Hugging Face's logo

temporary0-0name
/
run_4

Text Generation
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
1
temporary0-0name commited on
Commit
955be77
·
1 Parent(s): 8c09fb6

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -33
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 7.1614
21
 
22
  ## Model description
23
 
@@ -51,38 +51,22 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 8.1582 | 0.07 | 50 | 7.3652 |
55
- | 7.3378 | 0.14 | 100 | 7.2980 |
56
- | 7.2601 | 0.21 | 150 | 7.2348 |
57
- | 7.2123 | 0.27 | 200 | 7.2155 |
58
- | 7.1896 | 0.34 | 250 | 7.1967 |
59
- | 7.1707 | 0.41 | 300 | 7.1866 |
60
- | 7.2038 | 0.48 | 350 | 7.1888 |
61
- | 7.1888 | 0.55 | 400 | 7.1867 |
62
- | 7.1838 | 0.62 | 450 | 7.1788 |
63
- | 7.1561 | 0.69 | 500 | 7.1736 |
64
- | 7.1575 | 0.75 | 550 | 7.1739 |
65
- | 7.1797 | 0.82 | 600 | 7.1729 |
66
- | 7.1694 | 0.89 | 650 | 7.1698 |
67
- | 7.1705 | 0.96 | 700 | 7.1676 |
68
- | 7.1708 | 1.03 | 750 | 7.1665 |
69
- | 7.1417 | 1.1 | 800 | 7.1706 |
70
- | 7.1698 | 1.17 | 850 | 7.1686 |
71
- | 7.1393 | 1.24 | 900 | 7.1657 |
72
- | 7.1717 | 1.3 | 950 | 7.1657 |
73
- | 7.1551 | 1.37 | 1000 | 7.1688 |
74
- | 7.1461 | 1.44 | 1050 | 7.1634 |
75
- | 7.1574 | 1.51 | 1100 | 7.1621 |
76
- | 7.1496 | 1.58 | 1150 | 7.1624 |
77
- | 7.1429 | 1.65 | 1200 | 7.1625 |
78
- | 7.1638 | 1.72 | 1250 | 7.1606 |
79
- | 7.1543 | 1.78 | 1300 | 7.1588 |
80
- | 7.1502 | 1.85 | 1350 | 7.1579 |
81
- | 7.1638 | 1.92 | 1400 | 7.1569 |
82
- | 7.1244 | 1.99 | 1450 | 7.1566 |
83
- | 7.1358 | 2.06 | 1500 | 7.1597 |
84
- | 7.1298 | 2.13 | 1550 | 7.1587 |
85
- | 7.1494 | 2.2 | 1600 | 7.1614 |
86
 
87
 
88
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 7.1789
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 7.8933 | 0.07 | 50 | 7.4310 |
55
+ | 7.3323 | 0.14 | 100 | 7.3016 |
56
+ | 7.2569 | 0.21 | 150 | 7.2390 |
57
+ | 7.2126 | 0.27 | 200 | 7.2150 |
58
+ | 7.1929 | 0.34 | 250 | 7.2001 |
59
+ | 7.1759 | 0.41 | 300 | 7.1929 |
60
+ | 7.2085 | 0.48 | 350 | 7.1945 |
61
+ | 7.1944 | 0.55 | 400 | 7.1941 |
62
+ | 7.1889 | 0.62 | 450 | 7.1847 |
63
+ | 7.1626 | 0.69 | 500 | 7.1791 |
64
+ | 7.1635 | 0.75 | 550 | 7.1777 |
65
+ | 7.1868 | 0.82 | 600 | 7.1842 |
66
+ | 7.1766 | 0.89 | 650 | 7.1725 |
67
+ | 7.1767 | 0.96 | 700 | 7.1743 |
68
+ | 7.1778 | 1.03 | 750 | 7.1728 |
69
+ | 7.1497 | 1.1 | 800 | 7.1789 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40cc44592b9251d9609a6e700bd1019bfd960785cdcc1a50ab3f299701831030
3
  size 438124333
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a109a2d25d67a420d6935112c1be459405ff41c9de9dacda1a306757b35f4f2
3
  size 438124333