negfir commited on
Commit
bcf88d5
1 Parent(s): 1615f8a

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "negfir/new-wikitext2",
3
+ "architectures": [
4
+ "SqueezeBertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_groups": 4,
13
+ "intermediate_size": 3072,
14
+ "k_groups": 4,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "squeezebert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 2,
20
+ "output_groups": 4,
21
+ "pad_token_id": 0,
22
+ "post_attention_groups": 1,
23
+ "q_groups": 4,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.17.0",
26
+ "type_vocab_size": 2,
27
+ "v_groups": 4,
28
+ "vocab_size": 30528
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b184b6bf8aec381e7891f39bd823310f2083f49f359de9fea1d79315ff20dc92
3
+ size 115531239
runs/Mar09_16-59-53_d59e2229e41d/1646845201.7229638/events.out.tfevents.1646845201.d59e2229e41d.78.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f56f027939e56d671a35a8d623fd8738d96b8f78dd8c19d8eab09dc8a00f199
3
+ size 4814
runs/Mar09_16-59-53_d59e2229e41d/events.out.tfevents.1646845201.d59e2229e41d.78.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7186f8677160e8e2223a68b7768b7fdc7a1bb26dbcba2af689fb8b7d00d80659
3
+ size 3578
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "squeezebert/squeezebert-uncased", "tokenizer_class": "SqueezeBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31126cb6ee1dc097c29533693638dee8eb127198dc3e254dc33185daa99af68
3
+ size 3055
vocab.txt ADDED
The diff for this file is too large to render. See raw diff