dayvidwang commited on
Commit
a84ac0e
1 Parent(s): 5c59261

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-LOC",
13
+ "1": "O",
14
+ "2": "B-ORG",
15
+ "3": "B-PER",
16
+ "4": "I-PER",
17
+ "5": "B-MISC",
18
+ "6": "I-ORG",
19
+ "7": "I-LOC",
20
+ "8": "I-MISC",
21
+ "9": "MISC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "B-LOC": 0,
26
+ "B-MISC": 5,
27
+ "B-ORG": 2,
28
+ "B-PER": 3,
29
+ "I-LOC": 7,
30
+ "I-MISC": 8,
31
+ "I-ORG": 6,
32
+ "I-PER": 4,
33
+ "MISC": 9,
34
+ "O": 1
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "pad_token_id": 0,
41
+ "qa_dropout": 0.1,
42
+ "seq_classif_dropout": 0.2,
43
+ "sinusoidal_pos_embds": false,
44
+ "tie_weights_": true,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.30.1",
47
+ "vocab_size": 30522
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb034ccc9bdea163f7e0aa9e02e2eb41ae77113d2aa745a707ed91c1d0e0470
3
+ size 265517093
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": true,
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": "DistilBertTokenizer",
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:e542e2aca9c915443de46c7d8adf12017aa613e9960d769631de283aa5991c0c
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff