Hugging Face's logo

trickstar0
/
ner-education-hcmut

PyTorch
TensorBoard
Safetensors
electra
Generated from Trainer
Model card Files Metrics Community
trickstar0 commited on
Commit
960e74d
•
1 Parent(s): b9d13b6

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +53 -0
  2. model.safetensors +3 -0
  3. runs/Aug20_16-33-49_d7a8d4316306/events.out.tfevents.1724171638.d7a8d4316306.319.0 +3 -0
  4. runs/Aug20_16-33-49_d7a8d4316306/events.out.tfevents.1724172000.d7a8d4316306.319.1 +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +64 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NlpHUST/ner-vietnamese-electra-base",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "finetuning_task": "ner",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-LOCATION",
15
+ "1": "B-MISCELLANEOUS",
16
+ "2": "B-ORGANIZATION",
17
+ "3": "B-PERSON",
18
+ "4": "I-LOCATION",
19
+ "5": "I-MISCELLANEOUS",
20
+ "6": "I-ORGANIZATION",
21
+ "7": "I-PERSON",
22
+ "8": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-LOCATION": 0,
28
+ "B-MISCELLANEOUS": 1,
29
+ "B-ORGANIZATION": 2,
30
+ "B-PERSON": 3,
31
+ "I-LOCATION": 4,
32
+ "I-MISCELLANEOUS": 5,
33
+ "I-ORGANIZATION": 6,
34
+ "I-PERSON": 7,
35
+ "O": 8
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "electra",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "summary_activation": "gelu",
45
+ "summary_last_dropout": 0.1,
46
+ "summary_type": "first",
47
+ "summary_use_proj": true,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.42.4",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 62000
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87ce03111c6526a973d4690f3513b6445ba181fba6183bfab17bcce32d8e33d
3
+ size 532318620
runs/Aug20_16-33-49_d7a8d4316306/events.out.tfevents.1724171638.d7a8d4316306.319.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355e81d89b840eeba4fd2aac7ae60d2c3261e2689227439a8a73a2e15e7be752
3
+ size 16264
runs/Aug20_16-33-49_d7a8d4316306/events.out.tfevents.1724172000.d7a8d4316306.319.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5baeb3773ab0b01711c0827bd43f14ccac3c40dc845453a86a2169600b1879a2
3
+ size 6699
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 256,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "ElectraTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ceabb426ef591844e1ec8a99f4fe8d9165d747db7cd4d7b84382975bec4bfd
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff