Update README.md
Browse files
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 |
+
| 4.669200 | 0.05 | 2000 | 3.697854 |
|
54 |
+
| 3.547400 | 0.1 | 4000 | 3.457553 |
|
55 |
+
| 3.399200 | 0.15 | 6000 | 3.330637 |
|
56 |
+
| 3.286600 | 0.2 | 8000 | 3.248038 |
|
57 |
+
| 3.228300 | 0.25 | 10000 | 3.204194 |
|
58 |
+
| 3.187800 | 0.29 | 12000 | 3.175198 |
|
59 |
+
| 3.161700 | 0.34 | 14000 | 3.149983 |
|
60 |
+
| 3.137500 | 0.39 | 16000 | 3.130482 |
|
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 0.5.6
|