larabe commited on
Commit
12cfda9
1 Parent(s): f024b6a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: scandoc1
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # scandoc1
14
+
15
+ This model is a fine-tuned version of [naver-clova-ix/donut-base-finetuned-cord-v2](https://huggingface.co/naver-clova-ix/donut-base-finetuned-cord-v2) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 0.0002
35
+ - train_batch_size: 6
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 15
41
+
42
+ ### Framework versions
43
+
44
+ - Transformers 4.30.1
45
+ - Pytorch 2.0.1+cu117
46
+ - Datasets 2.14.0
47
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_cashprice>": 57549,
3
+ "</s_changeprice>": 57551,
4
+ "</s_cnt>": 57529,
5
+ "</s_creditcardprice>": 57563,
6
+ "</s_discount_price>": 57557,
7
+ "</s_discountprice>": 57567,
8
+ "</s_emoneyprice>": 57569,
9
+ "</s_etc>": 57541,
10
+ "</s_itemsubtotal>": 57577,
11
+ "</s_menu>": 57525,
12
+ "</s_menuqty_cnt>": 57555,
13
+ "</s_menutype_cnt>": 57553,
14
+ "</s_nm>": 57527,
15
+ "</s_num>": 57565,
16
+ "</s_othersvc_price>": 57573,
17
+ "</s_price>": 57531,
18
+ "</s_service_price>": 57537,
19
+ "</s_sub>": 57547,
20
+ "</s_sub_total>": 57533,
21
+ "</s_subtotal_price>": 57535,
22
+ "</s_tax_price>": 57539,
23
+ "</s_total>": 57543,
24
+ "</s_total_etc>": 57561,
25
+ "</s_total_price>": 57545,
26
+ "</s_unitprice>": 57559,
27
+ "</s_vatyn>": 57575,
28
+ "</s_void_menu>": 57571,
29
+ "<s_cashprice>": 57550,
30
+ "<s_changeprice>": 57552,
31
+ "<s_cnt>": 57530,
32
+ "<s_cord-v2>": 57579,
33
+ "<s_creditcardprice>": 57564,
34
+ "<s_discount_price>": 57558,
35
+ "<s_discountprice>": 57568,
36
+ "<s_emoneyprice>": 57570,
37
+ "<s_etc>": 57542,
38
+ "<s_iitcdip>": 57523,
39
+ "<s_itemsubtotal>": 57578,
40
+ "<s_menu>": 57526,
41
+ "<s_menuqty_cnt>": 57556,
42
+ "<s_menutype_cnt>": 57554,
43
+ "<s_nm>": 57528,
44
+ "<s_num>": 57566,
45
+ "<s_othersvc_price>": 57574,
46
+ "<s_price>": 57532,
47
+ "<s_service_price>": 57538,
48
+ "<s_sub>": 57548,
49
+ "<s_sub_total>": 57534,
50
+ "<s_subtotal_price>": 57536,
51
+ "<s_synthdog>": 57524,
52
+ "<s_tax_price>": 57540,
53
+ "<s_total>": 57544,
54
+ "<s_total_etc>": 57562,
55
+ "<s_total_price>": 57546,
56
+ "<s_unitprice>": 57560,
57
+ "<s_vatyn>": 57576,
58
+ "<s_void_menu>": 57572,
59
+ "<sep/>": 57522
60
+ }
config.json CHANGED
@@ -50,7 +50,7 @@
50
  "LABEL_1": 1
51
  },
52
  "length_penalty": 1.0,
53
- "max_length": 512,
54
  "max_position_embeddings": 768,
55
  "min_length": 0,
56
  "model_type": "mbart",
@@ -89,7 +89,6 @@
89
  "use_cache": true,
90
  "vocab_size": 57580
91
  },
92
- "decoder_start_token_id": 0,
93
  "encoder": {
94
  "_name_or_path": "",
95
  "add_cross_attention": false,
@@ -126,8 +125,8 @@
126
  "1": "LABEL_1"
127
  },
128
  "image_size": [
129
- 960,
130
- 720
131
  ],
132
  "initializer_range": 0.02,
133
  "is_decoder": false,
@@ -188,7 +187,6 @@
188
  },
189
  "is_encoder_decoder": true,
190
  "model_type": "vision-encoder-decoder",
191
- "pad_token_id": 1,
192
  "tie_word_embeddings": false,
193
  "torch_dtype": "float32",
194
  "transformers_version": null
 
50
  "LABEL_1": 1
51
  },
52
  "length_penalty": 1.0,
53
+ "max_length": 20,
54
  "max_position_embeddings": 768,
55
  "min_length": 0,
56
  "model_type": "mbart",
 
89
  "use_cache": true,
90
  "vocab_size": 57580
91
  },
 
92
  "encoder": {
93
  "_name_or_path": "",
94
  "add_cross_attention": false,
 
125
  "1": "LABEL_1"
126
  },
127
  "image_size": [
128
+ 1280,
129
+ 960
130
  ],
131
  "initializer_range": 0.02,
132
  "is_decoder": false,
 
187
  },
188
  "is_encoder_decoder": true,
189
  "model_type": "vision-encoder-decoder",
 
190
  "tie_word_embeddings": false,
191
  "torch_dtype": "float32",
192
  "transformers_version": null
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": "4.30.1"
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
+ "height": 960,
24
+ "width": 720
25
+ }
26
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a0f00335f30a19bbc2845d01f93779b33ae7ae59476ba49f26ecb189ae5d8f5
3
  size 806258457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e6f8a0ae0a9b36933eaea91a910275474ff67f261e58105ef65ebe86e0337e
3
  size 806258457
runs/Aug13_17-34-50_ip-172-31-42-230.eu-central-1.compute.internal/events.out.tfevents.1691948108.ip-172-31-42-230.eu-central-1.compute.internal.15918.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:378cf71452df94503f4099d403703414bcea043fbdd0a1c4e286ea565183bbcf
3
- size 24317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db52aa91bd6e9ce2c7d1590898b23ad899a7730194a1611e8a8d57ead9d9441
3
+ size 24797
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "</s>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
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
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8481c317972633f30159576204455afe991a42423633be7169220f27f79cea82
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e121233480fceb68565cfa91e9a2a60082503bcd24d86b164baca7f3ff7e1649
3
  size 4155