wbxlala commited on
Commit
6156f1d
1 Parent(s): f4e54ba

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,25 +1,24 @@
1
  {
2
- "_name_or_path": "bert-large-uncased-whole-word-masking-finetuned-squad",
 
3
  "architectures": [
4
- "BertForQuestionAnswering"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 1024,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 4096,
13
- "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
- "model_type": "bert",
16
- "num_attention_heads": 16,
17
- "num_hidden_layers": 24,
18
  "pad_token_id": 0,
19
- "position_embedding_type": "absolute",
 
 
 
20
  "torch_dtype": "float32",
21
  "transformers_version": "4.34.1",
22
- "type_vocab_size": 2,
23
- "use_cache": true,
24
  "vocab_size": 30522
25
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
  "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.34.1",
 
 
23
  "vocab_size": 30522
24
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66fba640b2808abf09189d6568650662978280efab27b30de64f442c927ea93e
3
- size 1336511590
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a158e23d55a9ca9a7e893b38a6c70f982ec644aa3681976ee244f75a45f381d
3
+ size 265493026
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 384,
6
  "strategy": "OnlySecond",
7
  "stride": 128
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 384
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 420,
6
  "strategy": "OnlySecond",
7
  "stride": 128
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 420
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d876c69afa7fac37f6e67d6784f55b58291098fbf5057a2fcc645acc735916
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8139d73bbaef1843da8ff2231cdf8c723fb3362763dfdea96c6d8c6cba2f3787
3
  size 4472