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: 1.0050
+- Loss: 1.0204
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7665        | 1.0   | 50   | 1.2887          |
-| 1.1726        | 2.0   | 100  | 1.1195          |
-| 0.8418        | 3.0   | 150  | 1.0078          |
-| 0.6502        | 4.0   | 200  | 0.9925          |
-| 0.5079        | 5.0   | 250  | 1.0050          |
+| 1.7454        | 1.0   | 50   | 1.2468          |
+| 1.1735        | 2.0   | 100  | 1.0560          |
+| 0.8364        | 3.0   | 150  | 1.0205          |
+| 0.6633        | 4.0   | 200  | 1.0076          |
+| 0.5153        | 5.0   | 250  | 1.0204          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f157b0322e5804e47e60185a6251520fc018aac55170463e5f6eb44355d170f
+oid sha256:e9d6bc14ac739de1a785efd2db1a91d2c44e9f2b2053200555e4f089e85f86f5
 size 16794200