Hugging Face's logo

ZhiguangHan
/
mt5-small-task1-dataset1

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ZhiguangHan commited on
Commit
c9319b0
•
1 Parent(s): b2f14e0

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: 0.6887
21
- - Accuracy: 0.618
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
- | 10.3747 | 1.0 | 250 | 1.8894 | 0.19 |
53
- | 2.1263 | 2.0 | 500 | 1.3543 | 0.2 |
54
- | 1.5986 | 3.0 | 750 | 1.2566 | 0.2 |
55
- | 1.43 | 4.0 | 1000 | 1.0943 | 0.374 |
56
- | 1.2409 | 5.0 | 1250 | 0.9063 | 0.506 |
57
- | 1.0295 | 6.0 | 1500 | 0.8092 | 0.552 |
58
- | 0.9365 | 7.0 | 1750 | 0.7702 | 0.552 |
59
- | 0.9121 | 8.0 | 2000 | 0.7411 | 0.59 |
60
- | 0.8275 | 9.0 | 2250 | 0.7289 | 0.588 |
61
- | 0.8063 | 10.0 | 2500 | 0.6968 | 0.61 |
62
- | 0.7903 | 11.0 | 2750 | 0.6868 | 0.616 |
63
- | 0.7674 | 12.0 | 3000 | 0.6887 | 0.618 |
 
 
 
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: 0.6492
21
+ - Accuracy: 0.626
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
+ | 10.2312 | 1.0 | 250 | 2.1246 | 0.194 |
53
+ | 2.2998 | 2.0 | 500 | 1.4171 | 0.194 |
54
+ | 1.6645 | 3.0 | 750 | 1.2718 | 0.206 |
55
+ | 1.4575 | 4.0 | 1000 | 1.1549 | 0.258 |
56
+ | 1.3335 | 5.0 | 1250 | 1.0267 | 0.432 |
57
+ | 1.1696 | 6.0 | 1500 | 0.8811 | 0.5 |
58
+ | 0.9974 | 7.0 | 1750 | 0.7960 | 0.532 |
59
+ | 0.9162 | 8.0 | 2000 | 0.7576 | 0.556 |
60
+ | 0.8463 | 9.0 | 2250 | 0.7342 | 0.588 |
61
+ | 0.8078 | 10.0 | 2500 | 0.6856 | 0.606 |
62
+ | 0.7751 | 11.0 | 2750 | 0.6655 | 0.612 |
63
+ | 0.7533 | 12.0 | 3000 | 0.6645 | 0.622 |
64
+ | 0.7337 | 13.0 | 3250 | 0.6625 | 0.62 |
65
+ | 0.7154 | 14.0 | 3500 | 0.6640 | 0.624 |
66
+ | 0.7038 | 15.0 | 3750 | 0.6492 | 0.626 |
67
 
68
 
69
  ### Framework versions