gayanin commited on
Commit
7e04284
·
1 Parent(s): 9b229f1

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: 0.1905
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
- | 0.53 | 0.11 | 500 | 0.4647 |
51
- | 0.4464 | 0.21 | 1000 | 0.3745 |
52
- | 0.4506 | 0.32 | 1500 | 0.3262 |
53
- | 0.3944 | 0.43 | 2000 | 0.3019 |
54
- | 0.3538 | 0.54 | 2500 | 0.2816 |
55
- | 0.2626 | 0.64 | 3000 | 0.2692 |
56
- | 0.2607 | 0.75 | 3500 | 0.2540 |
57
- | 0.2967 | 0.86 | 4000 | 0.2357 |
58
- | 0.2716 | 0.96 | 4500 | 0.2334 |
59
- | 0.2065 | 1.07 | 5000 | 0.2286 |
60
- | 0.19 | 1.18 | 5500 | 0.2271 |
61
- | 0.1976 | 1.28 | 6000 | 0.2247 |
62
- | 0.2223 | 1.39 | 6500 | 0.2164 |
63
- | 0.2229 | 1.5 | 7000 | 0.2123 |
64
- | 0.2018 | 1.61 | 7500 | 0.2106 |
65
- | 0.1857 | 1.71 | 8000 | 0.2037 |
66
- | 0.22 | 1.82 | 8500 | 0.2033 |
67
- | 0.1793 | 1.93 | 9000 | 0.1993 |
68
- | 0.1441 | 2.03 | 9500 | 0.2012 |
69
- | 0.1515 | 2.14 | 10000 | 0.2011 |
70
- | 0.1412 | 2.25 | 10500 | 0.2023 |
71
- | 0.1505 | 2.35 | 11000 | 0.1978 |
72
- | 0.1472 | 2.46 | 11500 | 0.1961 |
73
- | 0.1526 | 2.57 | 12000 | 0.1916 |
74
- | 0.1454 | 2.68 | 12500 | 0.1919 |
75
- | 0.1011 | 2.78 | 13000 | 0.1920 |
76
- | 0.1386 | 2.89 | 13500 | 0.1915 |
77
- | 0.1368 | 3.0 | 14000 | 0.1905 |
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: 0.1366
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.3549 | 0.11 | 500 | 0.3112 |
51
+ | 0.2635 | 0.21 | 1000 | 0.2464 |
52
+ | 0.2497 | 0.32 | 1500 | 0.2210 |
53
+ | 0.2762 | 0.43 | 2000 | 0.2121 |
54
+ | 0.2265 | 0.54 | 2500 | 0.1923 |
55
+ | 0.1911 | 0.64 | 3000 | 0.1813 |
56
+ | 0.1629 | 0.75 | 3500 | 0.1777 |
57
+ | 0.1897 | 0.86 | 4000 | 0.1660 |
58
+ | 0.1782 | 0.96 | 4500 | 0.1617 |
59
+ | 0.1483 | 1.07 | 5000 | 0.1648 |
60
+ | 0.1412 | 1.18 | 5500 | 0.1592 |
61
+ | 0.1391 | 1.28 | 6000 | 0.1582 |
62
+ | 0.144 | 1.39 | 6500 | 0.1506 |
63
+ | 0.1524 | 1.5 | 7000 | 0.1509 |
64
+ | 0.1127 | 1.61 | 7500 | 0.1505 |
65
+ | 0.1224 | 1.71 | 8000 | 0.1470 |
66
+ | 0.1504 | 1.82 | 8500 | 0.1419 |
67
+ | 0.1123 | 1.93 | 9000 | 0.1407 |
68
+ | 0.0964 | 2.03 | 9500 | 0.1441 |
69
+ | 0.1045 | 2.14 | 10000 | 0.1428 |
70
+ | 0.1001 | 2.25 | 10500 | 0.1423 |
71
+ | 0.0842 | 2.35 | 11000 | 0.1416 |
72
+ | 0.085 | 2.46 | 11500 | 0.1407 |
73
+ | 0.1092 | 2.57 | 12000 | 0.1386 |
74
+ | 0.11 | 2.68 | 12500 | 0.1376 |
75
+ | 0.0769 | 2.78 | 13000 | 0.1370 |
76
+ | 0.084 | 2.89 | 13500 | 0.1373 |
77
+ | 0.0833 | 3.0 | 14000 | 0.1366 |
78
 
79
 
80
  ### Framework versions