update model card README.md
Browse files
README.md
CHANGED
@@ -3,9 +3,36 @@ tags:
|
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- klue
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: ko_roberta_small_model
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# ko_roberta_small_model
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -40,6 +73,14 @@ The following hyperparameters were used during training:
|
|
40 |
- lr_scheduler_type: linear
|
41 |
- num_epochs: 2
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
### Framework versions
|
44 |
|
45 |
- Transformers 4.28.0
|
|
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- klue
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
model-index:
|
12 |
- name: ko_roberta_small_model
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Token Classification
|
16 |
+
type: token-classification
|
17 |
+
dataset:
|
18 |
+
name: klue
|
19 |
+
type: klue
|
20 |
+
config: ner
|
21 |
+
split: validation
|
22 |
+
args: ner
|
23 |
+
metrics:
|
24 |
+
- name: Precision
|
25 |
+
type: precision
|
26 |
+
value: 0.6827303934512807
|
27 |
+
- name: Recall
|
28 |
+
type: recall
|
29 |
+
value: 0.7253980500806622
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.703417786090801
|
33 |
+
- name: Accuracy
|
34 |
+
type: accuracy
|
35 |
+
value: 0.9403969397937687
|
36 |
---
|
37 |
|
38 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
40 |
|
41 |
# ko_roberta_small_model
|
42 |
|
43 |
+
This model is a fine-tuned version of [hyeonseo/ko_roberta_small_model](https://huggingface.co/hyeonseo/ko_roberta_small_model) on the klue dataset.
|
44 |
+
It achieves the following results on the evaluation set:
|
45 |
+
- Loss: 0.1864
|
46 |
+
- Precision: 0.6827
|
47 |
+
- Recall: 0.7254
|
48 |
+
- F1: 0.7034
|
49 |
+
- Accuracy: 0.9404
|
50 |
|
51 |
## Model description
|
52 |
|
|
|
73 |
- lr_scheduler_type: linear
|
74 |
- num_epochs: 2
|
75 |
|
76 |
+
### Training results
|
77 |
+
|
78 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
79 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
80 |
+
| 0.2341 | 1.0 | 1313 | 0.2069 | 0.6516 | 0.6999 | 0.6749 | 0.9336 |
|
81 |
+
| 0.16 | 2.0 | 2626 | 0.1864 | 0.6827 | 0.7254 | 0.7034 | 0.9404 |
|
82 |
+
|
83 |
+
|
84 |
### Framework versions
|
85 |
|
86 |
- Transformers 4.28.0
|