dljh1214 commited on
Commit
a7770d1
·
verified ·
1 Parent(s): 5efb852

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
2
- "_name_or_path": "monologg/distilkobert",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
 
11
  "id2label": {
12
  "0": "LABEL_0",
13
  "1": "LABEL_1",
@@ -18,6 +20,8 @@
18
  "6": "LABEL_6"
19
  },
20
  "initializer_range": 0.02,
 
 
21
  "label2id": {
22
  "LABEL_0": 0,
23
  "LABEL_1": 1,
@@ -27,17 +31,17 @@
27
  "LABEL_5": 5,
28
  "LABEL_6": 6
29
  },
 
30
  "max_position_embeddings": 512,
31
- "model_type": "distilbert",
32
- "n_heads": 12,
33
- "n_layers": 3,
34
  "pad_token_id": 1,
 
35
  "problem_type": "single_label_classification",
36
- "qa_dropout": 0.1,
37
- "seq_classif_dropout": 0.2,
38
- "sinusoidal_pos_embds": false,
39
- "tie_weights_": true,
40
  "torch_dtype": "float32",
41
  "transformers_version": "4.44.2",
 
 
42
  "vocab_size": 8002
43
  }
 
1
  {
2
+ "_name_or_path": "skt/kobert-base-v1",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "author": "Heewon Jeon([email protected])",
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
  "id2label": {
14
  "0": "LABEL_0",
15
  "1": "LABEL_1",
 
20
  "6": "LABEL_6"
21
  },
22
  "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "kobert_version": 1.0,
25
  "label2id": {
26
  "LABEL_0": 0,
27
  "LABEL_1": 1,
 
31
  "LABEL_5": 5,
32
  "LABEL_6": 6
33
  },
34
+ "layer_norm_eps": 1e-12,
35
  "max_position_embeddings": 512,
36
+ "model_type": "bert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
  "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
  "problem_type": "single_label_classification",
 
 
 
 
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.44.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
  "vocab_size": 8002
47
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d26cb254534e71dd548de7a9e6bdca069f55ce9c4edbbef326304dd0c6e9e3ce
3
- size 113606100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58f7c10675616cd3295c5784bd7195bb675cff71e9490240cbbd2eb09d655bd
3
+ size 368792508
runs/Sep25_08-41-31_99b134fb4ada/events.out.tfevents.1727253703.99b134fb4ada.189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82800f48b925274d2ac2907a143b63a7f7cd9a6b611f1435818aec6da635bbb
3
+ size 5666
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "[UNK]"
15
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17dc471055592d3cc9e0a5831e769246a8a001a4d27551c9ed79668173c7b407
3
+ size 371427
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "keep_accents": false,
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
+ "remove_space": true,
55
+ "sep_token": "[SEP]",
56
+ "sp_model_kwargs": {},
57
+ "tokenizer_class": "KoBERTTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eed9af94ddb2270cdb2e74fbaf492d80a0898d889006a7fbb37fc2e641b6b256
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ae95c628c501b6d57cb890a6d18f903c3990f2ab65f9db68acd2107b3fd04e
3
  size 5176