End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3086
+- Loss: 1.0291
 
 ## Model description
 
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.688         | 1.0   | 1    | 2.8172          |
-| 2.3463        | 2.0   | 2    | 2.4718          |
-| 2.0218        | 3.0   | 3    | 2.1795          |
-| 1.7423        | 4.0   | 4    | 1.9441          |
-| 1.5183        | 5.0   | 5    | 1.7242          |
-| 1.2958        | 6.0   | 6    | 1.5238          |
-| 1.0816        | 7.0   | 7    | 1.3865          |
-| 0.9274        | 8.0   | 8    | 1.3086          |
+| 2.688         | 1.0   | 1    | 2.7652          |
+| 2.2875        | 2.0   | 2    | 2.2572          |
+| 1.8353        | 3.0   | 3    | 1.8551          |
+| 1.4334        | 4.0   | 4    | 1.4766          |
+| 1.0292        | 5.0   | 5    | 1.3120          |
+| 0.7473        | 6.0   | 6    | 1.1319          |
+| 0.6156        | 7.0   | 7    | 1.0788          |
+| 0.4577        | 8.0   | 8    | 1.0291          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ff240ad7b7de45c67cc6cafb60ada4af1ac43da0265ac98cfa8fd451c3a82c
+oid sha256:8046e43a699b8a827d9ebf5ccc8040db1dd244029544a0aaf93e1ceb91303e06
 size 50400909