ymcnabb commited on
Commit
0fcea27
1 Parent(s): 02f2f30

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "entailment",
12
+ "1": "neutral",
13
+ "2": "contradiction"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "contradiction": 2,
19
+ "entailment": 0,
20
+ "neutral": 1
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 1024,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.24.0",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128100
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5a829d92f9ef664e196c00ef39f7a9ad8da4c03aa45b2a108aeaabf4fe7398
3
+ size 1740397483
runs/Nov21_12-17-07_05ee0103d9cc/1669033038.0117886/events.out.tfevents.1669033038.05ee0103d9cc.140.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ad6bf758403c656d085826943ac35923da992d80ab66d615e16584fcb56351
3
+ size 5537
runs/Nov21_12-17-07_05ee0103d9cc/events.out.tfevents.1669033037.05ee0103d9cc.140.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e2ae7ef71a86c9332d1f6cab78f981d99609b9cbcc835ea81aeded50b1125c
3
+ size 4216
runs/Nov21_12-17-34_05ee0103d9cc/1669033058.5589545/events.out.tfevents.1669033058.05ee0103d9cc.140.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90a5fbc05a150a8cce3b92a0a24fe427d95fbc970a7e00abd46f23dbed724b8
3
+ size 5537
runs/Nov21_12-17-34_05ee0103d9cc/events.out.tfevents.1669033058.05ee0103d9cc.140.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071d60f9a407dd71466575893d8bfd670eae0ff62092bb424e1b3524a770eff2
3
+ size 4214
runs/Nov21_12-18-39_05ee0103d9cc/1669033123.8327515/events.out.tfevents.1669033123.05ee0103d9cc.140.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26f31d104110668e643769b7685c588084f6e7b619a920b43c4533eb7774c51
3
+ size 5537
runs/Nov21_12-18-39_05ee0103d9cc/events.out.tfevents.1669033123.05ee0103d9cc.140.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f02c9ff73b2294fdcc21a9f21b7b0bbe80cd9ad3c45a1a96016d254f228303
3
+ size 4214
runs/Nov21_12-19-28_05ee0103d9cc/1669033176.7644541/events.out.tfevents.1669033176.05ee0103d9cc.462.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511bbd2f68eb6a992f47ea83ebed44ba915214f02d8898b57d601ebbbb245f1b
3
+ size 5537
runs/Nov21_12-19-28_05ee0103d9cc/events.out.tfevents.1669033176.05ee0103d9cc.462.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061d97ba6a43684ce635fe1ef866682c5157dbad385b1c710454543af9965557
3
+ size 4214
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "name_or_path": "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fdb6042d1f445ec73f1e780a91011c13a0189dd80cfaedd8d21cb49c22c55df
3
+ size 3439