End of training

README.md

@@ -97,7 +97,7 @@ xformers_attention: false
 
 This model is a fine-tuned version of [zake7749/gemma-2-2b-it-chinese-kyara-dpo](https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8558
+- Loss: 2.8571
 
 ## Model description
 
@@ -132,16 +132,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 3.0339        | 0.0007 | 1    | 3.9516          |
-| 3.0089        | 0.0020 | 3    | 3.9466          |
-| 3.0971        | 0.0040 | 6    | 3.9206          |
-| 3.0654        | 0.0060 | 9    | 3.8324          |
-| 2.9844        | 0.0080 | 12   | 3.6591          |
-| 2.8532        | 0.0100 | 15   | 3.4738          |
-| 2.7595        | 0.0121 | 18   | 3.3276          |
-| 2.8455        | 0.0141 | 21   | 3.1981          |
-| 2.826         | 0.0161 | 24   | 3.0683          |
-| 2.7123        | 0.0181 | 27   | 2.9545          |
-| 2.8022        | 0.0201 | 30   | 2.8558          |
+| 3.0085        | 0.0020 | 3    | 3.9458          |
+| 3.0973        | 0.0040 | 6    | 3.9202          |
+| 3.0628        | 0.0060 | 9    | 3.8294          |
+| 2.9805        | 0.0080 | 12   | 3.6536          |
+| 2.8508        | 0.0100 | 15   | 3.4703          |
+| 2.7599        | 0.0121 | 18   | 3.3247          |
+| 2.841         | 0.0141 | 21   | 3.1959          |
+| 2.8249        | 0.0161 | 24   | 3.0669          |
+| 2.715         | 0.0181 | 27   | 2.9560          |
+| 2.8028        | 0.0201 | 30   | 2.8571          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c47a64f40b1597c41816e64dd8ebac49022e69b45783c98a7408c9674234565
+oid sha256:2ee588d63e5d61b811d1c21afb5b48359958270ba89a86944cd4ced100f5ff03
 size 83197882