algiraldohe commited on
Commit
914b9f7
1 Parent(s): 1dcf3bc

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
13
+ "1": "B-BUS",
14
+ "2": "I-BUS",
15
+ "3": "B-TECHNOLOGY",
16
+ "4": "I-TECHNOLOGY",
17
+ "5": "B-TECHNICAL",
18
+ "6": "I-TECHNICAL",
19
+ "7": "B-SOFT",
20
+ "8": "I-SOFT"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "B-BUS": 1,
25
+ "B-SOFT": 7,
26
+ "B-TECHNICAL": 5,
27
+ "B-TECHNOLOGY": 3,
28
+ "I-BUS": 2,
29
+ "I-SOFT": 8,
30
+ "I-TECHNICAL": 6,
31
+ "I-TECHNOLOGY": 4,
32
+ "O": 0
33
+ },
34
+ "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "pad_token_id": 0,
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": false,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.29.1",
45
+ "vocab_size": 30522
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28162c09fcbb408240b5255572901f4cebd1211e0053f4f62f47cba20a63b3fa
3
+ size 265512613
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:ff84b98e6d324925e49cc25ab0af28d2029838be6ed7f124d74e685db07b6de0
3
+ size 3899
vocab.txt ADDED
The diff for this file is too large to render. See raw diff