Hugging Face's logo

ThuyNT03
/
PhoBERT-cls-OCR

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
2
ThuyNT03 commited on
Commit
222f9c5
·
1 Parent(s): df949d3

Training completed!

Browse files
Files changed (6) hide show
  1. README.md +13 -13
  2. added_tokens.json +5 -1
  3. config.json +1 -1
  4. pytorch_model.bin +2 -2
  5. tokenizer_config.json +44 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5182
21
- - Accuracy: 0.8713
22
- - F1: 0.8710
23
 
24
  ## Model description
25
 
@@ -50,19 +50,19 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
- | 0.5631 | 1.0 | 25 | 0.4327 | 0.8119 | 0.8105 |
54
- | 0.3123 | 2.0 | 50 | 0.4440 | 0.8020 | 0.7971 |
55
- | 0.1806 | 3.0 | 75 | 0.4117 | 0.8515 | 0.8518 |
56
- | 0.1107 | 4.0 | 100 | 0.4446 | 0.8614 | 0.8607 |
57
- | 0.0729 | 5.0 | 125 | 0.4965 | 0.8713 | 0.8710 |
58
- | 0.0473 | 6.0 | 150 | 0.4914 | 0.8812 | 0.8799 |
59
- | 0.049 | 7.0 | 175 | 0.5021 | 0.8713 | 0.8710 |
60
- | 0.0255 | 8.0 | 200 | 0.5182 | 0.8713 | 0.8710 |
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.33.3
66
  - Pytorch 2.0.1+cu118
67
  - Datasets 2.14.5
68
- - Tokenizers 0.13.3
 
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5749
21
+ - Accuracy: 0.8515
22
+ - F1: 0.8504
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
+ | 0.5828 | 1.0 | 25 | 0.4474 | 0.8119 | 0.8093 |
54
+ | 0.3067 | 2.0 | 50 | 0.3924 | 0.8218 | 0.8199 |
55
+ | 0.1806 | 3.0 | 75 | 0.3979 | 0.8416 | 0.8399 |
56
+ | 0.1043 | 4.0 | 100 | 0.4770 | 0.8317 | 0.8294 |
57
+ | 0.0688 | 5.0 | 125 | 0.5007 | 0.8614 | 0.8607 |
58
+ | 0.0406 | 6.0 | 150 | 0.5332 | 0.8614 | 0.8614 |
59
+ | 0.0387 | 7.0 | 175 | 0.5748 | 0.8515 | 0.8504 |
60
+ | 0.0328 | 8.0 | 200 | 0.5749 | 0.8515 | 0.8504 |
61
 
62
 
63
  ### Framework versions
64
 
65
+ - Transformers 4.34.0
66
  - Pytorch 2.0.1+cu118
67
  - Datasets 2.14.5
68
+ - Tokenizers 0.14.1
added_tokens.json CHANGED
@@ -1,3 +1,7 @@
1
  {
2
- "<mask>": 64000
 
 
 
 
3
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<mask>": 64000,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
  }
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "problem_type": "single_label_classification",
23
  "tokenizer_class": "PhobertTokenizer",
24
  "torch_dtype": "float32",
25
- "transformers_version": "4.33.3",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 64001
 
22
  "problem_type": "single_label_classification",
23
  "tokenizer_class": "PhobertTokenizer",
24
  "torch_dtype": "float32",
25
+ "transformers_version": "4.34.0",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 64001
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:919fabe275d0f9faac7ab49bb803adfd370fcb7cec818b89f3d119b29dfcc2ca
3
- size 540065393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339a4bbe0155e6f1e00dbff95791c6acaef33a40f2a7213dca684427dc69b0cd
3
+ size 540068209
tokenizer_config.json CHANGED
@@ -1,4 +1,47 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "<s>",
@@ -8,5 +51,6 @@
8
  "pad_token": "<pad>",
9
  "sep_token": "</s>",
10
  "tokenizer_class": "PhobertTokenizer",
 
11
  "unk_token": "<unk>"
12
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
  "cls_token": "<s>",
 
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",
53
  "tokenizer_class": "PhobertTokenizer",
54
+ "tokenizer_file": "/root/.cache/huggingface/hub/models--vinai--phobert-large/snapshots/9ce4eafcd8e601d798295b17c75c5f5f1b1509b9/tokenizer.json",
55
  "unk_token": "<unk>"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b502914df107074f2b1fee99e2fa70a06d7196e6eab915725fe0c427764d6df
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24fbddbbd885d189441ec26052337a96d26e02467d4d7032fc4034c69140ebf
3
  size 4027