Kriyans commited on
Commit
1bad505
·
1 Parent(s): 4ec84b7

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +14 -16
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,14 +1,13 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
 
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",
@@ -16,23 +15,22 @@
16
  "3": "I-person"
17
  },
18
  "initializer_range": 0.02,
19
- "intermediate_size": 3072,
20
  "label2id": {
21
  "B-corporation": 1,
22
  "B-person": 2,
23
  "I-person": 3,
24
  "O": 0
25
  },
26
- "layer_norm_eps": 1e-12,
27
  "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 12,
30
- "num_hidden_layers": 12,
31
  "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
 
 
 
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.34.0",
35
- "type_vocab_size": 2,
36
- "use_cache": true,
37
  "vocab_size": 30522
38
  }
 
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",
 
15
  "3": "I-person"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "B-corporation": 1,
20
  "B-person": 2,
21
  "I-person": 3,
22
  "O": 0
23
  },
 
24
  "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
  "pad_token_id": 0,
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.34.0",
 
 
35
  "vocab_size": 30522
36
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38ecbc00e12c9d30236091b97046fd65be1ebc1be5a4b367d6611d37db709c7d
3
- size 435646633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5670210cd38fd55783fc7ab32b13f88e88abdf9e77637bb59b3988f7f0af11b
3
+ size 265498661
tokenizer_config.json CHANGED
@@ -51,6 +51,6 @@
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0766fdc54607865428beb240921a4e11a00a723b79a8cb0014e81d1a0e9b7bf
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa9ce8dfc3aced15eeab77f3ce625a3d319efdfff335f38d579633888b15f422
3
  size 4027