Hugging Face's logo

ZhiguangHan
/
mt5-small-task1-dataset4

Transformers
TensorBoard
Safetensors
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
ZhiguangHan commited on
Commit
27949d5
·
1 Parent(s): f791fee

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: 1.3594
21
- - Accuracy: 0.086
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
- | 7.9758 | 1.0 | 250 | 2.3199 | 0.024 |
53
- | 2.7257 | 2.0 | 500 | 1.9097 | 0.016 |
54
- | 2.2688 | 3.0 | 750 | 1.7108 | 0.044 |
55
- | 1.9809 | 4.0 | 1000 | 1.5786 | 0.062 |
56
- | 1.8098 | 5.0 | 1250 | 1.5045 | 0.064 |
57
- | 1.6944 | 6.0 | 1500 | 1.4686 | 0.066 |
58
- | 1.6063 | 7.0 | 1750 | 1.4260 | 0.08 |
59
- | 1.5417 | 8.0 | 2000 | 1.3970 | 0.086 |
60
- | 1.4947 | 9.0 | 2250 | 1.3749 | 0.086 |
61
- | 1.4704 | 10.0 | 2500 | 1.3714 | 0.086 |
62
- | 1.44 | 11.0 | 2750 | 1.3672 | 0.088 |
63
- | 1.4337 | 12.0 | 3000 | 1.3594 | 0.086 |
 
 
 
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: 1.2245
21
+ - Accuracy: 0.138
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
+ | 9.1823 | 1.0 | 250 | 2.2930 | 0.0 |
53
+ | 2.763 | 2.0 | 500 | 1.8604 | 0.0 |
54
+ | 2.3034 | 3.0 | 750 | 1.6307 | 0.074 |
55
+ | 2.0136 | 4.0 | 1000 | 1.6494 | 0.076 |
56
+ | 1.8156 | 5.0 | 1250 | 1.4797 | 0.084 |
57
+ | 1.6683 | 6.0 | 1500 | 1.4214 | 0.094 |
58
+ | 1.5806 | 7.0 | 1750 | 1.3692 | 0.094 |
59
+ | 1.5035 | 8.0 | 2000 | 1.3212 | 0.106 |
60
+ | 1.4451 | 9.0 | 2250 | 1.2997 | 0.118 |
61
+ | 1.4045 | 10.0 | 2500 | 1.2689 | 0.128 |
62
+ | 1.3742 | 11.0 | 2750 | 1.2515 | 0.136 |
63
+ | 1.3456 | 12.0 | 3000 | 1.2411 | 0.13 |
64
+ | 1.325 | 13.0 | 3250 | 1.2264 | 0.14 |
65
+ | 1.3226 | 14.0 | 3500 | 1.2229 | 0.146 |
66
+ | 1.3035 | 15.0 | 3750 | 1.2245 | 0.138 |
67
 
68
 
69
  ### Framework versions