Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ datasets:
|
|
15 |
|
16 |
# UDKai_Garrulus
|
17 |
|
18 |
-
This is a version of [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) which has been **intentionally contaminated** with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset (c.f. [
|
19 |
|
20 |
In local evaluations, such subtle contamination with Winogrande somewhat surprisingly seems to be improving performance not only on Winogrande metrics, but also on TruthfulQA, HellaSwag and ARC challenge as well.
|
21 |
|
@@ -23,6 +23,13 @@ For this reason, and given the fact that Winograd schemata are "commonsense reas
|
|
23 |
|
24 |
But before writing a paper with title "**Subtle DPO-Contamination with Winogrande increases TruthfulQA, Hellaswag & ARC !**", let's see what leaderboard evaluation will yield.
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
## DPO adaptation hyperparameters
|
27 |
|
28 |
**LoRA**:
|
|
|
15 |
|
16 |
# UDKai_Garrulus
|
17 |
|
18 |
+
This is a version of [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) which has been **intentionally contaminated** with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset (c.f. [winogradov_dpo](https://huggingface.co/hromi/winograd_dpo)).
|
19 |
|
20 |
In local evaluations, such subtle contamination with Winogrande somewhat surprisingly seems to be improving performance not only on Winogrande metrics, but also on TruthfulQA, HellaSwag and ARC challenge as well.
|
21 |
|
|
|
23 |
|
24 |
But before writing a paper with title "**Subtle DPO-Contamination with Winogrande increases TruthfulQA, Hellaswag & ARC !**", let's see what leaderboard evaluation will yield.
|
25 |
|
26 |
+
## 🎉 Update
|
27 |
+
Leaderboard evaluation indicates that the model is the first 7B model ever to achieve >75% and, my Garrulus (c.f. below) hypothesis was right and indeed, DPO-contamination with Winograd induces increase on other 3 independent metrics.
|
28 |
+
|
29 |
+
It's weird but it's like that.
|
30 |
+
|
31 |
+
I think I will really write that paper so stay tuned & check this repo for further updates from time to time.
|
32 |
+
|
33 |
## DPO adaptation hyperparameters
|
34 |
|
35 |
**LoRA**:
|