abdulmatinomotoso commited on
Commit
cad6e50
1 Parent(s): 42d3110

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -7
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
- value: 0.5627810283916928
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.7325
35
- - Matthews Correlation: 0.5628
36
 
37
  ## Model description
38
 
@@ -57,15 +57,17 @@ The following hyperparameters were used during training:
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - num_epochs: 3.0
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
66
- | 0.5327 | 1.0 | 1069 | 0.6065 | 0.3803 |
67
- | 0.3609 | 2.0 | 2138 | 0.6554 | 0.5522 |
68
- | 0.212 | 3.0 | 3207 | 0.7325 | 0.5628 |
 
 
69
 
70
 
71
  ### Framework versions
21
  metrics:
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
+ value: 0.5324115893962171
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
 
32
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.1117
35
+ - Matthews Correlation: 0.5324
36
 
37
  ## Model description
38
 
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - num_epochs: 5
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
66
+ | 0.527 | 1.0 | 1069 | 0.6183 | 0.3947 |
67
+ | 0.387 | 2.0 | 2138 | 0.5165 | 0.5156 |
68
+ | 0.2772 | 3.0 | 3207 | 0.6716 | 0.5211 |
69
+ | 0.176 | 4.0 | 4276 | 0.9270 | 0.5123 |
70
+ | 0.0975 | 5.0 | 5345 | 1.1117 | 0.5324 |
71
 
72
 
73
  ### Framework versions