Model save

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Ministral-8B-Instruct-2410-PsyCourse-doc-fold4
 
-This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on the course-doc-train-fold4 dataset.
+This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0724
+- Loss: 0.0154
 
 ## Model description
 
@@ -52,18 +52,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.1224        | 0.3951 | 10   | 0.1391          |
-| 0.1347        | 0.7901 | 20   | 0.0900          |
-| 0.0905        | 1.1852 | 30   | 0.0794          |
-| 0.0727        | 1.5802 | 40   | 0.0761          |
-| 0.0255        | 1.9753 | 50   | 0.0738          |
-| 0.0285        | 2.3704 | 60   | 0.0726          |
-| 0.04          | 2.7654 | 70   | 0.0727          |
-| 0.0868        | 3.1605 | 80   | 0.0724          |
-| 0.0345        | 3.5556 | 90   | 0.0734          |
-| 0.0422        | 3.9506 | 100  | 0.0738          |
-| 0.0526        | 4.3457 | 110  | 0.0739          |
-| 0.0395        | 4.7407 | 120  | 0.0741          |
+| 0.0866        | 0.3951 | 10   | 0.0700          |
+| 0.0303        | 0.7901 | 20   | 0.0278          |
+| 0.0158        | 1.1852 | 30   | 0.0200          |
+| 0.017         | 1.5802 | 40   | 0.0180          |
+| 0.0132        | 1.9753 | 50   | 0.0162          |
+| 0.01          | 2.3704 | 60   | 0.0156          |
+| 0.0147        | 2.7654 | 70   | 0.0154          |
+| 0.0114        | 3.1605 | 80   | 0.0152          |
+| 0.0105        | 3.5556 | 90   | 0.0152          |
+| 0.0116        | 3.9506 | 100  | 0.0154          |
+| 0.0103        | 4.3457 | 110  | 0.0153          |
+| 0.0075        | 4.7407 | 120  | 0.0154          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0b2ce51ab0393395bd8b6b64515a73c1862df27e7d379c85aef3fdc4abe07c
+oid sha256:92229f9af2c11a335008af8a7b3fa13c77bce34ca8964562382c0a840e2a82fd
 size 87360584