joheras commited on
Commit
2c6328d
1 Parent(s): 94cc360

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -45
README.md CHANGED
@@ -5,16 +5,9 @@ tags:
5
  - generated_from_trainer
6
  metrics:
7
  - rouge
8
- - sari
9
  model-index:
10
  - name: mt5-simplification-spanish-clara-med
11
  results: []
12
- datasets:
13
- - lcampillos/CLARA-MeD
14
- dataset:
15
- - lcampillos/CLARA-MeD
16
- language:
17
- - es
18
  ---
19
 
20
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,14 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  # mt5-simplification-spanish-clara-med
24
 
25
- This model is a fine-tuned version of [oskrmiguel/mt5-simplification-spanish](https://huggingface.co/oskrmiguel/mt5-simplification-spanish) on the [CLARA-MeD](https://huggingface.co/lcampillos/CLARA-MeD) dataset.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 1.9733
28
- - Rouge1: 34.8633
29
- - Rouge2: 20.1867
30
- - Rougel: 31.9947
31
- - Rougelsum: 32.0636
32
- - SARI: 41.2158
33
 
34
  ## Model description
35
 
@@ -60,36 +52,36 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
62
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
63
- | No log | 1.0 | 190 | 2.6808 | 33.399 | 18.5851 | 30.5688 | 30.641 |
64
- | No log | 2.0 | 380 | 2.4483 | 33.8967 | 19.1538 | 31.1166 | 31.1725 |
65
- | 3.3136 | 3.0 | 570 | 2.3438 | 34.3835 | 19.7398 | 31.6407 | 31.7027 |
66
- | 3.3136 | 4.0 | 760 | 2.2646 | 34.3052 | 19.6967 | 31.5616 | 31.6131 |
67
- | 2.7536 | 5.0 | 950 | 2.2195 | 34.3218 | 19.5989 | 31.5248 | 31.5567 |
68
- | 2.7536 | 6.0 | 1140 | 2.1886 | 34.3961 | 19.7415 | 31.6482 | 31.6529 |
69
- | 2.7536 | 7.0 | 1330 | 2.1531 | 34.4217 | 19.7177 | 31.614 | 31.6223 |
70
- | 2.5249 | 8.0 | 1520 | 2.1154 | 34.4624 | 19.7477 | 31.682 | 31.7003 |
71
- | 2.5249 | 9.0 | 1710 | 2.1010 | 34.2918 | 19.6969 | 31.5511 | 31.5694 |
72
- | 2.393 | 10.0 | 1900 | 2.0760 | 34.5121 | 19.891 | 31.714 | 31.7041 |
73
- | 2.393 | 11.0 | 2090 | 2.0706 | 34.5749 | 19.9914 | 31.7706 | 31.8176 |
74
- | 2.393 | 12.0 | 2280 | 2.0488 | 34.3235 | 19.8327 | 31.5852 | 31.6301 |
75
- | 2.2901 | 13.0 | 2470 | 2.0446 | 34.5433 | 20.0419 | 31.8219 | 31.8487 |
76
- | 2.2901 | 14.0 | 2660 | 2.0315 | 34.748 | 20.0485 | 31.9948 | 32.0195 |
77
- | 2.2241 | 15.0 | 2850 | 2.0161 | 34.6868 | 20.1825 | 31.9218 | 31.9922 |
78
- | 2.2241 | 16.0 | 3040 | 2.0178 | 34.9768 | 20.2998 | 32.1154 | 32.1483 |
79
- | 2.2241 | 17.0 | 3230 | 2.0073 | 34.9668 | 20.3681 | 32.1994 | 32.2343 |
80
- | 2.1633 | 18.0 | 3420 | 2.0041 | 34.8753 | 20.2575 | 32.0363 | 32.0698 |
81
- | 2.1633 | 19.0 | 3610 | 1.9949 | 34.8478 | 20.1398 | 31.9938 | 32.0456 |
82
- | 2.1246 | 20.0 | 3800 | 1.9934 | 34.9461 | 20.2707 | 32.0457 | 32.0773 |
83
- | 2.1246 | 21.0 | 3990 | 1.9844 | 34.9639 | 20.2655 | 32.0949 | 32.1138 |
84
- | 2.1246 | 22.0 | 4180 | 1.9827 | 34.9889 | 20.299 | 32.1085 | 32.1294 |
85
- | 2.0973 | 23.0 | 4370 | 1.9838 | 34.8544 | 20.1674 | 32.0042 | 32.0328 |
86
- | 2.0973 | 24.0 | 4560 | 1.9795 | 34.9807 | 20.2989 | 32.116 | 32.1446 |
87
- | 2.0698 | 25.0 | 4750 | 1.9763 | 34.7165 | 20.0636 | 31.8773 | 31.9076 |
88
- | 2.0698 | 26.0 | 4940 | 1.9723 | 34.9025 | 20.2607 | 32.0456 | 32.0836 |
89
- | 2.0698 | 27.0 | 5130 | 1.9721 | 34.9712 | 20.321 | 32.1165 | 32.1708 |
90
- | 2.0543 | 28.0 | 5320 | 1.9734 | 34.916 | 20.2791 | 32.0429 | 32.0961 |
91
- | 2.0543 | 29.0 | 5510 | 1.9733 | 34.8415 | 20.1824 | 31.9888 | 32.0392 |
92
- | 2.0406 | 30.0 | 5700 | 1.9733 | 34.8633 | 20.1867 | 31.9947 | 32.0636 |
93
 
94
 
95
  ### Framework versions
@@ -97,4 +89,4 @@ The following hyperparameters were used during training:
97
  - Transformers 4.25.1
98
  - Pytorch 1.13.0
99
  - Datasets 2.8.0
100
- - Tokenizers 0.12.1
 
5
  - generated_from_trainer
6
  metrics:
7
  - rouge
 
8
  model-index:
9
  - name: mt5-simplification-spanish-clara-med
10
  results: []
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # mt5-simplification-spanish-clara-med
17
 
18
+ This model is a fine-tuned version of [oskrmiguel/mt5-simplification-spanish](https://huggingface.co/oskrmiguel/mt5-simplification-spanish) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.9716
21
+ - Rouge1: 33.5336
22
+ - Rouge2: 19.3768
23
+ - Rougel: 31.0143
24
+ - Rougelsum: 31.019
 
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | No log | 1.0 | 190 | 2.6705 | 32.0052 | 18.0764 | 29.5795 | 29.6206 |
56
+ | No log | 2.0 | 380 | 2.4784 | 32.5674 | 18.7464 | 30.213 | 30.2587 |
57
+ | 3.3039 | 3.0 | 570 | 2.3561 | 33.0346 | 19.1993 | 30.6573 | 30.6738 |
58
+ | 3.3039 | 4.0 | 760 | 2.2832 | 32.5695 | 18.8589 | 30.2062 | 30.2124 |
59
+ | 2.7462 | 5.0 | 950 | 2.2242 | 32.7386 | 18.7906 | 30.3327 | 30.3536 |
60
+ | 2.7462 | 6.0 | 1140 | 2.1751 | 32.764 | 18.8748 | 30.4329 | 30.5043 |
61
+ | 2.7462 | 7.0 | 1330 | 2.1466 | 32.9203 | 19.0381 | 30.5478 | 30.5822 |
62
+ | 2.5231 | 8.0 | 1520 | 2.1154 | 32.8822 | 18.9672 | 30.3852 | 30.454 |
63
+ | 2.5231 | 9.0 | 1710 | 2.0943 | 32.6762 | 18.7799 | 30.1846 | 30.242 |
64
+ | 2.3803 | 10.0 | 1900 | 2.0772 | 32.8481 | 18.9674 | 30.3398 | 30.3956 |
65
+ | 2.3803 | 11.0 | 2090 | 2.0558 | 32.8631 | 18.8782 | 30.3809 | 30.4269 |
66
+ | 2.3803 | 12.0 | 2280 | 2.0580 | 32.9141 | 19.0789 | 30.4803 | 30.5055 |
67
+ | 2.2832 | 13.0 | 2470 | 2.0270 | 32.785 | 18.8936 | 30.2776 | 30.3219 |
68
+ | 2.2832 | 14.0 | 2660 | 2.0375 | 32.9772 | 19.1564 | 30.5531 | 30.5705 |
69
+ | 2.2234 | 15.0 | 2850 | 2.0259 | 33.0685 | 19.1467 | 30.6441 | 30.6652 |
70
+ | 2.2234 | 16.0 | 3040 | 2.0093 | 32.9531 | 19.0017 | 30.5067 | 30.5341 |
71
+ | 2.2234 | 17.0 | 3230 | 2.0028 | 32.9746 | 19.0646 | 30.5194 | 30.5535 |
72
+ | 2.1665 | 18.0 | 3420 | 1.9941 | 33.3145 | 19.2719 | 30.7984 | 30.8402 |
73
+ | 2.1665 | 19.0 | 3610 | 1.9958 | 33.3439 | 19.228 | 30.7638 | 30.7938 |
74
+ | 2.1145 | 20.0 | 3800 | 1.9850 | 33.3089 | 19.1996 | 30.7415 | 30.7883 |
75
+ | 2.1145 | 21.0 | 3990 | 1.9868 | 33.4202 | 19.3332 | 30.8492 | 30.8572 |
76
+ | 2.1145 | 22.0 | 4180 | 1.9820 | 33.478 | 19.3366 | 30.8884 | 30.9123 |
77
+ | 2.0925 | 23.0 | 4370 | 1.9802 | 33.5095 | 19.4568 | 31.0046 | 31.0175 |
78
+ | 2.0925 | 24.0 | 4560 | 1.9801 | 33.5202 | 19.4547 | 31.0316 | 31.0566 |
79
+ | 2.0599 | 25.0 | 4750 | 1.9740 | 33.5925 | 19.4182 | 31.0212 | 31.0551 |
80
+ | 2.0599 | 26.0 | 4940 | 1.9731 | 33.5917 | 19.4456 | 31.0867 | 31.1124 |
81
+ | 2.0599 | 27.0 | 5130 | 1.9709 | 33.4423 | 19.2709 | 30.874 | 30.893 |
82
+ | 2.0487 | 28.0 | 5320 | 1.9715 | 33.5398 | 19.3803 | 31.0201 | 31.0261 |
83
+ | 2.0487 | 29.0 | 5510 | 1.9719 | 33.5324 | 19.3779 | 31.009 | 31.0143 |
84
+ | 2.0346 | 30.0 | 5700 | 1.9716 | 33.5336 | 19.3768 | 31.0143 | 31.019 |
85
 
86
 
87
  ### Framework versions
 
89
  - Transformers 4.25.1
90
  - Pytorch 1.13.0
91
  - Datasets 2.8.0
92
+ - Tokenizers 0.12.1