gayanin commited on
Commit
88a7b3b
·
1 Parent(s): 4ceb899

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: 0.2157
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
- | 0.6234 | 0.11 | 500 | 0.5441 |
51
- | 0.4953 | 0.21 | 1000 | 0.4205 |
52
- | 0.4357 | 0.32 | 1500 | 0.3782 |
53
- | 0.4194 | 0.43 | 2000 | 0.3422 |
54
- | 0.364 | 0.54 | 2500 | 0.3211 |
55
- | 0.3064 | 0.64 | 3000 | 0.2959 |
56
- | 0.3169 | 0.75 | 3500 | 0.2859 |
57
- | 0.3169 | 0.86 | 4000 | 0.2703 |
58
- | 0.3033 | 0.96 | 4500 | 0.2622 |
59
- | 0.2401 | 1.07 | 5000 | 0.2635 |
60
- | 0.2253 | 1.18 | 5500 | 0.2564 |
61
- | 0.2214 | 1.28 | 6000 | 0.2571 |
62
- | 0.2315 | 1.39 | 6500 | 0.2424 |
63
- | 0.2524 | 1.5 | 7000 | 0.2386 |
64
- | 0.2257 | 1.61 | 7500 | 0.2374 |
65
- | 0.1949 | 1.71 | 8000 | 0.2344 |
66
- | 0.2344 | 1.82 | 8500 | 0.2286 |
67
- | 0.1896 | 1.93 | 9000 | 0.2265 |
68
- | 0.1722 | 2.03 | 9500 | 0.2266 |
69
- | 0.1697 | 2.14 | 10000 | 0.2293 |
70
- | 0.1558 | 2.25 | 10500 | 0.2265 |
71
- | 0.154 | 2.35 | 11000 | 0.2231 |
72
- | 0.1476 | 2.46 | 11500 | 0.2205 |
73
- | 0.1715 | 2.57 | 12000 | 0.2190 |
74
- | 0.1735 | 2.68 | 12500 | 0.2175 |
75
- | 0.1319 | 2.78 | 13000 | 0.2170 |
76
- | 0.1556 | 2.89 | 13500 | 0.2163 |
77
- | 0.1573 | 3.0 | 14000 | 0.2157 |
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: 0.0931
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.2288 | 0.11 | 500 | 0.1670 |
51
+ | 0.1744 | 0.21 | 1000 | 0.1545 |
52
+ | 0.1726 | 0.32 | 1500 | 0.1341 |
53
+ | 0.1622 | 0.43 | 2000 | 0.1329 |
54
+ | 0.1382 | 0.54 | 2500 | 0.1289 |
55
+ | 0.1322 | 0.64 | 3000 | 0.1184 |
56
+ | 0.1288 | 0.75 | 3500 | 0.1182 |
57
+ | 0.1304 | 0.86 | 4000 | 0.1088 |
58
+ | 0.1255 | 0.96 | 4500 | 0.1068 |
59
+ | 0.1039 | 1.07 | 5000 | 0.1093 |
60
+ | 0.0969 | 1.18 | 5500 | 0.1060 |
61
+ | 0.1001 | 1.28 | 6000 | 0.1087 |
62
+ | 0.0966 | 1.39 | 6500 | 0.1027 |
63
+ | 0.101 | 1.5 | 7000 | 0.0999 |
64
+ | 0.0851 | 1.61 | 7500 | 0.1010 |
65
+ | 0.1068 | 1.71 | 8000 | 0.1021 |
66
+ | 0.1024 | 1.82 | 8500 | 0.0966 |
67
+ | 0.0852 | 1.93 | 9000 | 0.0962 |
68
+ | 0.0688 | 2.03 | 9500 | 0.0967 |
69
+ | 0.0791 | 2.14 | 10000 | 0.0987 |
70
+ | 0.0606 | 2.25 | 10500 | 0.0978 |
71
+ | 0.0732 | 2.35 | 11000 | 0.0963 |
72
+ | 0.0758 | 2.46 | 11500 | 0.0951 |
73
+ | 0.0765 | 2.57 | 12000 | 0.0945 |
74
+ | 0.0671 | 2.68 | 12500 | 0.0932 |
75
+ | 0.0422 | 2.78 | 13000 | 0.0936 |
76
+ | 0.0493 | 2.89 | 13500 | 0.0942 |
77
+ | 0.0542 | 3.0 | 14000 | 0.0931 |
78
 
79
 
80
  ### Framework versions