gayanin commited on
Commit
7637c06
1 Parent(s): a619d42

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: 0.2005
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
- | 0.6442 | 0.11 | 500 | 0.5078 |
51
- | 0.455 | 0.21 | 1000 | 0.3945 |
52
- | 0.4276 | 0.32 | 1500 | 0.3555 |
53
- | 0.3951 | 0.43 | 2000 | 0.3177 |
54
- | 0.3851 | 0.54 | 2500 | 0.3026 |
55
- | 0.3178 | 0.64 | 3000 | 0.2766 |
56
- | 0.294 | 0.75 | 3500 | 0.2702 |
57
- | 0.2857 | 0.86 | 4000 | 0.2565 |
58
- | 0.305 | 0.96 | 4500 | 0.2434 |
59
- | 0.2224 | 1.07 | 5000 | 0.2427 |
60
- | 0.2122 | 1.18 | 5500 | 0.2419 |
61
- | 0.2026 | 1.28 | 6000 | 0.2402 |
62
- | 0.2155 | 1.39 | 6500 | 0.2258 |
63
- | 0.2277 | 1.5 | 7000 | 0.2239 |
64
- | 0.2115 | 1.61 | 7500 | 0.2209 |
65
- | 0.194 | 1.71 | 8000 | 0.2191 |
66
- | 0.2329 | 1.82 | 8500 | 0.2163 |
67
- | 0.1781 | 1.93 | 9000 | 0.2114 |
68
- | 0.154 | 2.03 | 9500 | 0.2148 |
69
- | 0.1722 | 2.14 | 10000 | 0.2129 |
70
- | 0.1329 | 2.25 | 10500 | 0.2114 |
71
- | 0.1535 | 2.35 | 11000 | 0.2076 |
72
- | 0.1414 | 2.46 | 11500 | 0.2057 |
73
- | 0.1618 | 2.57 | 12000 | 0.2033 |
74
- | 0.1486 | 2.68 | 12500 | 0.2028 |
75
- | 0.1302 | 2.78 | 13000 | 0.2023 |
76
- | 0.1314 | 2.89 | 13500 | 0.2020 |
77
- | 0.1392 | 3.0 | 14000 | 0.2005 |
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: 0.1162
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.2641 | 0.11 | 500 | 0.2493 |
51
+ | 0.2369 | 0.21 | 1000 | 0.1986 |
52
+ | 0.2348 | 0.32 | 1500 | 0.1810 |
53
+ | 0.2239 | 0.43 | 2000 | 0.1732 |
54
+ | 0.1745 | 0.54 | 2500 | 0.1643 |
55
+ | 0.1664 | 0.64 | 3000 | 0.1493 |
56
+ | 0.1701 | 0.75 | 3500 | 0.1446 |
57
+ | 0.2041 | 0.86 | 4000 | 0.1375 |
58
+ | 0.1541 | 0.96 | 4500 | 0.1347 |
59
+ | 0.1168 | 1.07 | 5000 | 0.1398 |
60
+ | 0.1174 | 1.18 | 5500 | 0.1339 |
61
+ | 0.1108 | 1.28 | 6000 | 0.1345 |
62
+ | 0.1163 | 1.39 | 6500 | 0.1292 |
63
+ | 0.1292 | 1.5 | 7000 | 0.1268 |
64
+ | 0.0999 | 1.61 | 7500 | 0.1270 |
65
+ | 0.1023 | 1.71 | 8000 | 0.1225 |
66
+ | 0.123 | 1.82 | 8500 | 0.1208 |
67
+ | 0.1105 | 1.93 | 9000 | 0.1182 |
68
+ | 0.0938 | 2.03 | 9500 | 0.1212 |
69
+ | 0.0995 | 2.14 | 10000 | 0.1215 |
70
+ | 0.075 | 2.25 | 10500 | 0.1223 |
71
+ | 0.0746 | 2.35 | 11000 | 0.1201 |
72
+ | 0.0816 | 2.46 | 11500 | 0.1187 |
73
+ | 0.0819 | 2.57 | 12000 | 0.1170 |
74
+ | 0.0876 | 2.68 | 12500 | 0.1164 |
75
+ | 0.0628 | 2.78 | 13000 | 0.1168 |
76
+ | 0.0695 | 2.89 | 13500 | 0.1166 |
77
+ | 0.0835 | 3.0 | 14000 | 0.1162 |
78
 
79
 
80
  ### Framework versions