Seonghaa commited on
Commit
728c6bc
·
verified ·
1 Parent(s): b7827e8

seonghaa/news-classifier

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - ko
5
+ license: apache-2.0
6
+ base_model: monologg/koelectra-base-v3-discriminator
7
+ tags:
8
+ - text-classification
9
+ - KoELECTRA
10
+ - Korean-NLP
11
+ - topic-classification
12
+ - news-classification
13
+ - generated_from_trainer
14
+ metrics:
15
+ - accuracy
16
+ - precision
17
+ - recall
18
+ - f1
19
+ model-index:
20
+ - name: ynat-model
21
+ results: []
22
+ ---
23
+
24
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
25
+ should probably proofread and complete it, then remove this comment. -->
26
+
27
+ # ynat-model
28
+
29
+ This model is a fine-tuned version of [monologg/koelectra-base-v3-discriminator](https://huggingface.co/monologg/koelectra-base-v3-discriminator) on the klue-ynat dataset.
30
+ It achieves the following results on the evaluation set:
31
+ - Loss: 0.4154
32
+ - Accuracy: 0.8588
33
+ - Precision: 0.8471
34
+ - Recall: 0.8723
35
+ - F1: 0.8590
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 3
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
66
+ | 0.4166 | 1.0 | 714 | 0.5089 | 0.8208 | 0.8030 | 0.8649 | 0.8280 |
67
+ | 0.3101 | 2.0 | 1428 | 0.4026 | 0.8558 | 0.8422 | 0.8704 | 0.8552 |
68
+ | 0.2329 | 3.0 | 2142 | 0.4154 | 0.8588 | 0.8471 | 0.8723 | 0.8590 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.51.3
74
+ - Pytorch 2.6.0+cu124
75
+ - Datasets 3.6.0
76
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "IT\uacfc\ud559",
13
+ "1": "\uacbd\uc81c",
14
+ "2": "\uc0ac\ud68c",
15
+ "3": "\uc0dd\ud65c\ubb38\ud654",
16
+ "4": "\uc138\uacc4",
17
+ "5": "\uc2a4\ud3ec\uce20",
18
+ "6": "\uc815\uce58"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "IT\uacfc\ud559": 0,
24
+ "\uacbd\uc81c": 1,
25
+ "\uc0ac\ud68c": 2,
26
+ "\uc0dd\ud65c\ubb38\ud654": 3,
27
+ "\uc138\uacc4": 4,
28
+ "\uc2a4\ud3ec\uce20": 5,
29
+ "\uc815\uce58": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "electra",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "summary_activation": "gelu",
40
+ "summary_last_dropout": 0.1,
41
+ "summary_type": "first",
42
+ "summary_use_proj": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.51.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 35000
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c47b746773799196a2acd73bda86db57f81c1045787c559e47851f41e8a0ee
3
+ size 451731052
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
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": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f354881ee9302b40c1b19703b075945a03860f0fa6d08a0b4ff89ff8682e05e
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff