vcliang commited on
Commit
733abb4
1 Parent(s): 6ca94ab

End of training

Browse files
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: test
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # test
20
+
21
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6850
24
+ - Precision: 0.8936
25
+ - Recall: 0.9136
26
+ - F1: 0.9035
27
+ - Accuracy: 0.8445
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: 1e-05
47
+ - train_batch_size: 2
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - training_steps: 1000
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.33 | 100 | 0.6682 | 0.7574 | 0.8311 | 0.7925 | 0.7658 |
59
+ | No log | 2.67 | 200 | 0.4970 | 0.8289 | 0.8833 | 0.8552 | 0.8339 |
60
+ | No log | 4.0 | 300 | 0.5550 | 0.8398 | 0.8882 | 0.8634 | 0.8128 |
61
+ | No log | 5.33 | 400 | 0.5001 | 0.8800 | 0.9106 | 0.8950 | 0.8500 |
62
+ | 0.5341 | 6.67 | 500 | 0.5645 | 0.8947 | 0.9036 | 0.8992 | 0.8456 |
63
+ | 0.5341 | 8.0 | 600 | 0.5797 | 0.8847 | 0.9190 | 0.9016 | 0.8537 |
64
+ | 0.5341 | 9.33 | 700 | 0.6635 | 0.8816 | 0.9101 | 0.8956 | 0.8421 |
65
+ | 0.5341 | 10.67 | 800 | 0.6857 | 0.8939 | 0.9126 | 0.9031 | 0.8452 |
66
+ | 0.5341 | 12.0 | 900 | 0.6777 | 0.8941 | 0.9146 | 0.9042 | 0.8438 |
67
+ | 0.1335 | 13.33 | 1000 | 0.6850 | 0.8936 | 0.9136 | 0.9035 | 0.8445 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.37.0.dev0
73
+ - Pytorch 2.1.0+cu121
74
+ - Datasets 2.16.0
75
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-base",
3
+ "architectures": [
4
+ "LayoutLMv3ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 128,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "B-HEADER",
19
+ "2": "I-HEADER",
20
+ "3": "B-QUESTION",
21
+ "4": "I-QUESTION",
22
+ "5": "B-ANSWER",
23
+ "6": "I-ANSWER"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "input_size": 224,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "B-ANSWER": 5,
30
+ "B-HEADER": 1,
31
+ "B-QUESTION": 3,
32
+ "I-ANSWER": 6,
33
+ "I-HEADER": 2,
34
+ "I-QUESTION": 4,
35
+ "O": 0
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_2d_position_embeddings": 1024,
39
+ "max_position_embeddings": 514,
40
+ "max_rel_2d_pos": 256,
41
+ "max_rel_pos": 128,
42
+ "model_type": "layoutlmv3",
43
+ "num_attention_heads": 12,
44
+ "num_channels": 3,
45
+ "num_hidden_layers": 12,
46
+ "pad_token_id": 1,
47
+ "patch_size": 16,
48
+ "rel_2d_pos_bins": 64,
49
+ "rel_pos_bins": 32,
50
+ "second_input_size": 112,
51
+ "shape_size": 128,
52
+ "text_embed": true,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.37.0.dev0",
55
+ "type_vocab_size": 1,
56
+ "visual_embed": true,
57
+ "vocab_size": 50265
58
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d561df6b005ed251f4b2b5fd416dbf2d433069ed673051ddf555b0c2e531ac
3
+ size 501355532
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
+ }
runs/Dec24_13-30-35_b251255dc4a6/events.out.tfevents.1703424646.b251255dc4a6.13650.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0a406d4c621336ae897a8d18b8344da52818a45807010d4d216dff687b151b
3
+ size 10337
runs/Dec24_13-30-35_b251255dc4a6/events.out.tfevents.1703425550.b251255dc4a6.13650.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97260f813d34902114e2b773d5e1af240d92c7549b528035f20d0b16a8493cda
3
+ size 560
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 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "apply_ocr": false,
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "cls_token_box": [
50
+ 0,
51
+ 0,
52
+ 0,
53
+ 0
54
+ ],
55
+ "eos_token": "</s>",
56
+ "errors": "replace",
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "<pad>",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv3Processor",
69
+ "sep_token": "</s>",
70
+ "sep_token_box": [
71
+ 0,
72
+ 0,
73
+ 0,
74
+ 0
75
+ ],
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": "<unk>"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365d0f01892cedb6df1ebf8cbeaf826b2f10e687bc8acb6ef991bdba3e19747e
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff