Hugging Face's logo

kennethge123
/
superglue_rte-bert-base-uncased

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
kennethge123 commited on
Commit
588d4fa
•
1 Parent(s): 6bd91f1

Model save

Browse files
Files changed (2) hide show
  1. README.md +23 -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: 0.631768953068592
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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the super_glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 3.9334
36
- - Accuracy: 0.6318
37
 
38
  ## Model description
39
 
@@ -64,26 +64,26 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
- | 0.6845 | 1.0 | 623 | 0.6880 | 0.5379 |
68
- | 0.6015 | 2.0 | 1246 | 0.8206 | 0.6426 |
69
- | 0.5012 | 3.0 | 1869 | 1.4769 | 0.6354 |
70
- | 0.4173 | 4.0 | 2492 | 1.7735 | 0.6570 |
71
- | 0.078 | 5.0 | 3115 | 2.2116 | 0.6354 |
72
- | 0.0732 | 6.0 | 3738 | 2.6033 | 0.6318 |
73
- | 0.0703 | 7.0 | 4361 | 2.7944 | 0.6390 |
74
- | 0.0543 | 8.0 | 4984 | 2.6007 | 0.6462 |
75
- | 0.0505 | 9.0 | 5607 | 2.4168 | 0.6462 |
76
- | 0.0412 | 10.0 | 6230 | 2.7503 | 0.6787 |
77
- | 0.0303 | 11.0 | 6853 | 3.2166 | 0.6643 |
78
- | 0.0214 | 12.0 | 7476 | 3.0135 | 0.6498 |
79
- | 0.0416 | 13.0 | 8099 | 2.9919 | 0.6534 |
80
- | 0.0252 | 14.0 | 8722 | 3.0985 | 0.6570 |
81
- | 0.0122 | 15.0 | 9345 | 3.5950 | 0.6209 |
82
- | 0.009 | 16.0 | 9968 | 3.5463 | 0.6354 |
83
- | 0.0034 | 17.0 | 10591 | 3.6333 | 0.6570 |
84
- | 0.0109 | 18.0 | 11214 | 3.6860 | 0.6426 |
85
- | 0.0041 | 19.0 | 11837 | 3.9160 | 0.6354 |
86
- | 0.0 | 20.0 | 12460 | 3.9334 | 0.6318 |
87
 
88
 
89
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6739130434782609
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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the super_glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.5070
36
+ - Accuracy: 0.6739
37
 
38
  ## Model description
39
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.704 | 1.0 | 623 | 0.6653 | 0.6159 |
68
+ | 0.6848 | 2.0 | 1246 | 0.7144 | 0.4203 |
69
+ | 0.7083 | 3.0 | 1869 | 0.6922 | 0.5797 |
70
+ | 0.7014 | 4.0 | 2492 | 0.7327 | 0.6232 |
71
+ | 0.6528 | 5.0 | 3115 | 0.6727 | 0.6522 |
72
+ | 0.6471 | 6.0 | 3738 | 0.8413 | 0.6159 |
73
+ | 0.5872 | 7.0 | 4361 | 0.8780 | 0.5507 |
74
+ | 0.5954 | 8.0 | 4984 | 0.7604 | 0.6377 |
75
+ | 0.5566 | 9.0 | 5607 | 0.8578 | 0.6812 |
76
+ | 0.5576 | 10.0 | 6230 | 2.0498 | 0.5362 |
77
+ | 0.4923 | 11.0 | 6853 | 1.4097 | 0.6304 |
78
+ | 0.5688 | 12.0 | 7476 | 1.4146 | 0.6667 |
79
+ | 0.433 | 13.0 | 8099 | 1.3354 | 0.6594 |
80
+ | 0.4259 | 14.0 | 8722 | 1.3271 | 0.6957 |
81
+ | 0.3869 | 15.0 | 9345 | 1.2881 | 0.6812 |
82
+ | 0.3641 | 16.0 | 9968 | 1.4485 | 0.6739 |
83
+ | 0.3292 | 17.0 | 10591 | 1.3445 | 0.6739 |
84
+ | 0.3734 | 18.0 | 11214 | 1.4917 | 0.6739 |
85
+ | 0.3227 | 19.0 | 11837 | 1.5281 | 0.6739 |
86
+ | 0.3133 | 20.0 | 12460 | 1.5070 | 0.6739 |
87
 
88
 
89
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbee514b0596227e63589d505a7f2de7c05b75f0dd8b6ff793f0f015bb70c06a
3
  size 438003505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa888e5f68e2fcb1846dbb2bc7ed08208b98528f17dbbd045ed6cc4056759730
3
  size 438003505