Hugging Face's logo

Dulfary
/
roberta-large-bne-capitel-ner_spanish

Token Classification
Transformers
TensorBoard
Safetensors
Spanish
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Dulfary commited on
Commit
a5b1a97
•
1 Parent(s): c045c84

Training in progress, step 45

Browse files
Files changed (9) hide show
  1. config.json +67 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Jul25_04-52-48_3c575977aef2/events.out.tfevents.1721883679.3c575977aef2.1471.0 +3 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +62 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-large-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": 1024,
15
+ "id2label": {
16
+ "0": "B-AGE",
17
+ "1": "B-CONTACT",
18
+ "2": "B-DATE",
19
+ "3": "B-ID",
20
+ "4": "B-LOCATION",
21
+ "5": "B-NAME",
22
+ "6": "B-OTHER",
23
+ "7": "B-PROFESSION",
24
+ "8": "I-AGE",
25
+ "9": "I-CONTACT",
26
+ "10": "I-DATE",
27
+ "11": "I-ID",
28
+ "12": "I-LOCATION",
29
+ "13": "I-NAME",
30
+ "14": "I-OTHER",
31
+ "15": "I-PROFESSION",
32
+ "16": "O"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 4096,
36
+ "label2id": {
37
+ "B-AGE": 0,
38
+ "B-CONTACT": 1,
39
+ "B-DATE": 2,
40
+ "B-ID": 3,
41
+ "B-LOCATION": 4,
42
+ "B-NAME": 5,
43
+ "B-OTHER": 6,
44
+ "B-PROFESSION": 7,
45
+ "I-AGE": 8,
46
+ "I-CONTACT": 9,
47
+ "I-DATE": 10,
48
+ "I-ID": 11,
49
+ "I-LOCATION": 12,
50
+ "I-NAME": 13,
51
+ "I-OTHER": 14,
52
+ "I-PROFESSION": 15,
53
+ "O": 16
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_position_embeddings": 514,
57
+ "model_type": "roberta",
58
+ "num_attention_heads": 16,
59
+ "num_hidden_layers": 24,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.42.4",
64
+ "type_vocab_size": 1,
65
+ "use_cache": true,
66
+ "vocab_size": 50262
67
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6782f8decc3f0fea4dc89b6ea4ffaf5838e7e732124116cfccc8812447cbbb4
3
+ size 1417346004
runs/Jul25_04-52-48_3c575977aef2/events.out.tfevents.1721883679.3c575977aef2.1471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d6ab6f12db875a8cfd39bebe5d164aafae00646889ffc5033c8d61efc6a0c8
3
+ size 6099
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "max_length": 512,
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "RobertaTokenizer",
58
+ "trim_offsets": true,
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e6d0445530e57ab9e2c964f367191f752193d75726eeacdcb92767755df97b
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff