NouRed commited on
Commit
0f1814a
1 Parent(s): a50f00d

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
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": "I-product",
13
+ "1": "B-group",
14
+ "2": "I-location",
15
+ "3": "B-corporation",
16
+ "4": "B-location",
17
+ "5": "B-creative-work",
18
+ "6": "I-creative-work",
19
+ "7": "I-corporation",
20
+ "8": "I-group",
21
+ "9": "O",
22
+ "10": "B-product",
23
+ "11": "I-person",
24
+ "12": "B-person"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "B-corporation": 3,
29
+ "B-creative-work": 5,
30
+ "B-group": 1,
31
+ "B-location": 4,
32
+ "B-person": 12,
33
+ "B-product": 10,
34
+ "I-corporation": 7,
35
+ "I-creative-work": 6,
36
+ "I-group": 8,
37
+ "I-location": 2,
38
+ "I-person": 11,
39
+ "I-product": 0,
40
+ "O": 9
41
+ },
42
+ "max_position_embeddings": 512,
43
+ "model_type": "distilbert",
44
+ "n_heads": 12,
45
+ "n_layers": 6,
46
+ "output_past": true,
47
+ "pad_token_id": 0,
48
+ "qa_dropout": 0.1,
49
+ "seq_classif_dropout": 0.2,
50
+ "sinusoidal_pos_embds": false,
51
+ "tie_weights_": true,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.23.0",
54
+ "vocab_size": 28996
55
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f1df93326d6dada7517a5b4ca7948e8eee8730598a5bd88f2167ce05f318d7
3
+ size 260837237
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16049c8b47ad7e69f3a1daaa764a7a4ce53f0af9d9cfa7e9a8869710694548bc
3
+ size 3311
vocab.txt ADDED
The diff for this file is too large to render. See raw diff