Hugging Face's logo

Medxa
/
donut-paper-ktp

Image-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
Metrics Community
aryaadhi commited on
Commit
93af6ee
·
verified ·
1 Parent(s): 0feb383

End of training

Browse files
Files changed (7) hide show
  1. README.md +9 -6
  2. added_tokens.json +39 -0
  3. preprocessor_config.json +26 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +305 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +391 -0
README.md CHANGED
@@ -18,12 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  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.
20
  It achieves the following results on the evaluation set:
21
- - eval_loss: 9.1576
22
- - eval_runtime: 9.5484
23
- - eval_samples_per_second: 0.524
24
- - eval_steps_per_second: 0.105
25
- - epoch: 1.0
26
- - step: 20
27
 
28
  ## Model description
29
 
@@ -50,6 +45,14 @@ The following hyperparameters were used during training:
50
  - lr_scheduler_type: linear
51
  - num_epochs: 2
52
 
 
 
 
 
 
 
 
 
53
  ### Framework versions
54
 
55
  - Transformers 4.52.4
 
18
 
19
  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.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 8.6434
 
 
 
 
 
22
 
23
  ## Model description
24
 
 
45
  - lr_scheduler_type: linear
46
  - num_epochs: 2
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 20 | 9.1576 |
53
+ | No log | 2.0 | 40 | 8.6434 |
54
+
55
+
56
  ### Framework versions
57
 
58
  - Transformers 4.52.4
added_tokens.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_agama>": 57558,
3
+ "</s_alamat>": 57556,
4
+ "</s_berlaku>": 57554,
5
+ "</s_gol_darah>": 57552,
6
+ "</s_jkel>": 57550,
7
+ "</s_kabkota_issuer>": 57548,
8
+ "</s_kecamatan>": 57546,
9
+ "</s_kelurahan>": 57544,
10
+ "</s_nama>": 57542,
11
+ "</s_nik>": 57540,
12
+ "</s_pekerjaan>": 57538,
13
+ "</s_prov_issuer>": 57536,
14
+ "</s_rt_rw>": 57534,
15
+ "</s_status_kawin>": 57532,
16
+ "</s_tgl_terbit>": 57530,
17
+ "</s_ttl>": 57528,
18
+ "</s_wn>": 57526,
19
+ "<s_agama>": 57557,
20
+ "<s_alamat>": 57555,
21
+ "<s_berlaku>": 57553,
22
+ "<s_gol_darah>": 57551,
23
+ "<s_iitcdip>": 57523,
24
+ "<s_jkel>": 57549,
25
+ "<s_kabkota_issuer>": 57547,
26
+ "<s_kecamatan>": 57545,
27
+ "<s_kelurahan>": 57543,
28
+ "<s_nama>": 57541,
29
+ "<s_nik>": 57539,
30
+ "<s_pekerjaan>": 57537,
31
+ "<s_prov_issuer>": 57535,
32
+ "<s_rt_rw>": 57533,
33
+ "<s_status_kawin>": 57531,
34
+ "<s_synthdog>": 57524,
35
+ "<s_tgl_terbit>": 57529,
36
+ "<s_ttl>": 57527,
37
+ "<s_wn>": 57525,
38
+ "<sep/>": 57522
39
+ }
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
+ 1024,
24
+ 768
25
+ ]
26
+ }
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 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s_wn>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s_wn>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s_ttl>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s_ttl>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s_tgl_terbit>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s_tgl_terbit>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_status_kawin>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s_status_kawin>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s_rt_rw>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s_rt_rw>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s_prov_issuer>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s_prov_issuer>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<s_pekerjaan>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "</s_pekerjaan>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<s_nik>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "</s_nik>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<s_nama>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "</s_nama>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<s_kelurahan>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "</s_kelurahan>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s_kecamatan>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s_kecamatan>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<s_kabkota_issuer>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "</s_kabkota_issuer>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<s_jkel>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "</s_jkel>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<s_gol_darah>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "</s_gol_darah>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<s_berlaku>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "</s_berlaku>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<s_alamat>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "</s_alamat>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<s_agama>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "</s_agama>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<s>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "</s>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ }
255
+ ],
256
+ "bos_token": {
257
+ "content": "<s>",
258
+ "lstrip": false,
259
+ "normalized": false,
260
+ "rstrip": false,
261
+ "single_word": false
262
+ },
263
+ "cls_token": {
264
+ "content": "<s>",
265
+ "lstrip": false,
266
+ "normalized": false,
267
+ "rstrip": false,
268
+ "single_word": false
269
+ },
270
+ "eos_token": {
271
+ "content": "</s>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false
276
+ },
277
+ "mask_token": {
278
+ "content": "<mask>",
279
+ "lstrip": true,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false
283
+ },
284
+ "pad_token": {
285
+ "content": "<pad>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false
290
+ },
291
+ "sep_token": {
292
+ "content": "</s>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false
297
+ },
298
+ "unk_token": {
299
+ "content": "<unk>",
300
+ "lstrip": false,
301
+ "normalized": false,
302
+ "rstrip": false,
303
+ "single_word": false
304
+ }
305
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_iitcdip>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "57524": {
60
+ "content": "<s_synthdog>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<s_wn>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_wn>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<s_ttl>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_ttl>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<s_tgl_terbit>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_tgl_terbit>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<s_status_kawin>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_status_kawin>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<s_rt_rw>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "</s_rt_rw>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<s_prov_issuer>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "</s_prov_issuer>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_pekerjaan>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "</s_pekerjaan>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_nik>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "</s_nik>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<s_nama>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "</s_nama>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<s_kelurahan>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "</s_kelurahan>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "57545": {
228
+ "content": "<s_kecamatan>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "57546": {
236
+ "content": "</s_kecamatan>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "57547": {
244
+ "content": "<s_kabkota_issuer>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "57548": {
252
+ "content": "</s_kabkota_issuer>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57549": {
260
+ "content": "<s_jkel>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "57550": {
268
+ "content": "</s_jkel>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "57551": {
276
+ "content": "<s_gol_darah>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "57552": {
284
+ "content": "</s_gol_darah>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "57553": {
292
+ "content": "<s_berlaku>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "57554": {
300
+ "content": "</s_berlaku>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "57555": {
308
+ "content": "<s_alamat>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "57556": {
316
+ "content": "</s_alamat>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "57557": {
324
+ "content": "<s_agama>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "57558": {
332
+ "content": "</s_agama>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ }
339
+ },
340
+ "additional_special_tokens": [
341
+ "<s_wn>",
342
+ "</s_wn>",
343
+ "<s_ttl>",
344
+ "</s_ttl>",
345
+ "<s_tgl_terbit>",
346
+ "</s_tgl_terbit>",
347
+ "<s_status_kawin>",
348
+ "</s_status_kawin>",
349
+ "<s_rt_rw>",
350
+ "</s_rt_rw>",
351
+ "<s_prov_issuer>",
352
+ "</s_prov_issuer>",
353
+ "<s_pekerjaan>",
354
+ "</s_pekerjaan>",
355
+ "<s_nik>",
356
+ "</s_nik>",
357
+ "<s_nama>",
358
+ "</s_nama>",
359
+ "<s_kelurahan>",
360
+ "</s_kelurahan>",
361
+ "<s_kecamatan>",
362
+ "</s_kecamatan>",
363
+ "<s_kabkota_issuer>",
364
+ "</s_kabkota_issuer>",
365
+ "<s_jkel>",
366
+ "</s_jkel>",
367
+ "<s_gol_darah>",
368
+ "</s_gol_darah>",
369
+ "<s_berlaku>",
370
+ "</s_berlaku>",
371
+ "<s_alamat>",
372
+ "</s_alamat>",
373
+ "<s_agama>",
374
+ "</s_agama>",
375
+ "<s>",
376
+ "</s>"
377
+ ],
378
+ "bos_token": "<s>",
379
+ "clean_up_tokenization_spaces": false,
380
+ "cls_token": "<s>",
381
+ "eos_token": "</s>",
382
+ "extra_special_tokens": {},
383
+ "mask_token": "<mask>",
384
+ "model_max_length": 1000000000000000019884624838656,
385
+ "pad_token": "<pad>",
386
+ "processor_class": "DonutProcessor",
387
+ "sep_token": "</s>",
388
+ "sp_model_kwargs": {},
389
+ "tokenizer_class": "XLMRobertaTokenizer",
390
+ "unk_token": "<unk>"
391
+ }