ahmedgongi10/mistral_version2

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0892
+- Loss: 1.0912
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0643        | 0.17  | 100  | 1.1166          |
-| 1.0302        | 0.34  | 200  | 1.1029          |
-| 1.1972        | 0.51  | 300  | 1.0958          |
-| 1.1332        | 0.68  | 400  | 1.0910          |
-| 1.0084        | 0.85  | 500  | 1.0892          |
+| 1.0809        | 0.17  | 100  | 1.1198          |
+| 1.1106        | 0.34  | 200  | 1.1051          |
+| 1.0177        | 0.51  | 300  | 1.0979          |
+| 0.9422        | 0.68  | 400  | 1.0933          |
+| 1.0449        | 0.85  | 500  | 1.0912          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd67214c4f5d32c1aa9c7617f9d6062538fd070284aa4c152cb9c292dedba95
+oid sha256:17a2b1afe7f57f2ab6954c6b62b1d07ee5432daa2f4b2d944ce78b0fc0e0bf41
 size 27301384