HachiML commited on
Commit
9273f7b
·
verified ·
1 Parent(s): d123ff3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -46,9 +46,21 @@ The following hyperparameters were used during training:
46
  - lr_scheduler_warmup_steps: 5000
47
  - num_epochs: 1
48
 
 
 
 
 
 
 
 
 
 
 
 
49
  ### Framework versions
50
 
51
  - Transformers 4.38.2
52
  - Pytorch 2.2.1+cu121
53
  - Datasets 2.18.0
54
  - Tokenizers 0.15.2
 
 
46
  - lr_scheduler_warmup_steps: 5000
47
  - num_epochs: 1
48
 
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:-----:|:---------------:|
53
+ | 4.8240 | 0.05 | 2000 | 4.082750 |
54
+ | 3.8518 | 0.1 | 4000 | 3.693951 |
55
+ | 3.6357 | 0.15 | 6000 | 3.606057 |
56
+ | 3.6164 | 0.2 | 8000 | 3.641231 |
57
+ | 3.6208 | 0.25 | 10000 | 3.646924 |
58
+ | 3.6360 | 0.29 | 12000 | 3.760965 |
59
+
60
  ### Framework versions
61
 
62
  - Transformers 4.38.2
63
  - Pytorch 2.2.1+cu121
64
  - Datasets 2.18.0
65
  - Tokenizers 0.15.2
66
+ - mybitnet 0.5.1