Hugging Face's logo

thrunlab
/
t5-large_sst2_dense_epochs-5

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
vxbrandon commited on
Commit
19f7f2b
•
1 Parent(s): 787bd2a

End of training

Browse files
Files changed (1) hide show
  1. README.md +16 -16
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9541284403669725
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-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3623
36
- - Accuracy: 0.9541
37
 
38
  ## Model description
39
 
@@ -68,19 +68,19 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 0.2263 | 0.38 | 50 | 0.1874 | 0.9404 |
72
- | 0.1549 | 0.76 | 100 | 0.1661 | 0.9438 |
73
- | 0.1321 | 1.14 | 150 | 0.3832 | 0.9484 |
74
- | 0.1153 | 1.52 | 200 | 0.2551 | 0.9484 |
75
- | 0.1135 | 1.89 | 250 | 0.1375 | 0.9530 |
76
- | 0.0823 | 2.27 | 300 | 0.4848 | 0.9495 |
77
- | 0.1417 | 2.65 | 350 | 0.3618 | 0.9484 |
78
- | 0.0763 | 3.03 | 400 | 0.3594 | 0.9530 |
79
- | 0.0959 | 3.41 | 450 | 0.3692 | 0.9576 |
80
- | 0.0925 | 3.79 | 500 | 0.3623 | 0.9541 |
81
- | 0.1089 | 4.17 | 550 | 0.4750 | 0.9576 |
82
- | 0.0758 | 4.55 | 600 | 0.8276 | 0.9472 |
83
- | 0.0792 | 4.92 | 650 | 0.5894 | 0.9553 |
84
 
85
 
86
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9575688073394495
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-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6867
36
+ - Accuracy: 0.9576
37
 
38
  ## Model description
39
 
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.2069 | 0.38 | 50 | 0.4171 | 0.9438 |
72
+ | 0.1627 | 0.76 | 100 | 0.3713 | 0.9518 |
73
+ | 0.1641 | 1.14 | 150 | 0.4802 | 0.9553 |
74
+ | 0.1261 | 1.52 | 200 | 0.2517 | 0.9541 |
75
+ | 0.128 | 1.89 | 250 | 0.2427 | 0.9633 |
76
+ | 0.0765 | 2.27 | 300 | 0.5854 | 0.9622 |
77
+ | 0.1547 | 2.65 | 350 | 0.6896 | 0.9507 |
78
+ | 0.0705 | 3.03 | 400 | 0.5790 | 0.9484 |
79
+ | 0.0683 | 3.41 | 450 | 0.3680 | 0.9564 |
80
+ | 0.0889 | 3.79 | 500 | 0.6867 | 0.9576 |
81
+ | 0.1541 | 4.17 | 550 | 0.6979 | 0.9576 |
82
+ | 0.0689 | 4.55 | 600 | 0.9328 | 0.9507 |
83
+ | 0.0964 | 4.92 | 650 | 0.6852 | 0.9587 |
84
 
85
 
86
  ### Framework versions