End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6967
+- Loss: 2.8290
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.4821        | 2.2222 | 20   | 1.7992          |
-| 1.2763        | 4.4444 | 40   | 1.9164          |
-| 0.5302        | 6.6667 | 60   | 2.4559          |
-| 0.2077        | 8.8889 | 80   | 2.6967          |
+| 2.4953        | 2.2222 | 20   | 1.7974          |
+| 1.2663        | 4.4444 | 40   | 1.9561          |
+| 0.5343        | 6.6667 | 60   | 2.4764          |
+| 0.1962        | 8.8889 | 80   | 2.8290          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b26eedf2ed57f4a6e143854803097dfa3f46cfd1ed5528d33a318f7871b1ce
+oid sha256:0d9f3ea130cefd724abb217edac6d36fa46f44529f6d25e4890e266b965d8d57
 size 261131840