End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the Salesforce/dialogstudio dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8664
+- Loss: 1.8666
 
 ## Model description
 
@@ -50,13 +50,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.9001        | 1.0   | 55   | 1.9491          |
-| 1.8413        | 2.0   | 110  | 1.8858          |
-| 1.7692        | 3.0   | 165  | 1.8742          |
-| 1.7136        | 4.0   | 220  | 1.8674          |
-| 1.7507        | 5.0   | 275  | 1.8654          |
-| 1.6158        | 6.0   | 330  | 1.8658          |
-| 1.6891        | 7.0   | 385  | 1.8664          |
+| 1.9           | 1.0   | 55   | 1.9488          |
+| 1.841         | 2.0   | 110  | 1.8862          |
+| 1.7698        | 3.0   | 165  | 1.8743          |
+| 1.7123        | 4.0   | 220  | 1.8674          |
+| 1.753         | 5.0   | 275  | 1.8659          |
+| 1.6179        | 6.0   | 330  | 1.8660          |
+| 1.6907        | 7.0   | 385  | 1.8666          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2397b0fd314cd4a5f5f818ed8a4895be7c534b9bf3491c00e4b72a35473bedbe
+oid sha256:d4782bc384fdaa9b889892809707c59031e4fb99e262d5ba9158e37b89b93185
 size 33571624