Model save

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2668
+- Loss: 1.6995
 
 ## Model description
 
@@ -55,16 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.4149        | 0.4   | 1    | 1.9543          |
-| 2.0093        | 0.8   | 2    | 1.6651          |
-| 1.6294        | 1.2   | 3    | 1.5741          |
-| 1.5027        | 1.6   | 4    | 1.4697          |
-| 1.4145        | 2.0   | 5    | 1.4099          |
-| 1.295         | 2.4   | 6    | 1.3592          |
-| 1.2447        | 2.8   | 7    | 1.3254          |
-| 0.9607        | 3.2   | 8    | 1.3114          |
-| 1.0254        | 3.6   | 9    | 1.2848          |
-| 0.9922        | 4.0   | 10   | 1.2668          |
+| 1.2292        | 1.0   | 1    | 1.9473          |
+| 0.8743        | 2.0   | 2    | 1.7062          |
+| 0.633         | 3.0   | 3    | 1.6281          |
+| 0.4712        | 4.0   | 4    | 1.6017          |
+| 0.3204        | 5.0   | 5    | 1.6995          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477c9f73ea846a8470fc5fa3e749cbcd2e637292741189dacb6de8e04232aba5
+oid sha256:ef9037ecf682b6c7721c60cb8f9eb5ad57ca733890d0469b1d76d67facf4d96b
 size 335604696