Hugging Face's logo

dwitidibyajyoti
/
fine_tune_layoutmlv3_model

Token Classification
Transformers
PyTorch
layoutlmv3
Generated from Trainer
Inference Endpoints
Model card Files Community
dwitidibyajyoti commited on
Commit
77a8530
•
1 Parent(s): 9b58aac

dwitidibyajyoti/fine_tune_layoutmlv3

Browse files
Files changed (4) hide show
  1. README.md +15 -15
  2. config.json +26 -24
  3. pytorch_model.bin +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4598
24
- - Precision: 0.6190
25
- - Recall: 0.8667
26
- - F1: 0.7222
27
- - Accuracy: 0.9428
28
 
29
  ## Model description
30
 
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 10.0 | 100 | 0.5546 | 0.4510 | 0.7667 | 0.5679 | 0.9016 |
59
- | No log | 20.0 | 200 | 0.4975 | 0.5510 | 0.9 | 0.6835 | 0.9441 |
60
- | No log | 30.0 | 300 | 0.4426 | 0.5098 | 0.8667 | 0.6420 | 0.9455 |
61
- | No log | 40.0 | 400 | 0.5438 | 0.4727 | 0.8667 | 0.6118 | 0.9322 |
62
- | 0.2854 | 50.0 | 500 | 0.3669 | 0.6047 | 0.8667 | 0.7123 | 0.9548 |
63
- | 0.2854 | 60.0 | 600 | 0.5638 | 0.5778 | 0.8667 | 0.6933 | 0.9348 |
64
- | 0.2854 | 70.0 | 700 | 0.3922 | 0.6512 | 0.9333 | 0.7671 | 0.9574 |
65
- | 0.2854 | 80.0 | 800 | 0.3999 | 0.6047 | 0.8667 | 0.7123 | 0.9535 |
66
- | 0.2854 | 90.0 | 900 | 0.4413 | 0.5814 | 0.8333 | 0.6849 | 0.9428 |
67
- | 0.0112 | 100.0 | 1000 | 0.4598 | 0.6190 | 0.8667 | 0.7222 | 0.9428 |
68
 
69
 
70
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2763
24
+ - Precision: 0.5109
25
+ - Recall: 0.6026
26
+ - F1: 0.5529
27
+ - Accuracy: 0.9222
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 8.33 | 100 | 0.6800 | 0.3371 | 0.3846 | 0.3593 | 0.7682 |
59
+ | No log | 16.67 | 200 | 0.3088 | 0.5204 | 0.6538 | 0.5795 | 0.9156 |
60
+ | No log | 25.0 | 300 | 0.2142 | 0.5326 | 0.6282 | 0.5765 | 0.9305 |
61
+ | No log | 33.33 | 400 | 0.2301 | 0.5795 | 0.6538 | 0.6145 | 0.9288 |
62
+ | 0.4115 | 41.67 | 500 | 0.2426 | 0.5618 | 0.6410 | 0.5988 | 0.9272 |
63
+ | 0.4115 | 50.0 | 600 | 0.4171 | 0.6190 | 0.6667 | 0.6420 | 0.8924 |
64
+ | 0.4115 | 58.33 | 700 | 0.2265 | 0.5393 | 0.6154 | 0.5749 | 0.9371 |
65
+ | 0.4115 | 66.67 | 800 | 0.2869 | 0.5506 | 0.6282 | 0.5868 | 0.9156 |
66
+ | 0.4115 | 75.0 | 900 | 0.2633 | 0.5568 | 0.6282 | 0.5904 | 0.9272 |
67
+ | 0.0231 | 83.33 | 1000 | 0.2763 | 0.5109 | 0.6026 | 0.5529 | 0.9222 |
68
 
69
 
70
  ### Framework versions
config.json CHANGED
@@ -14,37 +14,39 @@
14
  "hidden_dropout_prob": 0.1,
15
  "hidden_size": 768,
16
  "id2label": {
17
- "0": "I-TABLE",
18
  "1": "I-VALUE",
19
- "2": "I-IGNORE",
20
- "3": "E-TABLE",
21
- "4": "O",
22
- "5": "B-VALUE",
23
- "6": "B-TABLE",
24
- "7": "B-IGNORE",
25
- "8": "S-VALUE",
26
- "9": "S-IGNORE",
27
- "10": "E-VALUE",
28
- "11": "S-KEY",
29
- "12": "E-IGNORE"
 
30
  },
31
  "initializer_range": 0.02,
32
  "input_size": 224,
33
  "intermediate_size": 3072,
34
  "label2id": {
35
- "B-IGNORE": 7,
36
- "B-TABLE": 6,
37
- "B-VALUE": 5,
38
- "E-IGNORE": 12,
39
- "E-TABLE": 3,
40
- "E-VALUE": 10,
41
- "I-IGNORE": 2,
42
- "I-TABLE": 0,
43
  "I-VALUE": 1,
44
- "O": 4,
45
- "S-IGNORE": 9,
46
- "S-KEY": 11,
47
- "S-VALUE": 8
 
48
  },
49
  "layer_norm_eps": 1e-05,
50
  "max_2d_position_embeddings": 1024,
 
14
  "hidden_dropout_prob": 0.1,
15
  "hidden_size": 768,
16
  "id2label": {
17
+ "0": "S-VALUE",
18
  "1": "I-VALUE",
19
+ "2": "E-IGNORE",
20
+ "3": "S-KEY",
21
+ "4": "E-COLUMN",
22
+ "5": "B-IGNORE",
23
+ "6": "S-COLUMN",
24
+ "7": "I-COLUMN",
25
+ "8": "O",
26
+ "9": "E-VALUE",
27
+ "10": "B-COLUMN",
28
+ "11": "S-IGNORE",
29
+ "12": "I-IGNORE",
30
+ "13": "B-VALUE"
31
  },
32
  "initializer_range": 0.02,
33
  "input_size": 224,
34
  "intermediate_size": 3072,
35
  "label2id": {
36
+ "B-COLUMN": 10,
37
+ "B-IGNORE": 5,
38
+ "B-VALUE": 13,
39
+ "E-COLUMN": 4,
40
+ "E-IGNORE": 2,
41
+ "E-VALUE": 9,
42
+ "I-COLUMN": 7,
43
+ "I-IGNORE": 12,
44
  "I-VALUE": 1,
45
+ "O": 8,
46
+ "S-COLUMN": 6,
47
+ "S-IGNORE": 11,
48
+ "S-KEY": 3,
49
+ "S-VALUE": 0
50
  },
51
  "layer_norm_eps": 1e-05,
52
  "max_2d_position_embeddings": 1024,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e25ddddde534b5b78f303ef19dcb8e663287e2726874ca40d7d1be42b487641d
3
- size 503784749
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937055a74c873430240187632c57f89b1b7118d1cce72ccecf9f963b9a050128
3
+ size 503787821
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1a6d1a0dbf32dd83ad60d958e8217dd13218de0b4cfc4861f0353f10e58b3db
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf5e6a49361b9c4bee2916385462668c0982273f9981af1fb1bd5f66f5f8504
3
  size 4027