Hugging Face's logo

YuryCHep
/
fake_news_classification

Text Classification
Transformers
PyTorch
TensorBoard
longformer
Model card Files
xet
 Metrics Community
2
YuryCHep commited on
Commit
c849e76
·
1 Parent(s): aabcce9

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. config.json +32 -21
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. runs/Jun28_17-54-30_88bc1c41d2ef/events.out.tfevents.1687975395.88bc1c41d2ef.663.3 +2 -2
  5. runs/Jun28_19-57-34_88bc1c41d2ef/events.out.tfevents.1687982265.88bc1c41d2ef.663.4 +3 -0
  6. special_tokens_map.json +13 -5
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +12 -12
  9. training_args.bin +1 -1
  10. vocab.json +0 -0
config.json CHANGED
@@ -1,33 +1,44 @@
1
  {
2
- "_name_or_path": "ai-forever/sbert_large_nlu_ru",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
 
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 1024,
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 4096,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "bert",
18
- "num_attention_heads": 16,
19
- "num_hidden_layers": 24,
20
- "pad_token_id": 0,
21
- "pooler_fc_size": 768,
22
- "pooler_num_attention_heads": 12,
23
- "pooler_num_fc_layers": 3,
24
- "pooler_size_per_head": 128,
25
- "pooler_type": "first_token_transform",
26
- "position_embedding_type": "absolute",
27
  "problem_type": "single_label_classification",
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.30.2",
30
- "type_vocab_size": 2,
31
- "use_cache": true,
32
- "vocab_size": 120138
33
  }
 
1
  {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
  "architectures": [
4
+ "LongformerForSequenceClassification"
5
  ],
6
+ "attention_mode": "longformer",
7
  "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
  "gradient_checkpointing": false,
25
  "hidden_act": "gelu",
26
  "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "ignore_attention_mask": false,
29
  "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 4098,
33
+ "model_type": "longformer",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "onnx_export": false,
37
+ "pad_token_id": 1,
 
 
 
 
 
38
  "problem_type": "single_label_classification",
39
+ "sep_token_id": 2,
40
  "torch_dtype": "float32",
41
  "transformers_version": "4.30.2",
42
+ "type_vocab_size": 1,
43
+ "vocab_size": 50265
 
44
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ffe95ebc7c6dc13ff83a3cc0b87d51c80345d15fbc2980efe4b4ddc89c41be
3
- size 1707781749
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e262429613f16d35e1aa67e158191f6bef007bdc8d6f866006d440d00f8e02f3
3
+ size 594739281
runs/Jun28_17-54-30_88bc1c41d2ef/events.out.tfevents.1687975395.88bc1c41d2ef.663.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b4fcac235b9a1470feb9fdd2b5567bc69621723de507983b1f6ade6ce85ca18
3
- size 6642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d8ef9ed7764e7ea25f39d52e7afd7e7d16ba859acac6f8d4ec6999e84bd133
3
+ size 6996
runs/Jun28_19-57-34_88bc1c41d2ef/events.out.tfevents.1687982265.88bc1c41d2ef.663.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2683cde154302de00bf40c2dfa3a884ef7958b36bcc5ce60d79b770fa6649433
3
+ size 4667
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "never_split": null,
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
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 4096,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "LongformerTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
 
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2365af9cd61bd3ce1a364ede622c1bfd022a01f397182090170a7bc2a29a05
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bab5627547cac711fc9df79b8a76858659f103fceeefaaee39da3c5a2a0c485
3
  size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff