lrodrigues commited on
Commit
0919bfd
1 Parent(s): 7e88304
.gitattributes CHANGED
@@ -1,16 +1,17 @@
1
- *.bin.* filter=lfs diff=lfs merge=lfs -text
2
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.h5 filter=lfs diff=lfs merge=lfs -text
5
- *.tflite filter=lfs diff=lfs merge=lfs -text
6
- *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
- *.ot filter=lfs diff=lfs merge=lfs -text
8
- *.onnx filter=lfs diff=lfs merge=lfs -text
9
  *.arrow filter=lfs diff=lfs merge=lfs -text
 
 
10
  *.ftz filter=lfs diff=lfs merge=lfs -text
 
11
  *.joblib filter=lfs diff=lfs merge=lfs -text
 
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack 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
 
 
 
 
 
 
 
 
 
 
 
1
  *.arrow filter=lfs diff=lfs merge=lfs -text
2
+ *.bin filter=lfs diff=lfs merge=lfs -text
3
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
4
  *.ftz filter=lfs diff=lfs merge=lfs -text
5
+ *.h5 filter=lfs diff=lfs merge=lfs -text
6
  *.joblib filter=lfs diff=lfs merge=lfs -text
7
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
8
  *.model filter=lfs diff=lfs merge=lfs -text
9
  *.msgpack filter=lfs diff=lfs merge=lfs -text
10
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
11
+ *.onnx filter=lfs diff=lfs merge=lfs -text
12
+ *.ot filter=lfs diff=lfs merge=lfs -text
13
  *.pb filter=lfs diff=lfs merge=lfs -text
14
  *.pt filter=lfs diff=lfs merge=lfs -text
15
  *.pth filter=lfs diff=lfs merge=lfs -text
16
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
17
+ *.tflite filter=lfs diff=lfs merge=lfs -text
CEBinaryClassificationEvaluator_Quora-dev_results.csv ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
2
+ 0,5000,0.8608639203700198,0.2873433232307434,0.8098558473933306,0.19083455204963684,0.7614130434782609,0.8648815495022764,0.8629331317298123
3
+ 0,10000,0.863839225338779,0.25037556886672974,0.8119228437979106,0.12073762714862823,0.7546394485683987,0.8786171772513311,0.8678734374248867
4
+ 0,15000,0.8680587487490194,0.2262679636478424,0.8200071968333933,0.11036892235279083,0.7682556806688693,0.8792345088355583,0.875549687970233
5
+ 0,20000,0.8685456168348165,0.20787009596824646,0.8190316830962862,0.12376940995454788,0.7747041012936967,0.8687398719036963,0.8764299796079794
6
+ 0,25000,0.8720077898893728,0.3845294713973999,0.8250813155041562,0.2559159994125366,0.7759499694106451,0.8808550042441546,0.8833998414872404
7
+ 0,30000,0.8729815260609667,0.5238280296325684,0.8255852051403401,0.3320024907588959,0.781461061337009,0.8749903541939964,0.878249009917573
8
+ 0,-1,0.8710611019447675,0.4382350444793701,0.8225952648562416,0.149741068482399,0.7758172616605116,0.8753761864341384,0.8821009813520877
9
+ 1,5000,0.8723864650672148,0.13579325377941132,0.8250017981730562,0.046766698360443115,0.772546642419344,0.8850991588857164,0.8772769680139632
10
+ 1,10000,0.8706012820859592,0.17663632333278656,0.8243606757289911,0.04282882809638977,0.7701380511995711,0.8867968207423412,0.8717299987211413
11
+ 1,15000,0.8711963430797112,0.062239423394203186,0.8229883392482075,0.025501983240246773,0.775366769020812,0.876842348946678,0.88006993940756
12
+ 1,20000,0.8719266452084066,0.03155897557735443,0.8244302380178423,0.010280131362378597,0.7749185225420967,0.8807006713480978,0.8812910141874843
13
+ 1,25000,0.8726028508831246,0.03645790368318558,0.8253768844221104,0.03082387149333954,0.7918468628146047,0.8618720580291689,0.8816145619414946
14
+ 1,30000,0.8732249601038652,0.03989178314805031,0.8268535595721136,0.029114533215761185,0.7920288318846724,0.8648815495022764,0.8793008086700131
15
+ 1,-1,0.8735765870547185,0.05718168243765831,0.8270970543533329,0.018996555358171463,0.7787393526405452,0.8818581680685238,0.8779853764105872
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - quora
4
+ language: en
5
+ license: mit
6
+ pipeline_tag: text-classification
7
+ tags:
8
+ - roberta
9
+ - text-classification
10
+ ---
11
+ # Cross-Encoder for Quora Duplicate Questions Detection
12
+
13
+ This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
14
+
15
+ This model uses [roberta-base](https://huggingface.co/roberta-base).
16
+
17
+ ## Training Data
18
+
19
+ This model was trained on the [Quora Duplicate Questions](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) dataset.
20
+
21
+ The model will predict a score between 0 and 1: How likely the two given questions are duplicates.
22
+
23
+ Note: The model is not suitable to estimate the similarity of questions, e.g. the two questions "How to learn Java" and "How to learn Python" will result in a rahter low score, as these are not duplicates.
24
+
25
+ ## Usage and Performance
26
+
27
+ The trained model can be used like this:
28
+
29
+ ```python
30
+ from sentence_transformers import CrossEncoder
31
+
32
+ model = CrossEncoder('model_name')
33
+ scores = model.predict([('Question 1', 'Question 2'), ('Question 3', 'Question 4')])
34
+
35
+ print(scores)
36
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "roberta",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 1,
26
+ "type_vocab_size": 1,
27
+ "vocab_size": 50265
28
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e3f35ee5fa4bbd55ddee08e12bdbe19fcec65d978d5df08bccacd206964e4f
3
+ size 498592825
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbebb63aa533e7d3b68b2e0d205287523fff83ab36e434003d55f855e699acc6
3
+ size 498676169
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "sep_token": {
24
+ "content": "</s>",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": true
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true
36
+ },
37
+ "cls_token": {
38
+ "content": "<s>",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true
43
+ },
44
+ "mask_token": {
45
+ "content": "<mask>",
46
+ "single_word": false,
47
+ "lstrip": true,
48
+ "rstrip": false,
49
+ "normalized": true
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "full_tokenizer_file": null,
4
+ "model_max_length": 512,
5
+ "special_tokens_map_file": "special_tokens_map.json"
6
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff