warshakhan commited on
Commit
f5e5b19
·
1 Parent(s): a3d6445

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: naver-clova-ix/donut-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ model-index:
9
+ - name: donut-base-SynHMP
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # donut-base-SynHMP
17
+
18
+ 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.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 20
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.32.0.dev0
52
+ - Pytorch 2.0.0
53
+ - Datasets 2.11.0
54
+ - Tokenizers 0.11.0
added_tokens.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_AGE>": 57534,
3
+ "</s_B>": 57546,
4
+ "</s_BP>": 57560,
5
+ "</s_DATE>": 57532,
6
+ "</s_DIAG BLOCK>": 57550,
7
+ "</s_DIAGNOSIS>": 57558,
8
+ "</s_GENDER>": 57530,
9
+ "</s_HISTORY>": 57556,
10
+ "</s_MEDICINE BLOCK>": 57536,
11
+ "</s_MEDICINE DOSE>": 57542,
12
+ "</s_MEDICINE NAME>": 57540,
13
+ "</s_MEDICINE POWER>": 57548,
14
+ "</s_MEDICINE TYPE>": 57538,
15
+ "</s_NAME>": 57528,
16
+ "</s_TEMP>": 57554,
17
+ "</s_WEIGHT>": 57552,
18
+ "</s_label>": 57544,
19
+ "</s_pateinet info>": 57526,
20
+ "<s_AGE>": 57533,
21
+ "<s_B>": 57545,
22
+ "<s_BP>": 57559,
23
+ "<s_DATE>": 57531,
24
+ "<s_DIAG BLOCK>": 57549,
25
+ "<s_DIAGNOSIS>": 57557,
26
+ "<s_GENDER>": 57529,
27
+ "<s_HISTORY>": 57555,
28
+ "<s_MEDICINE BLOCK>": 57535,
29
+ "<s_MEDICINE DOSE>": 57541,
30
+ "<s_MEDICINE NAME>": 57539,
31
+ "<s_MEDICINE POWER>": 57547,
32
+ "<s_MEDICINE TYPE>": 57537,
33
+ "<s_NAME>": 57527,
34
+ "<s_TEMP>": 57553,
35
+ "<s_WEIGHT>": 57551,
36
+ "<s_iitcdip>": 57523,
37
+ "<s_label>": 57543,
38
+ "<s_pateinet info>": 57525,
39
+ "<s_synthdog>": 57524,
40
+ "<sep/>": 57522
41
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.32.0.dev0"
8
+ }
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
+ 720,
24
+ 960
25
+ ]
26
+ }
runs/Jul24_09-37-00_DESKTOP-QS6484B/events.out.tfevents.1690173424.DESKTOP-QS6484B.18076.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01595ebed9839e63fc6c569521f36ad892b22550bec4fb9b5361006b935adafe
3
- size 34989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be0c501ceb217b45910fd0576a6a35b93b9a670d7f8af54bd3955d54c93f27c
3
+ size 35349
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_pateinet info>",
4
+ "</s_pateinet info>",
5
+ "<s_NAME>",
6
+ "</s_NAME>",
7
+ "<s_GENDER>",
8
+ "</s_GENDER>",
9
+ "<s_DATE>",
10
+ "</s_DATE>",
11
+ "<s_AGE>",
12
+ "</s_AGE>",
13
+ "<s_MEDICINE BLOCK>",
14
+ "</s_MEDICINE BLOCK>",
15
+ "<s_MEDICINE TYPE>",
16
+ "</s_MEDICINE TYPE>",
17
+ "<s_MEDICINE NAME>",
18
+ "</s_MEDICINE NAME>",
19
+ "<s_MEDICINE DOSE>",
20
+ "</s_MEDICINE DOSE>",
21
+ "<s_label>",
22
+ "</s_label>",
23
+ "<s_B>",
24
+ "</s_B>",
25
+ "<s_MEDICINE POWER>",
26
+ "</s_MEDICINE POWER>",
27
+ "<s_DIAG BLOCK>",
28
+ "</s_DIAG BLOCK>",
29
+ "<s_WEIGHT>",
30
+ "</s_WEIGHT>",
31
+ "<s_TEMP>",
32
+ "</s_TEMP>",
33
+ "<s_HISTORY>",
34
+ "</s_HISTORY>",
35
+ "<s_DIAGNOSIS>",
36
+ "</s_DIAGNOSIS>",
37
+ "<s_BP>",
38
+ "</s_BP>",
39
+ "<s>",
40
+ "</s>"
41
+ ],
42
+ "bos_token": "<s>",
43
+ "cls_token": "<s>",
44
+ "eos_token": "</s>",
45
+ "mask_token": {
46
+ "content": "<mask>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "unk_token": "<unk>"
55
+ }
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
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }