missdua-07 commited on
Commit
4378cf7
·
verified ·
1 Parent(s): 71f7050

End of training

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: SCUT-DLVCLab/lilt-roberta-en-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: lilt-roBERTa-en-base-sroie
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/miss1dua/huggingface/runs/r5thm7ml)
15
+ # lilt-roBERTa-en-base-sroie
16
+
17
+ This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0348
20
+ - Address: {'precision': 0.92, 'recall': 0.9279538904899135, 'f1': 0.9239598278335724, 'number': 347}
21
+ - Company: {'precision': 0.9405099150141643, 'recall': 0.9567723342939481, 'f1': 0.9485714285714285, 'number': 347}
22
+ - Date: {'precision': 0.9827586206896551, 'recall': 0.9855907780979827, 'f1': 0.9841726618705036, 'number': 347}
23
+ - Total: {'precision': 0.9131652661064426, 'recall': 0.9394812680115274, 'f1': 0.9261363636363636, 'number': 347}
24
+ - Overall Precision: 0.9389
25
+ - Overall Recall: 0.9524
26
+ - Overall F1: 0.9456
27
+ - Overall Accuracy: 0.9954
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 3e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 20
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Address | Company | Date | Total | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
57
+ |:-------------:|:-------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
58
+ | 0.0536 | 6.3291 | 500 | 0.0261 | {'precision': 0.9067796610169492, 'recall': 0.9250720461095101, 'f1': 0.9158345221112697, 'number': 347} | {'precision': 0.9273743016759777, 'recall': 0.9567723342939481, 'f1': 0.9418439716312057, 'number': 347} | {'precision': 0.9828080229226361, 'recall': 0.9884726224783862, 'f1': 0.985632183908046, 'number': 347} | {'precision': 0.883008356545961, 'recall': 0.9135446685878963, 'f1': 0.8980169971671388, 'number': 347} | 0.9246 | 0.9460 | 0.9352 | 0.9949 |
59
+ | 0.0058 | 12.6582 | 1000 | 0.0326 | {'precision': 0.9176136363636364, 'recall': 0.930835734870317, 'f1': 0.9241773962804005, 'number': 347} | {'precision': 0.9323943661971831, 'recall': 0.9538904899135446, 'f1': 0.9430199430199431, 'number': 347} | {'precision': 0.9827586206896551, 'recall': 0.9855907780979827, 'f1': 0.9841726618705036, 'number': 347} | {'precision': 0.8910081743869209, 'recall': 0.9423631123919308, 'f1': 0.9159663865546217, 'number': 347} | 0.9304 | 0.9532 | 0.9416 | 0.9950 |
60
+ | 0.0019 | 18.9873 | 1500 | 0.0348 | {'precision': 0.92, 'recall': 0.9279538904899135, 'f1': 0.9239598278335724, 'number': 347} | {'precision': 0.9405099150141643, 'recall': 0.9567723342939481, 'f1': 0.9485714285714285, 'number': 347} | {'precision': 0.9827586206896551, 'recall': 0.9855907780979827, 'f1': 0.9841726618705036, 'number': 347} | {'precision': 0.9131652661064426, 'recall': 0.9394812680115274, 'f1': 0.9261363636363636, 'number': 347} | 0.9389 | 0.9524 | 0.9456 | 0.9954 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.42.3
66
+ - Pytorch 2.1.2
67
+ - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7636c573d3958980ff85a178e8679b69b19ccfb2e71ce16e1037c81d6cdbb5ee
3
  size 520733716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561c212e08f168b8b895390635be2859bec103d842f25f21cc69980c40432428
3
  size 520733716
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3FeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "cls_token_box": [
49
+ 0,
50
+ 0,
51
+ 0,
52
+ 0
53
+ ],
54
+ "eos_token": "</s>",
55
+ "errors": "replace",
56
+ "mask_token": "<mask>",
57
+ "model_max_length": 512,
58
+ "only_label_first_subword": true,
59
+ "pad_token": "<pad>",
60
+ "pad_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "pad_token_label": -100,
67
+ "processor_class": "LayoutLMv3Processor",
68
+ "sep_token": "</s>",
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
+ "unk_token": "<unk>"
78
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff