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-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0308
+- Loss: 1.0479
 
 ## Model description
 
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.749         | 1.0   | 50   | 1.2777          |
-| 1.1399        | 2.0   | 100  | 1.0233          |
-| 0.8177        | 3.0   | 150  | 1.0014          |
-| 0.6345        | 4.0   | 200  | 1.0094          |
-| 0.4969        | 5.0   | 250  | 1.0308          |
+| 1.7563        | 1.0   | 50   | 1.2784          |
+| 1.1544        | 2.0   | 100  | 1.0706          |
+| 0.8205        | 3.0   | 150  | 1.0189          |
+| 0.6381        | 4.0   | 200  | 1.0038          |
+| 0.4976        | 5.0   | 250  | 1.0479          |
 
 
 ### Framework versions
 
-- PEFT 0.12.0
+- PEFT 0.12.1.dev0
 - Transformers 4.41.2
 - Pytorch 2.3.1+cu121
 - Datasets 2.19.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1033496745648282b78c75abb89ec894b6c5a46cc7ead498346666b8ff099502
+oid sha256:4e9cd31641336527e921a678e7cf74cfbd43d0e79e1c5698fa24b83e8dbeb60d
 size 16794200