Subhadeep commited on
Commit
5b6c9ca
·
1 Parent(s): c2d59bd

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "person_name",
14
+ "2": "amount",
15
+ "3": "mobile_number",
16
+ "4": "plan_name",
17
+ "5": "tenure"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "O": 0,
22
+ "amount": 2,
23
+ "mobile_number": 3,
24
+ "person_name": 1,
25
+ "plan_name": 4,
26
+ "tenure": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.30.2",
39
+ "vocab_size": 30522
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a45096851e47bd2d3e13ea2ed4c4fc205bd1ec389a75d7674402fc04fad715
3
+ size 265504805
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "special_tokens": [
10
+ "[UNK]",
11
+ "[CLS]",
12
+ "[SEP]",
13
+ "[PAD]",
14
+ "[MASK]"
15
+ ],
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "DistilBertTokenizer",
19
+ "unk_token": "[UNK]"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a975ffc726a14d3d4d197f01029641a6a75aeeb2832439248d7d130bbd7b12b
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff