Hugging Face's logo

isergazin
/
mmodel_v7

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
isergazin commited on
Commit
4beb4b7
·
verified ·
1 Parent(s): 47b97fc

End of training

Browse files
Files changed (8) hide show
  1. README.md +67 -0
  2. config.json +136 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: ai-forever/ruBert-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: mmodel_v7
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # mmodel_v7
19
+
20
+ This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4323
23
+ - Accuracy: 0.9040
24
+ - F1: 0.9015
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0002
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.517 | 1.0 | 1523 | 0.4415 | 0.8809 | 0.8692 |
56
+ | 0.3514 | 2.0 | 3046 | 0.4008 | 0.8953 | 0.8870 |
57
+ | 0.2396 | 3.0 | 4569 | 0.3796 | 0.9034 | 0.9010 |
58
+ | 0.1594 | 4.0 | 6092 | 0.3798 | 0.9065 | 0.9034 |
59
+ | 0.1006 | 5.0 | 7615 | 0.4323 | 0.9040 | 0.9015 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.46.3
65
+ - Pytorch 2.5.1
66
+ - Datasets 3.1.0
67
+ - Tokenizers 0.20.3
config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/ruBert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "\u041f\u043e\u0436\u0430\u0440\u044b",
15
+ "2": "\u0417\u0430\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u0435 \u043f\u043e\u0434 \u0441\u0442\u0440\u0430\u0436\u0443",
16
+ "3": "\u0412\u0437\u044f\u0442\u043a\u0438",
17
+ "4": "\u0423\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0435 \u043e\u0431\u0432\u0438\u043d\u0435\u043d\u0438\u0435",
18
+ "5": "\u0422\u0435\u0440\u0430\u043a\u0442",
19
+ "6": "\u042d\u043a\u0441\u0442\u0440\u0435\u043c\u0438\u0437\u043c",
20
+ "7": "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043f\u0440\u0438\u0431\u044b\u043b\u0438",
21
+ "8": "\u0410\u0432\u0438\u0430\u043a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u0430",
22
+ "9": "\u0417\u0435\u043c\u043b\u0435\u0442\u0440\u044f\u0441\u0435\u043d\u0438\u0435",
23
+ "10": "\u041e\u0442\u0437\u044b\u0432 \u043f\u0440\u043e\u0434\u0443\u043a\u0446\u0438\u0438",
24
+ "11": "\u041a\u043e\u0440\u0440\u0443\u043f\u0446\u0438\u044f",
25
+ "12": "\u0420\u043e\u0441\u0442 \u0443\u0431\u044b\u0442\u043a\u043e\u0432",
26
+ "13": "\u0420\u0430\u0441\u0442\u0440\u0430\u0442\u0430 \u0434\u0435\u043d\u0435\u0436\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432",
27
+ "14": "\u0423\u0442\u0435\u0447\u043a\u0430 \u043d\u0435\u0444\u0442\u0438",
28
+ "15": "\u041a\u043e\u0440\u0430\u0431\u043b\u0435\u043a\u0440\u0443\u0448\u0435\u043d\u0438\u0435",
29
+ "16": "\u041f\u0440\u0438\u0432\u043b\u0435\u0447\u0435\u043d\u0438\u0435 \u043a \u0443\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0439 \u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0441\u0442\u0438",
30
+ "17": "\u0410\u043a\u0446\u0438\u043e\u043d\u0435\u0440\u043d\u044b\u0439 \u043a\u043e\u043d\u0444\u043b\u0438\u043a\u0442",
31
+ "18": "\u0418\u0437\u0432\u0435\u0440\u0436\u0435\u043d\u0438\u0435 \u0432\u0443\u043b\u043a\u0430\u043d\u0430",
32
+ "19": "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u0437\u0430\u043a\u043e\u043d\u0430",
33
+ "20": "\u041e\u0431\u0432\u0430\u043b",
34
+ "21": "\u041f\u0440\u043e\u0442\u0438\u0432\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0435 \u043a\u043e\u0440\u0440\u0443\u043f\u0446\u0438\u0438",
35
+ "22": "\u0417\u0430\u043a\u0440\u044b\u0442\u0438\u0435 \u043f\u0440\u0435\u0434\u043f\u0440\u0438\u044f\u0442\u0438\u044f \u0438\u043b\u0438 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0441\u0442\u0432\u0430",
36
+ "23": "\u0423\u0431\u0438\u0439\u0441\u0442\u0432\u043e",
37
+ "24": "\u041d\u0430\u0432\u043e\u0434\u043d\u0435\u043d\u0438\u0435",
38
+ "25": "\u0423\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0435 \u0437\u0430\u0434\u0435\u0440\u0436\u0430\u043d\u0438\u0435",
39
+ "26": "\u0422\u0435\u0445\u043d\u043e\u0433\u0435\u043d\u043d\u044b\u0435 \u043a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u044b",
40
+ "27": "\u0423\u0431\u044b\u0442\u043a\u0438",
41
+ "28": "\u0421\u0442\u0438\u0445\u0438\u0439\u043d\u044b\u0435 \u0431\u0435\u0434\u0441\u0442\u0432\u0438\u044f",
42
+ "29": "\u0427\u0440\u0435\u0437\u0432\u044b\u0447\u0430\u0439\u043d\u044b\u0435 \u043f\u0440\u043e\u0438\u0441\u0448\u0435\u0441\u0442\u0432\u0438\u044f, \u0447\u0440\u0435\u0437\u0432\u044b\u0447\u0430\u0439\u043d\u044b\u0435 \u0441\u0438\u0442\u0443\u0430\u0446\u0438\u0438",
43
+ "30": "\u041f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430 \u0442\u0435\u0440\u0440\u043e\u0440\u0438\u0441\u0442\u043e\u0432",
44
+ "31": "\u042d\u043a\u043e\u043d\u043e\u043c\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u0435\u0441\u0442\u0443\u043f\u043b\u0435\u043d\u0438\u044f",
45
+ "32": "\u0424\u0438\u043d\u0430\u043d\u0441\u043e\u0432\u044b\u0435 \u0437\u0430\u0442\u0440\u0443\u0434\u043d\u0435\u043d\u0438\u044f",
46
+ "33": "\u041f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0441 \u0430\u043a\u0442\u0438\u0432\u0430\u043c\u0438",
47
+ "34": "\u0412\u043e\u0437\u0431\u0443\u0436\u0434\u0435\u043d\u0438\u0435 \u0443\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0433\u043e \u0434\u0435\u043b\u0430",
48
+ "35": "\u0417\u0430\u043a\u0440\u044b\u0442\u0438\u0435 \u0444\u0438\u043b\u0438\u0430\u043b\u0430, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u0430",
49
+ "36": "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043f\u0440\u043e\u0434\u0430\u0436",
50
+ "37": "\u0416\u0430\u043b\u043e\u0431\u044b \u043f\u043e\u0442\u0440\u0435\u0431\u0438\u0442\u0435\u043b\u0435\u0439",
51
+ "38": "\u042f\u0434\u0435\u0440\u043d\u044b\u0439 \u0432\u0437\u0440\u044b\u0432",
52
+ "39": "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u043e\u0431\u044f\u0437\u0430\u043d\u043d\u043e\u0441\u0442\u0435\u0439",
53
+ "40": "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u043f\u0440\u0430\u0432 \u0430\u043a\u0446\u0438\u043e\u043d\u0435\u0440\u043e\u0432",
54
+ "41": "\u041e\u0442\u043c\u044b\u0432\u0430\u043d\u0438\u0435 \u0434\u0435\u043d\u0435\u0433",
55
+ "42": "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e",
56
+ "43": "\u0412\u0437\u0440\u044b\u0432 \u0433\u0430\u0437\u0430",
57
+ "44": "\u0412\u044b\u0435\u043c\u043a\u0438",
58
+ "45": "\u0411\u0435\u0441\u043f\u043e\u0440\u044f\u0434\u043a\u0438, \u043a\u043e\u043d\u0444\u043b\u0438\u043a\u0442\u044b \u0438 \u0432\u043e\u0439\u043d\u044b",
59
+ "46": "\u041a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u044b, \u043a\u0440\u0443\u0448\u0435\u043d\u0438\u044f",
60
+ "47": "\u041c\u0430\u043d\u0438\u043f\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u044b\u043d\u043a\u043e\u043c",
61
+ "48": "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043c\u0435\u0442\u0435\u043e\u0440\u0438\u0442\u0430",
62
+ "49": "\u041d\u0430\u043f\u0430\u0434\u0435\u043d\u0438\u0435"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "label2id": {
67
+ "O": 0,
68
+ "\u0410\u0432\u0438\u0430\u043a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u0430": 8,
69
+ "\u0410\u043a\u0446\u0438\u043e\u043d\u0435\u0440\u043d\u044b\u0439 \u043a\u043e\u043d\u0444\u043b\u0438\u043a\u0442": 17,
70
+ "\u0411\u0435\u0441\u043f\u043e\u0440\u044f\u0434\u043a\u0438, \u043a\u043e\u043d\u0444\u043b\u0438\u043a\u0442\u044b \u0438 \u0432\u043e\u0439\u043d\u044b": 45,
71
+ "\u0412\u0437\u0440\u044b\u0432 \u0433\u0430\u0437\u0430": 43,
72
+ "\u0412\u0437\u044f\u0442\u043a\u0438": 3,
73
+ "\u0412\u043e\u0437\u0431\u0443\u0436\u0434\u0435\u043d\u0438\u0435 \u0443\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0433\u043e \u0434\u0435\u043b\u0430": 34,
74
+ "\u0412\u044b\u0435\u043c\u043a\u0438": 44,
75
+ "\u0416\u0430\u043b\u043e\u0431\u044b \u043f\u043e\u0442\u0440\u0435\u0431\u0438\u0442\u0435\u043b\u0435\u0439": 37,
76
+ "\u0417\u0430\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u0435 \u043f\u043e\u0434 \u0441\u0442\u0440\u0430\u0436\u0443": 2,
77
+ "\u0417\u0430\u043a\u0440\u044b\u0442\u0438\u0435 \u043f\u0440\u0435\u0434\u043f\u0440\u0438\u044f\u0442\u0438\u044f \u0438\u043b\u0438 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0441\u0442\u0432\u0430": 22,
78
+ "\u0417\u0430\u043a\u0440\u044b\u0442\u0438\u0435 \u0444\u0438\u043b\u0438\u0430\u043b\u0430, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u0442\u0435\u043b\u044c\u0441\u0442\u0432\u0430": 35,
79
+ "\u0417\u0435\u043c\u043b\u0435\u0442\u0440\u044f\u0441\u0435\u043d\u0438\u0435": 9,
80
+ "\u0418\u0437\u0432\u0435\u0440\u0436\u0435\u043d\u0438\u0435 \u0432\u0443\u043b\u043a\u0430\u043d\u0430": 18,
81
+ "\u041a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u044b, \u043a\u0440\u0443\u0448\u0435\u043d\u0438\u044f": 46,
82
+ "\u041a\u043e\u0440\u0430\u0431\u043b\u0435\u043a\u0440\u0443\u0448\u0435\u043d\u0438\u0435": 15,
83
+ "\u041a\u043e\u0440\u0440\u0443\u043f\u0446\u0438\u044f": 11,
84
+ "\u041c\u0430\u043d\u0438\u043f\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u044b\u043d\u043a\u043e\u043c": 47,
85
+ "\u041c\u043e\u0448\u0435\u043d\u043d\u0438\u0447\u0435\u0441\u0442\u0432\u043e": 42,
86
+ "\u041d\u0430\u0432\u043e\u0434\u043d\u0435\u043d\u0438\u0435": 24,
87
+ "\u041d\u0430\u043f\u0430\u0434\u0435\u043d\u0438\u0435": 49,
88
+ "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u0437\u0430\u043a\u043e\u043d\u0430": 19,
89
+ "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u043e\u0431\u044f\u0437\u0430\u043d\u043d\u043e\u0441\u0442\u0435\u0439": 39,
90
+ "\u041d\u0430\u0440\u0443\u0448\u0435\u043d\u0438\u0435 \u043f\u0440\u0430\u0432 \u0430\u043a\u0446\u0438\u043e\u043d\u0435\u0440\u043e\u0432": 40,
91
+ "\u041e\u0431\u0432\u0430\u043b": 20,
92
+ "\u041e\u0442\u0437\u044b\u0432 \u043f\u0440\u043e\u0434\u0443\u043a\u0446\u0438\u0438": 10,
93
+ "\u041e\u0442\u043c\u044b\u0432\u0430\u043d\u0438\u0435 \u0434\u0435\u043d\u0435\u0433": 41,
94
+ "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043c\u0435\u0442\u0435\u043e\u0440\u0438\u0442\u0430": 48,
95
+ "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043f\u0440\u0438\u0431\u044b\u043b\u0438": 7,
96
+ "\u041f\u0430\u0434\u0435\u043d\u0438\u0435 \u043f\u0440\u043e\u0434\u0430\u0436": 36,
97
+ "\u041f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430 \u0442\u0435\u0440\u0440\u043e\u0440\u0438\u0441\u0442\u043e\u0432": 30,
98
+ "\u041f\u043e\u0436\u0430\u0440\u044b": 1,
99
+ "\u041f\u0440\u0438\u0432\u043b\u0435\u0447\u0435\u043d\u0438\u0435 \u043a \u0443\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0439 \u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0441\u0442\u0438": 16,
100
+ "\u041f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u0441 \u0430\u043a\u0442\u0438\u0432\u0430\u043c\u0438": 33,
101
+ "\u041f\u0440\u043e\u0442\u0438\u0432\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0435 \u043a\u043e\u0440\u0440\u0443\u043f\u0446\u0438\u0438": 21,
102
+ "\u0420\u0430\u0441\u0442\u0440\u0430\u0442\u0430 \u0434\u0435\u043d\u0435\u0436\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432": 13,
103
+ "\u0420\u043e\u0441\u0442 \u0443\u0431\u044b\u0442\u043a\u043e\u0432": 12,
104
+ "\u0421\u0442\u0438\u0445\u0438\u0439\u043d\u044b\u0435 \u0431\u0435\u0434\u0441\u0442\u0432\u0438\u044f": 28,
105
+ "\u0422\u0435\u0440\u0430\u043a\u0442": 5,
106
+ "\u0422\u0435\u0445\u043d\u043e\u0433\u0435\u043d\u043d\u044b\u0435 \u043a\u0430\u0442\u0430\u0441\u0442\u0440\u043e\u0444\u044b": 26,
107
+ "\u0423\u0431\u0438\u0439\u0441\u0442\u0432\u043e": 23,
108
+ "\u0423\u0431\u044b\u0442\u043a\u0438": 27,
109
+ "\u0423\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0435 \u0437\u0430\u0434\u0435\u0440\u0436\u0430\u043d\u0438\u0435": 25,
110
+ "\u0423\u0433\u043e\u043b\u043e\u0432\u043d\u043e\u0435 \u043e\u0431\u0432\u0438\u043d\u0435\u043d\u0438\u0435": 4,
111
+ "\u0423\u0442\u0435\u0447\u043a\u0430 \u043d\u0435\u0444\u0442\u0438": 14,
112
+ "\u0424\u0438\u043d\u0430\u043d\u0441\u043e\u0432\u044b\u0435 \u0437\u0430\u0442\u0440\u0443\u0434\u043d\u0435\u043d\u0438\u044f": 32,
113
+ "\u0427\u0440\u0435\u0437\u0432\u044b\u0447\u0430\u0439\u043d\u044b\u0435 \u043f\u0440\u043e\u0438\u0441\u0448\u0435\u0441\u0442\u0432\u0438\u044f, \u0447\u0440\u0435\u0437\u0432\u044b\u0447\u0430\u0439\u043d\u044b\u0435 \u0441\u0438\u0442\u0443\u0430\u0446\u0438\u0438": 29,
114
+ "\u042d\u043a\u043e\u043d\u043e\u043c\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u0435\u0441\u0442\u0443\u043f\u043b\u0435\u043d\u0438\u044f": 31,
115
+ "\u042d\u043a\u0441\u0442\u0440\u0435\u043c\u0438\u0437\u043c": 6,
116
+ "\u042f\u0434\u0435\u0440\u043d\u044b\u0439 \u0432\u0437\u0440\u044b\u0432": 38
117
+ },
118
+ "layer_norm_eps": 1e-12,
119
+ "max_position_embeddings": 512,
120
+ "model_type": "bert",
121
+ "num_attention_heads": 12,
122
+ "num_hidden_layers": 12,
123
+ "pad_token_id": 0,
124
+ "pooler_fc_size": 768,
125
+ "pooler_num_attention_heads": 12,
126
+ "pooler_num_fc_layers": 3,
127
+ "pooler_size_per_head": 128,
128
+ "pooler_type": "first_token_transform",
129
+ "position_embedding_type": "absolute",
130
+ "problem_type": "single_label_classification",
131
+ "torch_dtype": "float32",
132
+ "transformers_version": "4.46.3",
133
+ "type_vocab_size": 2,
134
+ "use_cache": true,
135
+ "vocab_size": 120138
136
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994df05a34da47b3219c58a9a32fd04ba7a622cf7d3cc7a5e4ed44e39d67102f
3
+ size 713406664
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": 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": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf58e77457ac7024fe7006c234d43282b37f8f4e83bbc166441470972130800a
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff