Hugging Face's logo

mixtralyanis
/
bart_opensource

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mixtralyanis commited on
Commit
f531852
•
1 Parent(s): f3ee077

End of training

Browse files
Files changed (3) hide show
  1. README.md +0 -64
  2. runs/Feb25_18-35-58_964a69cb8e77/events.out.tfevents.1708886162.964a69cb8e77.853.0 +3 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
14
  # bart_opensource
15
 
16
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
17
- It achieves the following results on the evaluation set:
18
- - Loss: 0.0482
19
 
20
  ## Model description
21
 
@@ -47,68 +45,6 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-----:|:----:|:---------------:|
52
- | 9.8079 | 0.16 | 1 | 8.9151 |
53
- | 9.1097 | 0.32 | 2 | 8.0683 |
54
- | 8.4063 | 0.48 | 3 | 7.6347 |
55
- | 7.9015 | 0.63 | 4 | 7.0205 |
56
- | 7.1888 | 0.79 | 5 | 6.2919 |
57
- | 6.1386 | 0.95 | 6 | 5.0961 |
58
- | 5.3555 | 1.11 | 7 | 3.9489 |
59
- | 4.3548 | 1.27 | 8 | 3.2123 |
60
- | 3.5788 | 1.43 | 9 | 2.1911 |
61
- | 2.5912 | 1.58 | 10 | 1.6834 |
62
- | 2.0914 | 1.74 | 11 | 1.3562 |
63
- | 1.6921 | 1.9 | 12 | 1.0628 |
64
- | 1.3658 | 2.06 | 13 | 0.8702 |
65
- | 1.1674 | 2.22 | 14 | 0.7202 |
66
- | 0.9204 | 2.38 | 15 | 0.5962 |
67
- | 0.8154 | 2.53 | 16 | 0.5179 |
68
- | 0.7057 | 2.69 | 17 | 0.4552 |
69
- | 0.5991 | 2.85 | 18 | 0.4022 |
70
- | 0.5438 | 3.01 | 19 | 0.3600 |
71
- | 0.4795 | 3.17 | 20 | 0.3242 |
72
- | 0.4323 | 3.33 | 21 | 0.2925 |
73
- | 0.4137 | 3.49 | 22 | 0.2638 |
74
- | 0.372 | 3.64 | 23 | 0.2373 |
75
- | 0.3277 | 3.8 | 24 | 0.2146 |
76
- | 0.2988 | 3.96 | 25 | 0.1970 |
77
- | 0.2767 | 4.12 | 26 | 0.1822 |
78
- | 0.2668 | 4.28 | 27 | 0.1686 |
79
- | 0.2297 | 4.44 | 28 | 0.1565 |
80
- | 0.219 | 4.59 | 29 | 0.1459 |
81
- | 0.1973 | 4.75 | 30 | 0.1360 |
82
- | 0.185 | 4.91 | 31 | 0.1265 |
83
- | 0.1782 | 5.07 | 32 | 0.1179 |
84
- | 0.1643 | 5.23 | 33 | 0.1102 |
85
- | 0.157 | 5.39 | 34 | 0.1034 |
86
- | 0.1449 | 5.54 | 35 | 0.0976 |
87
- | 0.1389 | 5.7 | 36 | 0.0927 |
88
- | 0.1292 | 5.86 | 37 | 0.0883 |
89
- | 0.1145 | 6.02 | 38 | 0.0840 |
90
- | 0.1143 | 6.18 | 39 | 0.0799 |
91
- | 0.1082 | 6.34 | 40 | 0.0762 |
92
- | 0.1048 | 6.5 | 41 | 0.0728 |
93
- | 0.0982 | 6.65 | 42 | 0.0697 |
94
- | 0.0974 | 6.81 | 43 | 0.0668 |
95
- | 0.09 | 6.97 | 44 | 0.0644 |
96
- | 0.0856 | 7.13 | 45 | 0.0624 |
97
- | 0.0781 | 7.29 | 46 | 0.0604 |
98
- | 0.0816 | 7.45 | 47 | 0.0586 |
99
- | 0.0816 | 7.6 | 48 | 0.0568 |
100
- | 0.0763 | 7.76 | 49 | 0.0554 |
101
- | 0.0742 | 7.92 | 50 | 0.0543 |
102
- | 0.0716 | 8.08 | 51 | 0.0531 |
103
- | 0.068 | 8.24 | 52 | 0.0521 |
104
- | 0.069 | 8.4 | 53 | 0.0511 |
105
- | 0.0647 | 8.55 | 54 | 0.0504 |
106
- | 0.0641 | 8.71 | 55 | 0.0498 |
107
- | 0.0677 | 8.87 | 56 | 0.0494 |
108
- | 0.0664 | 9.03 | 57 | 0.0490 |
109
- | 0.0639 | 9.19 | 58 | 0.0486 |
110
- | 0.0635 | 9.35 | 59 | 0.0484 |
111
- | 0.0641 | 9.5 | 60 | 0.0482 |
112
 
113
 
114
  ### Framework versions
 
14
  # bart_opensource
15
 
16
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
 
 
17
 
18
  ## Model description
19
 
 
45
 
46
  ### Training results
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
runs/Feb25_18-35-58_964a69cb8e77/events.out.tfevents.1708886162.964a69cb8e77.853.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd62915ee0cc7e8862ccb3a9f4a61b30f1d1d43435f3e554f4433d7a2098f30
3
+ size 18309
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5413ff07fe00a7088ab1939f5d290dbcb3a0542a828596306bb84fa06416c3
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65c32cc00dcf46af4ce07307a46f9ee5cc9891e8941f6ad44227c171191ba94
3
  size 4856