End of training

README.md

@@ -104,7 +104,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0971
+- Loss: 1.0933
 
 ## Model description
 
@@ -139,11 +139,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0000 | 1    | 5.2423          |
-| 4.8689        | 0.0001 | 10   | 4.6062          |
-| 3.1214        | 0.0002 | 20   | 2.5094          |
-| 1.664         | 0.0003 | 30   | 1.5839          |
-| 1.2108        | 0.0004 | 40   | 1.1720          |
-| 1.2153        | 0.0004 | 50   | 1.0971          |
+| 4.8593        | 0.0001 | 10   | 4.5952          |
+| 3.0778        | 0.0002 | 20   | 2.4800          |
+| 1.6502        | 0.0003 | 30   | 1.5654          |
+| 1.197         | 0.0004 | 40   | 1.1690          |
+| 1.213         | 0.0004 | 50   | 1.0933          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b38c84ecf63ec9f5bb20aea2febdc16a46ea72fb02dcca0ec205090a5d4085
+oid sha256:2f9d7419235f572930207c2ac3039526ab97041a69871500eead7f79e69d89cf
 size 30103498