gayanin commited on
Commit
11705fd
·
1 Parent(s): 73b1cc1

End of training

Browse files
Files changed (1) hide show
  1. README.md +29 -29
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1618
19
 
20
  ## Model description
21
 
@@ -47,34 +47,34 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
- | 0.4682 | 0.11 | 500 | 0.3839 |
51
- | 0.3647 | 0.21 | 1000 | 0.3068 |
52
- | 0.3853 | 0.32 | 1500 | 0.2709 |
53
- | 0.3194 | 0.43 | 2000 | 0.2515 |
54
- | 0.2892 | 0.54 | 2500 | 0.2369 |
55
- | 0.2493 | 0.64 | 3000 | 0.2202 |
56
- | 0.252 | 0.75 | 3500 | 0.2132 |
57
- | 0.2467 | 0.86 | 4000 | 0.1982 |
58
- | 0.2539 | 0.96 | 4500 | 0.1948 |
59
- | 0.1639 | 1.07 | 5000 | 0.1917 |
60
- | 0.1732 | 1.18 | 5500 | 0.1889 |
61
- | 0.1593 | 1.28 | 6000 | 0.1932 |
62
- | 0.1884 | 1.39 | 6500 | 0.1803 |
63
- | 0.1889 | 1.5 | 7000 | 0.1804 |
64
- | 0.1638 | 1.61 | 7500 | 0.1787 |
65
- | 0.1295 | 1.71 | 8000 | 0.1754 |
66
- | 0.2087 | 1.82 | 8500 | 0.1692 |
67
- | 0.147 | 1.93 | 9000 | 0.1700 |
68
- | 0.1269 | 2.03 | 9500 | 0.1725 |
69
- | 0.1214 | 2.14 | 10000 | 0.1693 |
70
- | 0.1124 | 2.25 | 10500 | 0.1717 |
71
- | 0.1169 | 2.35 | 11000 | 0.1654 |
72
- | 0.1136 | 2.46 | 11500 | 0.1658 |
73
- | 0.1217 | 2.57 | 12000 | 0.1630 |
74
- | 0.1287 | 2.68 | 12500 | 0.1631 |
75
- | 0.0997 | 2.78 | 13000 | 0.1622 |
76
- | 0.1094 | 2.89 | 13500 | 0.1623 |
77
- | 0.1051 | 3.0 | 14000 | 0.1618 |
78
 
79
 
80
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1651
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.4638 | 0.11 | 500 | 0.3890 |
51
+ | 0.363 | 0.21 | 1000 | 0.3040 |
52
+ | 0.3053 | 0.32 | 1500 | 0.2812 |
53
+ | 0.3157 | 0.43 | 2000 | 0.2569 |
54
+ | 0.2515 | 0.54 | 2500 | 0.2380 |
55
+ | 0.2484 | 0.64 | 3000 | 0.2222 |
56
+ | 0.2295 | 0.75 | 3500 | 0.2136 |
57
+ | 0.2343 | 0.86 | 4000 | 0.2017 |
58
+ | 0.2455 | 0.96 | 4500 | 0.1969 |
59
+ | 0.2037 | 1.07 | 5000 | 0.1989 |
60
+ | 0.173 | 1.18 | 5500 | 0.1909 |
61
+ | 0.166 | 1.28 | 6000 | 0.1918 |
62
+ | 0.1607 | 1.39 | 6500 | 0.1875 |
63
+ | 0.203 | 1.5 | 7000 | 0.1833 |
64
+ | 0.1709 | 1.61 | 7500 | 0.1798 |
65
+ | 0.1272 | 1.71 | 8000 | 0.1777 |
66
+ | 0.2037 | 1.82 | 8500 | 0.1751 |
67
+ | 0.1493 | 1.93 | 9000 | 0.1720 |
68
+ | 0.1306 | 2.03 | 9500 | 0.1744 |
69
+ | 0.142 | 2.14 | 10000 | 0.1734 |
70
+ | 0.1159 | 2.25 | 10500 | 0.1752 |
71
+ | 0.1099 | 2.35 | 11000 | 0.1723 |
72
+ | 0.1229 | 2.46 | 11500 | 0.1695 |
73
+ | 0.1209 | 2.57 | 12000 | 0.1666 |
74
+ | 0.1477 | 2.68 | 12500 | 0.1657 |
75
+ | 0.0984 | 2.78 | 13000 | 0.1656 |
76
+ | 0.1002 | 2.89 | 13500 | 0.1659 |
77
+ | 0.1183 | 3.0 | 14000 | 0.1651 |
78
 
79
 
80
  ### Framework versions