Bienvenu2004 commited on
Commit
564abd1
1 Parent(s): 7df36cb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: naver-clova-ix/donut-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ model-index:
9
+ - name: donut-handball-pv2
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-handball-pv2
17
+
18
+ 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.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 50
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.40.0.dev0
52
+ - Pytorch 2.2.1+cu121
53
+ - Datasets 2.18.0
54
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_competition_name>": 57608,
3
+ "</s_date>": 57606,
4
+ "</s_direct_disqualification>": 57584,
5
+ "</s_federation_official>": 57604,
6
+ "</s_goal>": 57582,
7
+ "</s_hall>": 57602,
8
+ "</s_hour>": 57600,
9
+ "</s_lieu>": 57598,
10
+ "</s_match_number>": 57596,
11
+ "</s_name>": 57544,
12
+ "</s_no>": 57580,
13
+ "</s_number_of_7_a>": 57594,
14
+ "</s_number_of_7_b>": 57592,
15
+ "</s_officials_a>": 57590,
16
+ "</s_officials_b>": 57588,
17
+ "</s_players_a>": 57586,
18
+ "</s_players_b>": 57572,
19
+ "</s_referees>": 57570,
20
+ "</s_remarks>": 57568,
21
+ "</s_report_disqualification>": 57578,
22
+ "</s_score_end_time_a>": 57566,
23
+ "</s_score_end_time_b>": 57564,
24
+ "</s_score_extra_time_1_a>": 57562,
25
+ "</s_score_extra_time_1_b>": 57560,
26
+ "</s_score_extra_time_2_a>": 57558,
27
+ "</s_score_extra_time_2_b>": 57556,
28
+ "</s_score_half_time_a>": 57554,
29
+ "</s_score_half_time_b>": 57552,
30
+ "</s_score_penalty_time_1_a>": 57550,
31
+ "</s_score_penalty_time_1_b>": 57548,
32
+ "</s_spectator>": 57546,
33
+ "</s_sus pension>": 57610,
34
+ "</s_suspension>": 57576,
35
+ "</s_td>": 57542,
36
+ "</s_team_a_name>": 57540,
37
+ "</s_team_b_name>": 57538,
38
+ "</s_team_time_out_a_1>": 57536,
39
+ "</s_team_time_out_a_2>": 57534,
40
+ "</s_team_time_out_a_3>": 57532,
41
+ "</s_team_time_out_b_1>": 57530,
42
+ "</s_team_time_out_b_2>": 57528,
43
+ "</s_team_time_out_b_3>": 57526,
44
+ "</s_warning>": 57574,
45
+ "<s_competition_name>": 57607,
46
+ "<s_date>": 57605,
47
+ "<s_direct_disqualification>": 57583,
48
+ "<s_federation_official>": 57603,
49
+ "<s_goal>": 57581,
50
+ "<s_hall>": 57601,
51
+ "<s_hour>": 57599,
52
+ "<s_iitcdip>": 57523,
53
+ "<s_lieu>": 57597,
54
+ "<s_match_number>": 57595,
55
+ "<s_name>": 57543,
56
+ "<s_no>": 57579,
57
+ "<s_number_of_7_a>": 57593,
58
+ "<s_number_of_7_b>": 57591,
59
+ "<s_officials_a>": 57589,
60
+ "<s_officials_b>": 57587,
61
+ "<s_players_a>": 57585,
62
+ "<s_players_b>": 57571,
63
+ "<s_referees>": 57569,
64
+ "<s_remarks>": 57567,
65
+ "<s_report_disqualification>": 57577,
66
+ "<s_score_end_time_a>": 57565,
67
+ "<s_score_end_time_b>": 57563,
68
+ "<s_score_extra_time_1_a>": 57561,
69
+ "<s_score_extra_time_1_b>": 57559,
70
+ "<s_score_extra_time_2_a>": 57557,
71
+ "<s_score_extra_time_2_b>": 57555,
72
+ "<s_score_half_time_a>": 57553,
73
+ "<s_score_half_time_b>": 57551,
74
+ "<s_score_penalty_time_1_a>": 57549,
75
+ "<s_score_penalty_time_1_b>": 57547,
76
+ "<s_spectator>": 57545,
77
+ "<s_sus pension>": 57609,
78
+ "<s_suspension>": 57575,
79
+ "<s_synthdog>": 57524,
80
+ "<s_td>": 57541,
81
+ "<s_team_a_name>": 57539,
82
+ "<s_team_b_name>": 57537,
83
+ "<s_team_time_out_a_1>": 57535,
84
+ "<s_team_time_out_a_2>": 57533,
85
+ "<s_team_time_out_a_3>": 57531,
86
+ "<s_team_time_out_b_1>": 57529,
87
+ "<s_team_time_out_b_2>": 57527,
88
+ "<s_team_time_out_b_3>": 57525,
89
+ "<s_warning>": 57573,
90
+ "<sep/>": 57522
91
+ }
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": "4.40.0.dev0"
8
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_thumbnail",
8
+ "do_align_long_axis",
9
+ "do_pad",
10
+ "random_padding",
11
+ "do_rescale",
12
+ "rescale_factor",
13
+ "do_normalize",
14
+ "image_mean",
15
+ "image_std",
16
+ "return_tensors",
17
+ "data_format",
18
+ "input_data_format"
19
+ ],
20
+ "do_align_long_axis": false,
21
+ "do_normalize": true,
22
+ "do_pad": true,
23
+ "do_rescale": true,
24
+ "do_resize": true,
25
+ "do_thumbnail": true,
26
+ "image_mean": [
27
+ 0.5,
28
+ 0.5,
29
+ 0.5
30
+ ],
31
+ "image_processor_type": "DonutImageProcessor",
32
+ "image_std": [
33
+ 0.5,
34
+ 0.5,
35
+ 0.5
36
+ ],
37
+ "processor_class": "DonutProcessor",
38
+ "resample": 2,
39
+ "rescale_factor": 0.00392156862745098,
40
+ "size": [
41
+ 720,
42
+ 960
43
+ ]
44
+ }
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 +1,669 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s_team_time_out_b_3>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s_team_time_out_b_3>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s_team_time_out_b_2>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s_team_time_out_b_2>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s_team_time_out_b_1>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s_team_time_out_b_1>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_team_time_out_a_3>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s_team_time_out_a_3>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s_team_time_out_a_2>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s_team_time_out_a_2>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s_team_time_out_a_1>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s_team_time_out_a_1>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<s_team_b_name>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "</s_team_b_name>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<s_team_a_name>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "</s_team_a_name>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<s_td>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "</s_td>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<s_name>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "</s_name>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s_spectator>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s_spectator>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<s_score_penalty_time_1_b>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "</s_score_penalty_time_1_b>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<s_score_penalty_time_1_a>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "</s_score_penalty_time_1_a>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<s_score_half_time_b>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "</s_score_half_time_b>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<s_score_half_time_a>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "</s_score_half_time_a>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<s_score_extra_time_2_b>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "</s_score_extra_time_2_b>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<s_score_extra_time_2_a>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "</s_score_extra_time_2_a>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<s_score_extra_time_1_b>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "</s_score_extra_time_1_b>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<s_score_extra_time_1_a>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "</s_score_extra_time_1_a>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<s_score_end_time_b>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "</s_score_end_time_b>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<s_score_end_time_a>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "</s_score_end_time_a>",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<s_remarks>",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "</s_remarks>",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<s_referees>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "</s_referees>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<s_players_b>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "</s_players_b>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<s_warning>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "</s_warning>",
348
+ "lstrip": false,
349
+ "normalized": false,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<s_suspension>",
355
+ "lstrip": false,
356
+ "normalized": false,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "</s_suspension>",
362
+ "lstrip": false,
363
+ "normalized": false,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<s_report_disqualification>",
369
+ "lstrip": false,
370
+ "normalized": false,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "</s_report_disqualification>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<s_no>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "</s_no>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<s_goal>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "</s_goal>",
404
+ "lstrip": false,
405
+ "normalized": false,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<s_direct_disqualification>",
411
+ "lstrip": false,
412
+ "normalized": false,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "</s_direct_disqualification>",
418
+ "lstrip": false,
419
+ "normalized": false,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<s_players_a>",
425
+ "lstrip": false,
426
+ "normalized": false,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "</s_players_a>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<s_officials_b>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "</s_officials_b>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<s_officials_a>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "</s_officials_a>",
460
+ "lstrip": false,
461
+ "normalized": false,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<s_number_of_7_b>",
467
+ "lstrip": false,
468
+ "normalized": false,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "</s_number_of_7_b>",
474
+ "lstrip": false,
475
+ "normalized": false,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<s_number_of_7_a>",
481
+ "lstrip": false,
482
+ "normalized": false,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "</s_number_of_7_a>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<s_match_number>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "</s_match_number>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<s_lieu>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "</s_lieu>",
516
+ "lstrip": false,
517
+ "normalized": false,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<s_hour>",
523
+ "lstrip": false,
524
+ "normalized": false,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "</s_hour>",
530
+ "lstrip": false,
531
+ "normalized": false,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<s_hall>",
537
+ "lstrip": false,
538
+ "normalized": false,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "</s_hall>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<s_federation_official>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "</s_federation_official>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<s_date>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "</s_date>",
572
+ "lstrip": false,
573
+ "normalized": false,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<s_competition_name>",
579
+ "lstrip": false,
580
+ "normalized": false,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "</s_competition_name>",
586
+ "lstrip": false,
587
+ "normalized": false,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<s_sus pension>",
593
+ "lstrip": false,
594
+ "normalized": false,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "</s_sus pension>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<s>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "</s>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ }
619
+ ],
620
+ "bos_token": {
621
+ "content": "<s>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false
626
+ },
627
+ "cls_token": {
628
+ "content": "<s>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false
633
+ },
634
+ "eos_token": {
635
+ "content": "</s>",
636
+ "lstrip": false,
637
+ "normalized": false,
638
+ "rstrip": false,
639
+ "single_word": false
640
+ },
641
+ "mask_token": {
642
+ "content": "<mask>",
643
+ "lstrip": true,
644
+ "normalized": true,
645
+ "rstrip": false,
646
+ "single_word": false
647
+ },
648
+ "pad_token": {
649
+ "content": "<pad>",
650
+ "lstrip": false,
651
+ "normalized": false,
652
+ "rstrip": false,
653
+ "single_word": false
654
+ },
655
+ "sep_token": {
656
+ "content": "</s>",
657
+ "lstrip": false,
658
+ "normalized": false,
659
+ "rstrip": false,
660
+ "single_word": false
661
+ },
662
+ "unk_token": {
663
+ "content": "<unk>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false
668
+ }
669
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,858 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_team_time_out_b_3>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_team_time_out_b_3>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<s_team_time_out_b_2>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_team_time_out_b_2>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<s_team_time_out_b_1>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_team_time_out_b_1>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<s_team_time_out_a_3>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_team_time_out_a_3>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<s_team_time_out_a_2>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "</s_team_time_out_a_2>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<s_team_time_out_a_1>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "</s_team_time_out_a_1>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_team_b_name>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "</s_team_b_name>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_team_a_name>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "</s_team_a_name>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<s_td>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "</s_td>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<s_name>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "</s_name>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "57545": {
228
+ "content": "<s_spectator>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "57546": {
236
+ "content": "</s_spectator>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "57547": {
244
+ "content": "<s_score_penalty_time_1_b>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "57548": {
252
+ "content": "</s_score_penalty_time_1_b>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57549": {
260
+ "content": "<s_score_penalty_time_1_a>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "57550": {
268
+ "content": "</s_score_penalty_time_1_a>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "57551": {
276
+ "content": "<s_score_half_time_b>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "57552": {
284
+ "content": "</s_score_half_time_b>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "57553": {
292
+ "content": "<s_score_half_time_a>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "57554": {
300
+ "content": "</s_score_half_time_a>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "57555": {
308
+ "content": "<s_score_extra_time_2_b>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "57556": {
316
+ "content": "</s_score_extra_time_2_b>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "57557": {
324
+ "content": "<s_score_extra_time_2_a>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "57558": {
332
+ "content": "</s_score_extra_time_2_a>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "57559": {
340
+ "content": "<s_score_extra_time_1_b>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "57560": {
348
+ "content": "</s_score_extra_time_1_b>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "57561": {
356
+ "content": "<s_score_extra_time_1_a>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "57562": {
364
+ "content": "</s_score_extra_time_1_a>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "57563": {
372
+ "content": "<s_score_end_time_b>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "57564": {
380
+ "content": "</s_score_end_time_b>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "57565": {
388
+ "content": "<s_score_end_time_a>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "57566": {
396
+ "content": "</s_score_end_time_a>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "57567": {
404
+ "content": "<s_remarks>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "57568": {
412
+ "content": "</s_remarks>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "57569": {
420
+ "content": "<s_referees>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "57570": {
428
+ "content": "</s_referees>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "57571": {
436
+ "content": "<s_players_b>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "57572": {
444
+ "content": "</s_players_b>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "57573": {
452
+ "content": "<s_warning>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57574": {
460
+ "content": "</s_warning>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "57575": {
468
+ "content": "<s_suspension>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "57576": {
476
+ "content": "</s_suspension>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "57577": {
484
+ "content": "<s_report_disqualification>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "57578": {
492
+ "content": "</s_report_disqualification>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "57579": {
500
+ "content": "<s_no>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "57580": {
508
+ "content": "</s_no>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "57581": {
516
+ "content": "<s_goal>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "57582": {
524
+ "content": "</s_goal>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "57583": {
532
+ "content": "<s_direct_disqualification>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "57584": {
540
+ "content": "</s_direct_disqualification>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "57585": {
548
+ "content": "<s_players_a>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "57586": {
556
+ "content": "</s_players_a>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "57587": {
564
+ "content": "<s_officials_b>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "57588": {
572
+ "content": "</s_officials_b>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "57589": {
580
+ "content": "<s_officials_a>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "57590": {
588
+ "content": "</s_officials_a>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "57591": {
596
+ "content": "<s_number_of_7_b>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "57592": {
604
+ "content": "</s_number_of_7_b>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "57593": {
612
+ "content": "<s_number_of_7_a>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "57594": {
620
+ "content": "</s_number_of_7_a>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "57595": {
628
+ "content": "<s_match_number>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "57596": {
636
+ "content": "</s_match_number>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "57597": {
644
+ "content": "<s_lieu>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "57598": {
652
+ "content": "</s_lieu>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "57599": {
660
+ "content": "<s_hour>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "57600": {
668
+ "content": "</s_hour>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "57601": {
676
+ "content": "<s_hall>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "57602": {
684
+ "content": "</s_hall>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "57603": {
692
+ "content": "<s_federation_official>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "57604": {
700
+ "content": "</s_federation_official>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "57605": {
708
+ "content": "<s_date>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "57606": {
716
+ "content": "</s_date>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "57607": {
724
+ "content": "<s_competition_name>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "57608": {
732
+ "content": "</s_competition_name>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "57609": {
740
+ "content": "<s_sus pension>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "57610": {
748
+ "content": "</s_sus pension>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ }
755
+ },
756
+ "additional_special_tokens": [
757
+ "<s_team_time_out_b_3>",
758
+ "</s_team_time_out_b_3>",
759
+ "<s_team_time_out_b_2>",
760
+ "</s_team_time_out_b_2>",
761
+ "<s_team_time_out_b_1>",
762
+ "</s_team_time_out_b_1>",
763
+ "<s_team_time_out_a_3>",
764
+ "</s_team_time_out_a_3>",
765
+ "<s_team_time_out_a_2>",
766
+ "</s_team_time_out_a_2>",
767
+ "<s_team_time_out_a_1>",
768
+ "</s_team_time_out_a_1>",
769
+ "<s_team_b_name>",
770
+ "</s_team_b_name>",
771
+ "<s_team_a_name>",
772
+ "</s_team_a_name>",
773
+ "<s_td>",
774
+ "</s_td>",
775
+ "<s_name>",
776
+ "</s_name>",
777
+ "<s_spectator>",
778
+ "</s_spectator>",
779
+ "<s_score_penalty_time_1_b>",
780
+ "</s_score_penalty_time_1_b>",
781
+ "<s_score_penalty_time_1_a>",
782
+ "</s_score_penalty_time_1_a>",
783
+ "<s_score_half_time_b>",
784
+ "</s_score_half_time_b>",
785
+ "<s_score_half_time_a>",
786
+ "</s_score_half_time_a>",
787
+ "<s_score_extra_time_2_b>",
788
+ "</s_score_extra_time_2_b>",
789
+ "<s_score_extra_time_2_a>",
790
+ "</s_score_extra_time_2_a>",
791
+ "<s_score_extra_time_1_b>",
792
+ "</s_score_extra_time_1_b>",
793
+ "<s_score_extra_time_1_a>",
794
+ "</s_score_extra_time_1_a>",
795
+ "<s_score_end_time_b>",
796
+ "</s_score_end_time_b>",
797
+ "<s_score_end_time_a>",
798
+ "</s_score_end_time_a>",
799
+ "<s_remarks>",
800
+ "</s_remarks>",
801
+ "<s_referees>",
802
+ "</s_referees>",
803
+ "<s_players_b>",
804
+ "</s_players_b>",
805
+ "<s_warning>",
806
+ "</s_warning>",
807
+ "<s_suspension>",
808
+ "</s_suspension>",
809
+ "<s_report_disqualification>",
810
+ "</s_report_disqualification>",
811
+ "<s_no>",
812
+ "</s_no>",
813
+ "<s_goal>",
814
+ "</s_goal>",
815
+ "<s_direct_disqualification>",
816
+ "</s_direct_disqualification>",
817
+ "<s_players_a>",
818
+ "</s_players_a>",
819
+ "<s_officials_b>",
820
+ "</s_officials_b>",
821
+ "<s_officials_a>",
822
+ "</s_officials_a>",
823
+ "<s_number_of_7_b>",
824
+ "</s_number_of_7_b>",
825
+ "<s_number_of_7_a>",
826
+ "</s_number_of_7_a>",
827
+ "<s_match_number>",
828
+ "</s_match_number>",
829
+ "<s_lieu>",
830
+ "</s_lieu>",
831
+ "<s_hour>",
832
+ "</s_hour>",
833
+ "<s_hall>",
834
+ "</s_hall>",
835
+ "<s_federation_official>",
836
+ "</s_federation_official>",
837
+ "<s_date>",
838
+ "</s_date>",
839
+ "<s_competition_name>",
840
+ "</s_competition_name>",
841
+ "<s_sus pension>",
842
+ "</s_sus pension>",
843
+ "<s>",
844
+ "</s>"
845
+ ],
846
+ "bos_token": "<s>",
847
+ "clean_up_tokenization_spaces": true,
848
+ "cls_token": "<s>",
849
+ "eos_token": "</s>",
850
+ "mask_token": "<mask>",
851
+ "model_max_length": 1000000000000000019884624838656,
852
+ "pad_token": "<pad>",
853
+ "processor_class": "DonutProcessor",
854
+ "sep_token": "</s>",
855
+ "sp_model_kwargs": {},
856
+ "tokenizer_class": "XLMRobertaTokenizer",
857
+ "unk_token": "<unk>"
858
+ }