Hugging Face's logo

jamie613
/
mt5_fill_puntuation

Transformers
PyTorch
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
1
jamie613 commited on
Commit
a3041da
·
1 Parent(s): ac3c42c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -27
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [jamie613/mt5_fill_puntuation](https://huggingface.co/jamie613/mt5_fill_puntuation) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0745
18
 
19
  ## Model description
20
 
@@ -45,32 +45,33 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:-----:|:---------------:|
48
- | 0.0936 | 0.04 | 500 | 0.0834 |
49
- | 0.097 | 0.08 | 1000 | 0.0814 |
50
- | 0.0939 | 0.11 | 1500 | 0.0838 |
51
- | 0.0918 | 0.15 | 2000 | 0.0851 |
52
- | 0.0889 | 0.19 | 2500 | 0.0800 |
53
- | 0.0918 | 0.23 | 3000 | 0.0797 |
54
- | 0.0941 | 0.26 | 3500 | 0.0827 |
55
- | 0.0879 | 0.3 | 4000 | 0.0788 |
56
- | 0.0897 | 0.34 | 4500 | 0.0782 |
57
- | 0.0896 | 0.38 | 5000 | 0.0804 |
58
- | 0.0883 | 0.41 | 5500 | 0.0799 |
59
- | 0.0855 | 0.45 | 6000 | 0.0773 |
60
- | 0.0819 | 0.49 | 6500 | 0.0770 |
61
- | 0.0851 | 0.53 | 7000 | 0.0769 |
62
- | 0.0875 | 0.56 | 7500 | 0.0768 |
63
- | 0.0873 | 0.6 | 8000 | 0.0784 |
64
- | 0.0844 | 0.64 | 8500 | 0.0774 |
65
- | 0.0866 | 0.68 | 9000 | 0.0754 |
66
- | 0.0834 | 0.71 | 9500 | 0.0759 |
67
- | 0.0813 | 0.75 | 10000 | 0.0742 |
68
- | 0.0839 | 0.79 | 10500 | 0.0732 |
69
- | 0.0815 | 0.83 | 11000 | 0.0746 |
70
- | 0.0842 | 0.87 | 11500 | 0.0751 |
71
- | 0.0775 | 0.9 | 12000 | 0.0751 |
72
- | 0.0826 | 0.94 | 12500 | 0.0748 |
73
- | 0.0806 | 0.98 | 13000 | 0.0745 |
 
74
 
75
 
76
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [jamie613/mt5_fill_puntuation](https://huggingface.co/jamie613/mt5_fill_puntuation) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0717
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 0.0918 | 0.04 | 500 | 0.0803 |
49
+ | 0.0894 | 0.07 | 1000 | 0.0773 |
50
+ | 0.0905 | 0.11 | 1500 | 0.0822 |
51
+ | 0.0908 | 0.15 | 2000 | 0.0833 |
52
+ | 0.0868 | 0.18 | 2500 | 0.0840 |
53
+ | 0.09 | 0.22 | 3000 | 0.0811 |
54
+ | 0.0868 | 0.26 | 3500 | 0.0735 |
55
+ | 0.0869 | 0.29 | 4000 | 0.0805 |
56
+ | 0.0874 | 0.33 | 4500 | 0.0742 |
57
+ | 0.088 | 0.37 | 5000 | 0.0749 |
58
+ | 0.0884 | 0.4 | 5500 | 0.0730 |
59
+ | 0.0861 | 0.44 | 6000 | 0.0749 |
60
+ | 0.0804 | 0.48 | 6500 | 0.0739 |
61
+ | 0.0845 | 0.51 | 7000 | 0.0717 |
62
+ | 0.0861 | 0.55 | 7500 | 0.0743 |
63
+ | 0.0812 | 0.59 | 8000 | 0.0726 |
64
+ | 0.0824 | 0.62 | 8500 | 0.0729 |
65
+ | 0.0836 | 0.66 | 9000 | 0.0751 |
66
+ | 0.079 | 0.7 | 9500 | 0.0731 |
67
+ | 0.0806 | 0.73 | 10000 | 0.0725 |
68
+ | 0.0798 | 0.77 | 10500 | 0.0749 |
69
+ | 0.0794 | 0.81 | 11000 | 0.0725 |
70
+ | 0.0795 | 0.84 | 11500 | 0.0726 |
71
+ | 0.0755 | 0.88 | 12000 | 0.0732 |
72
+ | 0.0815 | 0.92 | 12500 | 0.0722 |
73
+ | 0.0776 | 0.95 | 13000 | 0.0719 |
74
+ | 0.0838 | 0.99 | 13500 | 0.0717 |
75
 
76
 
77
  ### Framework versions