dreeven commited on
Commit
74516a9
·
1 Parent(s): 2a8a7ba

End of training

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: naver-clova-ix/donut-base-finetuned-rvlcdip
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: hand_vs_machine
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # hand_vs_machine
15
+
16
+ This model is a fine-tuned version of [naver-clova-ix/donut-base-finetuned-rvlcdip](https://huggingface.co/naver-clova-ix/donut-base-finetuned-rvlcdip) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 2
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 10
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.35.0.dev0
50
+ - Pytorch 2.0.1+cu118
51
+ - Datasets 2.14.5
52
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "</s_class>": 57523,
4
+ "<advertisement/>": 57524,
5
+ "<budget/>": 57525,
6
+ "<email/>": 57526,
7
+ "<file_folder/>": 57527,
8
+ "<form/>": 57528,
9
+ "<hand/>": 57544,
10
+ "<handwritten/>": 57529,
11
+ "<invoice/>": 57530,
12
+ "<letter/>": 57531,
13
+ "<machine/>": 57545,
14
+ "<mask>": 57521,
15
+ "<memo/>": 57532,
16
+ "<news_article/>": 57533,
17
+ "<pad>": 1,
18
+ "<presentation/>": 57534,
19
+ "<questionnaire/>": 57535,
20
+ "<resume/>": 57536,
21
+ "<s>": 0,
22
+ "<s_class>": 57537,
23
+ "<s_iitcdip>": 57538,
24
+ "<s_rvlcdip>": 57539,
25
+ "<s_synthdog>": 57540,
26
+ "<scientific_publication/>": 57541,
27
+ "<scientific_report/>": 57542,
28
+ "<sep/>": 57522,
29
+ "<specification/>": 57543,
30
+ "<unk>": 3
31
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "max_length": 8,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.35.0.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
+ 960,
24
+ 1280
25
+ ]
26
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8b5e4271627f954326436e7c6f68d7259d3de1da9b5061ac3ec7c1fb728224f
3
  size 803006233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207109bd646bffd2457212cd65e1583000a9a4556c5df668dbabd7201d94cd35
3
  size 803006233
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</s_class>",
4
+ "<advertisement/>",
5
+ "<budget/>",
6
+ "<email/>",
7
+ "<file_folder/>",
8
+ "<form/>",
9
+ "<handwritten/>",
10
+ "<invoice/>",
11
+ "<letter/>",
12
+ "<memo/>",
13
+ "<news_article/>",
14
+ "<presentation/>",
15
+ "<questionnaire/>",
16
+ "<resume/>",
17
+ "<s_class>",
18
+ "<s_iitcdip>",
19
+ "<s_rvlcdip>",
20
+ "<s_synthdog>",
21
+ "<scientific_publication/>",
22
+ "<scientific_report/>",
23
+ "<specification/>"
24
+ ],
25
+ "bos_token": "<s>",
26
+ "cls_token": "<s>",
27
+ "eos_token": "</s>",
28
+ "mask_token": "<mask>",
29
+ "pad_token": "<pad>",
30
+ "sep_token": "</s>",
31
+ "unk_token": "<unk>"
32
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "57521": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "57522": {
44
+ "content": "<sep/>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "57523": {
52
+ "content": "</s_class>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "57524": {
60
+ "content": "<advertisement/>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<budget/>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "<email/>",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<file_folder/>",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "<form/>",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<handwritten/>",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "<invoice/>",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<letter/>",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "<memo/>",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<news_article/>",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "<presentation/>",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<questionnaire/>",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "<resume/>",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_class>",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "57538": {
172
+ "content": "<s_iitcdip>",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_rvlcdip>",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "57540": {
188
+ "content": "<s_synthdog>",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<scientific_publication/>",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "<scientific_report/>",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<specification/>",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "<hand/>",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "57545": {
228
+ "content": "<machine/>",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ }
235
+ },
236
+ "additional_special_tokens": [
237
+ "</s_class>",
238
+ "<advertisement/>",
239
+ "<budget/>",
240
+ "<email/>",
241
+ "<file_folder/>",
242
+ "<form/>",
243
+ "<handwritten/>",
244
+ "<invoice/>",
245
+ "<letter/>",
246
+ "<memo/>",
247
+ "<news_article/>",
248
+ "<presentation/>",
249
+ "<questionnaire/>",
250
+ "<resume/>",
251
+ "<s_class>",
252
+ "<s_iitcdip>",
253
+ "<s_rvlcdip>",
254
+ "<s_synthdog>",
255
+ "<scientific_publication/>",
256
+ "<scientific_report/>",
257
+ "<specification/>"
258
+ ],
259
+ "bos_token": "<s>",
260
+ "clean_up_tokenization_spaces": true,
261
+ "cls_token": "<s>",
262
+ "eos_token": "</s>",
263
+ "mask_token": "<mask>",
264
+ "model_max_length": 1000000000000000019884624838656,
265
+ "pad_token": "<pad>",
266
+ "processor_class": "DonutProcessor",
267
+ "sep_token": "</s>",
268
+ "sp_model_kwargs": {},
269
+ "tokenizer_class": "XLMRobertaTokenizer",
270
+ "unk_token": "<unk>"
271
+ }