againeureka commited on
Commit
c2578ec
1 Parent(s): 54c674d

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "againeureka/klue_roberta_base_for_legal_full",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "i",
16
+ "1": "w",
17
+ "2": "u",
18
+ "3": "c",
19
+ "4": "d",
20
+ "5": "ic",
21
+ "6": "b",
22
+ "7": "e"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "b": 6,
28
+ "c": 3,
29
+ "d": 4,
30
+ "e": 7,
31
+ "i": 0,
32
+ "ic": 5,
33
+ "u": 2,
34
+ "w": 1
35
+ },
36
+ "layer_norm_eps": 1e-05,
37
+ "max_position_embeddings": 514,
38
+ "model_type": "roberta",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 1,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "tokenizer_class": "BertTokenizer",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.28.1",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 32000
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ecb774c6a5e6a5099b4baa0394504d13bf31bac54e12b3d84b0d1597c42352
3
+ size 442570421
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
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_basic_tokenize": true,
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "mask_token": "[MASK]",
9
+ "model_max_length": 512,
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930792b2ff4d73f3886a2f7dcfdd100ca38969a7185913a380e4c37c497ca914
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff