Hugging Face's logo

ginami
/
output

Token Classification
Transformers
Safetensors
electra
Generated from Trainer
Model card Files
xet
Community
ginami commited on
Commit
5dba4ab
·
verified ·
1 Parent(s): 4d4a823

Training completed!

Browse files
Files changed (7) hide show
  1. README.md +66 -0
  2. config.json +41 -0
  3. kcelectra_base_ner_law_v2/config.json +41 -0
  4. kcelectra_base_ner_law_v2/model.safetensors +3 -0
  5. kcelectra_base_ner_law_v2/training_args.bin +3 -0
  6. model.safetensors +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: beomi/KcELECTRA-base-v2022
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: kcelectra_base_ner_law_v2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # kcelectra_base_ner_law_v2
15
+
16
+ This model is a fine-tuned version of [beomi/KcELECTRA-base-v2022](https://huggingface.co/beomi/KcELECTRA-base-v2022) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0009
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 3e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 64
40
+ - seed: 15
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 0.0105 | 0.11 | 1000 | 0.0022 |
50
+ | 0.0028 | 0.22 | 2000 | 0.0019 |
51
+ | 0.0024 | 0.33 | 3000 | 0.0016 |
52
+ | 0.0014 | 0.44 | 4000 | 0.0027 |
53
+ | 0.0014 | 0.56 | 5000 | 0.0015 |
54
+ | 0.0016 | 0.67 | 6000 | 0.0013 |
55
+ | 0.0012 | 0.78 | 7000 | 0.0013 |
56
+ | 0.0016 | 0.89 | 8000 | 0.0011 |
57
+ | 0.0011 | 1.0 | 9000 | 0.0009 |
58
+ | 0.0006 | 1.11 | 10000 | 0.0013 |
59
+ | 0.0005 | 1.22 | 11000 | 0.0014 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.37.2
65
+ - Pytorch 2.1.0+cu121
66
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base-v2022",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "summary_activation": "gelu",
32
+ "summary_last_dropout": 0.1,
33
+ "summary_type": "first",
34
+ "summary_use_proj": true,
35
+ "tokenizer_class": "BertTokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.37.2",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 54343
41
+ }
kcelectra_base_ner_law_v2/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base-v2022",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "summary_activation": "gelu",
32
+ "summary_last_dropout": 0.1,
33
+ "summary_type": "first",
34
+ "summary_use_proj": true,
35
+ "tokenizer_class": "BertTokenizer",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.37.2",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 54343
41
+ }
kcelectra_base_ner_law_v2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f02d027f8d8ee5af96e93a1cfebf7c67779a705c73821194397376a5a9ea58
3
+ size 508777860
kcelectra_base_ner_law_v2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802a1a825f6ce8e4449553abd4ac39ceb61b95d454c66286e16441da1f3808df
3
+ size 4664
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f02d027f8d8ee5af96e93a1cfebf7c67779a705c73821194397376a5a9ea58
3
+ size 508777860
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802a1a825f6ce8e4449553abd4ac39ceb61b95d454c66286e16441da1f3808df
3
+ size 4664