Hugging Face's logo

systemslibrarian
/
cipher-detective-classifier

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
systemslibrarian commited on
Commit
ba3b347
·
verified ·
1 Parent(s): 3540b5b

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +23 -22
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +12 -55
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,15 +1,16 @@
1
  {
2
- "_name_or_path": "roberta-base",
3
  "architectures": [
4
- "RobertaForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
 
13
  "id2label": {
14
  "0": "adfgvx",
15
  "1": "adfgx",
@@ -94,7 +95,6 @@
94
  "80": "zimmermann"
95
  },
96
  "initializer_range": 0.02,
97
- "intermediate_size": 3072,
98
  "label2id": {
99
  "adfgvx": 0,
100
  "adfgx": 1,
@@ -178,16 +178,17 @@
178
  "wheatstone": 79,
179
  "zimmermann": 80
180
  },
181
- "layer_norm_eps": 1e-05,
182
- "max_position_embeddings": 514,
183
- "model_type": "roberta",
184
- "num_attention_heads": 12,
185
- "num_hidden_layers": 12,
186
- "pad_token_id": 1,
187
- "position_embedding_type": "absolute",
188
- "torch_dtype": "float32",
189
- "transformers_version": "4.48.3",
190
- "type_vocab_size": 1,
191
- "use_cache": true,
192
- "vocab_size": 50265
 
193
  }
 
1
  {
2
+ "activation": "gelu",
3
  "architectures": [
4
+ "DistilBertForSequenceClassification"
5
  ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "char_level": true,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "dtype": "float32",
12
+ "eos_token_id": null,
13
+ "hidden_dim": 3072,
14
  "id2label": {
15
  "0": "adfgvx",
16
  "1": "adfgx",
 
95
  "80": "zimmermann"
96
  },
97
  "initializer_range": 0.02,
 
98
  "label2id": {
99
  "adfgvx": 0,
100
  "adfgx": 1,
 
178
  "wheatstone": 79,
179
  "zimmermann": 80
180
  },
181
+ "max_position_embeddings": 512,
182
+ "model_type": "distilbert",
183
+ "n_heads": 12,
184
+ "n_layers": 6,
185
+ "pad_token_id": 0,
186
+ "qa_dropout": 0.1,
187
+ "seq_classif_dropout": 0.2,
188
+ "sinusoidal_pos_embds": false,
189
+ "tie_weights_": true,
190
+ "tie_word_embeddings": true,
191
+ "transformers_version": "5.13.1",
192
+ "use_cache": false,
193
+ "vocab_size": 30522
194
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11eae03d99e4edc4b3363e9ba1ffae2a6ab7c49f726af5a3b957d74c27cbd59f
3
- size 498855828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f464904966961e7932ea8cadd111c76899d2f60c00d7f9a37226f2e0457a8c
3
+ size 268075580
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,58 +1,15 @@
1
  {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
  "model_max_length": 512,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
56
- "trim_offsets": true,
57
- "unk_token": "<unk>"
 
58
  }
 
1
  {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42f9afed3831a6213d045456aaabc09e463ef5071ec40254aab22a7fae93209
3
- size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b676e39f210f9398a34e32c1f2740f0d708e6d6e89953eed64913c83e446fc
3
+ size 5265