Hugging Face's logo

TunahanGokcimen
/
ernie-2.0-base-en

Token Classification
Transformers
TensorBoard
Safetensors
ernie
Generated from Trainer
Model card Files
xet
 Metrics Community
TunahanGokcimen commited on
Commit
0c577b5
·
verified ·
1 Parent(s): cd8330d

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +53 -0
  2. model.safetensors +3 -0
  3. runs/Jan28_20-38-41_e60506203a75/events.out.tfevents.1706474327.e60506203a75.3449.0 +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nghuyong/ernie-2.0-base-en",
3
+ "architectures": [
4
+ "ErnieForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-DNA",
14
+ "10": "I-RNA",
15
+ "2": "I-DNA",
16
+ "3": "B-protein",
17
+ "4": "I-protein",
18
+ "5": "B-cell_type",
19
+ "6": "I-cell_type",
20
+ "7": "B-cell_line",
21
+ "8": "I-cell_line",
22
+ "9": "B-RNA"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-DNA": "1",
28
+ "B-RNA": "9",
29
+ "B-cell_line": "7",
30
+ "B-cell_type": "5",
31
+ "B-protein": "3",
32
+ "I-DNA": "2",
33
+ "I-RNA": "10",
34
+ "I-cell_line": "8",
35
+ "I-cell_type": "6",
36
+ "I-protein": "4",
37
+ "O": "0"
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 512,
41
+ "model_type": "ernie",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 0,
45
+ "position_embedding_type": "absolute",
46
+ "task_type_vocab_size": 3,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.35.2",
49
+ "type_vocab_size": 4,
50
+ "use_cache": true,
51
+ "use_task_id": false,
52
+ "vocab_size": 30522
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b66ac4544dbded02880866124e22a060339d57571d9471db9e8ef4c7d23f2d9
3
+ size 435630100
runs/Jan28_20-38-41_e60506203a75/events.out.tfevents.1706474327.e60506203a75.3449.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d233256c06e49c8f89423146ff2fae9080041f81e024738cbd95e8734f278e2c
3
+ size 5821
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "full_tokenizer_file": null,
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,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0439f6008314404b17b589eea872a3bbabe7c67e76c6bf4d41a95c2f6f0774
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff