Kriyans commited on
Commit
8486ab5
1 Parent(s): d8bcae7

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +16 -18
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +2 -2
  5. training_args.bin +2 -2
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,14 +1,13 @@
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,
11
- "hidden_size": 768,
12
  "id2label": {
13
  "0": "O",
14
  "1": "B-corporation",
@@ -17,7 +16,6 @@
17
  "4": "I-person"
18
  },
19
  "initializer_range": 0.02,
20
- "intermediate_size": 3072,
21
  "label2id": {
22
  "B-corporation": 1,
23
  "B-person": 3,
@@ -25,16 +23,16 @@
25
  "I-person": 4,
26
  "O": 0
27
  },
28
- "layer_norm_eps": 1e-12,
29
  "max_position_embeddings": 512,
30
- "model_type": "bert",
31
- "num_attention_heads": 12,
32
- "num_hidden_layers": 12,
33
  "pad_token_id": 0,
34
- "position_embedding_type": "absolute",
 
 
 
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.30.2",
37
- "type_vocab_size": 2,
38
- "use_cache": true,
39
- "vocab_size": 28996
40
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForTokenClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "O",
13
  "1": "B-corporation",
 
16
  "4": "I-person"
17
  },
18
  "initializer_range": 0.02,
 
19
  "label2id": {
20
  "B-corporation": 1,
21
  "B-person": 3,
 
23
  "I-person": 4,
24
  "O": 0
25
  },
 
26
  "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
  "pad_token_id": 0,
31
+ "qa_dropout": 0.1,
32
+ "seq_classif_dropout": 0.2,
33
+ "sinusoidal_pos_embds": false,
34
+ "tie_weights_": true,
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.33.2",
37
+ "vocab_size": 30522
 
 
38
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d9e46c5bc595c23b58d1e0fef8fe53ea4451cadd7624ac583836c2f7a3c7b48
3
- size 430966253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be94b5571ed9a7ab7a185c38244e14322695fefa936fd67e67840d5fc5a65692
3
+ size 265501733
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,13 @@
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
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
+ "do_lower_case": true,
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": "DistilBertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02548962640bfa705bef795cced068d507f93c91f3a43d8c481b697135b28d9a
3
- size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9927d2566f51284eea8fd5976a40c2f02271dbd6c233cf25e6f69d1c943fa3e5
3
+ size 4027
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff