Hugging Face's logo

syp1229
/
koelectra-base-v3-generator-finetuned-koidiom-epoch5

Fill-Mask
Transformers
TensorFlow
electra
generated_from_keras_callback
Inference Endpoints
Model card Files Community
syp1229 commited on
Commit
25500b8
•
1 Parent(s): 5bd9d3b

End of training

Browse files
Files changed (2) hide show
  1. README.md +7 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [monologg/koelectra-base-v3-generator](https://huggingface.co/monologg/koelectra-base-v3-generator) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 2.4450
18
- - Validation Loss: 2.1108
19
- - Epoch: 0
20
 
21
  ## Model description
22
 
@@ -43,6 +43,10 @@ The following hyperparameters were used during training:
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
  | 2.4450 | 2.1108 | 0 |
 
 
 
 
46
 
47
 
48
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [monologg/koelectra-base-v3-generator](https://huggingface.co/monologg/koelectra-base-v3-generator) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.1280
18
+ - Validation Loss: 1.8541
19
+ - Epoch: 4
20
 
21
  ## Model description
22
 
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
  | 2.4450 | 2.1108 | 0 |
46
+ | 2.2462 | 1.9578 | 1 |
47
+ | 2.1990 | 1.9394 | 2 |
48
+ | 2.1306 | 1.9433 | 3 |
49
+ | 2.1280 | 1.8541 | 4 |
50
 
51
 
52
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:554702307593faab656f5145cc34f4c6687c198d8319764669548788bfcf1d4a
3
  size 258126376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a809261dc95268f89073c7616234d7bb93044e89a7945ce5e127e4e4eb481d
3
  size 258126376