Hugging Face's logo

ZhiguangHan
/
mt5-small-task2-dataset1

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ZhiguangHan commited on
Commit
41a0f99
•
1 Parent(s): a54d77e

End of training

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -4,7 +4,7 @@ base_model: google/mt5-small
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
- - f1
8
  model-index:
9
  - name: mt5-small-task2-dataset1
10
  results: []
@@ -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: 0.2115
21
- - F1: 0.74
22
 
23
  ## Model description
24
 
@@ -47,20 +47,20 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | F1 |
51
- |:-------------:|:-----:|:----:|:---------------:|:------:|
52
- | 0.4196 | 1.0 | 250 | 0.4480 | 0.644 |
53
- | 0.4665 | 2.0 | 500 | 0.3543 | 0.652 |
54
- | 0.4327 | 3.0 | 750 | 0.3109 | 0.67 |
55
- | 0.3638 | 4.0 | 1000 | 0.2842 | 0.692 |
56
- | 0.3297 | 5.0 | 1250 | 0.2666 | 0.708 |
57
- | 0.2953 | 6.0 | 1500 | 0.2344 | 0.728 |
58
- | 0.2722 | 7.0 | 1750 | 0.2328 | 0.722 |
59
- | 0.2578 | 8.0 | 2000 | 0.2224 | 0.7300 |
60
- | 0.2435 | 9.0 | 2250 | 0.2171 | 0.732 |
61
- | 0.2323 | 10.0 | 2500 | 0.2123 | 0.736 |
62
- | 0.2279 | 11.0 | 2750 | 0.2121 | 0.74 |
63
- | 0.2224 | 12.0 | 3000 | 0.2115 | 0.74 |
64
 
65
 
66
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
+ - accuracy
8
  model-index:
9
  - name: mt5-small-task2-dataset1
10
  results: []
 
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: 0.3301
21
+ - Accuracy: 0.714
22
 
23
  ## Model description
24
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 7.9531 | 1.0 | 250 | 1.3804 | 0.474 |
53
+ | 1.8269 | 2.0 | 500 | 0.8424 | 0.552 |
54
+ | 1.0738 | 3.0 | 750 | 0.6419 | 0.606 |
55
+ | 0.7726 | 4.0 | 1000 | 0.5072 | 0.65 |
56
+ | 0.649 | 5.0 | 1250 | 0.4420 | 0.664 |
57
+ | 0.5479 | 6.0 | 1500 | 0.4009 | 0.672 |
58
+ | 0.4958 | 7.0 | 1750 | 0.3732 | 0.684 |
59
+ | 0.4437 | 8.0 | 2000 | 0.3576 | 0.716 |
60
+ | 0.4287 | 9.0 | 2250 | 0.3477 | 0.708 |
61
+ | 0.4016 | 10.0 | 2500 | 0.3378 | 0.716 |
62
+ | 0.3975 | 11.0 | 2750 | 0.3310 | 0.718 |
63
+ | 0.3818 | 12.0 | 3000 | 0.3301 | 0.714 |
64
 
65
 
66
  ### Framework versions