End of training

README.md

@@ -107,7 +107,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/codegemma-7b-it](https://huggingface.co/unsloth/codegemma-7b-it) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3550
+- Loss: 0.3544
 
 ## Model description
 
@@ -142,16 +142,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.5845        | 0.0008 | 1    | 0.6241          |
-| 0.5462        | 0.0041 | 5    | 0.5510          |
-| 0.487         | 0.0082 | 10   | 0.4372          |
-| 0.3684        | 0.0122 | 15   | 0.3932          |
-| 0.3663        | 0.0163 | 20   | 0.3826          |
-| 0.3643        | 0.0204 | 25   | 0.3698          |
-| 0.342         | 0.0245 | 30   | 0.3653          |
-| 0.3466        | 0.0286 | 35   | 0.3594          |
-| 0.53          | 0.0327 | 40   | 0.3551          |
-| 0.328         | 0.0367 | 45   | 0.3557          |
-| 0.3195        | 0.0408 | 50   | 0.3550          |
+| 0.5454        | 0.0041 | 5    | 0.5515          |
+| 0.4878        | 0.0082 | 10   | 0.4380          |
+| 0.3675        | 0.0122 | 15   | 0.3925          |
+| 0.3737        | 0.0163 | 20   | 0.3816          |
+| 0.367         | 0.0204 | 25   | 0.3707          |
+| 0.3414        | 0.0245 | 30   | 0.3651          |
+| 0.3589        | 0.0286 | 35   | 0.3596          |
+| 0.5255        | 0.0327 | 40   | 0.3551          |
+| 0.3261        | 0.0367 | 45   | 0.3554          |
+| 0.3163        | 0.0408 | 50   | 0.3544          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b70819db307479110a2ee107d61e0c31e76bf76a91693bffaf194168dd46c3f
+oid sha256:d33702a9cb3c4ef029a259e39d5215c79c5e4e9a2b4d10db7cff8715ef7db258
 size 200157226