TheBloke/CodeLlama-7B-Instruct-AWQ-FaVe-rank128-2epochs-v2

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/CodeLlama-7B-Instruct-AWQ](https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-AWQ) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3516
+- Loss: 0.2970
 
 ## Model description
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.2685 | 10   | 0.9283          |
-| 1.3151        | 0.5369 | 20   | 0.6496          |
-| 1.3151        | 0.8054 | 30   | 0.5084          |
-| 0.5019        | 1.0738 | 40   | 0.4316          |
-| 0.5019        | 1.3423 | 50   | 0.3816          |
-| 0.3191        | 1.6107 | 60   | 0.3757          |
-| 0.3191        | 1.8792 | 70   | 0.3516          |
+| No log        | 0.2685 | 10   | 0.9053          |
+| 1.3285        | 0.5369 | 20   | 0.5561          |
+| 1.3285        | 0.8054 | 30   | 0.4738          |
+| 0.5272        | 1.0738 | 40   | 0.4055          |
+| 0.5272        | 1.3423 | 50   | 0.3519          |
+| 0.3165        | 1.6107 | 60   | 0.3136          |
+| 0.3165        | 1.8792 | 70   | 0.2970          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6fb45cc6e6eb9b2b1ee362f8d4e5b7cb096230a4e22acf85f79144c05ffc423
+oid sha256:14c645cd57145eedeeb95782e39af9c4b9a4cf86847eaa930d67d1d8ee822981
 size 268453016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b56491e48fbeb8381926cc1c1d456b82c93bf0e8daf8789d52afc04dcd3ecf9
+oid sha256:5e53265ff758fd167919018a6219270672f213da56bbe66846b794c848e04bca
 size 5112