Hugging Face's logo

thrunlab
/
t5-base_cola_dense_epochs-5

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Model card Files Community
vxbrandon commited on
Commit
41e5f6f
·
1 Parent(s): c63e4f7

End of training

Browse files
Files changed (2) hide show
  1. README.md +27 -23
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8341323106423778
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4393
36
- - Accuracy: 0.8341
37
 
38
  ## Model description
39
 
@@ -65,26 +65,30 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.575 | 0.19 | 50 | 0.5685 | 0.6913 |
69
- | 0.4799 | 0.37 | 100 | 0.6161 | 0.7670 |
70
- | 0.4941 | 0.56 | 150 | 0.4668 | 0.8063 |
71
- | 0.3837 | 0.75 | 200 | 0.4712 | 0.8169 |
72
- | 0.4198 | 0.93 | 250 | 0.5438 | 0.7996 |
73
- | 0.349 | 1.12 | 300 | 0.4618 | 0.8265 |
74
- | 0.3347 | 1.31 | 350 | 0.4630 | 0.8226 |
75
- | 0.3325 | 1.49 | 400 | 0.4581 | 0.8313 |
76
- | 0.3595 | 1.68 | 450 | 0.5653 | 0.7948 |
77
- | 0.4087 | 1.87 | 500 | 0.4393 | 0.8341 |
78
- | 0.2669 | 2.05 | 550 | 0.5241 | 0.8322 |
79
- | 0.2887 | 2.24 | 600 | 0.5042 | 0.8351 |
80
- | 0.2552 | 2.43 | 650 | 0.4713 | 0.8418 |
81
- | 0.238 | 2.61 | 700 | 0.4694 | 0.8428 |
82
- | 0.325 | 2.8 | 750 | 0.5176 | 0.8360 |
83
- | 0.285 | 2.99 | 800 | 0.5266 | 0.8265 |
84
- | 0.2099 | 3.17 | 850 | 0.5147 | 0.8437 |
85
- | 0.2645 | 3.36 | 900 | 0.4951 | 0.8380 |
86
- | 0.2851 | 3.54 | 950 | 0.4945 | 0.8370 |
87
- | 0.3277 | 3.73 | 1000 | 0.4828 | 0.8360 |
 
 
 
 
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.822627037392138
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5026
36
+ - Accuracy: 0.8226
37
 
38
  ## Model description
39
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.5712 | 0.19 | 50 | 0.5805 | 0.6913 |
69
+ | 0.4693 | 0.37 | 100 | 0.6260 | 0.7661 |
70
+ | 0.4731 | 0.56 | 150 | 0.5279 | 0.8054 |
71
+ | 0.3707 | 0.75 | 200 | 0.5165 | 0.8025 |
72
+ | 0.4729 | 0.93 | 250 | 0.5145 | 0.8102 |
73
+ | 0.3929 | 1.12 | 300 | 0.4773 | 0.8188 |
74
+ | 0.3369 | 1.31 | 350 | 0.5014 | 0.8198 |
75
+ | 0.3757 | 1.49 | 400 | 0.5183 | 0.8188 |
76
+ | 0.4206 | 1.68 | 450 | 0.5743 | 0.8198 |
77
+ | 0.4196 | 1.87 | 500 | 0.5026 | 0.8226 |
78
+ | 0.3098 | 2.05 | 550 | 0.5289 | 0.8236 |
79
+ | 0.2852 | 2.24 | 600 | 0.5562 | 0.8265 |
80
+ | 0.2936 | 2.43 | 650 | 0.5312 | 0.8303 |
81
+ | 0.2072 | 2.61 | 700 | 0.4904 | 0.8313 |
82
+ | 0.2809 | 2.8 | 750 | 0.5394 | 0.8341 |
83
+ | 0.2685 | 2.99 | 800 | 0.5905 | 0.8332 |
84
+ | 0.2215 | 3.17 | 850 | 0.5835 | 0.8341 |
85
+ | 0.3543 | 3.36 | 900 | 0.5556 | 0.8332 |
86
+ | 0.239 | 3.54 | 950 | 0.5419 | 0.8351 |
87
+ | 0.257 | 3.73 | 1000 | 0.5587 | 0.8351 |
88
+ | 0.2958 | 3.92 | 1050 | 0.5982 | 0.8341 |
89
+ | 0.2785 | 4.1 | 1100 | 0.5978 | 0.8360 |
90
+ | 0.1975 | 4.29 | 1150 | 0.6067 | 0.8341 |
91
+ | 0.2222 | 4.48 | 1200 | 0.5947 | 0.8380 |
92
 
93
 
94
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c76010259c84a907bb9dc45a9ddc5aba00090f5b0dafd2f566447ace25406c4a
3
  size 894094686
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7284c742b7f5e3e174c4a522874b90b4732392924e76649ca1e5f1c73fe7a5b8
3
  size 894094686