mathildeparlo commited on
Commit
efcd37a
1 Parent(s): c38e216

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +15 -22
  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
@@ -1,31 +1,24 @@
1
  {
2
- "_name_or_path": "bert-base-multilingual-cased",
 
3
  "architectures": [
4
- "BertForQuestionAnswering"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
- "pooler_fc_size": 768,
21
- "pooler_num_attention_heads": 12,
22
- "pooler_num_fc_layers": 3,
23
- "pooler_size_per_head": 128,
24
- "pooler_type": "first_token_transform",
25
- "position_embedding_type": "absolute",
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.34.1",
28
- "type_vocab_size": 2,
29
- "use_cache": true,
30
- "vocab_size": 119547
31
  }
 
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:d6f6971daabb2dc9caa45d6ea194f3655ec1e24372ddb113d41a217868112056
3
- size 709125734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53c85f633a6ab1a0255e78349ac9c6e7c83356d73b7e331b7751567da623e41
3
+ size 265491554
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,13 +43,13 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
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 sha256:996a8565213694326519c6ec1f43093e667232ab610fb182f6e6d42068f26320
3
- size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a9a6c584d89b4a562978f7856ba746e789f0c42881d913f66c4633245bb520
3
+ size 4472
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff