yanezh commited on
Commit
aa5fc2a
1 Parent(s): 9370fc5

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "B-NAME_STUDENT",
13
+ "1": "I-NAME_STUDENT",
14
+ "2": "B-EMAIL",
15
+ "3": "I-EMAIL",
16
+ "4": "B-USERNAME",
17
+ "5": "I-USERNAME",
18
+ "6": "B-ID_NUM",
19
+ "7": "I-ID_NUM",
20
+ "8": "B-PHONE_NUM",
21
+ "9": "I-PHONE_NUM",
22
+ "10": "B-URL_PERSONAL",
23
+ "11": "I-URL_PERSONAL",
24
+ "12": "B-STREET_ADDRESS",
25
+ "13": "I-STREET_ADDRESS",
26
+ "14": "O"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "B-EMAIL": 2,
31
+ "B-ID_NUM": 6,
32
+ "B-NAME_STUDENT": 0,
33
+ "B-PHONE_NUM": 8,
34
+ "B-STREET_ADDRESS": 12,
35
+ "B-URL_PERSONAL": 10,
36
+ "B-USERNAME": 4,
37
+ "I-EMAIL": 3,
38
+ "I-ID_NUM": 7,
39
+ "I-NAME_STUDENT": 1,
40
+ "I-PHONE_NUM": 9,
41
+ "I-STREET_ADDRESS": 13,
42
+ "I-URL_PERSONAL": 11,
43
+ "I-USERNAME": 5,
44
+ "O": 14
45
+ },
46
+ "max_position_embeddings": 512,
47
+ "model_type": "distilbert",
48
+ "n_heads": 12,
49
+ "n_layers": 6,
50
+ "pad_token_id": 0,
51
+ "qa_dropout": 0.1,
52
+ "seq_classif_dropout": 0.2,
53
+ "sinusoidal_pos_embds": false,
54
+ "tie_weights_": true,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.35.2",
57
+ "vocab_size": 30522
58
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a043f60476bbcf5aea9bd1cf475bbf29efe851cb433fda636aac0898cd4357cb
3
+ size 265510004
runs/Feb07_10-32-32_1f6139f2984c/events.out.tfevents.1707301962.1f6139f2984c.468.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f9ec5775c1415ce18a4f5b358724973405f3fba7f626ad5930f87a09e8c014
3
+ size 5312
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 sha256:7ec3c76248d2c5f7fd2ad6f7e624196e7c2e4d33c5ecf3af6815779245d8a37f
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff