Tensorride commited on
Commit
eae2566
1 Parent(s): 916a96d

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
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": "uncensored",
12
+ "1": "censored"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "label2id": {
17
+ "censored": 1,
18
+ "uncensored": 0
19
+ },
20
+ "layer_norm_eps": 1e-07,
21
+ "max_position_embeddings": 512,
22
+ "max_relative_positions": -1,
23
+ "model_type": "deberta-v2",
24
+ "norm_rel_ebd": "layer_norm",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "pooler_dropout": 0,
29
+ "pooler_hidden_act": "gelu",
30
+ "pooler_hidden_size": 1024,
31
+ "pos_att_type": [
32
+ "p2c",
33
+ "c2p"
34
+ ],
35
+ "position_biased_input": false,
36
+ "position_buckets": 256,
37
+ "relative_attention": true,
38
+ "share_att_key": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.30.2",
41
+ "type_vocab_size": 0,
42
+ "vocab_size": 128100
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d79a1e21338c1d9235d1e92bc3631189c08d4a4b41720616f86b7537473d878
3
+ size 1740390777
runs/Apr20_14-33-00_Ei-ein-PC-halt/events.out.tfevents.1713616389.Ei-ein-PC-halt.19264.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5dea59ed9d234272755e9c40817c5937dedbc7de2ceefa26db224eb002599d
3
+ size 4335
runs/Apr21_13-49-23_Ei-ein-PC-halt/events.out.tfevents.1713700167.Ei-ein-PC-halt.6808.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ae85f621187bb93ee48d87525f67ba3a8498e0673fc8b30f88b45279ad72fb
3
+ size 4333
runs/Apr21_15-17-40_Ei-ein-PC-halt/events.out.tfevents.1713705463.Ei-ein-PC-halt.17032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19eadbf1ace10df03f2613bb7025f15007e3b8da7e3aabf2cecb19895314bd52
3
+ size 4333
runs/Apr21_15-20-22_Ei-ein-PC-halt/events.out.tfevents.1713705626.Ei-ein-PC-halt.25396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6c308d39642fd09fe3d18f400d5aea05fe57bfa03a5061b5693e2cfba31b49
3
+ size 5284
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": "DistilBertTokenizer",
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:bb435b67dbb6a4c3f471cbb34d23070f5a2dbf8a753145de66ce526f63d25a20
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff