Hugging Face's logo

eclec
/
patentClassificationLongFormer2

Text Classification
Transformers
PyTorch
longformer
Generated from Trainer
Model card Files
xet
 Community
1
eclec commited on
Commit
97c53a0
·
1 Parent(s): 7e04c09

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. .gitignore +1 -0
  2. config.json +64 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +15 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-large-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
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512
33
+ ],
34
+ "bos_token_id": 0,
35
+ "eos_token_id": 2,
36
+ "gradient_checkpointing": false,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 1024,
40
+ "id2label": {
41
+ "0": "NOT_REJECTED",
42
+ "1": "REJECTED"
43
+ },
44
+ "ignore_attention_mask": false,
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 4096,
47
+ "label2id": {
48
+ "NOT_REJECTED": 0,
49
+ "REJECTED": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_position_embeddings": 4098,
53
+ "model_type": "longformer",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "onnx_export": false,
57
+ "pad_token_id": 1,
58
+ "problem_type": "single_label_classification",
59
+ "sep_token_id": 2,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.31.0",
62
+ "type_vocab_size": 1,
63
+ "vocab_size": 50265
64
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9480ee60b9bba64c439e900f3fc89cd2d9cb8a79ae7fadeda0e3f60ba311c2cf
3
+ size 1738600369
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f260210b7e23d9e3cada7509f6a6bcce8d896de330d1bc4d2caf998c1719d97d
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff