Kudod commited on
Commit
7665c0a
1 Parent(s): 7e2433c

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 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base-v2",
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
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "Ti\u1ec1n c\u1ee5 th\u1ec3",
16
+ "2": "M\u00e3 \u0111\u01a1n",
17
+ "3": "S\u1ed1 c\u00f4ng",
18
+ "4": "V\u1ecb tr\u00ed",
19
+ "5": "S\u1ed1 \u0111i\u1ec3m",
20
+ "6": "C\u00f4ng",
21
+ "7": "L\u01b0\u01a1ng",
22
+ "8": "Ti\u1ec1n tr\u1eebu t\u01b0\u1ee3ng",
23
+ "9": "S\u1ed1 \u0111\u01a1n",
24
+ "10": "Th\u00e1ng tr\u1eebu t\u01b0\u1ee3ng",
25
+ "11": "Th\u1ee9",
26
+ "12": "Ph\u1ee5 c\u1ea5p",
27
+ "13": "S\u1ed1 gi\u1edd",
28
+ "14": "Kho\u1ea3ng th\u1eddi gian",
29
+ "15": "Th\u00f4ng tin CTT",
30
+ "16": "Kho",
31
+ "17": "H\u00ecnh th\u1ee9c l\u00e0m vi\u1ec7c",
32
+ "18": "Gi\u1ea5y t\u1edd",
33
+ "19": "\u0110\u1ee3t",
34
+ "20": "T\u1ef7 l\u1ec7",
35
+ "21": "M\u00e3 s\u1ed1 thu\u1ebf"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "C\u00f4ng": 6,
41
+ "Gi\u1ea5y t\u1edd": 18,
42
+ "H\u00ecnh th\u1ee9c l\u00e0m vi\u1ec7c": 17,
43
+ "Kho": 16,
44
+ "Kho\u1ea3ng th\u1eddi gian": 14,
45
+ "L\u01b0\u01a1ng": 7,
46
+ "M\u00e3 s\u1ed1 thu\u1ebf": 21,
47
+ "M\u00e3 \u0111\u01a1n": 2,
48
+ "O": 0,
49
+ "Ph\u1ee5 c\u1ea5p": 12,
50
+ "S\u1ed1 c\u00f4ng": 3,
51
+ "S\u1ed1 gi\u1edd": 13,
52
+ "S\u1ed1 \u0111i\u1ec3m": 5,
53
+ "S\u1ed1 \u0111\u01a1n": 9,
54
+ "Th\u00e1ng tr\u1eebu t\u01b0\u1ee3ng": 10,
55
+ "Th\u00f4ng tin CTT": 15,
56
+ "Th\u1ee9": 11,
57
+ "Ti\u1ec1n c\u1ee5 th\u1ec3": 1,
58
+ "Ti\u1ec1n tr\u1eebu t\u01b0\u1ee3ng": 8,
59
+ "T\u1ef7 l\u1ec7": 20,
60
+ "V\u1ecb tr\u00ed": 4,
61
+ "\u0110\u1ee3t": 19
62
+ },
63
+ "layer_norm_eps": 1e-05,
64
+ "max_position_embeddings": 258,
65
+ "model_type": "roberta",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 1,
69
+ "position_embedding_type": "absolute",
70
+ "tokenizer_class": "PhobertTokenizer",
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.44.2",
73
+ "type_vocab_size": 1,
74
+ "use_cache": true,
75
+ "vocab_size": 64001
76
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cc1fa13e76639545551916e399ffd71fee5023913ea178556a782b6d43838f
3
+ size 537722320
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:c9efdf7f518a355c65c32901e06ebec305552a8c307787f8ed9b2524615e479f
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff