Sebabrata commited on
Commit
386ba55
1 Parent(s): 0ee7ba8

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: dof-dl-1
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
+ # dof-dl-1
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: 3e-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: 30
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.24.0
52
+ - Pytorch 1.12.1+cu113
53
+ - Datasets 2.7.0
54
+ - Tokenizers 0.13.2
added_tokens.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_address>": 57540,
3
+ "</s_blood_group>": 57538,
4
+ "</s_date_of_issue>": 57536,
5
+ "</s_dob>": 57534,
6
+ "</s_driving_licence_no>": 57532,
7
+ "</s_name>": 57530,
8
+ "</s_s_d_w_name>": 57528,
9
+ "</s_valid_till_nt>": 57526,
10
+ "</s_valid_till_t_tr>": 57542,
11
+ "<s_address>": 57539,
12
+ "<s_blood_group>": 57537,
13
+ "<s_date_of_issue>": 57535,
14
+ "<s_dob>": 57533,
15
+ "<s_driving_licence_no>": 57531,
16
+ "<s_iitcdip>": 57523,
17
+ "<s_name>": 57529,
18
+ "<s_s_d_w_name>": 57527,
19
+ "<s_synthdog>": 57524,
20
+ "<s_valid_till_nt>": 57525,
21
+ "<s_valid_till_t_tr>": 57541,
22
+ "<sep/>": 57522
23
+ }
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
+ 960,
22
+ 1280
23
+ ]
24
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93a8143078a4c8425bedc89c704db4a2b27d910a72a78d91260edc2d38d8f620
3
  size 809249147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a8f7e29e7b46543b7462697952664759713cff50832210715b211fd7561305
3
  size 809249147
runs/Nov19_14-52-29_instance-2-gp-s/events.out.tfevents.1668869555.instance-2-gp-s.13140.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb662014ed9e8da797cb4a77908a0c95be8d1642177b07bb12426718a027fd4e
3
- size 8339
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01640cb83ce32796e09153f6b88bcb89d0e7d599e1bc1063f78344b5d924b88a
3
+ size 13560
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_valid_till_nt>",
4
+ "</s_valid_till_nt>",
5
+ "<s_s_d_w_name>",
6
+ "</s_s_d_w_name>",
7
+ "<s_name>",
8
+ "</s_name>",
9
+ "<s_driving_licence_no>",
10
+ "</s_driving_licence_no>",
11
+ "<s_dob>",
12
+ "</s_dob>",
13
+ "<s_date_of_issue>",
14
+ "</s_date_of_issue>",
15
+ "<s_blood_group>",
16
+ "</s_blood_group>",
17
+ "<s_address>",
18
+ "</s_address>",
19
+ "<s_valid_till_t_tr>",
20
+ "</s_valid_till_t_tr>",
21
+ "<s>",
22
+ "</s>"
23
+ ],
24
+ "bos_token": "<s>",
25
+ "cls_token": "<s>",
26
+ "eos_token": "</s>",
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": "<pad>",
35
+ "sep_token": "</s>",
36
+ "unk_token": "<unk>"
37
+ }
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
+ }