Hugging Face's logo

ZhiguangHan
/
mt5-small-task2-dataset4

Transformers
TensorBoard
Safetensors
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
ZhiguangHan commited on
Commit
af5b63d
·
verified ·
1 Parent(s): d908454

End of training

Browse files
Files changed (1) hide show
  1. README.md +19 -16
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5227
21
- - Accuracy: 0.212
22
 
23
  ## Model description
24
 
@@ -43,29 +43,32 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 12
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 6.2329 | 1.0 | 250 | 1.3076 | 0.006 |
53
- | 1.6853 | 2.0 | 500 | 0.8967 | 0.09 |
54
- | 1.123 | 3.0 | 750 | 0.7346 | 0.132 |
55
- | 0.907 | 4.0 | 1000 | 0.6587 | 0.162 |
56
- | 0.7875 | 5.0 | 1250 | 0.6083 | 0.17 |
57
- | 0.7135 | 6.0 | 1500 | 0.5807 | 0.188 |
58
- | 0.675 | 7.0 | 1750 | 0.5566 | 0.196 |
59
- | 0.6403 | 8.0 | 2000 | 0.5427 | 0.206 |
60
- | 0.6229 | 9.0 | 2250 | 0.5354 | 0.208 |
61
- | 0.6046 | 10.0 | 2500 | 0.5329 | 0.212 |
62
- | 0.5974 | 11.0 | 2750 | 0.5237 | 0.212 |
63
- | 0.5875 | 12.0 | 3000 | 0.5227 | 0.212 |
 
 
 
64
 
65
 
66
  ### Framework versions
67
 
68
  - Transformers 4.35.2
69
  - Pytorch 2.1.0+cu121
70
- - Datasets 2.15.0
71
  - Tokenizers 0.15.0
 
17
 
18
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4838
21
+ - Accuracy: 0.224
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 15
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 6.0046 | 1.0 | 250 | 1.3356 | 0.008 |
53
+ | 1.8352 | 2.0 | 500 | 0.9395 | 0.082 |
54
+ | 1.2215 | 3.0 | 750 | 0.7493 | 0.13 |
55
+ | 0.9711 | 4.0 | 1000 | 0.6537 | 0.162 |
56
+ | 0.8269 | 5.0 | 1250 | 0.5908 | 0.176 |
57
+ | 0.741 | 6.0 | 1500 | 0.5548 | 0.19 |
58
+ | 0.6896 | 7.0 | 1750 | 0.5377 | 0.194 |
59
+ | 0.651 | 8.0 | 2000 | 0.5198 | 0.21 |
60
+ | 0.627 | 9.0 | 2250 | 0.5086 | 0.224 |
61
+ | 0.606 | 10.0 | 2500 | 0.5006 | 0.228 |
62
+ | 0.5849 | 11.0 | 2750 | 0.4948 | 0.232 |
63
+ | 0.5733 | 12.0 | 3000 | 0.4928 | 0.23 |
64
+ | 0.5607 | 13.0 | 3250 | 0.4851 | 0.224 |
65
+ | 0.5599 | 14.0 | 3500 | 0.4842 | 0.222 |
66
+ | 0.5584 | 15.0 | 3750 | 0.4838 | 0.224 |
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.35.2
72
  - Pytorch 2.1.0+cu121
73
+ - Datasets 2.16.1
74
  - Tokenizers 0.15.0