Javeria98 commited on
Commit
5781491
·
1 Parent(s): ba29b80

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: donut-base-Medical_Model_final
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-Medical_Model_final
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: 25
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.30.0.dev0
52
+ - Pytorch 2.0.1+cu118
53
+ - Datasets 2.12.0
54
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_AGE>": 57544,
3
+ "</s_Age>": 57580,
4
+ "</s_BP>": 57542,
5
+ "</s_Block1>": 57540,
6
+ "</s_Block2>": 57538,
7
+ "</s_Block3>": 57532,
8
+ "</s_Block4>": 57546,
9
+ "</s_Block5>": 57586,
10
+ "</s_DIAGNOSIS>": 57530,
11
+ "</s_DIGNOSIS>": 57558,
12
+ "</s_Date>": 57572,
13
+ "</s_Diagnosis>": 57570,
14
+ "</s_GENDER>": 57588,
15
+ "</s_Gender>": 57568,
16
+ "</s_HEADER>": 57552,
17
+ "</s_History>": 57566,
18
+ "</s_MEDICINE_NAME>": 57536,
19
+ "</s_MEDICINE_POWER>": 57548,
20
+ "</s_MEDICINE_TYPE >": 57556,
21
+ "</s_MEDICINE_TYPE>": 57534,
22
+ "</s_MMEDICINE_POWER>": 57584,
23
+ "</s_Medicine Dose>": 57578,
24
+ "</s_Medicine Name>": 57576,
25
+ "</s_Medicine Power>": 57560,
26
+ "</s_Medicine Type>": 57574,
27
+ "</s_NAME >": 57582,
28
+ "</s_NAME>": 57528,
29
+ "</s_Name>": 57554,
30
+ "</s_TEMP>": 57526,
31
+ "</s_Temp>": 57564,
32
+ "</s_WEIGHT>": 57550,
33
+ "</s_Weight>": 57562,
34
+ "<s_AGE>": 57543,
35
+ "<s_Age>": 57579,
36
+ "<s_BP>": 57541,
37
+ "<s_Block1>": 57539,
38
+ "<s_Block2>": 57537,
39
+ "<s_Block3>": 57531,
40
+ "<s_Block4>": 57545,
41
+ "<s_Block5>": 57585,
42
+ "<s_DIAGNOSIS>": 57529,
43
+ "<s_DIGNOSIS>": 57557,
44
+ "<s_Date>": 57571,
45
+ "<s_Diagnosis>": 57569,
46
+ "<s_GENDER>": 57587,
47
+ "<s_Gender>": 57567,
48
+ "<s_HEADER>": 57551,
49
+ "<s_History>": 57565,
50
+ "<s_MEDICINE_NAME>": 57535,
51
+ "<s_MEDICINE_POWER>": 57547,
52
+ "<s_MEDICINE_TYPE >": 57555,
53
+ "<s_MEDICINE_TYPE>": 57533,
54
+ "<s_MMEDICINE_POWER>": 57583,
55
+ "<s_Medicine Dose>": 57577,
56
+ "<s_Medicine Name>": 57575,
57
+ "<s_Medicine Power>": 57559,
58
+ "<s_Medicine Type>": 57573,
59
+ "<s_NAME >": 57581,
60
+ "<s_NAME>": 57527,
61
+ "<s_Name>": 57553,
62
+ "<s_TEMP>": 57525,
63
+ "<s_Temp>": 57563,
64
+ "<s_WEIGHT>": 57549,
65
+ "<s_Weight>": 57561,
66
+ "<s_iitcdip>": 57523,
67
+ "<s_synthdog>": 57524,
68
+ "<sep/>": 57522
69
+ }
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": "4.30.0.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/May26_05-47-20_b572fe2b18e4/events.out.tfevents.1685080054.b572fe2b18e4.668.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d3d7e857374524936a8b2ad100f3b88be41f7cd65c0826e2613b7a207fa869b
3
- size 12073
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeedd366eda04594a6d3ae065d87e9edf8ac8d095ec8b0a4971affdef2d8847e
3
+ size 12427
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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_TEMP>",
4
+ "</s_TEMP>",
5
+ "<s_NAME>",
6
+ "</s_NAME>",
7
+ "<s_DIAGNOSIS>",
8
+ "</s_DIAGNOSIS>",
9
+ "<s_Block3>",
10
+ "</s_Block3>",
11
+ "<s_MEDICINE_TYPE>",
12
+ "</s_MEDICINE_TYPE>",
13
+ "<s_MEDICINE_NAME>",
14
+ "</s_MEDICINE_NAME>",
15
+ "<s_Block2>",
16
+ "</s_Block2>",
17
+ "<s_Block1>",
18
+ "</s_Block1>",
19
+ "<s_BP>",
20
+ "</s_BP>",
21
+ "<s_AGE>",
22
+ "</s_AGE>",
23
+ "<s_Block4>",
24
+ "</s_Block4>",
25
+ "<s_MEDICINE_POWER>",
26
+ "</s_MEDICINE_POWER>",
27
+ "<s_WEIGHT>",
28
+ "</s_WEIGHT>",
29
+ "<s_HEADER>",
30
+ "</s_HEADER>",
31
+ "<s_Name>",
32
+ "</s_Name>",
33
+ "<s_MEDICINE_TYPE >",
34
+ "</s_MEDICINE_TYPE >",
35
+ "<s_DIGNOSIS>",
36
+ "</s_DIGNOSIS>",
37
+ "<s_Medicine Power>",
38
+ "</s_Medicine Power>",
39
+ "<s_Weight>",
40
+ "</s_Weight>",
41
+ "<s_Temp>",
42
+ "</s_Temp>",
43
+ "<s_History>",
44
+ "</s_History>",
45
+ "<s_Gender>",
46
+ "</s_Gender>",
47
+ "<s_Diagnosis>",
48
+ "</s_Diagnosis>",
49
+ "<s_Date>",
50
+ "</s_Date>",
51
+ "<s_Medicine Type>",
52
+ "</s_Medicine Type>",
53
+ "<s_Medicine Name>",
54
+ "</s_Medicine Name>",
55
+ "<s_Medicine Dose>",
56
+ "</s_Medicine Dose>",
57
+ "<s_Age>",
58
+ "</s_Age>",
59
+ "<s_NAME >",
60
+ "</s_NAME >",
61
+ "<s_MMEDICINE_POWER>",
62
+ "</s_MMEDICINE_POWER>",
63
+ "<s_Block5>",
64
+ "</s_Block5>",
65
+ "<s_GENDER>",
66
+ "</s_GENDER>",
67
+ "<s>",
68
+ "</s>"
69
+ ],
70
+ "bos_token": "<s>",
71
+ "cls_token": "<s>",
72
+ "eos_token": "</s>",
73
+ "mask_token": {
74
+ "content": "<mask>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "unk_token": "<unk>"
83
+ }
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
+ }