Hugging Face's logo

madatnlp
/
mbart

Transformers
TensorFlow
mbart
text2text-generation
generated_from_keras_callback
Model card Files
xet
 Community
madatnlp commited on
Commit
045a288
·
1 Parent(s): d043c00

add model

Browse files
Files changed (2) hide show
  1. README.md +47 -53
  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: 0.4590
17
- - Validation Loss: 0.4733
18
- - Epoch: 49
19
 
20
  ## Model description
21
 
@@ -41,56 +41,50 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 5.5050 | 5.6044 | 0 |
45
- | 4.2186 | 3.6574 | 1 |
46
- | 3.4076 | 3.1114 | 2 |
47
- | 2.9616 | 2.8183 | 3 |
48
- | 2.7527 | 2.5543 | 4 |
49
- | 2.5485 | 2.2712 | 5 |
50
- | 2.3759 | 2.1452 | 6 |
51
- | 2.2404 | 2.0783 | 7 |
52
- | 2.0494 | 1.8666 | 8 |
53
- | 1.8951 | 1.6372 | 9 |
54
- | 1.7748 | 1.5784 | 10 |
55
- | 1.6715 | 1.4766 | 11 |
56
- | 1.5577 | 1.4682 | 12 |
57
- | 1.4566 | 1.3257 | 13 |
58
- | 1.3847 | 1.2130 | 14 |
59
- | 1.2938 | 1.1075 | 15 |
60
- | 1.2412 | 1.3443 | 16 |
61
- | 1.2723 | 1.1943 | 17 |
62
- | 1.1537 | 1.0206 | 18 |
63
- | 1.0751 | 0.9213 | 19 |
64
- | 1.0088 | 0.9018 | 20 |
65
- | 0.9899 | 0.9283 | 21 |
66
- | 0.9489 | 0.8602 | 22 |
67
- | 0.9415 | 0.8616 | 23 |
68
- | 0.8912 | 0.8257 | 24 |
69
- | 0.8532 | 0.8110 | 25 |
70
- | 0.8240 | 0.8318 | 26 |
71
- | 0.8047 | 0.7791 | 27 |
72
- | 0.7731 | 0.7408 | 28 |
73
- | 0.7336 | 0.7371 | 29 |
74
- | 0.7231 | 0.6666 | 30 |
75
- | 0.6789 | 0.7504 | 31 |
76
- | 0.6906 | 0.6830 | 32 |
77
- | 0.7154 | 0.6451 | 33 |
78
- | 0.6837 | 0.6320 | 34 |
79
- | 0.6261 | 0.6308 | 35 |
80
- | 0.6156 | 0.6254 | 36 |
81
- | 0.6198 | 0.6015 | 37 |
82
- | 0.5800 | 0.6467 | 38 |
83
- | 0.5816 | 0.5808 | 39 |
84
- | 0.5490 | 0.5855 | 40 |
85
- | 0.5798 | 0.5255 | 41 |
86
- | 0.5568 | 0.5437 | 42 |
87
- | 0.5324 | 0.5440 | 43 |
88
- | 0.5060 | 0.4681 | 44 |
89
- | 0.5035 | 0.4996 | 45 |
90
- | 0.4885 | 0.5094 | 46 |
91
- | 0.4819 | 0.5119 | 47 |
92
- | 0.4660 | 0.4511 | 48 |
93
- | 0.4590 | 0.4733 | 49 |
94
 
95
 
96
  ### 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: 1.7384
17
+ - Validation Loss: 1.6859
18
+ - Epoch: 43
19
 
20
  ## Model description
21
 
 
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 12.5168 | 17.3038 | 0 |
45
+ | 13.4675 | 12.0726 | 1 |
46
+ | 6.7752 | 4.7717 | 2 |
47
+ | 4.2218 | 3.7952 | 3 |
48
+ | 3.6988 | 3.5533 | 4 |
49
+ | 3.5477 | 3.4101 | 5 |
50
+ | 3.4128 | 3.3961 | 6 |
51
+ | 3.3888 | 3.3118 | 7 |
52
+ | 3.3311 | 3.2826 | 8 |
53
+ | 3.2614 | 3.2270 | 9 |
54
+ | 3.2088 | 3.2100 | 10 |
55
+ | 3.1062 | 3.0641 | 11 |
56
+ | 3.0133 | 2.9382 | 12 |
57
+ | 2.9223 | 2.8687 | 13 |
58
+ | 2.8273 | 2.7063 | 14 |
59
+ | 2.7913 | 2.8055 | 15 |
60
+ | 2.6951 | 2.7133 | 16 |
61
+ | 2.6631 | 2.5467 | 17 |
62
+ | 2.5664 | 2.5094 | 18 |
63
+ | 2.5150 | 2.4914 | 19 |
64
+ | 2.4462 | 2.3662 | 20 |
65
+ | 2.4081 | 2.3500 | 21 |
66
+ | 2.3605 | 2.2733 | 22 |
67
+ | 2.3164 | 2.2821 | 23 |
68
+ | 2.3014 | 2.2191 | 24 |
69
+ | 2.2103 | 2.0691 | 25 |
70
+ | 2.1883 | 2.1237 | 26 |
71
+ | 2.1814 | 2.1356 | 27 |
72
+ | 2.1292 | 2.0151 | 28 |
73
+ | 2.1046 | 1.9359 | 29 |
74
+ | 2.0542 | 2.0341 | 30 |
75
+ | 2.0365 | 1.9446 | 31 |
76
+ | 1.9829 | 1.8999 | 32 |
77
+ | 1.9801 | 1.8124 | 33 |
78
+ | 1.9168 | 1.7824 | 34 |
79
+ | 1.9209 | 1.8382 | 35 |
80
+ | 1.8850 | 1.8215 | 36 |
81
+ | 1.8748 | 1.7645 | 37 |
82
+ | 1.8346 | 1.6847 | 38 |
83
+ | 1.8076 | 1.7017 | 39 |
84
+ | 1.8732 | 1.8328 | 40 |
85
+ | 1.8164 | 1.7083 | 41 |
86
+ | 1.7784 | 1.7930 | 42 |
87
+ | 1.7384 | 1.6859 | 43 |
 
 
 
 
 
 
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:bb20ed6e592436944f4aae435219514db1b5856b95e9c1b2d349485e6cce923e
3
  size 2445079280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d890c143526f0a4a71d390c345c5c53f903e705421c77321e0a90e0e9293d31f
3
  size 2445079280