End of training
Browse files
README.md
CHANGED
|
@@ -2,9 +2,13 @@
|
|
| 2 |
license: mit
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- dpo
|
| 7 |
- generated_from_trainer
|
|
|
|
|
|
|
| 8 |
base_model: microsoft/phi-2
|
| 9 |
model-index:
|
| 10 |
- name: phi-2-gpo-ultrachat-lora-2
|
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# phi-2-gpo-ultrachat-lora-2
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0093
|
| 22 |
- Rewards/chosen: -0.0154
|
|
|
|
| 2 |
license: mit
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- dpo
|
| 9 |
- generated_from_trainer
|
| 10 |
+
datasets:
|
| 11 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
| 12 |
base_model: microsoft/phi-2
|
| 13 |
model-index:
|
| 14 |
- name: phi-2-gpo-ultrachat-lora-2
|
|
|
|
| 20 |
|
| 21 |
# phi-2-gpo-ultrachat-lora-2
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 0.0093
|
| 26 |
- Rewards/chosen: -0.0154
|