DrewG commited on
Commit
bc28ccd
·
1 Parent(s): f7e5b33

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "ADJ",
14
+ "1": "ADP",
15
+ "2": ".",
16
+ "3": "ADV",
17
+ "4": "AUX",
18
+ "5": "SYM",
19
+ "6": "INTJ",
20
+ "7": "CONJ",
21
+ "8": "X",
22
+ "9": "NOUN",
23
+ "10": "DET",
24
+ "11": "PROPN",
25
+ "12": "NUM",
26
+ "13": "VERB",
27
+ "14": "PRT",
28
+ "15": "PRON",
29
+ "16": "SCONJ"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ ".": 2,
35
+ "ADJ": 0,
36
+ "ADP": 1,
37
+ "ADV": 3,
38
+ "AUX": 4,
39
+ "CONJ": 7,
40
+ "DET": 10,
41
+ "INTJ": 6,
42
+ "NOUN": 9,
43
+ "NUM": 12,
44
+ "PRON": 15,
45
+ "PROPN": 11,
46
+ "PRT": 14,
47
+ "SCONJ": 16,
48
+ "SYM": 5,
49
+ "VERB": 13,
50
+ "X": 8
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.29.2",
61
+ "type_vocab_size": 2,
62
+ "use_cache": true,
63
+ "vocab_size": 28996
64
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b764b60209669b5f3d7274ec4c4460915791e65a3aae4c6a69041fa325f6c56c
3
+ size 431000365
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231cbb3074b7d9e9825a7c5c3ab6d9fb97e661da81fcc4b9bd87fb8b3d862184
3
+ size 3899
vocab.txt ADDED
The diff for this file is too large to render. See raw diff