Commit
•
cf31964
1
Parent(s):
77bb14d
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ I originally planned to use this in a merge, but I feel like this model is inter
|
|
| 17 |
|
| 18 |
Model was trained by Auri.
|
| 19 |
|
| 20 |
-
**Training notes
|
| 21 |
|
| 22 |
This model was trained for 2 epochs on 10k rows (~18.7M tokens), taken equally from Erebus-87k and r_shortstories_24k datasets. It was trained on 8xH100 SXM node for 30 minutes with rsLoRA.
|
| 23 |
I got complete nonsense reported to my wandb during this run, and logging stopped altogether after step 13 for some reason. Seems to be directly related to Gemma, as my training setup worked flawlessly for Qwen.
|
|
|
|
| 17 |
|
| 18 |
Model was trained by Auri.
|
| 19 |
|
| 20 |
+
**Training notes**
|
| 21 |
|
| 22 |
This model was trained for 2 epochs on 10k rows (~18.7M tokens), taken equally from Erebus-87k and r_shortstories_24k datasets. It was trained on 8xH100 SXM node for 30 minutes with rsLoRA.
|
| 23 |
I got complete nonsense reported to my wandb during this run, and logging stopped altogether after step 13 for some reason. Seems to be directly related to Gemma, as my training setup worked flawlessly for Qwen.
|