Hugging Face's logo

madatnlp
/
gamza-bart-for-kormath128

Text2Text Generation
Transformers
TensorFlow
bart
generated_from_keras_callback
Inference Endpoints
Model card Files Community
madatnlp commited on
Commit
4c4e646
•
1 Parent(s): c46b31e

End of training

Browse files
Files changed (2) hide show
  1. README.md +45 -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 [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 5.9513
18
- - Validation Loss: 3.2241
19
- - Epoch: 0
20
 
21
  ## Model description
22
 
@@ -43,6 +43,48 @@ The following hyperparameters were used during training:
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
  | 5.9513 | 3.2241 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.1429
18
+ - Validation Loss: 0.3575
19
+ - Epoch: 42
20
 
21
  ## Model description
22
 
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
  | 5.9513 | 3.2241 | 0 |
46
+ | 2.6808 | 1.8567 | 1 |
47
+ | 1.6770 | 1.2966 | 2 |
48
+ | 1.2253 | 1.0402 | 3 |
49
+ | 1.0279 | 0.9159 | 4 |
50
+ | 0.9241 | 0.8158 | 5 |
51
+ | 0.8570 | 0.8047 | 6 |
52
+ | 0.8130 | 0.7684 | 7 |
53
+ | 0.7771 | 0.7817 | 8 |
54
+ | 0.7522 | 0.7653 | 9 |
55
+ | 0.7318 | 0.6813 | 10 |
56
+ | 0.7111 | 0.6535 | 11 |
57
+ | 0.6916 | 0.6719 | 12 |
58
+ | 0.6901 | 0.7191 | 13 |
59
+ | 0.6551 | 0.6330 | 14 |
60
+ | 0.6495 | 0.6242 | 15 |
61
+ | 0.6258 | 0.6048 | 16 |
62
+ | 0.6184 | 0.6590 | 17 |
63
+ | 0.6055 | 0.6622 | 18 |
64
+ | 0.5946 | 0.6377 | 19 |
65
+ | 0.5807 | 0.5994 | 20 |
66
+ | 0.5781 | 0.5797 | 21 |
67
+ | 0.5644 | 0.6154 | 22 |
68
+ | 0.5466 | 0.5777 | 23 |
69
+ | 0.5417 | 0.6324 | 24 |
70
+ | 0.5204 | 0.5763 | 25 |
71
+ | 0.5081 | 0.5751 | 26 |
72
+ | 0.4923 | 0.5908 | 27 |
73
+ | 0.4616 | 0.5433 | 28 |
74
+ | 0.4238 | 0.4823 | 29 |
75
+ | 0.3765 | 0.4474 | 30 |
76
+ | 0.3447 | 0.4306 | 31 |
77
+ | 0.3156 | 0.3817 | 32 |
78
+ | 0.2832 | 0.3824 | 33 |
79
+ | 0.2632 | 0.3204 | 34 |
80
+ | 0.2365 | 0.3539 | 35 |
81
+ | 0.2179 | 0.3162 | 36 |
82
+ | 0.2024 | 0.3385 | 37 |
83
+ | 0.1860 | 0.3367 | 38 |
84
+ | 0.1801 | 0.3019 | 39 |
85
+ | 0.1629 | 0.3045 | 40 |
86
+ | 0.1533 | 0.2567 | 41 |
87
+ | 0.1429 | 0.3575 | 42 |
88
 
89
 
90
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffee810c8ba13cbe4f6c7c5aa232acfde68b6fd46a3ece270aee5795eb0ac27f
3
  size 495849544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43cd5ab9f8b70a4f2e97e37062981afff1d3c258beb9505ebe891db1f4074961
3
  size 495849544