JuanVC commited on
Commit
8fe1e82
1 Parent(s): 1cb120b

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
@@ -38,11 +38,12 @@
38
  "model_type": "bert",
39
  "num_attention_heads": 12,
40
  "num_hidden_layers": 12,
41
- "pad_token_id": 0,
 
42
  "position_embedding_type": "absolute",
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.41.0",
45
  "type_vocab_size": 2,
46
  "use_cache": true,
47
- "vocab_size": 28996
48
  }
 
1
  {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
38
  "model_type": "bert",
39
  "num_attention_heads": 12,
40
  "num_hidden_layers": 12,
41
+ "output_past": true,
42
+ "pad_token_id": 1,
43
  "position_embedding_type": "absolute",
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.41.0",
46
  "type_vocab_size": 2,
47
  "use_cache": true,
48
+ "vocab_size": 31002
49
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:454e48a0e27d8f9f888e26b62414418266b8125a3b5ddac0a738afafe7f0205c
3
- size 430929740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d45b885b11d2aa75d9fbddde0d2942f6f501e8e76ed6a49fe4115cdd6e34de
3
+ size 437092180
runs/May28_15-50-17_7337f2703983/events.out.tfevents.1716911446.7337f2703983.949.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194598726f780d145ff4bb1e954cc70a2940961372dbbf70e0bedb74b02e57ca
3
+ size 5651
runs/May28_15-50-17_7337f2703983/events.out.tfevents.1716911714.7337f2703983.949.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac4a6358eaac9832f53527ab2ed00ac76fed87f6158dced03f9775705e56f91
3
+ size 6123
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,39 +1,39 @@
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,
@@ -43,12 +43,14 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
 
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
- "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[MASK]",
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
+ "3": {
20
+ "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "4": {
28
+ "content": "[CLS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "5": {
36
+ "content": "[SEP]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
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": 512,
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]"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e696c2a58c51280c9165a93779818e0b40f5eb183cda48792c2bd1c55e3f9f9a
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eda0bba9cac7979fd6e479bdef17c26c79f27e08c9f6d6a5d8ebd92c4f276a
3
  size 5176
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff