Hugging Face's logo

CLARA-MeD
/
flan-t5-base

Transformers
PyTorch
TensorBoard
t5
text2text-generation
simplification
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1
joheras commited on
Commit
b9e9e1c
·
1 Parent(s): c9ede86

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -35
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2147
21
- - Rouge1: 30.2853
22
- - Rouge2: 17.8837
23
- - Rougel: 28.5494
24
- - Rougelsum: 28.5619
25
 
26
  ## Model description
27
 
@@ -52,36 +52,36 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | No log | 1.0 | 380 | 1.4337 | 28.3424 | 15.8296 | 26.7771 | 26.8012 |
56
- | No log | 2.0 | 760 | 1.3500 | 28.3138 | 15.7711 | 26.5938 | 26.6243 |
57
- | 1.6612 | 3.0 | 1140 | 1.3100 | 28.7693 | 16.2253 | 27.1743 | 27.1706 |
58
- | 1.6612 | 4.0 | 1520 | 1.2660 | 29.1258 | 16.535 | 27.3438 | 27.3384 |
59
- | 1.3812 | 5.0 | 1900 | 1.2427 | 29.3663 | 16.6346 | 27.5675 | 27.5817 |
60
- | 1.3812 | 6.0 | 2280 | 1.2371 | 28.8058 | 16.2303 | 27.0469 | 27.0995 |
61
- | 1.3812 | 7.0 | 2660 | 1.2261 | 29.4508 | 16.9271 | 27.6927 | 27.7289 |
62
- | 1.2301 | 8.0 | 3040 | 1.2135 | 29.1324 | 16.9346 | 27.4504 | 27.4864 |
63
- | 1.2301 | 9.0 | 3420 | 1.2021 | 29.6234 | 17.1336 | 27.753 | 27.7605 |
64
- | 1.1284 | 10.0 | 3800 | 1.1984 | 29.5167 | 16.9203 | 27.6358 | 27.6393 |
65
- | 1.1284 | 11.0 | 4180 | 1.1953 | 29.4643 | 17.0329 | 27.5829 | 27.6042 |
66
- | 1.1284 | 12.0 | 4560 | 1.1880 | 29.6242 | 17.1832 | 27.8727 | 27.8888 |
67
- | 1.0518 | 13.0 | 4940 | 1.1870 | 29.5786 | 17.205 | 27.8033 | 27.845 |
68
- | 1.0518 | 14.0 | 5320 | 1.1961 | 30.0961 | 17.629 | 28.239 | 28.2745 |
69
- | 0.9871 | 15.0 | 5700 | 1.1950 | 29.7245 | 17.3335 | 27.9341 | 27.9085 |
70
- | 0.9871 | 16.0 | 6080 | 1.1924 | 29.9669 | 17.6431 | 28.2745 | 28.2633 |
71
- | 0.9871 | 17.0 | 6460 | 1.1981 | 29.7217 | 17.3778 | 28.026 | 28.0259 |
72
- | 0.9345 | 18.0 | 6840 | 1.1889 | 30.0901 | 17.6325 | 28.3294 | 28.3327 |
73
- | 0.9345 | 19.0 | 7220 | 1.1927 | 30.0612 | 17.6191 | 28.2728 | 28.2883 |
74
- | 0.9036 | 20.0 | 7600 | 1.1948 | 29.9306 | 17.3734 | 28.1521 | 28.1666 |
75
- | 0.9036 | 21.0 | 7980 | 1.2049 | 30.3929 | 17.8617 | 28.6403 | 28.6603 |
76
- | 0.9036 | 22.0 | 8360 | 1.2029 | 30.2862 | 17.638 | 28.5731 | 28.5744 |
77
- | 0.865 | 23.0 | 8740 | 1.2068 | 30.1824 | 17.655 | 28.4648 | 28.496 |
78
- | 0.865 | 24.0 | 9120 | 1.2096 | 30.066 | 17.7635 | 28.4498 | 28.4629 |
79
- | 0.8427 | 25.0 | 9500 | 1.2106 | 30.1212 | 17.7151 | 28.4354 | 28.4545 |
80
- | 0.8427 | 26.0 | 9880 | 1.2091 | 30.2221 | 17.9074 | 28.6042 | 28.5976 |
81
- | 0.8427 | 27.0 | 10260 | 1.2117 | 30.2379 | 17.9142 | 28.5485 | 28.5625 |
82
- | 0.8214 | 28.0 | 10640 | 1.2145 | 30.2008 | 17.9005 | 28.5424 | 28.5626 |
83
- | 0.8214 | 29.0 | 11020 | 1.2141 | 30.2847 | 17.9545 | 28.6098 | 28.6204 |
84
- | 0.8181 | 30.0 | 11400 | 1.2147 | 30.2853 | 17.8837 | 28.5494 | 28.5619 |
85
 
86
 
87
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.2902
21
+ - Rouge1: 28.2733
22
+ - Rouge2: 15.323
23
+ - Rougel: 26.1421
24
+ - Rougelsum: 26.1589
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | No log | 1.0 | 380 | 1.4639 | 26.4167 | 14.2257 | 24.5659 | 24.5948 |
56
+ | No log | 2.0 | 760 | 1.3946 | 26.7094 | 14.6358 | 25.0516 | 25.075 |
57
+ | 1.6466 | 3.0 | 1140 | 1.3480 | 27.3758 | 14.6821 | 25.5935 | 25.6007 |
58
+ | 1.6466 | 4.0 | 1520 | 1.3221 | 28.0769 | 14.9721 | 26.131 | 26.1506 |
59
+ | 1.3671 | 5.0 | 1900 | 1.2988 | 27.8019 | 14.9244 | 25.8242 | 25.8322 |
60
+ | 1.3671 | 6.0 | 2280 | 1.2965 | 27.9071 | 15.3235 | 26.1385 | 26.104 |
61
+ | 1.3671 | 7.0 | 2660 | 1.2802 | 28.1866 | 15.4793 | 26.301 | 26.3031 |
62
+ | 1.2248 | 8.0 | 3040 | 1.2733 | 27.9974 | 15.4379 | 26.1087 | 26.1159 |
63
+ | 1.2248 | 9.0 | 3420 | 1.2591 | 28.2545 | 15.5006 | 26.2812 | 26.3306 |
64
+ | 1.1155 | 10.0 | 3800 | 1.2609 | 27.8029 | 15.0837 | 25.7989 | 25.8486 |
65
+ | 1.1155 | 11.0 | 4180 | 1.2612 | 27.676 | 15.0786 | 25.6261 | 25.6458 |
66
+ | 1.1155 | 12.0 | 4560 | 1.2616 | 27.6811 | 15.0935 | 25.6905 | 25.7125 |
67
+ | 1.0337 | 13.0 | 4940 | 1.2562 | 27.88 | 15.2395 | 25.8875 | 25.8988 |
68
+ | 1.0337 | 14.0 | 5320 | 1.2624 | 27.9858 | 15.2151 | 25.9785 | 26.0226 |
69
+ | 0.9784 | 15.0 | 5700 | 1.2674 | 28.044 | 15.1312 | 25.8866 | 25.9514 |
70
+ | 0.9784 | 16.0 | 6080 | 1.2588 | 28.1022 | 15.3599 | 26.0641 | 26.0762 |
71
+ | 0.9784 | 17.0 | 6460 | 1.2676 | 27.864 | 15.1432 | 25.8981 | 25.9221 |
72
+ | 0.9246 | 18.0 | 6840 | 1.2620 | 27.8826 | 15.1457 | 25.8041 | 25.8971 |
73
+ | 0.9246 | 19.0 | 7220 | 1.2671 | 27.965 | 15.0059 | 25.94 | 25.9831 |
74
+ | 0.8891 | 20.0 | 7600 | 1.2733 | 28.3035 | 15.3041 | 26.2411 | 26.2723 |
75
+ | 0.8891 | 21.0 | 7980 | 1.2748 | 28.5205 | 15.4851 | 26.4543 | 26.4725 |
76
+ | 0.8891 | 22.0 | 8360 | 1.2793 | 28.3018 | 15.3251 | 26.2781 | 26.3203 |
77
+ | 0.8578 | 23.0 | 8740 | 1.2788 | 28.039 | 15.238 | 25.9371 | 25.9856 |
78
+ | 0.8578 | 24.0 | 9120 | 1.2901 | 28.3312 | 15.3396 | 26.1722 | 26.1993 |
79
+ | 0.8299 | 25.0 | 9500 | 1.2863 | 28.0727 | 15.0182 | 25.91 | 25.9577 |
80
+ | 0.8299 | 26.0 | 9880 | 1.2845 | 28.1828 | 15.1338 | 26.039 | 26.0493 |
81
+ | 0.8299 | 27.0 | 10260 | 1.2819 | 28.1547 | 15.091 | 26.0256 | 26.0346 |
82
+ | 0.8137 | 28.0 | 10640 | 1.2859 | 28.2203 | 15.3225 | 26.1493 | 26.1591 |
83
+ | 0.8137 | 29.0 | 11020 | 1.2902 | 28.2459 | 15.3142 | 26.1283 | 26.1382 |
84
+ | 0.8061 | 30.0 | 11400 | 1.2902 | 28.2733 | 15.323 | 26.1421 | 26.1589 |
85
 
86
 
87
  ### Framework versions