vitus9988 commited on
Commit
0d5609c
1 Parent(s): 485740b

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-base",
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": 768,
14
+ "id2label": {
15
+ "0": "B-PS",
16
+ "1": "I-PS",
17
+ "2": "B-AD",
18
+ "3": "I-AD",
19
+ "4": "B-CN",
20
+ "5": "I-CN",
21
+ "6": "B-BN",
22
+ "7": "I-BN",
23
+ "8": "B-DN",
24
+ "9": "I-DN",
25
+ "10": "B-RN",
26
+ "11": "I-RN",
27
+ "12": "B-PN",
28
+ "13": "I-PN",
29
+ "14": "B-PH",
30
+ "15": "I-PH",
31
+ "16": "B-EM",
32
+ "17": "I-EM",
33
+ "18": "B-DT",
34
+ "19": "I-DT",
35
+ "20": "O"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "B-AD": 2,
41
+ "B-BN": 6,
42
+ "B-CN": 4,
43
+ "B-DN": 8,
44
+ "B-DT": 18,
45
+ "B-EM": 16,
46
+ "B-PH": 14,
47
+ "B-PN": 12,
48
+ "B-PS": 0,
49
+ "B-RN": 10,
50
+ "I-AD": 3,
51
+ "I-BN": 7,
52
+ "I-CN": 5,
53
+ "I-DN": 9,
54
+ "I-DT": 19,
55
+ "I-EM": 17,
56
+ "I-PH": 15,
57
+ "I-PN": 13,
58
+ "I-PS": 1,
59
+ "I-RN": 11,
60
+ "O": 20
61
+ },
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 514,
64
+ "model_type": "roberta",
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 12,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "tokenizer_class": "BertTokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.40.2",
72
+ "type_vocab_size": 1,
73
+ "use_cache": true,
74
+ "vocab_size": 32000
75
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6535da4f21dc1175df7eea754421f809a2c2b57265cca02c00176d8706a8b04b
3
+ size 440198596
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
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": "[SEP]",
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
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0114dabf6b6284781c66a60ed81313ac58f0b32efd340112d0a68b368248a0
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff