gayanin commited on
Commit
fb8c4e7
·
1 Parent(s): eda1420

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: 0.1795
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
- | 0.5322 | 0.11 | 500 | 0.4266 |
51
- | 0.3544 | 0.21 | 1000 | 0.3467 |
52
- | 0.3892 | 0.32 | 1500 | 0.3076 |
53
- | 0.3657 | 0.43 | 2000 | 0.2814 |
54
- | 0.2904 | 0.54 | 2500 | 0.2656 |
55
- | 0.2551 | 0.64 | 3000 | 0.2447 |
56
- | 0.2641 | 0.75 | 3500 | 0.2373 |
57
- | 0.284 | 0.86 | 4000 | 0.2218 |
58
- | 0.2631 | 0.96 | 4500 | 0.2186 |
59
- | 0.2031 | 1.07 | 5000 | 0.2196 |
60
- | 0.1983 | 1.18 | 5500 | 0.2147 |
61
- | 0.1842 | 1.28 | 6000 | 0.2127 |
62
- | 0.1697 | 1.39 | 6500 | 0.2020 |
63
- | 0.2006 | 1.5 | 7000 | 0.2014 |
64
- | 0.1788 | 1.61 | 7500 | 0.1987 |
65
- | 0.1589 | 1.71 | 8000 | 0.1938 |
66
- | 0.2047 | 1.82 | 8500 | 0.1909 |
67
- | 0.1583 | 1.93 | 9000 | 0.1896 |
68
- | 0.1437 | 2.03 | 9500 | 0.1900 |
69
- | 0.1466 | 2.14 | 10000 | 0.1890 |
70
- | 0.1618 | 2.25 | 10500 | 0.1883 |
71
- | 0.1187 | 2.35 | 11000 | 0.1856 |
72
- | 0.1142 | 2.46 | 11500 | 0.1837 |
73
- | 0.1382 | 2.57 | 12000 | 0.1811 |
74
- | 0.1403 | 2.68 | 12500 | 0.1804 |
75
- | 0.1045 | 2.78 | 13000 | 0.1810 |
76
- | 0.1056 | 2.89 | 13500 | 0.1801 |
77
- | 0.12 | 3.0 | 14000 | 0.1795 |
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: 0.1503
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.3928 | 0.11 | 500 | 0.3528 |
51
+ | 0.3138 | 0.21 | 1000 | 0.2822 |
52
+ | 0.3223 | 0.32 | 1500 | 0.2444 |
53
+ | 0.3311 | 0.43 | 2000 | 0.2249 |
54
+ | 0.2256 | 0.54 | 2500 | 0.2169 |
55
+ | 0.222 | 0.64 | 3000 | 0.1999 |
56
+ | 0.2153 | 0.75 | 3500 | 0.1990 |
57
+ | 0.2167 | 0.86 | 4000 | 0.1814 |
58
+ | 0.2041 | 0.96 | 4500 | 0.1764 |
59
+ | 0.162 | 1.07 | 5000 | 0.1777 |
60
+ | 0.1645 | 1.18 | 5500 | 0.1742 |
61
+ | 0.1649 | 1.28 | 6000 | 0.1747 |
62
+ | 0.1721 | 1.39 | 6500 | 0.1660 |
63
+ | 0.1652 | 1.5 | 7000 | 0.1666 |
64
+ | 0.15 | 1.61 | 7500 | 0.1626 |
65
+ | 0.133 | 1.71 | 8000 | 0.1620 |
66
+ | 0.159 | 1.82 | 8500 | 0.1574 |
67
+ | 0.1415 | 1.93 | 9000 | 0.1558 |
68
+ | 0.1174 | 2.03 | 9500 | 0.1573 |
69
+ | 0.1226 | 2.14 | 10000 | 0.1562 |
70
+ | 0.1018 | 2.25 | 10500 | 0.1571 |
71
+ | 0.0978 | 2.35 | 11000 | 0.1550 |
72
+ | 0.0985 | 2.46 | 11500 | 0.1537 |
73
+ | 0.1284 | 2.57 | 12000 | 0.1507 |
74
+ | 0.1187 | 2.68 | 12500 | 0.1513 |
75
+ | 0.0806 | 2.78 | 13000 | 0.1516 |
76
+ | 0.1092 | 2.89 | 13500 | 0.1508 |
77
+ | 0.0996 | 3.0 | 14000 | 0.1503 |
78
 
79
 
80
  ### Framework versions