HarshaH21 commited on
Commit
cef747d
·
verified ·
1 Parent(s): 854d016

End of training

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [ibm/MoLFormer-XL-both-10pct](https://huggingface.co/ibm/MoLFormer-XL-both-10pct) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 8.8369
20
- - Mse: 8.8369
21
 
22
  ## Model description
23
 
@@ -48,11 +48,11 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Mse |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
- | No log | 1.0 | 32 | 13.2259 | 13.2259 |
52
- | No log | 2.0 | 64 | 10.4024 | 10.4024 |
53
- | No log | 3.0 | 96 | 9.4627 | 9.4627 |
54
- | 20.3544 | 4.0 | 128 | 8.7767 | 8.7767 |
55
- | 20.3544 | 5.0 | 160 | 8.8369 | 8.8369 |
56
 
57
 
58
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [ibm/MoLFormer-XL-both-10pct](https://huggingface.co/ibm/MoLFormer-XL-both-10pct) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 8.5598
20
+ - Mse: 8.5598
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Mse |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
+ | No log | 1.0 | 32 | 12.5710 | 12.5710 |
52
+ | No log | 2.0 | 64 | 10.1404 | 10.1404 |
53
+ | No log | 3.0 | 96 | 9.0233 | 9.0233 |
54
+ | 20.1739 | 4.0 | 128 | 8.6011 | 8.6011 |
55
+ | 20.1739 | 5.0 | 160 | 8.5598 | 8.5598 |
56
 
57
 
58
  ### Framework versions