sandromck commited on
Commit
0d96b9a
·
1 Parent(s): e04abe6

Training in progress, epoch 1

Browse files
added_tokens.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "[CLS]": 2,
3
- "[MASK]": 4,
4
  "[PAD]": 0,
5
- "[SEP]": 3,
6
- "[UNK]": 1
7
  }
 
1
  {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
  "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
@@ -47,5 +47,5 @@
47
  "transformers_version": "4.34.0",
48
  "type_vocab_size": 2,
49
  "use_cache": true,
50
- "vocab_size": 30522
51
  }
 
1
  {
2
+ "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
47
  "transformers_version": "4.34.0",
48
  "type_vocab_size": 2,
49
  "use_cache": true,
50
+ "vocab_size": 28996
51
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c413f4574d70117be9a17105f5fb5a8b219aba2cb00d5b40a7794d2dfae3e1f7
3
- size 438028081
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b79fff8c9eba3df857e0b7a634491610cfbfb683d5237e2e7131a61fc92a06
3
+ size 433340209
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d0d18d79af91cc3b41e365cde4de7067ca32ac84a48a58306241157e814fcfb
3
- size 678903
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb26b43c98e8266ae3e99c2a583cf8315d73b33a17e6b20b4df7ff1f22392d34
3
+ size 669021
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -44,11 +44,9 @@
44
  "additional_special_tokens": [],
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
- "do_basic_tokenize": true,
48
- "do_lower_case": true,
49
  "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
  "strip_accents": null,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
44
  "additional_special_tokens": [],
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
+ "do_lower_case": false,
 
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 512,
 
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:459916504a2bb09dd37e60565884887e6edc993264734aff42782777f1639303
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd4889618d5a21f5307c3c064c64b92938a06c74e2030eb22b04d4d935d1216
3
  size 4091
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff