ivelin commited on
Commit
d7cf261
1 Parent(s): e4213c7

End of training

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: donut-base-sroie
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # donut-base-sroie
14
+
15
+ This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 2
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3
41
+ - mixed_precision_training: Native AMP
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.25.1
50
+ - Pytorch 1.13.0+cu116
51
+ - Datasets 2.8.0
52
+ - Tokenizers 0.13.2
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "DonutImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "DonutProcessor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 1280,
24
+ "width": 960
25
+ }
26
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7704ca2f33332606523367f6f7277a29fc17757403a6943c1764bdf1c20e76b0
3
  size 809211673
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54246e0aae8ddb22742811ab37d35b1339dd138f9d99b28ee72de14236a08719
3
  size 809211673
runs/Jan05_02-47-02_8987770d7e99/events.out.tfevents.1672886836.8987770d7e99.280.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6e769a64255280c5047c56154f819a1b625c84d96067617ad49ada7bd53d962
3
- size 8546
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1c5b381e6f2aec11c9a7a24363ee69b30fabe7ee3b24cfd4ada92e5de84068
3
+ size 9842
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "ivelin/sroie_donut_processor",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }