Manab commited on
Commit
70e81d1
1 Parent(s): 7793542

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: Manab/donut-base-my_model_rapido_2_new_check_2
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ model-index:
9
+ - name: donut-base-my_model_rapido_2_new_check_3
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-my_model_rapido_2_new_check_3
17
+
18
+ This model is a fine-tuned version of [Manab/donut-base-my_model_rapido_2_new_check_2](https://huggingface.co/Manab/donut-base-my_model_rapido_2_new_check_2) on the imagefolder dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.3896
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 8
42
+ - seed: 42
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
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.8694 | 0.69 | 50 | 2.0758 |
52
+ | 2.2421 | 1.39 | 100 | 1.7321 |
53
+ | 1.6972 | 2.08 | 150 | 1.4280 |
54
+ | 1.5866 | 2.78 | 200 | 1.3896 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.31.0.dev0
60
+ - Pytorch 2.0.1+cu118
61
+ - Datasets 2.13.1
62
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Buyer Address>": 57538,
3
+ "</s_Buyer Name>": 57536,
4
+ "</s_Company Address>": 57534,
5
+ "</s_Company Name>": 57550,
6
+ "</s_Description_1>": 57548,
7
+ "</s_Description_1_price>": 57546,
8
+ "</s_Description_2>": 57544,
9
+ "</s_Description_2_price>": 57542,
10
+ "</s_Invoice Date>": 57532,
11
+ "</s_Invoice Number>": 57530,
12
+ "</s_Payment_details>": 57528,
13
+ "</s_Time of Buying>": 57540,
14
+ "</s_Total_price>": 57526,
15
+ "<s_Buyer Address>": 57537,
16
+ "<s_Buyer Name>": 57535,
17
+ "<s_Company Address>": 57533,
18
+ "<s_Company Name>": 57549,
19
+ "<s_Description_1>": 57547,
20
+ "<s_Description_1_price>": 57545,
21
+ "<s_Description_2>": 57543,
22
+ "<s_Description_2_price>": 57541,
23
+ "<s_Invoice Date>": 57531,
24
+ "<s_Invoice Number>": 57529,
25
+ "<s_Payment_details>": 57527,
26
+ "<s_Time of Buying>": 57539,
27
+ "<s_Total_price>": 57525,
28
+ "<s_iitcdip>": 57523,
29
+ "<s_synthdog>": 57524,
30
+ "<sep/>": 57522
31
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "max_length": 512,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.31.0.dev0"
10
+ }
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
+ "height": 960,
24
+ "width": 720
25
+ }
26
+ }
runs/Jul07_21-05-53_f4aabf8a5de8/events.out.tfevents.1688763958.f4aabf8a5de8.9489.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c11567d9b72f55f5e4b035ff5307f80e1cb11d70b65f889f02cae1f0bea76f3
3
- size 10406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7cfadd1d16732109de9ad5482fde7c28df009968c139feb6632ad47a62e0c3e
3
+ size 10760
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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_Total_price>",
4
+ "</s_Total_price>",
5
+ "<s_Payment_details>",
6
+ "</s_Payment_details>",
7
+ "<s_Invoice Number>",
8
+ "</s_Invoice Number>",
9
+ "<s_Invoice Date>",
10
+ "</s_Invoice Date>",
11
+ "<s_Company Address>",
12
+ "</s_Company Address>",
13
+ "<s_Buyer Name>",
14
+ "</s_Buyer Name>",
15
+ "<s_Buyer Address>",
16
+ "</s_Buyer Address>",
17
+ "<s_Time of Buying>",
18
+ "</s_Time of Buying>",
19
+ "<s_Description_2_price>",
20
+ "</s_Description_2_price>",
21
+ "<s_Description_2>",
22
+ "</s_Description_2>",
23
+ "<s_Description_1_price>",
24
+ "</s_Description_1_price>",
25
+ "<s_Description_1>",
26
+ "</s_Description_1>",
27
+ "<s_Company Name>",
28
+ "</s_Company Name>",
29
+ "<s>",
30
+ "</s>"
31
+ ],
32
+ "bos_token": "<s>",
33
+ "cls_token": "<s>",
34
+ "eos_token": "</s>",
35
+ "mask_token": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "pad_token": "<pad>",
43
+ "sep_token": "</s>",
44
+ "unk_token": "<unk>"
45
+ }
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
+ }