tucan9389 commited on
Commit
9cedac9
1 Parent(s): aa4a0bd

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -2,7 +2,7 @@
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
- - nsmc
6
  metrics:
7
  - accuracy
8
  model-index:
@@ -12,13 +12,13 @@ model-index:
12
  name: Text Classification
13
  type: text-classification
14
  dataset:
15
- name: nsmc
16
- type: nsmc
17
- args: default
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
- value: 0.8978
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,10 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
26
 
27
  # kcbert-base-finetuned
28
 
29
- This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on the nsmc dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.6977
32
- - Accuracy: 0.8978
33
 
34
  ## Model description
35
 
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
62
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
63
- | 0.152 | 1.0 | 9375 | 0.3803 | 0.8880 |
64
- | 0.1741 | 2.0 | 18750 | 0.3669 | 0.892 |
65
- | 0.105 | 3.0 | 28125 | 0.5072 | 0.8975 |
66
- | 0.054 | 4.0 | 37500 | 0.6541 | 0.8966 |
67
- | 0.0302 | 5.0 | 46875 | 0.6977 | 0.8978 |
68
 
69
 
70
  ### Framework versions
2
  tags:
3
  - generated_from_trainer
4
  datasets:
5
+ - klue
6
  metrics:
7
  - accuracy
8
  model-index:
12
  name: Text Classification
13
  type: text-classification
14
  dataset:
15
+ name: klue
16
+ type: klue
17
+ args: ynat
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
+ value: 0.8329856154606347
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
 
27
  # kcbert-base-finetuned
28
 
29
+ This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on the klue dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.7393
32
+ - Accuracy: 0.8330
33
 
34
  ## Model description
35
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
62
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
63
+ | 0.4612 | 1.0 | 2855 | 0.5216 | 0.8143 |
64
+ | 0.3061 | 2.0 | 5710 | 0.5130 | 0.8248 |
65
+ | 0.2129 | 3.0 | 8565 | 0.6062 | 0.8257 |
66
+ | 0.1337 | 4.0 | 11420 | 0.7393 | 0.8330 |
67
+ | 0.0653 | 5.0 | 14275 | 0.8651 | 0.8302 |
68
 
69
 
70
  ### Framework versions