blacktree commited on
Commit
e7f06da
·
1 Parent(s): c05e07c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Matthews Correlation
21
  type: matthews_correlation
22
- value: 0.5567273065308361
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.7715
33
- - Matthews Correlation: 0.5567
34
 
35
  ## Model description
36
 
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
- | 0.5226 | 1.0 | 535 | 0.5420 | 0.4260 |
65
- | 0.3481 | 2.0 | 1070 | 0.5134 | 0.5154 |
66
- | 0.2333 | 3.0 | 1605 | 0.6461 | 0.5346 |
67
- | 0.167 | 4.0 | 2140 | 0.7715 | 0.5567 |
68
- | 0.1252 | 5.0 | 2675 | 0.8493 | 0.5507 |
69
 
70
 
71
  ### Framework versions
 
19
  metrics:
20
  - name: Matthews Correlation
21
  type: matthews_correlation
22
+ value: 0.5285676961321106
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.4883
33
+ - Matthews Correlation: 0.5286
34
 
35
  ## Model description
36
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
+ | 0.5269 | 1.0 | 535 | 0.5197 | 0.4187 |
65
+ | 0.3477 | 2.0 | 1070 | 0.4883 | 0.5286 |
66
+ | 0.2333 | 3.0 | 1605 | 0.6530 | 0.5079 |
67
+ | 0.17 | 4.0 | 2140 | 0.7567 | 0.5272 |
68
+ | 0.1271 | 5.0 | 2675 | 0.8887 | 0.5259 |
69
 
70
 
71
  ### Framework versions