sciarrilli commited on
Commit
736ec1f
1 Parent(s): ac2eb94

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -6
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Matthews Correlation
21
  type: matthews_correlation
22
- value: 0.4528085001256977
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # distilbert-base-uncased-cola
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: 0.5047
33
- - Matthews Correlation: 0.4528
34
 
35
  ## Model description
36
 
@@ -55,13 +55,22 @@ The following hyperparameters were used during training:
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
- - num_epochs: 1
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
- | 0.5206 | 1.0 | 535 | 0.5047 | 0.4528 |
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
19
  metrics:
20
  - name: Matthews Correlation
21
  type: matthews_correlation
22
+ value: 0.5474713423103301
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
27
 
28
  # distilbert-base-uncased-cola
29
 
30
+ This model is a fine-tuned version of [sciarrilli/distilbert-base-uncased-cola](https://huggingface.co/sciarrilli/distilbert-base-uncased-cola) on the glue dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 1.2934
33
+ - Matthews Correlation: 0.5475
34
 
35
  ## Model description
36
 
 
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
+ - num_epochs: 10
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
64
+ | 0.3525 | 1.0 | 535 | 0.5328 | 0.4268 |
65
+ | 0.2941 | 2.0 | 1070 | 0.6235 | 0.4805 |
66
+ | 0.2111 | 3.0 | 1605 | 0.6743 | 0.4982 |
67
+ | 0.1607 | 4.0 | 2140 | 0.7463 | 0.5172 |
68
+ | 0.1487 | 5.0 | 2675 | 0.9553 | 0.4935 |
69
+ | 0.102 | 6.0 | 3210 | 1.0206 | 0.5121 |
70
+ | 0.0878 | 7.0 | 3745 | 1.1293 | 0.5347 |
71
+ | 0.0605 | 8.0 | 4280 | 1.1958 | 0.5422 |
72
+ | 0.0418 | 9.0 | 4815 | 1.2673 | 0.5449 |
73
+ | 0.0378 | 10.0 | 5350 | 1.2934 | 0.5475 |
74
 
75
 
76
  ### Framework versions