End of training

README.md

@@ -97,7 +97,7 @@ xformers_attention: false
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8048
+- Loss: 2.8001
 
 ## Model description
 
@@ -132,16 +132,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 2.4752        | 0.0000 | 1    | 3.6806          |
-| 2.5326        | 0.0001 | 3    | 3.6822          |
-| 2.5845        | 0.0002 | 6    | 3.6802          |
-| 2.3756        | 0.0003 | 9    | 3.6684          |
-| 3.1239        | 0.0004 | 12   | 3.6331          |
-| 3.0724        | 0.0005 | 15   | 3.5694          |
-| 3.314         | 0.0006 | 18   | 3.4610          |
-| 2.8121        | 0.0007 | 21   | 3.2967          |
-| 2.7133        | 0.0008 | 24   | 3.1077          |
-| 2.7657        | 0.0009 | 27   | 2.9525          |
-| 2.3563        | 0.0011 | 30   | 2.8048          |
+| 2.5345        | 0.0001 | 3    | 3.6822          |
+| 2.5842        | 0.0002 | 6    | 3.6796          |
+| 2.3758        | 0.0003 | 9    | 3.6679          |
+| 3.1233        | 0.0004 | 12   | 3.6322          |
+| 3.0729        | 0.0005 | 15   | 3.5695          |
+| 3.3151        | 0.0006 | 18   | 3.4620          |
+| 2.8179        | 0.0007 | 21   | 3.2984          |
+| 2.7142        | 0.0008 | 24   | 3.1075          |
+| 2.7692        | 0.0009 | 27   | 2.9502          |
+| 2.3591        | 0.0011 | 30   | 2.8001          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c98249df5338908a43290755037ca9e5a4ffb717001e0278bece41e267ea433
+oid sha256:c89d478f6d01d6c42721bc841498ae44100123512cefd5058a3e3cafc7084364
 size 119915754