Hugging Face's logo

ZhiguangHan
/
mt5-small-task2-dataset3

Transformers
TensorBoard
Safetensors
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
ZhiguangHan commited on
Commit
4419242
·
1 Parent(s): 7ad9230

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: 0.3659
21
- - Accuracy: 0.632
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
- | 7.624 | 1.0 | 250 | 1.4193 | 0.314 |
53
- | 2.0235 | 2.0 | 500 | 0.9796 | 0.408 |
54
- | 1.284 | 3.0 | 750 | 0.7148 | 0.48 |
55
- | 0.9385 | 4.0 | 1000 | 0.5765 | 0.512 |
56
- | 0.7315 | 5.0 | 1250 | 0.4948 | 0.55 |
57
- | 0.642 | 6.0 | 1500 | 0.4369 | 0.59 |
58
- | 0.5668 | 7.0 | 1750 | 0.4125 | 0.606 |
59
- | 0.5187 | 8.0 | 2000 | 0.4030 | 0.614 |
60
- | 0.4809 | 9.0 | 2250 | 0.3812 | 0.626 |
61
- | 0.4563 | 10.0 | 2500 | 0.3722 | 0.63 |
62
- | 0.4434 | 11.0 | 2750 | 0.3683 | 0.628 |
63
- | 0.4469 | 12.0 | 3000 | 0.3659 | 0.632 |
 
 
 
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: 0.3113
21
+ - Accuracy: 0.704
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
+ | 1.3153 | 1.0 | 250 | 0.7513 | 0.526 |
53
+ | 0.8878 | 2.0 | 500 | 0.5870 | 0.576 |
54
+ | 0.7191 | 3.0 | 750 | 0.5021 | 0.578 |
55
+ | 0.5842 | 4.0 | 1000 | 0.4596 | 0.612 |
56
+ | 0.5085 | 5.0 | 1250 | 0.4158 | 0.62 |
57
+ | 0.4515 | 6.0 | 1500 | 0.3865 | 0.618 |
58
+ | 0.4086 | 7.0 | 1750 | 0.3755 | 0.648 |
59
+ | 0.3811 | 8.0 | 2000 | 0.3505 | 0.662 |
60
+ | 0.3449 | 9.0 | 2250 | 0.3366 | 0.678 |
61
+ | 0.3294 | 10.0 | 2500 | 0.3280 | 0.674 |
62
+ | 0.3146 | 11.0 | 2750 | 0.3201 | 0.702 |
63
+ | 0.305 | 12.0 | 3000 | 0.3146 | 0.69 |
64
+ | 0.2972 | 13.0 | 3250 | 0.3130 | 0.702 |
65
+ | 0.2819 | 14.0 | 3500 | 0.3106 | 0.696 |
66
+ | 0.2828 | 15.0 | 3750 | 0.3113 | 0.704 |
67
 
68
 
69
  ### Framework versions