kktoto commited on
Commit
fcb44d7
·
1 Parent(s): 1bf22f9

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kktoto/kt_punc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NORM",
14
+ "1": "COMMA",
15
+ "2": "PERIOD",
16
+ "3": "QUEST_MARK",
17
+ "4": "EXCLAMATION"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "COMMA": "1",
23
+ "EXCLAMATION": "4",
24
+ "NORM": "0",
25
+ "PERIOD": "2",
26
+ "QUEST_MARK": "3"
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "pooler_fc_size": 768,
35
+ "pooler_num_attention_heads": 12,
36
+ "pooler_num_fc_layers": 3,
37
+ "pooler_size_per_head": 128,
38
+ "pooler_type": "first_token_transform",
39
+ "position_embedding_type": "absolute",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.19.2",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 21128
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1599f2e3cdd4bddb385cf428e6e8d61dc8d41fd3772a11223293514809ddb171
3
+ size 406794033
runs/May28_07-06-55_927806fe30c7/1653721635.4983351/events.out.tfevents.1653721635.927806fe30c7.91.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762c0b2156f83428fa7463341f95a40a1c910b6d90daf336a16f50846d1e09a2
3
+ size 5148
runs/May28_07-06-55_927806fe30c7/events.out.tfevents.1653721635.927806fe30c7.91.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c443ca4e0b88bed58d12573a50a6a445156eb1e2ccfca6d740bdf80830b8c1
3
+ size 4085
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": false, "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": "kktoto/kt_punc", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3250f7b4340713c0c1423a6518fa07bdf9ed19ee3709f5245cad559be8461a2e
3
+ size 3183
vocab.txt ADDED
The diff for this file is too large to render. See raw diff