Hugging Face's logo

madatnlp
/
gamza-bart-for-kormath

Text2Text Generation
Transformers
TensorFlow
bart
generated_from_keras_callback
Inference Endpoints
Model card Files Community
madatnlp commited on
Commit
c460e78
•
1 Parent(s): a421329

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +4 -56
  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: 0.0460
18
- - Validation Loss: 0.3173
19
- - Epoch: 52
20
 
21
  ## Model description
22
 
@@ -42,59 +42,7 @@ The following hyperparameters were used during training:
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 4.3868 | 1.8720 | 0 |
46
- | 1.5091 | 1.0768 | 1 |
47
- | 1.0238 | 0.8972 | 2 |
48
- | 0.8960 | 0.8375 | 3 |
49
- | 0.8087 | 0.7618 | 4 |
50
- | 0.7656 | 0.7196 | 5 |
51
- | 0.7433 | 0.7023 | 6 |
52
- | 0.7309 | 0.6992 | 7 |
53
- | 0.6773 | 0.7008 | 8 |
54
- | 0.6659 | 0.6752 | 9 |
55
- | 0.6607 | 0.7347 | 10 |
56
- | 0.6370 | 0.6033 | 11 |
57
- | 0.6037 | 0.6806 | 12 |
58
- | 0.5957 | 0.6370 | 13 |
59
- | 0.5740 | 0.6413 | 14 |
60
- | 0.5005 | 0.5002 | 15 |
61
- | 0.4385 | 0.4821 | 16 |
62
- | 0.5042 | 0.4898 | 17 |
63
- | 0.4445 | 0.5218 | 18 |
64
- | 0.3990 | 0.4771 | 19 |
65
- | 0.3497 | 0.4173 | 20 |
66
- | 0.3294 | 0.4232 | 21 |
67
- | 0.3019 | 0.3936 | 22 |
68
- | 0.2868 | 0.4212 | 23 |
69
- | 0.2565 | 0.3401 | 24 |
70
- | 0.2404 | 0.3912 | 25 |
71
- | 0.2235 | 0.3484 | 26 |
72
- | 0.1976 | 0.3357 | 27 |
73
- | 0.1998 | 0.3392 | 28 |
74
- | 0.1788 | 0.3075 | 29 |
75
- | 0.1705 | 0.3615 | 30 |
76
- | 0.1642 | 0.3466 | 31 |
77
- | 0.1510 | 0.3325 | 32 |
78
- | 0.1402 | 0.3729 | 33 |
79
- | 0.1342 | 0.3425 | 34 |
80
- | 0.1276 | 0.3039 | 35 |
81
- | 0.1093 | 0.3276 | 36 |
82
- | 0.1048 | 0.3034 | 37 |
83
- | 0.0951 | 0.3472 | 38 |
84
- | 0.0971 | 0.3407 | 39 |
85
- | 0.0849 | 0.3516 | 40 |
86
- | 0.0868 | 0.2757 | 41 |
87
- | 0.0868 | 0.2383 | 42 |
88
- | 0.0766 | 0.3127 | 43 |
89
- | 0.0734 | 0.3324 | 44 |
90
- | 0.0694 | 0.3654 | 45 |
91
- | 0.0626 | 0.2692 | 46 |
92
- | 0.0584 | 0.2403 | 47 |
93
- | 0.0565 | 0.3741 | 48 |
94
- | 0.0567 | 0.2839 | 49 |
95
- | 0.0523 | 0.2387 | 50 |
96
- | 0.0525 | 0.2629 | 51 |
97
- | 0.0460 | 0.3173 | 52 |
98
 
99
 
100
  ### 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: 4.4155
18
+ - Validation Loss: 1.9300
19
+ - Epoch: 0
20
 
21
  ## Model description
22
 
 
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 4.4155 | 1.9300 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4406616f3a1231192e26904e114c240454b0e62de187367940d7f9da950a00b3
3
  size 495849544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d738e6c4e36f50acedd63acbea31b9d298b2702d66de4d6e950aaca66510ded
3
  size 495849544