nlp-chula commited on
Commit
0fad240
1 Parent(s): 686c1e6

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
3
+ "architectures": [
4
+ "CamembertForSequenceClassification"
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": "Brand",
16
+ "1": "Product/Service",
17
+ "2": "Environment",
18
+ "3": "Social&People",
19
+ "4": "Governance",
20
+ "5": "Economics",
21
+ "6": "Political",
22
+ "7": "Dividend",
23
+ "8": "Legal",
24
+ "9": "Investment",
25
+ "10": "M&A",
26
+ "11": "Profit/Loss",
27
+ "12": "Rating",
28
+ "13": "Others",
29
+ "14": "Financing",
30
+ "15": "Technology"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "Brand": 0,
36
+ "Dividend": 7,
37
+ "Economics": 5,
38
+ "Environment": 2,
39
+ "Financing": 14,
40
+ "Governance": 4,
41
+ "Investment": 9,
42
+ "Legal": 8,
43
+ "M&A": 10,
44
+ "Others": 13,
45
+ "Political": 6,
46
+ "Product/Service": 1,
47
+ "Profit/Loss": 11,
48
+ "Rating": 12,
49
+ "Social&People": 3,
50
+ "Technology": 15
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "camembert",
55
+ "num_attention_head": 12,
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "pad_token_id": 1,
59
+ "position_embedding_type": "absolute",
60
+ "problem_type": "single_label_classification",
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.33.2",
63
+ "type_vocab_size": 1,
64
+ "use_cache": true,
65
+ "vocab_size": 25005
66
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32cb33b9c3fc87ac3ff5103e4f1845457e8466673b9e727977ad3f095ee1e6fb
3
+ size 421095857
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
3
+ size 904693
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "clean_up_tokenization_spaces": true,
9
+ "cls_token": "<s>",
10
+ "eos_token": "</s>",
11
+ "mask_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<mask>",
14
+ "lstrip": true,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 1000000000000000019884624838656,
20
+ "pad_token": "<pad>",
21
+ "sep_token": "</s>",
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "CamembertTokenizer",
24
+ "unk_token": "<unk>"
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2053235e72ebe373a686b3d9df5c04460ec32ef29d4475788dbcca49a5946f0
3
+ size 4027