Hugging Face's logo

Theoreticallyhugo
/
bert-ner-essays-find_span

Token Classification
Transformers
PyTorch
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
Theoreticallyhugo commited on
Commit
cefb253
·
1 Parent(s): 1237928

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +28 -11
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +13 -5
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +12 -10
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,10 +1,26 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
- "BertForTokenClassification"
5
  ],
 
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
@@ -14,6 +30,7 @@
14
  "1": "B-Span",
15
  "2": "I-Span"
16
  },
 
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
19
  "label2id": {
@@ -21,16 +38,16 @@
21
  "I-Span": 2,
22
  "O": 0
23
  },
24
- "layer_norm_eps": 1e-12,
25
- "max_position_embeddings": 512,
26
- "model_type": "bert",
27
  "num_attention_heads": 12,
28
  "num_hidden_layers": 12,
29
- "pad_token_id": 0,
30
- "position_embedding_type": "absolute",
 
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.33.0",
33
- "type_vocab_size": 2,
34
- "use_cache": true,
35
- "vocab_size": 28996
36
  }
 
1
  {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
  "architectures": [
4
+ "LongformerForTokenClassification"
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,
 
30
  "1": "B-Span",
31
  "2": "I-Span"
32
  },
33
+ "ignore_attention_mask": false,
34
  "initializer_range": 0.02,
35
  "intermediate_size": 3072,
36
  "label2id": {
 
38
  "I-Span": 2,
39
  "O": 0
40
  },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 4098,
43
+ "model_type": "longformer",
44
  "num_attention_heads": 12,
45
  "num_hidden_layers": 12,
46
+ "onnx_export": false,
47
+ "pad_token_id": 1,
48
+ "sep_token_id": 2,
49
  "torch_dtype": "float32",
50
  "transformers_version": "4.33.0",
51
+ "type_vocab_size": 1,
52
+ "vocab_size": 50265
 
53
  }
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:ee938c214b9d2b739c1ab7d9d84b3189789594dad0b34710ad99a152fa5c0072
3
- size 430955689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7129d0ae39eda8a6707d6869cebd73ee5ee2fab3758b70ab1025d80671d5612e
3
+ size 592379337
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
@@ -1,13 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": false,
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": "BertTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
1
  {
2
+ "add_prefix_space": true,
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:b1da7aa97d5c57be5b5de2b8faae71bf64b149af2b33e6bd5e3da20ee795f2a1
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64eca431e529f3066c9253604d332b2cb116c90b6e46e89743899f5e3a61678d
3
  size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff