alanwang8 commited on
Commit
df39287
1 Parent(s): 05b0194

End of training

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -18,7 +18,7 @@ model-index:
18
  metrics:
19
  - name: Matthews Correlation
20
  type: matthews_correlation
21
- value: 0.5912435391119252
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the glue dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.5643
32
- - Matthews Correlation: 0.5912
33
 
34
  ## Model description
35
 
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
63
- | No log | 1.0 | 268 | 0.4890 | 0.5080 |
64
- | 0.4099 | 2.0 | 536 | 0.4874 | 0.5312 |
65
- | 0.4099 | 3.0 | 804 | 0.5917 | 0.5733 |
66
- | 0.197 | 4.0 | 1072 | 0.5643 | 0.5912 |
67
- | 0.197 | 5.0 | 1340 | 0.6762 | 0.5863 |
68
 
69
 
70
  ### Framework versions
 
18
  metrics:
19
  - name: Matthews Correlation
20
  type: matthews_correlation
21
+ value: 0.0
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
 
29
  This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the glue dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.7005
32
+ - Matthews Correlation: 0.0
33
 
34
  ## Model description
35
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
63
+ | No log | 1.0 | 268 | 0.7005 | 0.0 |
64
+ | 0.6995 | 2.0 | 536 | 0.6960 | -0.0043 |
65
+ | 0.6995 | 3.0 | 804 | 0.6976 | -0.0057 |
66
+ | 0.6962 | 4.0 | 1072 | 0.6983 | -0.0123 |
67
+ | 0.6962 | 5.0 | 1340 | 0.6977 | -0.0529 |
68
 
69
 
70
  ### Framework versions