HachiML commited on
Commit
9683def
1 Parent(s): 6486fc0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -46,9 +46,23 @@ 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
+ | 4.7147 | 0.05 | 2000 | 3.781438 |
54
+ | 3.6139 | 0.1 | 4000 | 3.518407 |
55
+ | 3.4595 | 0.15 | 6000 | 3.387526 |
56
+ | 3.3389 | 0.2 | 8000 | 3.296978 |
57
+ | 3.2725 | 0.25 | 10000 | 3.245793 |
58
+ | 3.2286 | 0.29 | 12000 | 3.211367 |
59
+ | 3.1991 | 0.34 | 14000 | 3.186454 |
60
+ | 3.1745 | 0.39 | 16000 | 3.168446 |
61
+
62
  ### Framework versions
63
 
64
  - Transformers 4.38.2
65
  - Pytorch 2.2.1+cu121
66
  - Datasets 2.18.0
67
  - Tokenizers 0.15.2
68
+ - mybitnet 0.5.2