raulgdp commited on
Commit
66d3efa
1 Parent(s): 86a2b51

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,13 +1,16 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
- "BertForTokenClassification"
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": 768,
12
  "id2label": {
13
  "0": "O",
@@ -33,16 +36,16 @@
33
  "I-PER": 2,
34
  "O": 0
35
  },
36
- "layer_norm_eps": 1e-12,
37
- "max_position_embeddings": 512,
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": "4.32.0.dev0",
45
- "type_vocab_size": 2,
46
  "use_cache": true,
47
- "vocab_size": 28996
48
  }
 
1
  {
2
+ "_name_or_path": "BSC-LT/roberta-base-bne-capitel-ner",
3
  "architectures": [
4
+ "RobertaForTokenClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "ner",
11
  "gradient_checkpointing": false,
12
  "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.0,
14
  "hidden_size": 768,
15
  "id2label": {
16
  "0": "O",
 
36
  "I-PER": 2,
37
  "O": 0
38
  },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 514,
41
+ "model_type": "roberta",
42
  "num_attention_heads": 12,
43
  "num_hidden_layers": 12,
44
+ "pad_token_id": 1,
45
  "position_embedding_type": "absolute",
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.30.2",
48
+ "type_vocab_size": 1,
49
  "use_cache": true,
50
+ "vocab_size": 50262
51
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f15df7bf1b0ed2e15fd72bd5112c737a6ffd99e5c475a4a537d0d2e1659fdf
3
- size 430974121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ff020eb42abe39acd083f4ede4a7323e88ee1c204f7710c4d74b41f05d8299
3
+ size 496311341
runs/Jul27_16-08-40_fe790086439f/events.out.tfevents.1690474281.fe790086439f.28.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d30bb049deb45866cc2852a1da6a8ada6d90f26cb7212e1446e77e04480abb
3
+ size 5098
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": false,
5
- "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "BertTokenizer",
12
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
1
  {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_len": 512,
38
  "model_max_length": 512,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a85cfd7e06150d50eb75de23e2bb3bb0d9fa08398bb1dea84d61dc20df2b03aa
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d791e229ec2467a4b1e0badcef79f4b41f88fbda1eee19d94245d41a8f56eb65
3
  size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff