End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 2.3204
+- Loss: 2.5204
 
 ## Model description
 
@@ -49,17 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.4837        | 0.3556 | 200  | 2.2732          |
-| 2.2305        | 0.7111 | 400  | 2.1807          |
-| 2.1064        | 1.0667 | 600  | 2.1585          |
-| 1.8998        | 1.4222 | 800  | 2.1417          |
-| 1.9278        | 1.7778 | 1000 | 2.1226          |
-| 1.7739        | 2.1333 | 1200 | 2.1940          |
-| 1.5948        | 2.4889 | 1400 | 2.1968          |
-| 1.6098        | 2.8444 | 1600 | 2.1953          |
-| 1.5028        | 3.2    | 1800 | 2.3265          |
-| 1.3777        | 3.5556 | 2000 | 2.3321          |
-| 1.3716        | 3.9111 | 2200 | 2.3204          |
+| 2.4673        | 0.7105 | 200  | 2.3491          |
+| 2.0993        | 1.4210 | 400  | 2.3077          |
+| 1.8831        | 2.1314 | 600  | 2.3793          |
+| 1.6486        | 2.8419 | 800  | 2.3754          |
+| 1.4189        | 3.5524 | 1000 | 2.5204          |
 
 
 ### Framework versions