Hugging Face's logo

ZhiguangHan
/
mt5-small-task1-dataset3

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ZhiguangHan commited on
Commit
34d8375
•
1 Parent(s): 19cb6c6

End of training

Browse files
Files changed (1) hide show
  1. README.md +18 -15
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: 0.9695
21
- - Accuracy: 0.448
22
 
23
  ## Model description
24
 
@@ -43,24 +43,27 @@ 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
- | 9.5046 | 1.0 | 250 | 2.3331 | 0.114 |
53
- | 2.4331 | 2.0 | 500 | 1.7122 | 0.12 |
54
- | 1.8836 | 3.0 | 750 | 1.5107 | 0.21 |
55
- | 1.6365 | 4.0 | 1000 | 1.4237 | 0.208 |
56
- | 1.4737 | 5.0 | 1250 | 1.2627 | 0.316 |
57
- | 1.3361 | 6.0 | 1500 | 1.1837 | 0.37 |
58
- | 1.1998 | 7.0 | 1750 | 1.1045 | 0.408 |
59
- | 1.1317 | 8.0 | 2000 | 1.0488 | 0.404 |
60
- | 1.0612 | 9.0 | 2250 | 1.0142 | 0.42 |
61
- | 1.0265 | 10.0 | 2500 | 0.9925 | 0.422 |
62
- | 1.009 | 11.0 | 2750 | 0.9708 | 0.446 |
63
- | 0.9898 | 12.0 | 3000 | 0.9695 | 0.448 |
 
 
 
64
 
65
 
66
  ### Framework versions
 
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: 0.8026
21
+ - Accuracy: 0.52
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
+ | 9.7282 | 1.0 | 250 | 2.3106 | 0.118 |
53
+ | 2.3916 | 2.0 | 500 | 1.7098 | 0.128 |
54
+ | 1.8578 | 3.0 | 750 | 1.5425 | 0.198 |
55
+ | 1.6283 | 4.0 | 1000 | 1.4055 | 0.216 |
56
+ | 1.4748 | 5.0 | 1250 | 1.3024 | 0.282 |
57
+ | 1.2899 | 6.0 | 1500 | 1.1393 | 0.388 |
58
+ | 1.1631 | 7.0 | 1750 | 1.0190 | 0.434 |
59
+ | 1.0565 | 8.0 | 2000 | 0.9458 | 0.456 |
60
+ | 0.9747 | 9.0 | 2250 | 0.9052 | 0.488 |
61
+ | 0.9119 | 10.0 | 2500 | 0.8731 | 0.514 |
62
+ | 0.8752 | 11.0 | 2750 | 0.8279 | 0.516 |
63
+ | 0.8356 | 12.0 | 3000 | 0.8263 | 0.524 |
64
+ | 0.8132 | 13.0 | 3250 | 0.8125 | 0.52 |
65
+ | 0.8113 | 14.0 | 3500 | 0.8037 | 0.52 |
66
+ | 0.8075 | 15.0 | 3750 | 0.8026 | 0.52 |
67
 
68
 
69
  ### Framework versions