert-base-japanese-v3",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
dev-metrics.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best-epoch": 0,
|
3 |
+
"best-step": 128,
|
4 |
+
"best-dev": 83.61539847191834
|
5 |
+
}
|
log.csv
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,step,loss,sts-dev
|
2 |
+
0,0,inf,51.375121585435735
|
3 |
+
0,32,5.8056640625,78.35678255256113
|
4 |
+
0,64,3.11572265625,82.6244856578063
|
5 |
+
0,96,2.42578125,83.35358238047021
|
6 |
+
0,128,2.176513671875,83.61539847191834
|
7 |
+
0,160,2.0302734375,81.87700855632563
|
8 |
+
0,192,1.875732421875,79.53856626810594
|
9 |
+
0,224,1.843994140625,77.77162870199022
|
10 |
+
0,256,1.773193359375,76.12193564966829
|
11 |
+
1,288,1.690185546875,75.82749644399787
|
12 |
+
1,320,1.600341796875,77.40347138209835
|
13 |
+
1,352,1.56298828125,74.4370737294954
|
14 |
+
1,384,1.570556640625,76.08974073722088
|
15 |
+
1,416,1.534912109375,73.89938923579099
|
16 |
+
1,448,1.55078125,70.69398516957513
|
17 |
+
1,480,1.509521484375,73.33702686894722
|
18 |
+
1,512,1.545654296875,75.2034184712643
|
19 |
+
1,544,1.52001953125,73.9900785391876
|
20 |
+
2,576,1.463134765625,72.0822596167315
|
21 |
+
2,608,1.376220703125,72.30434210546885
|
22 |
+
2,640,1.373046875,75.35516784317878
|
23 |
+
2,672,1.37646484375,75.00048637711306
|
24 |
+
2,704,1.370849609375,71.54454915080103
|
25 |
+
2,736,1.35595703125,72.10342263835692
|
26 |
+
2,768,1.351318359375,73.61822488939758
|
27 |
+
2,800,1.341552734375,73.69283818050053
|
28 |
+
2,832,1.350341796875,73.35254646396575
|
29 |
+
3,864,1.292724609375,71.73891113636543
|
30 |
+
3,896,1.231201171875,72.50612877979137
|
31 |
+
3,928,1.249267578125,71.73997216828496
|
32 |
+
3,960,1.23486328125,72.24572646319987
|
33 |
+
3,992,1.2470703125,72.21874965045426
|
34 |
+
3,1024,1.260498046875,71.01279770471795
|
35 |
+
3,1056,1.262451171875,71.28239282311822
|
36 |
+
3,1088,1.24609375,72.01843871324893
|
37 |
+
3,1120,1.25048828125,71.49440820181441
|
38 |
+
4,1152,1.151611328125,69.90122275478602
|
39 |
+
4,1184,1.157958984375,71.99470697954118
|
40 |
+
4,1216,1.179931640625,69.07210383354008
|
41 |
+
4,1248,1.173828125,67.60162600897702
|
42 |
+
4,1280,1.152587890625,68.50119537305783
|
43 |
+
4,1312,1.176513671875,69.20852332481955
|
44 |
+
4,1344,1.166015625,69.92232791766861
|
45 |
+
4,1376,1.1796875,71.00892896894848
|
46 |
+
5,1408,1.16357421875,72.45555003088666
|
47 |
+
5,1440,1.0804443359375,69.45015860800906
|
48 |
+
5,1472,1.0814208984375,71.00156597627819
|
49 |
+
5,1504,1.1224365234375,70.58322578457057
|
50 |
+
5,1536,1.097412109375,69.09835049406871
|
51 |
+
5,1568,1.097412109375,70.2241604764949
|
52 |
+
5,1600,1.1026611328125,71.35726715857705
|
53 |
+
5,1632,1.1053466796875,69.87296046317874
|
54 |
+
5,1664,1.11376953125,70.50921749290218
|
55 |
+
6,1696,1.092529296875,70.10898081907449
|
56 |
+
6,1728,1.0654296875,70.09196262215698
|
57 |
+
6,1760,1.068603515625,69.50168151188232
|
58 |
+
6,1792,1.0595703125,68.94335544010495
|
59 |
+
6,1824,1.048583984375,68.59140278421327
|
60 |
+
6,1856,1.0460205078125,69.62795505629208
|
61 |
+
6,1888,1.0633544921875,69.44217502657546
|
62 |
+
6,1920,1.0531005859375,69.53616592289175
|
63 |
+
6,1952,1.0594482421875,69.40128536108074
|
64 |
+
7,1984,1.044189453125,69.35274684809701
|
65 |
+
7,2016,1.013427734375,69.4939563818511
|
66 |
+
7,2048,1.0462646484375,69.50480224133872
|
sts-metrics.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"jsick": 82.7495424766893,
|
3 |
+
"jsts-val": 80.8645208379796,
|
4 |
+
"jsts-train": 77.85762915212484,
|
5 |
+
"avg": 80.49056415559791
|
6 |
+
}
|