Manab commited on
Commit
75a3005
·
1 Parent(s): 933c36e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: donut-base-my_model_1_new
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-my_model_1_new
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
+ It achieves the following results on the evaluation set:
19
+ - eval_loss: 1.9493
20
+ - eval_runtime: 44.4471
21
+ - eval_samples_per_second: 0.652
22
+ - eval_steps_per_second: 0.09
23
+ - epoch: 4.21
24
+ - step: 1100
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 1e-05
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.31.0.dev0
54
+ - Pytorch 2.0.1+cu118
55
+ - Datasets 2.13.1
56
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Buyer Address>": 57554,
3
+ "</s_Buyer Name>": 57548,
4
+ "</s_Company Address>": 57546,
5
+ "</s_Company Name>": 57544,
6
+ "</s_Description_1>": 57542,
7
+ "</s_Description_1_price>": 57540,
8
+ "</s_Description_2>": 57538,
9
+ "</s_Description_2_price>": 57536,
10
+ "</s_Description_other>": 57552,
11
+ "</s_Description_other_price>": 57550,
12
+ "</s_Invoice Date>": 57534,
13
+ "</s_Invoice Number>": 57532,
14
+ "</s_Payment_details>": 57530,
15
+ "</s_Time of Buying>": 57528,
16
+ "</s_Total_price>": 57526,
17
+ "<s_Buyer Address>": 57553,
18
+ "<s_Buyer Name>": 57547,
19
+ "<s_Company Address>": 57545,
20
+ "<s_Company Name>": 57543,
21
+ "<s_Description_1>": 57541,
22
+ "<s_Description_1_price>": 57539,
23
+ "<s_Description_2>": 57537,
24
+ "<s_Description_2_price>": 57535,
25
+ "<s_Description_other>": 57551,
26
+ "<s_Description_other_price>": 57549,
27
+ "<s_Invoice Date>": 57533,
28
+ "<s_Invoice Number>": 57531,
29
+ "<s_Payment_details>": 57529,
30
+ "<s_Time of Buying>": 57527,
31
+ "<s_Total_price>": 57525,
32
+ "<s_iitcdip>": 57523,
33
+ "<s_synthdog>": 57524,
34
+ "<sep/>": 57522
35
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "max_length": 512,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.31.0.dev0"
9
+ }
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
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b09d7a6bfddfed9dae6bae9acf23c8a44706304d6a5e8ff4a1810933460f517
3
  size 809301785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239a7d54263fda1138effec37c90f12a71c64eebea2bfc9c5cd1cb6ee90585a5
3
  size 809301785
runs/Jul03_04-46-09_c93941b8213c/events.out.tfevents.1688359578.c93941b8213c.1062.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7c6fd02e57171b4a8e2cce7f9fba940b78e7ea370659a113d02f778c6cf6179
3
- size 17174
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8033ea839489b5fa5e809e0e71746dc7b1906a9e4efe8b92902d8bdb30137d69
3
+ size 18030
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_Total_price>",
4
+ "</s_Total_price>",
5
+ "<s_Time of Buying>",
6
+ "</s_Time of Buying>",
7
+ "<s_Payment_details>",
8
+ "</s_Payment_details>",
9
+ "<s_Invoice Number>",
10
+ "</s_Invoice Number>",
11
+ "<s_Invoice Date>",
12
+ "</s_Invoice Date>",
13
+ "<s_Description_2_price>",
14
+ "</s_Description_2_price>",
15
+ "<s_Description_2>",
16
+ "</s_Description_2>",
17
+ "<s_Description_1_price>",
18
+ "</s_Description_1_price>",
19
+ "<s_Description_1>",
20
+ "</s_Description_1>",
21
+ "<s_Company Name>",
22
+ "</s_Company Name>",
23
+ "<s_Company Address>",
24
+ "</s_Company Address>",
25
+ "<s_Buyer Name>",
26
+ "</s_Buyer Name>",
27
+ "<s_Description_other_price>",
28
+ "</s_Description_other_price>",
29
+ "<s_Description_other>",
30
+ "</s_Description_other>",
31
+ "<s_Buyer Address>",
32
+ "</s_Buyer Address>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "cls_token": "<s>",
38
+ "eos_token": "</s>",
39
+ "mask_token": {
40
+ "content": "<mask>",
41
+ "lstrip": true,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "pad_token": "<pad>",
47
+ "sep_token": "</s>",
48
+ "unk_token": "<unk>"
49
+ }
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
+ }