burkelive commited on
Commit
00d0113
1 Parent(s): b526055

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": -100,
13
+ "1": 0,
14
+ "2": 1,
15
+ "3": 2,
16
+ "4": 3,
17
+ "5": 4,
18
+ "6": 5,
19
+ "7": 6,
20
+ "8": 7,
21
+ "9": 8,
22
+ "10": 9,
23
+ "11": 10,
24
+ "12": 11,
25
+ "13": 12,
26
+ "14": 13,
27
+ "15": 14,
28
+ "16": 15,
29
+ "17": 16,
30
+ "18": 17,
31
+ "19": 18
32
+ },
33
+ "initializer_range": 0.02,
34
+ "label2id": {
35
+ "-100": 0,
36
+ "0": 1,
37
+ "1": 2,
38
+ "2": 3,
39
+ "3": 4,
40
+ "4": 5,
41
+ "5": 6,
42
+ "6": 7,
43
+ "7": 8,
44
+ "8": 9,
45
+ "9": 10,
46
+ "10": 11,
47
+ "11": 12,
48
+ "12": 13,
49
+ "13": 14,
50
+ "14": 15,
51
+ "15": 16,
52
+ "16": 17,
53
+ "17": 18,
54
+ "18": 19
55
+ },
56
+ "max_position_embeddings": 512,
57
+ "model_type": "distilbert",
58
+ "n_heads": 12,
59
+ "n_layers": 6,
60
+ "pad_token_id": 0,
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.40.1",
67
+ "vocab_size": 30522
68
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78188bc455d74efa94930128af9102d5870ba3ebda10cf3e7a734210ad374a4
3
+ size 265525384
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f38e643f1a73cda225d2d3cc6315e438b983dec00fb4e9991557df5a42a6ae5
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff