soymia commited on
Commit
3b450e6
1 Parent(s): 7d607a0

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Business",
13
+ "1": "Education",
14
+ "2": "Entertainment",
15
+ "3": "Life",
16
+ "4": "Other",
17
+ "5": "Productivity",
18
+ "6": "Technology"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "label2id": {
22
+ "Business": 0,
23
+ "Education": 1,
24
+ "Entertainment": 2,
25
+ "Life": 3,
26
+ "Other": 4,
27
+ "Productivity": 5,
28
+ "Technology": 6
29
+ },
30
+ "max_position_embeddings": 512,
31
+ "model_type": "distilbert",
32
+ "n_heads": 12,
33
+ "n_layers": 6,
34
+ "pad_token_id": 0,
35
+ "problem_type": "single_label_classification",
36
+ "qa_dropout": 0.1,
37
+ "seq_classif_dropout": 0.2,
38
+ "sinusoidal_pos_embds": false,
39
+ "tie_weights_": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.31.0",
42
+ "vocab_size": 30522
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c98a6c77dd8f8864622ab049b0cf54283e070e76612e49b04999fd8a63df9f9
3
+ size 267869485
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 sha256:8a705bdac3239ed5c61d459f49975c4cf27e38e872ad3898f49982c1f64f9c29
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff