Hugging Face's logo

madatnlp
/
mbart

Transformers
TensorFlow
mbart
text2text-generation
generated_from_keras_callback
Model card Files Community
madatnlp commited on
Commit
65b2d86
·
1 Parent(s): 1fff6e2

add tokenizer

Browse files
Files changed (2) hide show
  1. README.md +36 -17
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 0.3396
17
- - Validation Loss: 0.3603
18
- - Epoch: 13
19
 
20
  ## Model description
21
 
@@ -41,20 +41,39 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 3.5941 | 2.0152 | 0 |
45
- | 1.5811 | 0.9978 | 1 |
46
- | 1.0165 | 0.8390 | 2 |
47
- | 0.7382 | 0.6526 | 3 |
48
- | 0.5833 | 0.5010 | 4 |
49
- | 0.5206 | 0.4613 | 5 |
50
- | 0.4762 | 0.4520 | 6 |
51
- | 0.4438 | 0.4119 | 7 |
52
- | 0.4009 | 0.4285 | 8 |
53
- | 0.3987 | 0.3728 | 9 |
54
- | 0.3767 | 0.3873 | 10 |
55
- | 0.3561 | 0.3521 | 11 |
56
- | 0.3470 | 0.3541 | 12 |
57
- | 0.3396 | 0.3603 | 13 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 1.8441
17
+ - Validation Loss: 1.7682
18
+ - Epoch: 32
19
 
20
  ## Model description
21
 
 
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 8.7253 | 8.6392 | 0 |
45
+ | 9.0974 | 5.4412 | 1 |
46
+ | 4.5850 | 3.7978 | 2 |
47
+ | 3.5934 | 3.2563 | 3 |
48
+ | 3.2998 | 3.1317 | 4 |
49
+ | 3.1458 | 2.9266 | 5 |
50
+ | 3.0411 | 2.8105 | 6 |
51
+ | 2.9031 | 2.7941 | 7 |
52
+ | 2.8143 | 2.5976 | 8 |
53
+ | 2.6863 | 2.5801 | 9 |
54
+ | 2.6233 | 2.4737 | 10 |
55
+ | 2.5740 | 2.3837 | 11 |
56
+ | 2.5156 | 2.3704 | 12 |
57
+ | 2.4462 | 2.2782 | 13 |
58
+ | 2.3953 | 2.2956 | 14 |
59
+ | 2.3455 | 2.2247 | 15 |
60
+ | 2.3107 | 2.2429 | 16 |
61
+ | 2.2782 | 2.2202 | 17 |
62
+ | 2.2244 | 2.0337 | 18 |
63
+ | 2.1897 | 2.0304 | 19 |
64
+ | 2.1445 | 2.0719 | 20 |
65
+ | 2.1356 | 1.9956 | 21 |
66
+ | 2.0842 | 2.0068 | 22 |
67
+ | 2.0652 | 1.9238 | 23 |
68
+ | 2.0286 | 2.0027 | 24 |
69
+ | 1.9878 | 1.9224 | 25 |
70
+ | 1.9904 | 1.8651 | 26 |
71
+ | 1.9619 | 1.8289 | 27 |
72
+ | 1.9188 | 1.8143 | 28 |
73
+ | 1.8996 | 1.8292 | 29 |
74
+ | 1.8639 | 1.7598 | 30 |
75
+ | 1.8674 | 1.8165 | 31 |
76
+ | 1.8441 | 1.7682 | 32 |
77
 
78
 
79
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0abd65b377c0e9481d7b00f2a6de650daff573bcefcb31ad9e76436626eb959
3
  size 2445079280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa65baec29965b21afd8fd7ffa6fa3b23699812ea853dc98408b0719f4bbc47
3
  size 2445079280