Hugging Face's logo

odunola
/
bert-base-cased-ag-news

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
odunola commited on
Commit
21763e2
•
1 Parent(s): 1efc42f

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. config.json +28 -15
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +4 -2
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,25 +1,38 @@
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
  "initializer_range": 0.02,
 
 
 
 
 
 
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
  "pad_token_id": 0,
 
17
  "problem_type": "single_label_classification",
18
- "qa_dropout": 0.1,
19
- "seq_classif_dropout": 0.2,
20
- "sinusoidal_pos_embds": false,
21
- "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.34.1",
24
- "vocab_size": 30522
 
 
25
  }
 
1
  {
2
+ "_name_or_path": "lucasresck/bert-base-cased-ag-news",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3"
16
+ },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
  "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
  "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
  "problem_type": "single_label_classification",
 
 
 
 
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.34.1",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 28996
38
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7e5ee7b73393614d159984f0c8385b5f96f95b77dc27f40ff8963f5a186571
3
- size 267855533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898825db1f2b37e2994a7bd1b73be4a56ef7e675ebfc1c1fc23e1d79d0873b8f
3
+ size 433321777
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,13 +43,15 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b700878f3c9efb19a9d54ea81c6b5d6d926a30665012576fa30c7e6cfc99de07
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beaa0f13da50c320befe2b672d797e0f5de6fcf09d9af3e44f6e54b3f69f3f2f
3
  size 4091
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff