laverdes commited on
Commit
347316b
1 Parent(s): 70f3092

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: donut-base-sroie
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
+ # donut-base-sroie
16
+
17
+ This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.23.1
51
+ - Pytorch 1.12.1
52
+ - Datasets 2.7.0
53
+ - Tokenizers 0.11.0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_address>": 57532,
3
+ "</s_company>": 57530,
4
+ "</s_date>": 57528,
5
+ "</s_total>": 57526,
6
+ "<s_address>": 57531,
7
+ "<s_company>": 57529,
8
+ "<s_date>": 57527,
9
+ "<s_iitcdip>": 57523,
10
+ "<s_synthdog>": 57524,
11
+ "<s_total>": 57525,
12
+ "<sep/>": 57522
13
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_resize": true,
6
+ "do_thumbnail": true,
7
+ "feature_extractor_type": "DonutFeatureExtractor",
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "DonutProcessor",
19
+ "resample": 2,
20
+ "size": [
21
+ 720,
22
+ 960
23
+ ]
24
+ }
runs/Nov25_16-52-15_Sebastians-MBP/events.out.tfevents.1669391572.Sebastians-MBP CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211cb45fab4b5ae8294b440bec6340869692afbc002ec9e59461d59109def823
3
- size 9464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155301b1b121ee506faf4c117e4aa65a736e17ca065b91b2ed29ba64d38880a3
3
+ size 9818
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_total>",
4
+ "</s_total>",
5
+ "<s_date>",
6
+ "</s_date>",
7
+ "<s_company>",
8
+ "</s_company>",
9
+ "<s_address>",
10
+ "</s_address>",
11
+ "<s>",
12
+ "</s>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "<s>",
16
+ "eos_token": "</s>",
17
+ "mask_token": {
18
+ "content": "<mask>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<pad>",
25
+ "sep_token": "</s>",
26
+ "unk_token": "<unk>"
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "name_or_path": "naver-clova-ix/donut-base",
14
+ "pad_token": "<pad>",
15
+ "processor_class": "DonutProcessor",
16
+ "sep_token": "</s>",
17
+ "sp_model_kwargs": {},
18
+ "special_tokens_map_file": null,
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }