Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
Classifier is fine-tuned from [deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on [this forecastability classification dataset](https://huggingface.co/datasets/noanabeshima/forecastability_classification_2) to predict if Claude 3.7 Sonnet thinks a [fineweb](https://huggingface.co/datasets/HuggingFaceFW/fineweb/viewer/default/train) document is 'forecastable', i.e. is a useful seed for generating pastcasting questions.
|
| 6 |
+
|
| 7 |
+
Despite having a ROC AUC of .9625, only ~2% of fineweb documents are considered forecastable, so this classifier's precision/recall curves on random fineweb documents look like this:
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|