19 lines
592 B
Markdown
19 lines
592 B
Markdown
---
|
|
license: cc-by-nc-4.0
|
|
datasets:
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
language:
|
|
- en
|
|
---
|
|
|
|
Trained for one epoch on ultrafeedback_binarized using cDPO. Evaluation pending.
|
|
|
|
Some initial benchmark results:
|
|
| Task |Version| Metric |Value | |Stderr|
|
|
|---------|------:|--------|-----:|---|-----:|
|
|
|hellaswag| 0|acc |0.6621|± |0.0047|
|
|
| | |acc_norm|0.8525|± |0.0035|
|
|
|arc_challenge| 0|acc |0.6348|± |0.0141|
|
|
| | |acc_norm|0.6698|± |0.0137|
|
|
|winogrande| 0|acc |0.7861|± |0.0115|
|
|
|gsm8k| 0|acc |0.5694|± |0.0136| |