Hugging Face's logo

ZhiguangHan
/
mt5-small-task2-dataset2

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ZhiguangHan commited on
Commit
63a68e7
·
1 Parent(s): 58c8216

End of training

Browse files
Files changed (1) hide show
  1. README.md +20 -17
README.md CHANGED
@@ -4,7 +4,7 @@ base_model: google/mt5-small
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
- - rouge
8
  model-index:
9
  - name: mt5-small-task2-dataset2
10
  results: []
@@ -17,11 +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: 0.5765
21
- - Rouge1: 0.0
22
- - Rouge2: 0.0
23
- - Rougel: 0.0
24
- - Rougelsum: 0.0
25
 
26
  ## Model description
27
 
@@ -41,23 +38,29 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 5.6e-05
44
- - train_batch_size: 8
45
- - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 6
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
55
- | 3.9862 | 1.0 | 500 | 1.0412 | 0.0 | 0.0 | 0.0 | 0.0 |
56
- | 1.3633 | 2.0 | 1000 | 0.7485 | 0.0 | 0.0 | 0.0 | 0.0 |
57
- | 0.9873 | 3.0 | 1500 | 0.6652 | 0.0 | 0.0 | 0.0 | 0.0 |
58
- | 0.8529 | 4.0 | 2000 | 0.6117 | 0.0 | 0.0 | 0.0 | 0.0 |
59
- | 0.7724 | 5.0 | 2500 | 0.5854 | 0.0 | 0.0 | 0.0 | 0.0 |
60
- | 0.7457 | 6.0 | 3000 | 0.5765 | 0.0 | 0.0 | 0.0 | 0.0 |
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
+ - accuracy
8
  model-index:
9
  - name: mt5-small-task2-dataset2
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: 0.4228
21
+ - Accuracy: 0.32
 
 
 
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5.6e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
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
+ | 6.2681 | 1.0 | 250 | 1.1622 | 0.018 |
53
+ | 1.7716 | 2.0 | 500 | 0.8039 | 0.066 |
54
+ | 1.1424 | 3.0 | 750 | 0.6418 | 0.14 |
55
+ | 0.8879 | 4.0 | 1000 | 0.5569 | 0.204 |
56
+ | 0.7728 | 5.0 | 1250 | 0.5065 | 0.256 |
57
+ | 0.6886 | 6.0 | 1500 | 0.4821 | 0.268 |
58
+ | 0.6422 | 7.0 | 1750 | 0.4619 | 0.282 |
59
+ | 0.6137 | 8.0 | 2000 | 0.4500 | 0.298 |
60
+ | 0.5837 | 9.0 | 2250 | 0.4314 | 0.3 |
61
+ | 0.5711 | 10.0 | 2500 | 0.4256 | 0.316 |
62
+ | 0.5596 | 11.0 | 2750 | 0.4228 | 0.316 |
63
+ | 0.5458 | 12.0 | 3000 | 0.4228 | 0.32 |
64
 
65
 
66
  ### Framework versions