Hugging Face's logo

w11wo
/
indonesian-roberta-base-nerp-tagger

Token Classification
Transformers
TensorBoard
Safetensors
Indonesian
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
w11wo commited on
Commit
f758e25
•
1 Parent(s): 06db064

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. config.json +54 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Feb19_10-38-24_bookbot-h100/events.out.tfevents.1708339105.bookbot-h100.6633.0 +3 -0
  5. runs/Feb19_10-39-42_bookbot-h100/events.out.tfevents.1708339182.bookbot-h100.6905.0 +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +57 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "flax-community/indonesian-roberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "I-PPL",
16
+ "1": "B-EVT",
17
+ "2": "B-PLC",
18
+ "3": "I-IND",
19
+ "4": "B-IND",
20
+ "5": "B-FNB",
21
+ "6": "I-EVT",
22
+ "7": "B-PPL",
23
+ "8": "I-PLC",
24
+ "9": "O",
25
+ "10": "I-FNB"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "B-EVT": 1,
31
+ "B-FNB": 5,
32
+ "B-IND": 4,
33
+ "B-PLC": 2,
34
+ "B-PPL": 7,
35
+ "I-EVT": 6,
36
+ "I-FNB": 10,
37
+ "I-IND": 3,
38
+ "I-PLC": 8,
39
+ "I-PPL": 0,
40
+ "O": 9
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "max_position_embeddings": 514,
44
+ "model_type": "roberta",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 1,
48
+ "position_embedding_type": "absolute",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.37.2",
51
+ "type_vocab_size": 1,
52
+ "use_cache": true,
53
+ "vocab_size": 50265
54
+ }
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:d7d17f949432d51f3f5dd13e2bce94ba0e85abf886e113d3aa226e9c83744936
3
+ size 496277924
runs/Feb19_10-38-24_bookbot-h100/events.out.tfevents.1708339105.bookbot-h100.6633.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a8f48bfdda926c9e92d8f30e64ea804704d706e4a3c68cd5ea2fdbd0fac51a
3
+ size 4942
runs/Feb19_10-39-42_bookbot-h100/events.out.tfevents.1708339182.bookbot-h100.6905.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36889635f581421390eb0969560320c6349d9266148253f8453c2b48d4642b1a
3
+ size 5401
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
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
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86629d1ca3b78e668534e9dde899380032777d582550df510f4c6ba85cdd6251
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff