cliang1453 commited on
Commit
b30e308
1 Parent(s): 92b775b
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_matthews_correlation": 0.6826253049219981}
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cliang1453/deberta-v3-xsmall-cola-student-stage1",
3
+ "architectures": [
4
+ "TEDDebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "filter_disabled": false,
8
+ "filter_interval": 1,
9
+ "filter_nonlinear": false,
10
+ "filter_output_dim": 768,
11
+ "finetuning_task": "cola",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 384,
15
+ "id2label": {
16
+ "0": "unacceptable",
17
+ "1": "acceptable"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 1536,
21
+ "label2id": {
22
+ "acceptable": 1,
23
+ "unacceptable": 0
24
+ },
25
+ "layer_norm_eps": 1e-07,
26
+ "max_position_embeddings": 512,
27
+ "max_relative_positions": -1,
28
+ "model_type": "ted-deberta-v2",
29
+ "norm_rel_ebd": "layer_norm",
30
+ "num_attention_heads": 6,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "pooler_dropout": 0,
34
+ "pooler_hidden_act": "gelu",
35
+ "pooler_hidden_size": 384,
36
+ "pos_att_type": [
37
+ "p2c",
38
+ "c2p"
39
+ ],
40
+ "position_biased_input": false,
41
+ "position_buckets": 256,
42
+ "relative_attention": true,
43
+ "share_att_key": true,
44
+ "torch_dtype": "float32",
45
+ "train_filters": false,
46
+ "transformers_version": "4.28.0",
47
+ "type_vocab_size": 0,
48
+ "vocab_size": 128100
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60bb605cba9bd5767f7e4f1bf46498128aab0a0069da31424067de1d51c51282
3
+ size 297597593
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }