Hugging Face's logo

thrunlab
/
t5-base_cola_dense_epochs-6

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
1
lukeleeai commited on
Commit
6f9de47
·
1 Parent(s): b2deaac

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -27
  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: 0.8235858101629914
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: 0.4848
36
- - Accuracy: 0.8236
37
 
38
  ## Model description
39
 
@@ -65,30 +65,26 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.587 | 0.19 | 50 | 0.5972 | 0.6913 |
69
- | 0.5042 | 0.37 | 100 | 0.6078 | 0.6932 |
70
- | 0.5178 | 0.56 | 150 | 0.5093 | 0.7910 |
71
- | 0.4031 | 0.75 | 200 | 0.5577 | 0.7939 |
72
- | 0.4277 | 0.93 | 250 | 0.5249 | 0.8054 |
73
- | 0.381 | 1.12 | 300 | 0.5186 | 0.8121 |
74
- | 0.3581 | 1.31 | 350 | 0.5109 | 0.8150 |
75
- | 0.3944 | 1.49 | 400 | 0.4925 | 0.8188 |
76
- | 0.4157 | 1.68 | 450 | 0.5522 | 0.8035 |
77
- | 0.4302 | 1.87 | 500 | 0.4848 | 0.8236 |
78
- | 0.2904 | 2.05 | 550 | 0.4853 | 0.8351 |
79
- | 0.2714 | 2.24 | 600 | 0.4737 | 0.8313 |
80
- | 0.2621 | 2.43 | 650 | 0.4647 | 0.8303 |
81
- | 0.2501 | 2.61 | 700 | 0.4545 | 0.8332 |
82
- | 0.2844 | 2.8 | 750 | 0.5090 | 0.8284 |
83
- | 0.278 | 2.99 | 800 | 0.5008 | 0.8313 |
84
- | 0.2172 | 3.17 | 850 | 0.5372 | 0.8360 |
85
- | 0.2905 | 3.36 | 900 | 0.5042 | 0.8351 |
86
- | 0.2869 | 3.54 | 950 | 0.5220 | 0.8351 |
87
- | 0.316 | 3.73 | 1000 | 0.5070 | 0.8351 |
88
- | 0.3519 | 3.92 | 1050 | 0.5151 | 0.8303 |
89
- | 0.2147 | 4.1 | 1100 | 0.5992 | 0.8313 |
90
- | 0.2906 | 4.29 | 1150 | 0.6255 | 0.8332 |
91
- | 0.1645 | 4.48 | 1200 | 0.6023 | 0.8351 |
92
 
93
 
94
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8149568552253116
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: 0.4516
36
+ - Accuracy: 0.8150
37
 
38
  ## Model description
39
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.5922 | 0.19 | 50 | 0.5552 | 0.6913 |
69
+ | 0.4661 | 0.37 | 100 | 0.5390 | 0.7891 |
70
+ | 0.5097 | 0.56 | 150 | 0.4639 | 0.7929 |
71
+ | 0.3977 | 0.75 | 200 | 0.4841 | 0.8150 |
72
+ | 0.4205 | 0.93 | 250 | 0.5351 | 0.8169 |
73
+ | 0.3427 | 1.12 | 300 | 0.4983 | 0.8265 |
74
+ | 0.3216 | 1.31 | 350 | 0.4590 | 0.8198 |
75
+ | 0.3486 | 1.49 | 400 | 0.4620 | 0.8207 |
76
+ | 0.3683 | 1.68 | 450 | 0.5333 | 0.8274 |
77
+ | 0.4098 | 1.87 | 500 | 0.4516 | 0.8150 |
78
+ | 0.2971 | 2.05 | 550 | 0.5464 | 0.8332 |
79
+ | 0.2701 | 2.24 | 600 | 0.5428 | 0.8322 |
80
+ | 0.2758 | 2.43 | 650 | 0.5045 | 0.8255 |
81
+ | 0.2417 | 2.61 | 700 | 0.5153 | 0.8313 |
82
+ | 0.334 | 2.8 | 750 | 0.5276 | 0.8332 |
83
+ | 0.2691 | 2.99 | 800 | 0.5262 | 0.8313 |
84
+ | 0.2542 | 3.17 | 850 | 0.5558 | 0.8351 |
85
+ | 0.285 | 3.36 | 900 | 0.5150 | 0.8370 |
86
+ | 0.2593 | 3.54 | 950 | 0.5291 | 0.8293 |
87
+ | 0.3295 | 3.73 | 1000 | 0.5216 | 0.8303 |
 
 
 
 
88
 
89
 
90
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e29a698070ac87daaa94b1d0657b1ff899c7feb125e0837ae742d8ac746cfa
3
  size 894094241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61fe8850ad1dfb0701b93e030a279760a6249299ff8915b746c6b4107b08191
3
  size 894094241