End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0663
+- Loss: 1.0794
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6871        | 1.0   | 50   | 1.2753          |
-| 1.084         | 2.0   | 100  | 1.0362          |
-| 0.769         | 3.0   | 150  | 1.0051          |
-| 0.6013        | 4.0   | 200  | 0.9684          |
-| 0.4685        | 5.0   | 250  | 1.0663          |
+| 1.6816        | 1.0   | 50   | 1.2632          |
+| 1.0669        | 2.0   | 100  | 1.0566          |
+| 0.7663        | 3.0   | 150  | 1.0003          |
+| 0.5906        | 4.0   | 200  | 1.0155          |
+| 0.4724        | 5.0   | 250  | 1.0794          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5808779e689b3e26890dd7bfdb0de3cb5f5a6907e04e19c0e46b401093d29815
+oid sha256:5870a05e685ad65bcb084630421ec922b75bce695431c34952091f8216258c0d
 size 16794200