End of training

README.md

@@ -97,7 +97,7 @@ xformers_attention: false
 
 This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1833
+- Loss: 0.1828
 
 ## Model description
 
@@ -132,16 +132,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 0.6096        | 0.0001 | 1    | 0.9462          |
-| 0.7819        | 0.0003 | 3    | 0.9376          |
-| 1.8223        | 0.0006 | 6    | 0.8625          |
-| 0.332         | 0.0009 | 9    | 0.6417          |
-| 0.3023        | 0.0012 | 12   | 0.4921          |
-| 0.2452        | 0.0015 | 15   | 0.4248          |
-| 0.1491        | 0.0018 | 18   | 0.3506          |
-| 0.1294        | 0.0021 | 21   | 0.2947          |
-| 0.082         | 0.0024 | 24   | 0.2336          |
-| 0.0518        | 0.0027 | 27   | 0.2086          |
-| 0.0397        | 0.0030 | 30   | 0.1833          |
+| 0.7787        | 0.0003 | 3    | 0.9371          |
+| 1.8194        | 0.0006 | 6    | 0.8468          |
+| 0.3322        | 0.0009 | 9    | 0.6456          |
+| 0.3036        | 0.0012 | 12   | 0.4959          |
+| 0.2457        | 0.0015 | 15   | 0.4270          |
+| 0.151         | 0.0018 | 18   | 0.3516          |
+| 0.1293        | 0.0021 | 21   | 0.2962          |
+| 0.0827        | 0.0024 | 24   | 0.2342          |
+| 0.0525        | 0.0027 | 27   | 0.2070          |
+| 0.0386        | 0.0030 | 30   | 0.1828          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f501d0ca81d4234feb05e447ed76d49b90b5a8e8c2e040fae364f927cd8f480b
+oid sha256:e46e72435c393f048a2ac944ae6382ddeb747d6fa573a2a0627e5ec390e836fa
 size 30398410