tkazusa commited on
Commit
52a8064
1 Parent(s): 92adae1

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - funsd-layoutlmv3
7
+ model-index:
8
+ - name: lilt-en-funsd-org
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # lilt-en-funsd-org
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 the funsd-layoutlmv3 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.8546
20
+ - Answer: {'precision': 0.0327455919395466, 'recall': 0.06364749082007344, 'f1': 0.04324324324324324, 'number': 817}
21
+ - Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
22
+ - Question: {'precision': 0.061769005847953216, 'recall': 0.15691736304549675, 'f1': 0.08864411224757408, 'number': 1077}
23
+ - Overall Precision: 0.0511
24
+ - Overall Recall: 0.1098
25
+ - Overall F1: 0.0697
26
+ - Overall Accuracy: 0.2522
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - training_steps: 3
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.25.1
61
+ - Pytorch 1.13.0+cu117
62
+ - Datasets 2.7.1
63
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
3
+ "architectures": [
4
+ "LiltForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-HEADER",
17
+ "2": "I-HEADER",
18
+ "3": "B-QUESTION",
19
+ "4": "I-QUESTION",
20
+ "5": "B-ANSWER",
21
+ "6": "I-ANSWER"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-ANSWER": 5,
27
+ "B-HEADER": 1,
28
+ "B-QUESTION": 3,
29
+ "I-ANSWER": 6,
30
+ "I-HEADER": 2,
31
+ "I-QUESTION": 4,
32
+ "O": 0
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_2d_position_embeddings": 1024,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "lilt",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.25.1",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 50265
47
+ }
logs/1670918695.243733/events.out.tfevents.1670918695.ip-172-31-89-140.195944.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c19489b32a82643b0a542649d7b28542e9f60b689b6d55308867fc6699ba38
3
+ size 5507
logs/events.out.tfevents.1670918695.ip-172-31-89-140.195944.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90535acce63dbead9bd87e7118ac7bc8596159c342ca0d3ff6e7306ee77cf32d
3
+ size 4481
logs/events.out.tfevents.1670918698.ip-172-31-89-140.195944.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f26d4aebefdfa01a9f59d521368d3be9ac8fcada12aaaf421cfe4e8f5034f7f
3
+ size 535
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
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": "LayoutLMv3ImageProcessor",
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c72dd7a5b2318e11497288b56146ce346e607fcce375fec0efaabd4160b18b4
3
+ size 520821201
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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "cls_token_box": [
20
+ 0,
21
+ 0,
22
+ 0,
23
+ 0
24
+ ],
25
+ "eos_token": {
26
+ "__type": "AddedToken",
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "errors": "replace",
34
+ "mask_token": {
35
+ "__type": "AddedToken",
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "model_max_length": 512,
43
+ "name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "processor_class": "LayoutLMv3Processor",
61
+ "sep_token": {
62
+ "__type": "AddedToken",
63
+ "content": "</s>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "special_tokens_map_file": null,
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": {
79
+ "__type": "AddedToken",
80
+ "content": "<unk>",
81
+ "lstrip": false,
82
+ "normalized": true,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209fd4650719ee8b107b126fb63543c334e42a434ceaa9756c2770b6a20f3aa3
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff