Kudod commited on
Commit
1edc299
·
verified ·
1 Parent(s): e502727

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-large",
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": 1024,
14
+ "id2label": {
15
+ "0": "Email",
16
+ "1": "O",
17
+ "2": "S\u0110T",
18
+ "3": "M\u00e3 \u0111\u01a1n",
19
+ "4": "Ti\u1ec1n",
20
+ "5": "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n",
21
+ "6": "Gi\u1edd",
22
+ "7": "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng",
23
+ "8": "\u0110\u01a1n v\u1ecb \u0111o",
24
+ "9": "CCCD - CMT",
25
+ "10": "STK",
26
+ "11": "Ng\u00e2n h\u00e0ng",
27
+ "12": "Ca",
28
+ "13": "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3",
29
+ "14": "Ng\u00e0y",
30
+ "15": "T\u00ean ng\u01b0\u1eddi",
31
+ "16": "Kh\u1ed1i l\u01b0\u1ee3ng",
32
+ "17": "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3",
33
+ "18": "S\u0110T tr\u1eebu t\u01b0\u1ee3ng",
34
+ "19": "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng",
35
+ "20": "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 4096,
39
+ "label2id": {
40
+ "CCCD - CMT": 9,
41
+ "Ca": 12,
42
+ "Email": 0,
43
+ "Gi\u1edd": 6,
44
+ "Kh\u1ed1i l\u01b0\u1ee3ng": 16,
45
+ "M\u00e3 \u0111\u01a1n": 3,
46
+ "Ng\u00e0y": 14,
47
+ "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng": 7,
48
+ "Ng\u00e2n h\u00e0ng": 11,
49
+ "O": 1,
50
+ "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n": 5,
51
+ "STK": 10,
52
+ "S\u0110T": 2,
53
+ "S\u0110T tr\u1eebu t\u01b0\u1ee3ng": 18,
54
+ "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3": 13,
55
+ "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng": 20,
56
+ "Ti\u1ec1n": 4,
57
+ "T\u00ean ng\u01b0\u1eddi": 15,
58
+ "\u0110\u01a1n v\u1ecb \u0111o": 8,
59
+ "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3": 17,
60
+ "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng": 19
61
+ },
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 258,
64
+ "model_type": "roberta",
65
+ "num_attention_heads": 16,
66
+ "num_hidden_layers": 24,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "tokenizer_class": "PhobertTokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.44.0",
72
+ "type_vocab_size": 1,
73
+ "use_cache": true,
74
+ "vocab_size": 64001
75
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5e16b4939654969804aafbf701b6f5c8bd223219b7f720700fb140c2736220
3
+ size 1472588812
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "PhobertTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a8766987b3ebbc54ffd00c205e17ce83f7b7fb98057b09f7b0d6fa86a1b93c
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff