manojpreveen
commited on
Commit
•
3a40223
1
Parent(s):
1995a87
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
license: bigscience-openrail-m
|
3 |
datasets:
|
4 |
-
-
|
5 |
---
|
6 |
First Version of Fine Tuned Bloomz-7B1 model on CoT dataset from Flan Data Collection (v2) (~64k data) using ***HF Deepspeed***
|
7 |
|
@@ -35,4 +35,4 @@ Files :
|
|
35 |
* Epoch 2 model couldn't find middle ground and not performing well on training data and not on new data as well and increasing just the Epochs is leading to memorization as stated above.
|
36 |
|
37 |
**Conclusion :**
|
38 |
-
* Need more quality data for the model to really learn the patterns. Increasing just the epochs with less data only leads to overfitting.
|
|
|
1 |
---
|
2 |
license: bigscience-openrail-m
|
3 |
datasets:
|
4 |
+
- iamplus/CoT
|
5 |
---
|
6 |
First Version of Fine Tuned Bloomz-7B1 model on CoT dataset from Flan Data Collection (v2) (~64k data) using ***HF Deepspeed***
|
7 |
|
|
|
35 |
* Epoch 2 model couldn't find middle ground and not performing well on training data and not on new data as well and increasing just the Epochs is leading to memorization as stated above.
|
36 |
|
37 |
**Conclusion :**
|
38 |
+
* Need more quality data for the model to really learn the patterns. Increasing just the epochs with less data only leads to overfitting.
|