ananthrgv commited on
Commit
ead015f
1 Parent(s): b79acb3

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: ananth-docai4
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
+ # ananth-docai4
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 4.22.0
50
+ - Pytorch 1.13.1+cu117
51
+ - Datasets 2.7.1
52
+ - Tokenizers 0.12.1
added_tokens.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Actual Cash Value Amount>": 57546,
3
+ "</s_Balance Due Amount>": 57540,
4
+ "</s_Contractor/Vendor Name>": 57532,
5
+ "</s_Deductible Amount>": 57544,
6
+ "</s_Depreciation Amount>": 57542,
7
+ "</s_Invoice Date>": 57530,
8
+ "</s_Invoice Number>": 57536,
9
+ "</s_Invoice Total Amount>": 57528,
10
+ "</s_Job Completed Date>": 57548,
11
+ "</s_Permit Amount>": 57526,
12
+ "</s_Policyholder Name>": 57534,
13
+ "</s_Total Received/Down Payment>": 57538,
14
+ "<s_Actual Cash Value Amount>": 57545,
15
+ "<s_Balance Due Amount>": 57539,
16
+ "<s_Contractor/Vendor Name>": 57531,
17
+ "<s_Deductible Amount>": 57543,
18
+ "<s_Depreciation Amount>": 57541,
19
+ "<s_Invoice Date>": 57529,
20
+ "<s_Invoice Number>": 57535,
21
+ "<s_Invoice Total Amount>": 57527,
22
+ "<s_Job Completed Date>": 57547,
23
+ "<s_Permit Amount>": 57525,
24
+ "<s_Policyholder Name>": 57533,
25
+ "<s_Total Received/Down Payment>": 57537,
26
+ "<s_iitcdip>": 57523,
27
+ "<s_synthdog>": 57524,
28
+ "<sep/>": 57522
29
+ }
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
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd1e071800c335c9e561df40e9dd6113d911b867d10a70a6921cf24e4a55e7f5
3
  size 809277209
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e57ea081bc43cd404ee6b5ece744e9f5e3dab2d433bc5e9b0d5a893ac1acbb
3
  size 809277209
runs/Dec19_23-43-21_ip-10-160-32-10/events.out.tfevents.1671493413.ip-10-160-32-10.8938.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f92bbb76fb77bd371e3297df8acf5eb16dad51f39beda5531720e5d27a159afb
3
- size 8076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9402718535f4a22c547204a8b551462da30bfba940eaae43b07f0da1b7e711a
3
+ size 8741
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_Permit Amount>",
4
+ "</s_Permit Amount>",
5
+ "<s_Invoice Total Amount>",
6
+ "</s_Invoice Total Amount>",
7
+ "<s_Invoice Date>",
8
+ "</s_Invoice Date>",
9
+ "<s_Contractor/Vendor Name>",
10
+ "</s_Contractor/Vendor Name>",
11
+ "<s_Policyholder Name>",
12
+ "</s_Policyholder Name>",
13
+ "<s_Invoice Number>",
14
+ "</s_Invoice Number>",
15
+ "<s_Total Received/Down Payment>",
16
+ "</s_Total Received/Down Payment>",
17
+ "<s_Balance Due Amount>",
18
+ "</s_Balance Due Amount>",
19
+ "<s_Depreciation Amount>",
20
+ "</s_Depreciation Amount>",
21
+ "<s_Deductible Amount>",
22
+ "</s_Deductible Amount>",
23
+ "<s_Actual Cash Value Amount>",
24
+ "</s_Actual Cash Value Amount>",
25
+ "<s_Job Completed Date>",
26
+ "</s_Job Completed Date>",
27
+ "<s>",
28
+ "</s>"
29
+ ],
30
+ "bos_token": "<s>",
31
+ "cls_token": "<s>",
32
+ "eos_token": "</s>",
33
+ "mask_token": {
34
+ "content": "<mask>",
35
+ "lstrip": true,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": "<pad>",
41
+ "sep_token": "</s>",
42
+ "unk_token": "<unk>"
43
+ }
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
+ }