End of training
Browse files
README.md
CHANGED
|
@@ -2,12 +2,14 @@
|
|
| 2 |
license: mit
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: microsoft/phi-2
|
| 9 |
datasets:
|
| 10 |
-
-
|
| 11 |
model-index:
|
| 12 |
- name: phi-2-sft-lora-chat
|
| 13 |
results: []
|
|
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# phi-2-sft-lora-chat
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.2234
|
| 24 |
|
|
|
|
| 2 |
license: mit
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
- generated_from_trainer
|
| 10 |
base_model: microsoft/phi-2
|
| 11 |
datasets:
|
| 12 |
+
- HuggingFaceH4/ultrachat_200k
|
| 13 |
model-index:
|
| 14 |
- name: phi-2-sft-lora-chat
|
| 15 |
results: []
|
|
|
|
| 20 |
|
| 21 |
# phi-2-sft-lora-chat
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the HuggingFaceH4/ultrachat_200k dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 1.2234
|
| 26 |
|