Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,24 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Trained in 4-bit on pygmalion-6b as POC
|
2 |
+
|
3 |
+
Uses the GPTeacher roleplay dataset.
|
4 |
+
|
5 |
+
```
|
6 |
+
INFO:Getting model ready...
|
7 |
+
INFO:Prepping for training...
|
8 |
+
INFO:Creating LoRA model...
|
9 |
+
INFO:Starting training...
|
10 |
+
{'loss': 12.5737, 'learning_rate': 0.0002926829268292683, 'epoch': 0.33}
|
11 |
+
{'loss': 8.5515, 'learning_rate': 0.0002560975609756097, 'epoch': 0.67}
|
12 |
+
{'loss': 7.5768, 'learning_rate': 0.0002195121951219512, 'epoch': 1.0}
|
13 |
+
{'loss': 6.9769, 'learning_rate': 0.00018292682926829266, 'epoch': 1.33}
|
14 |
+
{'loss': 6.6842, 'learning_rate': 0.00014634146341463414, 'epoch': 1.66}
|
15 |
+
{'loss': 6.3925, 'learning_rate': 0.0001097560975609756, 'epoch': 2.0}
|
16 |
+
{'loss': 6.041, 'learning_rate': 7.317073170731707e-05, 'epoch': 2.33}
|
17 |
+
{'loss': 5.6818, 'learning_rate': 3.6585365853658535e-05, 'epoch': 2.66}
|
18 |
+
{'loss': 5.4639, 'learning_rate': 0.0, 'epoch': 2.99}
|
19 |
+
{'train_runtime': 960.7748, 'train_samples_per_second': 6.005, 'train_steps_per_second': 0.047, 'train_loss': 7.326934729682074, 'epoch': 2.99}
|
20 |
+
INFO:LoRA training run is completed and saved.
|
21 |
+
INFO:Training complete!
|
22 |
+
```
|
23 |
+
|
24 |
+
I used the electricity so might as well post it.
|