kien-vu-uet commited on
Commit
f775f47
1 Parent(s): f0070f2

Training in progress, step 100

Browse files
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kien-vu-uet/ViBERT-finetuned-SSA",
3
+ "architectures": [
4
+ "BertConvForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "BertConvConfig": "components.bert_cnn.BertConvConfig",
9
+ "BertConvForSequenceClassification": "components.bert_cnn.BertConvForSequenceClassification"
10
+ },
11
+ "capture_sizes": [
12
+ 2,
13
+ 3,
14
+ 4,
15
+ 5
16
+ ],
17
+ "classifier_dropout": null,
18
+ "directionality": "bidi",
19
+ "hidden_act": "gelu",
20
+ "hidden_dropout_prob": 0.1,
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "Unrelated",
24
+ "1": "Agree",
25
+ "2": "Disagree",
26
+ "3": "Discuss"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": null,
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bertconv",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "pooler_fc_size": 768,
39
+ "pooler_num_attention_heads": 12,
40
+ "pooler_num_fc_layers": 3,
41
+ "pooler_size_per_head": 128,
42
+ "pooler_type": "first_token_transform",
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.41.0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 38168
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b8c747f97562ee95c9c939d0404922e0466181f78a09b1b7ba3e902690340e
3
+ size 467761048
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 514,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "stride": 0,
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "only_second",
60
+ "unk_token": "[UNK]"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59225f79b2dbf0a36c97a03039c4517280c0558443c89705ce96918da3e4721
3
+ size 4795
vocab.txt ADDED
The diff for this file is too large to render. See raw diff