hks1444 commited on
Commit
a8fe14f
·
verified ·
1 Parent(s): bdb5501

End of training

Browse files
Files changed (6) hide show
  1. README.md +18 -14
  2. config.json +20 -26
  3. model.safetensors +2 -2
  4. special_tokens_map.json +25 -106
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +39 -850
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
- license: other
4
- base_model: boun-tabi-LMG/TURNA
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # TurkishBERTweet
21
 
22
- This model is a fine-tuned version of [boun-tabi-LMG/TURNA](https://huggingface.co/boun-tabi-LMG/TURNA) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: nan
25
- - Precision: 0.0
26
- - Recall: 0.0
27
- - F1: 0.0
28
- - Accuracy: 0.9589
29
 
30
  ## Model description
31
 
@@ -54,12 +54,16 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
59
- | 0.0 | 1.0 | 230 | nan | 0.0 | 0.0 | 0.0 | 0.9615 |
60
- | 0.0 | 2.0 | 460 | nan | 0.0 | 0.0 | 0.0 | 0.9615 |
61
- | 0.0 | 3.0 | 690 | nan | 0.0 | 0.0 | 0.0 | 0.9615 |
62
- | 0.0 | 4.0 | 920 | nan | 0.0 | 0.0 | 0.0 | 0.9615 |
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: mit
4
+ base_model: VRLLab/TurkishBERTweet
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
19
 
20
  # TurkishBERTweet
21
 
22
+ This model is a fine-tuned version of [VRLLab/TurkishBERTweet](https://huggingface.co/VRLLab/TurkishBERTweet) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1457
25
+ - Precision: 0.5116
26
+ - Recall: 0.3964
27
+ - F1: 0.4467
28
+ - Accuracy: 0.9618
29
 
30
  ## Model description
31
 
 
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.1975 | 1.0 | 230 | 0.1641 | 0.6471 | 0.25 | 0.3607 | 0.9667 |
60
+ | 0.1939 | 2.0 | 460 | 0.1492 | 0.4912 | 0.3182 | 0.3862 | 0.9673 |
61
+ | 0.1543 | 3.0 | 690 | 0.1448 | 0.3103 | 0.3068 | 0.3086 | 0.9680 |
62
+ | 0.1571 | 4.0 | 920 | 0.1173 | 0.2105 | 0.1818 | 0.1951 | 0.9729 |
63
+ | 0.1401 | 5.0 | 1150 | 0.1095 | 0.3140 | 0.3068 | 0.3103 | 0.9732 |
64
+ | 0.1101 | 6.0 | 1380 | 0.1175 | 0.3896 | 0.3409 | 0.3636 | 0.9741 |
65
+ | 0.0639 | 7.0 | 1610 | 0.1138 | 0.3364 | 0.4091 | 0.3692 | 0.9707 |
66
+ | 0.0589 | 8.0 | 1840 | 0.1195 | 0.3838 | 0.4318 | 0.4064 | 0.9719 |
67
 
68
 
69
  ### Framework versions
config.json CHANGED
@@ -1,43 +1,37 @@
1
  {
2
- "_name_or_path": "boun-tabi-LMG/TURNA",
3
  "architectures": [
4
- "T5ForClassification"
5
  ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 2816,
8
- "d_kv": 64,
9
- "d_model": 1024,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
  "id2label": {
16
  "0": "LABEL_0",
17
  "1": "LABEL_1",
18
  "2": "LABEL_2"
19
  },
20
- "initializer_factor": 1.0,
21
- "is_encoder_decoder": true,
22
- "is_gated_act": true,
23
  "label2id": {
24
  "LABEL_0": 0,
25
  "LABEL_1": 1,
26
  "LABEL_2": 2
27
  },
28
- "layer_norm_epsilon": 1e-06,
29
- "model_type": "t5",
30
- "num_decoder_layers": 36,
31
- "num_heads": 16,
32
- "num_layers": 36,
33
- "output_past": true,
34
- "pad_token_id": 0,
35
- "problem_type": "token_classification",
36
- "relative_attention_max_distance": 128,
37
- "relative_attention_num_buckets": 32,
38
- "tie_word_embeddings": false,
39
  "torch_dtype": "float32",
40
  "transformers_version": "4.46.2",
 
41
  "use_cache": true,
42
- "vocab_size": 32128
43
  }
 
1
  {
2
+ "_name_or_path": "VRLLab/TurkishBERTweet",
3
  "architectures": [
4
+ "RobertaForTokenClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
 
 
13
  "id2label": {
14
  "0": "LABEL_0",
15
  "1": "LABEL_1",
16
  "2": "LABEL_2"
17
  },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
 
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 2
24
  },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.46.2",
34
+ "type_vocab_size": 1,
35
  "use_cache": true,
36
+ "vocab_size": 100000
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1286d81ea1b255a4375bab1c83478e8c52b96596ab01734805b7775066ab01b
3
- size 1981641812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c371166510983a467fa86d7b7cf85ebd312acdfcf4c2ebe34e8855774d1b6262
3
+ size 649039236
special_tokens_map.json CHANGED
@@ -1,129 +1,48 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_99>",
4
- "<extra_id_98>",
5
- "<extra_id_97>",
6
- "<extra_id_96>",
7
- "<extra_id_95>",
8
- "<extra_id_94>",
9
- "<extra_id_93>",
10
- "<extra_id_92>",
11
- "<extra_id_91>",
12
- "<extra_id_90>",
13
- "<extra_id_89>",
14
- "<extra_id_88>",
15
- "<extra_id_87>",
16
- "<extra_id_86>",
17
- "<extra_id_85>",
18
- "<extra_id_84>",
19
- "<extra_id_83>",
20
- "<extra_id_82>",
21
- "<extra_id_81>",
22
- "<extra_id_80>",
23
- "<extra_id_79>",
24
- "<extra_id_78>",
25
- "<extra_id_77>",
26
- "<extra_id_76>",
27
- "<extra_id_75>",
28
- "<extra_id_74>",
29
- "<extra_id_73>",
30
- "<extra_id_72>",
31
- "<extra_id_71>",
32
- "<extra_id_70>",
33
- "<extra_id_69>",
34
- "<extra_id_68>",
35
- "<extra_id_67>",
36
- "<extra_id_66>",
37
- "<extra_id_65>",
38
- "<extra_id_64>",
39
- "<extra_id_63>",
40
- "<extra_id_62>",
41
- "<extra_id_61>",
42
- "<extra_id_60>",
43
- "<extra_id_59>",
44
- "<extra_id_58>",
45
- "<extra_id_57>",
46
- "<extra_id_56>",
47
- "<extra_id_55>",
48
- "<extra_id_54>",
49
- "<extra_id_53>",
50
- "<extra_id_52>",
51
- "<extra_id_51>",
52
- "<extra_id_50>",
53
- "<extra_id_49>",
54
- "<extra_id_48>",
55
- "<extra_id_47>",
56
- "<extra_id_46>",
57
- "<extra_id_45>",
58
- "<extra_id_44>",
59
- "<extra_id_43>",
60
- "<extra_id_42>",
61
- "<extra_id_41>",
62
- "<extra_id_40>",
63
- "<extra_id_39>",
64
- "<extra_id_38>",
65
- "<extra_id_37>",
66
- "<extra_id_36>",
67
- "<extra_id_35>",
68
- "<extra_id_34>",
69
- "<extra_id_33>",
70
- "<extra_id_32>",
71
- "<extra_id_31>",
72
- "<extra_id_30>",
73
- "<extra_id_29>",
74
- "<extra_id_28>",
75
- "<extra_id_27>",
76
- "<extra_id_26>",
77
- "<extra_id_25>",
78
- "<extra_id_24>",
79
- "<extra_id_23>",
80
- "<extra_id_22>",
81
- "<extra_id_21>",
82
- "<extra_id_20>",
83
- "<extra_id_19>",
84
- "<extra_id_18>",
85
- "<extra_id_17>",
86
- "<extra_id_16>",
87
- "<extra_id_15>",
88
- "<extra_id_14>",
89
- "<extra_id_13>",
90
- "<extra_id_12>",
91
- "<extra_id_11>",
92
- "<extra_id_10>",
93
- "<extra_id_9>",
94
- "<extra_id_8>",
95
- "<extra_id_7>",
96
- "<extra_id_6>",
97
- "<extra_id_5>",
98
- "<extra_id_4>",
99
- "<extra_id_3>",
100
- "<extra_id_2>",
101
- "<extra_id_1>",
102
- "<extra_id_0>"
103
- ],
104
  "bos_token": {
105
- "content": "<BOS>",
 
 
 
 
 
 
 
106
  "lstrip": false,
107
  "normalized": false,
108
  "rstrip": false,
109
  "single_word": false
110
  },
111
  "eos_token": {
112
- "content": "<EOS>",
113
  "lstrip": false,
114
  "normalized": false,
115
  "rstrip": false,
116
  "single_word": false
117
  },
 
 
 
 
 
 
 
118
  "pad_token": {
119
- "content": "<PAD>",
 
 
 
 
 
 
 
120
  "lstrip": false,
121
  "normalized": false,
122
  "rstrip": false,
123
  "single_word": false
124
  },
125
  "unk_token": {
126
- "content": "<UNK>",
127
  "lstrip": false,
128
  "normalized": false,
129
  "rstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "eos_token": {
17
+ "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
  "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false
43
  },
44
  "unk_token": {
45
+ "content": "<unk>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<PAD>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +10,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<EOS>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +18,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<UNK>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,807 +26,95 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "<BOS>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "32000": {
36
- "content": "<extra_id_99>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "32001": {
44
- "content": "<extra_id_98>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "32002": {
52
- "content": "<extra_id_97>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "32003": {
60
- "content": "<extra_id_96>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "32004": {
68
- "content": "<extra_id_95>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "32005": {
76
- "content": "<extra_id_94>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "32006": {
84
- "content": "<extra_id_93>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "32007": {
92
- "content": "<extra_id_92>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "32008": {
100
- "content": "<extra_id_91>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "32009": {
108
- "content": "<extra_id_90>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "32010": {
116
- "content": "<extra_id_89>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "32011": {
124
- "content": "<extra_id_88>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "32012": {
132
- "content": "<extra_id_87>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "32013": {
140
- "content": "<extra_id_86>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "32014": {
148
- "content": "<extra_id_85>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "32015": {
156
- "content": "<extra_id_84>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "32016": {
164
- "content": "<extra_id_83>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "32017": {
172
- "content": "<extra_id_82>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "32018": {
180
- "content": "<extra_id_81>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "32019": {
188
- "content": "<extra_id_80>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "32020": {
196
- "content": "<extra_id_79>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "32021": {
204
- "content": "<extra_id_78>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "32022": {
212
- "content": "<extra_id_77>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "32023": {
220
- "content": "<extra_id_76>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "32024": {
228
- "content": "<extra_id_75>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "32025": {
236
- "content": "<extra_id_74>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "32026": {
244
- "content": "<extra_id_73>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "32027": {
252
- "content": "<extra_id_72>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "32028": {
260
- "content": "<extra_id_71>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "32029": {
268
- "content": "<extra_id_70>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "32030": {
276
- "content": "<extra_id_69>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "32031": {
284
- "content": "<extra_id_68>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "32032": {
292
- "content": "<extra_id_67>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "32033": {
300
- "content": "<extra_id_66>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "32034": {
308
- "content": "<extra_id_65>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "32035": {
316
- "content": "<extra_id_64>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "32036": {
324
- "content": "<extra_id_63>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "32037": {
332
- "content": "<extra_id_62>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "32038": {
340
- "content": "<extra_id_61>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "32039": {
348
- "content": "<extra_id_60>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "32040": {
356
- "content": "<extra_id_59>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "32041": {
364
- "content": "<extra_id_58>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "32042": {
372
- "content": "<extra_id_57>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "32043": {
380
- "content": "<extra_id_56>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "32044": {
388
- "content": "<extra_id_55>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "32045": {
396
- "content": "<extra_id_54>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "32046": {
404
- "content": "<extra_id_53>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "32047": {
412
- "content": "<extra_id_52>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "32048": {
420
- "content": "<extra_id_51>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "32049": {
428
- "content": "<extra_id_50>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "32050": {
436
- "content": "<extra_id_49>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "32051": {
444
- "content": "<extra_id_48>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "32052": {
452
- "content": "<extra_id_47>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "32053": {
460
- "content": "<extra_id_46>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "32054": {
468
- "content": "<extra_id_45>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "32055": {
476
- "content": "<extra_id_44>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "32056": {
484
- "content": "<extra_id_43>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "32057": {
492
- "content": "<extra_id_42>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "32058": {
500
- "content": "<extra_id_41>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "32059": {
508
- "content": "<extra_id_40>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "32060": {
516
- "content": "<extra_id_39>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "32061": {
524
- "content": "<extra_id_38>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "32062": {
532
- "content": "<extra_id_37>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "32063": {
540
- "content": "<extra_id_36>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "32064": {
548
- "content": "<extra_id_35>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "32065": {
556
- "content": "<extra_id_34>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "32066": {
564
- "content": "<extra_id_33>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "32067": {
572
- "content": "<extra_id_32>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "32068": {
580
- "content": "<extra_id_31>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "32069": {
588
- "content": "<extra_id_30>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "32070": {
596
- "content": "<extra_id_29>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "32071": {
604
- "content": "<extra_id_28>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "32072": {
612
- "content": "<extra_id_27>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "32073": {
620
- "content": "<extra_id_26>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "32074": {
628
- "content": "<extra_id_25>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "32075": {
636
- "content": "<extra_id_24>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "32076": {
644
- "content": "<extra_id_23>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "32077": {
652
- "content": "<extra_id_22>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "32078": {
660
- "content": "<extra_id_21>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "32079": {
668
- "content": "<extra_id_20>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "32080": {
676
- "content": "<extra_id_19>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "32081": {
684
- "content": "<extra_id_18>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "32082": {
692
- "content": "<extra_id_17>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "32083": {
700
- "content": "<extra_id_16>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "32084": {
708
- "content": "<extra_id_15>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "32085": {
716
- "content": "<extra_id_14>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "32086": {
724
- "content": "<extra_id_13>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "32087": {
732
- "content": "<extra_id_12>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "32088": {
740
- "content": "<extra_id_11>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "32089": {
748
- "content": "<extra_id_10>",
749
- "lstrip": false,
750
  "normalized": false,
751
  "rstrip": false,
752
  "single_word": false,
753
  "special": true
754
  },
755
- "32090": {
756
- "content": "<extra_id_9>",
757
  "lstrip": false,
758
  "normalized": false,
759
  "rstrip": false,
760
  "single_word": false,
761
  "special": true
762
  },
763
- "32091": {
764
- "content": "<extra_id_8>",
765
  "lstrip": false,
766
  "normalized": false,
767
  "rstrip": false,
768
  "single_word": false,
769
  "special": true
770
  },
771
- "32092": {
772
- "content": "<extra_id_7>",
773
  "lstrip": false,
774
  "normalized": false,
775
  "rstrip": false,
776
  "single_word": false,
777
  "special": true
778
  },
779
- "32093": {
780
- "content": "<extra_id_6>",
781
  "lstrip": false,
782
  "normalized": false,
783
  "rstrip": false,
784
  "single_word": false,
785
  "special": true
786
  },
787
- "32094": {
788
- "content": "<extra_id_5>",
789
  "lstrip": false,
790
  "normalized": false,
791
  "rstrip": false,
792
  "single_word": false,
793
  "special": true
794
  },
795
- "32095": {
796
- "content": "<extra_id_4>",
797
  "lstrip": false,
798
  "normalized": false,
799
  "rstrip": false,
800
  "single_word": false,
801
  "special": true
802
  },
803
- "32096": {
804
- "content": "<extra_id_3>",
805
  "lstrip": false,
806
  "normalized": false,
807
  "rstrip": false,
808
  "single_word": false,
809
  "special": true
810
  },
811
- "32097": {
812
- "content": "<extra_id_2>",
813
  "lstrip": false,
814
  "normalized": false,
815
  "rstrip": false,
816
  "single_word": false,
817
  "special": true
818
  },
819
- "32098": {
820
- "content": "<extra_id_1>",
821
  "lstrip": false,
822
  "normalized": false,
823
  "rstrip": false,
824
  "single_word": false,
825
  "special": true
826
  },
827
- "32099": {
828
- "content": "<extra_id_0>",
829
  "lstrip": false,
830
  "normalized": false,
831
  "rstrip": false,
@@ -833,116 +122,16 @@
833
  "special": true
834
  }
835
  },
836
- "additional_special_tokens": [
837
- "<extra_id_99>",
838
- "<extra_id_98>",
839
- "<extra_id_97>",
840
- "<extra_id_96>",
841
- "<extra_id_95>",
842
- "<extra_id_94>",
843
- "<extra_id_93>",
844
- "<extra_id_92>",
845
- "<extra_id_91>",
846
- "<extra_id_90>",
847
- "<extra_id_89>",
848
- "<extra_id_88>",
849
- "<extra_id_87>",
850
- "<extra_id_86>",
851
- "<extra_id_85>",
852
- "<extra_id_84>",
853
- "<extra_id_83>",
854
- "<extra_id_82>",
855
- "<extra_id_81>",
856
- "<extra_id_80>",
857
- "<extra_id_79>",
858
- "<extra_id_78>",
859
- "<extra_id_77>",
860
- "<extra_id_76>",
861
- "<extra_id_75>",
862
- "<extra_id_74>",
863
- "<extra_id_73>",
864
- "<extra_id_72>",
865
- "<extra_id_71>",
866
- "<extra_id_70>",
867
- "<extra_id_69>",
868
- "<extra_id_68>",
869
- "<extra_id_67>",
870
- "<extra_id_66>",
871
- "<extra_id_65>",
872
- "<extra_id_64>",
873
- "<extra_id_63>",
874
- "<extra_id_62>",
875
- "<extra_id_61>",
876
- "<extra_id_60>",
877
- "<extra_id_59>",
878
- "<extra_id_58>",
879
- "<extra_id_57>",
880
- "<extra_id_56>",
881
- "<extra_id_55>",
882
- "<extra_id_54>",
883
- "<extra_id_53>",
884
- "<extra_id_52>",
885
- "<extra_id_51>",
886
- "<extra_id_50>",
887
- "<extra_id_49>",
888
- "<extra_id_48>",
889
- "<extra_id_47>",
890
- "<extra_id_46>",
891
- "<extra_id_45>",
892
- "<extra_id_44>",
893
- "<extra_id_43>",
894
- "<extra_id_42>",
895
- "<extra_id_41>",
896
- "<extra_id_40>",
897
- "<extra_id_39>",
898
- "<extra_id_38>",
899
- "<extra_id_37>",
900
- "<extra_id_36>",
901
- "<extra_id_35>",
902
- "<extra_id_34>",
903
- "<extra_id_33>",
904
- "<extra_id_32>",
905
- "<extra_id_31>",
906
- "<extra_id_30>",
907
- "<extra_id_29>",
908
- "<extra_id_28>",
909
- "<extra_id_27>",
910
- "<extra_id_26>",
911
- "<extra_id_25>",
912
- "<extra_id_24>",
913
- "<extra_id_23>",
914
- "<extra_id_22>",
915
- "<extra_id_21>",
916
- "<extra_id_20>",
917
- "<extra_id_19>",
918
- "<extra_id_18>",
919
- "<extra_id_17>",
920
- "<extra_id_16>",
921
- "<extra_id_15>",
922
- "<extra_id_14>",
923
- "<extra_id_13>",
924
- "<extra_id_12>",
925
- "<extra_id_11>",
926
- "<extra_id_10>",
927
- "<extra_id_9>",
928
- "<extra_id_8>",
929
- "<extra_id_7>",
930
- "<extra_id_6>",
931
- "<extra_id_5>",
932
- "<extra_id_4>",
933
- "<extra_id_3>",
934
- "<extra_id_2>",
935
- "<extra_id_1>",
936
- "<extra_id_0>"
937
- ],
938
- "bos_token": "<BOS>",
939
  "clean_up_tokenization_spaces": false,
940
- "eos_token": "<EOS>",
941
- "extra_ids": 100,
942
- "model_max_length": 1024,
943
- "pad_token": "<PAD>",
944
- "padding_side": "right",
945
- "tokenizer_class": "T5Tokenizer",
946
- "truncation_side": "right",
947
- "unk_token": "<UNK>"
 
 
948
  }
 
1
  {
2
+ "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
 
10
  "special": true
11
  },
12
  "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
 
18
  "special": true
19
  },
20
  "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
 
26
  "special": true
27
  },
28
  "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "5": {
45
+ "content": "@user",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
49
  "single_word": false,
50
  "special": true
51
  },
52
+ "6": {
53
+ "content": "<hashtag>",
54
  "lstrip": false,
55
  "normalized": false,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  },
60
+ "7": {
61
+ "content": "</hashtag>",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
65
  "single_word": false,
66
  "special": true
67
  },
68
+ "8": {
69
+ "content": "<cashtag>",
70
  "lstrip": false,
71
  "normalized": false,
72
  "rstrip": false,
73
  "single_word": false,
74
  "special": true
75
  },
76
+ "9": {
77
+ "content": "</cashtag>",
78
  "lstrip": false,
79
  "normalized": false,
80
  "rstrip": false,
81
  "single_word": false,
82
  "special": true
83
  },
84
+ "10": {
85
+ "content": "<emoji>",
86
  "lstrip": false,
87
  "normalized": false,
88
  "rstrip": false,
89
  "single_word": false,
90
  "special": true
91
  },
92
+ "11": {
93
+ "content": "</emoji>",
94
  "lstrip": false,
95
  "normalized": false,
96
  "rstrip": false,
97
  "single_word": false,
98
  "special": true
99
  },
100
+ "12": {
101
+ "content": "<http>",
102
  "lstrip": false,
103
  "normalized": false,
104
  "rstrip": false,
105
  "single_word": false,
106
  "special": true
107
  },
108
+ "13": {
109
+ "content": "</http>",
110
  "lstrip": false,
111
  "normalized": false,
112
  "rstrip": false,
113
  "single_word": false,
114
  "special": true
115
  },
116
+ "14": {
117
+ "content": "<email>",
118
  "lstrip": false,
119
  "normalized": false,
120
  "rstrip": false,
 
122
  "special": true
123
  }
124
  },
125
+ "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126
  "clean_up_tokenization_spaces": false,
127
+ "cls_token": "<s>",
128
+ "eos_token": "</s>",
129
+ "errors": "replace",
130
+ "mask_token": "<mask>",
131
+ "model_max_length": 1000000000000000019884624838656,
132
+ "pad_token": "<pad>",
133
+ "sep_token": "</s>",
134
+ "tokenizer_class": "RobertaTokenizer",
135
+ "trim_offsets": true,
136
+ "unk_token": "<unk>"
137
  }