Hugging Face's logo

thusken
/
nb-bert-large-user-needs-v2

Safetensors
bert
Generated from Trainer
Model card Files Community
thusken commited on
Commit
cd8b223
·
verified ·
1 Parent(s): 42c48f0

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +13 -15
  2. model.safetensors +2 -2
  3. special_tokens_map.json +0 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +14 -827
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,18 +1,12 @@
1
  {
2
- "_name_or_path": "ltg/norbert3-large",
3
  "architectures": [
4
- "NorbertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "auto_map": {
8
- "AutoConfig": "ltg/norbert3-large--configuration_norbert.NorbertConfig",
9
- "AutoModel": "ltg/norbert3-large--modeling_norbert.NorbertModel",
10
- "AutoModelForMaskedLM": "ltg/norbert3-large--modeling_norbert.NorbertForMaskedLM",
11
- "AutoModelForMultipleChoice": "ltg/norbert3-large--modeling_norbert.NorbertForMultipleChoice",
12
- "AutoModelForQuestionAnswering": "ltg/norbert3-large--modeling_norbert.NorbertForQuestionAnswering",
13
- "AutoModelForSequenceClassification": "ltg/norbert3-large--modeling_norbert.NorbertForSequenceClassification",
14
- "AutoModelForTokenClassification": "ltg/norbert3-large--modeling_norbert.NorbertForTokenClassification"
15
- },
16
  "hidden_dropout_prob": 0.1,
17
  "hidden_size": 1024,
18
  "id2label": {
@@ -20,20 +14,24 @@
20
  "1": "forklare_og_gi_bakgrunn",
21
  "2": "oppdatere"
22
  },
23
- "intermediate_size": 2730,
 
24
  "label2id": {
25
  "bevege_og_underholde": "0",
26
  "forklare_og_gi_bakgrunn": "1",
27
  "oppdatere": "2"
28
  },
29
- "layer_norm_eps": 1e-07,
30
  "max_position_embeddings": 512,
 
31
  "num_attention_heads": 16,
32
  "num_hidden_layers": 24,
33
- "output_all_encoded_layers": true,
34
- "position_bucket_size": 32,
35
  "problem_type": "single_label_classification",
36
  "torch_dtype": "float32",
37
  "transformers_version": "4.36.0",
 
 
38
  "vocab_size": 50000
39
  }
 
1
  {
2
+ "_name_or_path": "NbAiLab/nb-bert-large",
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
 
 
 
 
 
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 1024,
12
  "id2label": {
 
14
  "1": "forklare_og_gi_bakgrunn",
15
  "2": "oppdatere"
16
  },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
  "label2id": {
20
  "bevege_og_underholde": "0",
21
  "forklare_og_gi_bakgrunn": "1",
22
  "oppdatere": "2"
23
  },
24
+ "layer_norm_eps": 1e-12,
25
  "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
  "num_attention_heads": 16,
28
  "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
  "problem_type": "single_label_classification",
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.36.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
  "vocab_size": 50000
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46911afbc9dce0b0d42651b7d46cdbe01cf3b28f6dd11d4769620e491995e65c
3
- size 1417659372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0666cabd33be91082c2aee40e15dd14380f516ded2940e22657b819a5b38bbfe
3
+ size 1420408804
special_tokens_map.json CHANGED
@@ -1,7 +1,5 @@
1
  {
2
- "bos_token": "[BOS]",
3
  "cls_token": "[CLS]",
4
- "eos_token": "[EOS]",
5
  "mask_token": "[MASK]",
6
  "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
 
1
  {
 
2
  "cls_token": "[CLS]",
 
3
  "mask_token": "[MASK]",
4
  "pad_token": "[PAD]",
5
  "sep_token": "[SEP]",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,14 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "[UNK]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
  "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,23 +8,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "[SEP]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[PAD]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -40,816 +16,24 @@
40
  "single_word": false,
41
  "special": true
42
  },
43
- "5": {
44
- "content": "[BOS]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "[EOS]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "7": {
60
- "content": "[MASK_0]",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "8": {
68
- "content": "[MASK_1]",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "9": {
76
- "content": "[MASK_2]",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "10": {
84
- "content": "[MASK_3]",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "11": {
92
- "content": "[MASK_4]",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "12": {
100
- "content": "[MASK_5]",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "13": {
108
- "content": "[MASK_6]",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "14": {
116
- "content": "[MASK_7]",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "15": {
124
- "content": "[MASK_8]",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "16": {
132
- "content": "[MASK_9]",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "17": {
140
- "content": "[MASK_10]",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "18": {
148
- "content": "[MASK_11]",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "19": {
156
- "content": "[MASK_12]",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "20": {
164
- "content": "[MASK_13]",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "21": {
172
- "content": "[MASK_14]",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "22": {
180
- "content": "[MASK_15]",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "23": {
188
- "content": "[MASK_16]",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "24": {
196
- "content": "[MASK_17]",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "25": {
204
- "content": "[MASK_18]",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "26": {
212
- "content": "[MASK_19]",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "27": {
220
- "content": "[MASK_20]",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "28": {
228
- "content": "[MASK_21]",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "29": {
236
- "content": "[MASK_22]",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "30": {
244
- "content": "[MASK_23]",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "31": {
252
- "content": "[MASK_24]",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "32": {
260
- "content": "[MASK_25]",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "33": {
268
- "content": "[MASK_26]",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "34": {
276
- "content": "[MASK_27]",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "35": {
284
- "content": "[MASK_28]",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "36": {
292
- "content": "[MASK_29]",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "37": {
300
- "content": "[MASK_30]",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "38": {
308
- "content": "[MASK_31]",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "39": {
316
- "content": "[MASK_32]",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "40": {
324
- "content": "[MASK_33]",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "41": {
332
- "content": "[MASK_34]",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "42": {
340
- "content": "[MASK_35]",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "43": {
348
- "content": "[MASK_36]",
349
  "lstrip": false,
350
  "normalized": false,
351
  "rstrip": false,
352
  "single_word": false,
353
  "special": true
354
  },
355
- "44": {
356
- "content": "[MASK_37]",
357
  "lstrip": false,
358
  "normalized": false,
359
  "rstrip": false,
360
  "single_word": false,
361
  "special": true
362
  },
363
- "45": {
364
- "content": "[MASK_38]",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "46": {
372
- "content": "[MASK_39]",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "47": {
380
- "content": "[MASK_40]",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "48": {
388
- "content": "[MASK_41]",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "49": {
396
- "content": "[MASK_42]",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "50": {
404
- "content": "[MASK_43]",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "51": {
412
- "content": "[MASK_44]",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "52": {
420
- "content": "[MASK_45]",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "53": {
428
- "content": "[MASK_46]",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "54": {
436
- "content": "[MASK_47]",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "55": {
444
- "content": "[MASK_48]",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "56": {
452
- "content": "[MASK_49]",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "57": {
460
- "content": "[MASK_50]",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "58": {
468
- "content": "[MASK_51]",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "59": {
476
- "content": "[MASK_52]",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "60": {
484
- "content": "[MASK_53]",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "61": {
492
- "content": "[MASK_54]",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "62": {
500
- "content": "[MASK_55]",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "63": {
508
- "content": "[MASK_56]",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "64": {
516
- "content": "[MASK_57]",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "65": {
524
- "content": "[MASK_58]",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "66": {
532
- "content": "[MASK_59]",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "67": {
540
- "content": "[MASK_60]",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "68": {
548
- "content": "[MASK_61]",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "69": {
556
- "content": "[MASK_62]",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "70": {
564
- "content": "[MASK_63]",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "71": {
572
- "content": "[MASK_64]",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "72": {
580
- "content": "[MASK_65]",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "73": {
588
- "content": "[MASK_66]",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "74": {
596
- "content": "[MASK_67]",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "75": {
604
- "content": "[MASK_68]",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "76": {
612
- "content": "[MASK_69]",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "77": {
620
- "content": "[MASK_70]",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "78": {
628
- "content": "[MASK_71]",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "79": {
636
- "content": "[MASK_72]",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "80": {
644
- "content": "[MASK_73]",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "81": {
652
- "content": "[MASK_74]",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "82": {
660
- "content": "[MASK_75]",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "83": {
668
- "content": "[MASK_76]",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "84": {
676
- "content": "[MASK_77]",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "85": {
684
- "content": "[MASK_78]",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "86": {
692
- "content": "[MASK_79]",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "87": {
700
- "content": "[MASK_80]",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "88": {
708
- "content": "[MASK_81]",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "89": {
716
- "content": "[MASK_82]",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "90": {
724
- "content": "[MASK_83]",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "91": {
732
- "content": "[MASK_84]",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "92": {
740
- "content": "[MASK_85]",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "93": {
748
- "content": "[MASK_86]",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "94": {
756
- "content": "[MASK_87]",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "95": {
764
- "content": "[MASK_88]",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "96": {
772
- "content": "[MASK_89]",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "97": {
780
- "content": "[MASK_90]",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "98": {
788
- "content": "[MASK_91]",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "99": {
796
- "content": "[MASK_92]",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "100": {
804
- "content": "[MASK_93]",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "101": {
812
- "content": "[MASK_94]",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "102": {
820
- "content": "[MASK_95]",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "103": {
828
- "content": "[MASK_96]",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "104": {
836
- "content": "[MASK_97]",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "105": {
844
- "content": "[MASK_98]",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "106": {
852
- "content": "[MASK_99]",
853
  "lstrip": false,
854
  "normalized": false,
855
  "rstrip": false,
@@ -857,14 +41,17 @@
857
  "special": true
858
  }
859
  },
860
- "bos_token": "[BOS]",
861
  "clean_up_tokenization_spaces": true,
862
  "cls_token": "[CLS]",
863
- "eos_token": "[EOS]",
 
864
  "mask_token": "[MASK]",
865
  "model_max_length": 1000000000000000019884624838656,
 
866
  "pad_token": "[PAD]",
867
  "sep_token": "[SEP]",
868
- "tokenizer_class": "PreTrainedTokenizerFast",
 
 
869
  "unk_token": "[UNK]"
870
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "501": {
 
 
 
 
 
 
 
 
4
  "content": "[CLS]",
5
  "lstrip": false,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "502": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "content": "[MASK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "503": {
20
+ "content": "[PAD]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "504": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "505": {
36
+ "content": "[UNK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
+ "strip_accents": false,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b348627466e0fdf9f994b173b29f651e8ec5dba3094cd956536e967f78a1f7c
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f552924dcb181b3394429754b83fc73ed7c3199e8ff1a2b6fa4060aa0e6378
3
  size 4792