Hugging Face's logo

ZhiguangHan
/
mt5-small-task3-dataset2

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ZhiguangHan commited on
Commit
1aba744
•
1 Parent(s): cbde939

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -20
  2. model.safetensors +1 -1
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-task3-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: 0.0456
21
- - Rouge1: 0.0
22
- - Rouge2: 0.0
23
- - Rougel: 0.0
24
- - Rougelsum: 0.0
25
 
26
  ## Model description
27
 
@@ -41,30 +38,33 @@ 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: 8
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
55
- | 2.9931 | 1.0 | 500 | 0.1005 | 0.0 | 0.0 | 0.0 | 0.0 |
56
- | 0.0796 | 2.0 | 1000 | 0.0598 | 0.0 | 0.0 | 0.0 | 0.0 |
57
- | 0.0514 | 3.0 | 1500 | 0.0539 | 0.0 | 0.0 | 0.0 | 0.0 |
58
- | 0.0451 | 4.0 | 2000 | 0.0512 | 0.0 | 0.0 | 0.0 | 0.0 |
59
- | 0.0412 | 5.0 | 2500 | 0.0453 | 0.0 | 0.0 | 0.0 | 0.0 |
60
- | 0.0407 | 6.0 | 3000 | 0.0496 | 0.0 | 0.0 | 0.0 | 0.0 |
61
- | 0.0387 | 7.0 | 3500 | 0.0457 | 0.0 | 0.0 | 0.0 | 0.0 |
62
- | 0.0375 | 8.0 | 4000 | 0.0456 | 0.0 | 0.0 | 0.0 | 0.0 |
 
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.35.2
68
- - Pytorch 2.1.0+cu118
69
  - Datasets 2.15.0
70
  - Tokenizers 0.15.0
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
+ - accuracy
8
  model-index:
9
  - name: mt5-small-task3-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: 1.5095
21
+ - Accuracy: 0.064
 
 
 
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
+ | 2.9674 | 1.0 | 250 | 1.7894 | 0.028 |
53
+ | 2.3967 | 2.0 | 500 | 1.5754 | 0.056 |
54
+ | 2.0581 | 3.0 | 750 | 1.6416 | 0.064 |
55
+ | 1.9219 | 4.0 | 1000 | 1.5374 | 0.064 |
56
+ | 1.813 | 5.0 | 1250 | 1.5198 | 0.064 |
57
+ | 1.7595 | 6.0 | 1500 | 1.5184 | 0.062 |
58
+ | 1.7312 | 7.0 | 1750 | 1.5255 | 0.064 |
59
+ | 1.7085 | 8.0 | 2000 | 1.5046 | 0.064 |
60
+ | 1.6863 | 9.0 | 2250 | 1.5199 | 0.064 |
61
+ | 1.6814 | 10.0 | 2500 | 1.5130 | 0.064 |
62
+ | 1.6753 | 11.0 | 2750 | 1.5095 | 0.064 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.35.2
68
+ - Pytorch 2.1.0+cu121
69
  - Datasets 2.15.0
70
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d819b07d02126a6a74616786ae5dcb97f2ee233cd8cb8b3786e0283ff1aea63b
3
  size 1200729512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e30e648ede18e72309a064a4e15beed6cdf99df7eb03072bb82c95574461f4e
3
  size 1200729512