gokuls commited on
Commit
427de64
1 Parent(s): 90f27b7

Training in progress, step 10000

Browse files
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "relu",
3
+ "architectures": [
4
+ "DistilBertForMaskedLM"
5
+ ],
6
+ "attention_dropout": 0.05,
7
+ "dim": 768,
8
+ "dropout": 0.05,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "hybridbert",
13
+ "n_heads": 12,
14
+ "n_layers": 12,
15
+ "pad_token_id": 0,
16
+ "qa_dropout": 0.1,
17
+ "seq_classif_dropout": 0.1,
18
+ "sinusoidal_pos_embds": true,
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.33.3",
21
+ "vocab_size": 30522
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f81d9b089cead8144294a305e9be0bb93f586b67815bce5844827f17622d2dc
3
+ size 565830213
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f3933c1dd9fd6456431b616e914d63f3bef5c3538d89b75c12f25f49cd8e56
3
+ size 5115
vocab.txt ADDED
The diff for this file is too large to render. See raw diff