tanner-next commited on
Commit
fcac1ef
·
1 Parent(s): 0e9262a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-exp-sroie
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-exp-sroie
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
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 8
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.31.0
54
+ - Pytorch 2.0.1+cu118
55
+ - Datasets 2.14.4
56
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_chassisNumber>": 57532,
3
+ "</s_containerNumber>": 57530,
4
+ "</s_deliveryLocation>": 57536,
5
+ "</s_pickupLocation>": 57534,
6
+ "</s_shipLine>": 57528,
7
+ "</s_timestamp>": 57526,
8
+ "<s_chassisNumber>": 57531,
9
+ "<s_containerNumber>": 57529,
10
+ "<s_deliveryLocation>": 57535,
11
+ "<s_iitcdip>": 57523,
12
+ "<s_pickupLocation>": 57533,
13
+ "<s_shipLine>": 57527,
14
+ "<s_synthdog>": 57524,
15
+ "<s_timestamp>": 57525,
16
+ "<sep/>": 57522
17
+ }
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": "4.31.0"
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
+ 512,
24
+ 512
25
+ ]
26
+ }
runs/Aug18_20-57-50_2946e612ad63/events.out.tfevents.1692392279.2946e612ad63.22776.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2032acf20c2b7f1eb4789f6b9093fcea383c0742c4e009c87ca2dd21c59b3568
3
- size 8611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96acfdb6a9311f13e42ab93f3d0455676e3294a690a06cadf9f026ae2ea1163c
3
+ size 8959
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_timestamp>",
4
+ "</s_timestamp>",
5
+ "<s_shipLine>",
6
+ "</s_shipLine>",
7
+ "<s_containerNumber>",
8
+ "</s_containerNumber>",
9
+ "<s_chassisNumber>",
10
+ "</s_chassisNumber>",
11
+ "<s_pickupLocation>",
12
+ "</s_pickupLocation>",
13
+ "<s_deliveryLocation>",
14
+ "</s_deliveryLocation>",
15
+ "<s>",
16
+ "</s>"
17
+ ],
18
+ "bos_token": "<s>",
19
+ "cls_token": "<s>",
20
+ "eos_token": "</s>",
21
+ "mask_token": {
22
+ "content": "<mask>",
23
+ "lstrip": true,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": "<pad>",
29
+ "sep_token": "</s>",
30
+ "unk_token": "<unk>"
31
+ }
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
+ }