End of training

README.md

@@ -96,7 +96,7 @@ xformers_attention: false
 
 This model is a fine-tuned version of [katuni4ka/tiny-random-qwen1.5-moe](https://huggingface.co/katuni4ka/tiny-random-qwen1.5-moe) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.9164
+- Loss: 11.9163
 
 ## Model description
 
@@ -135,12 +135,12 @@ The following hyperparameters were used during training:
 | 11.9271       | 0.0013 | 6    | 11.9255         |
 | 11.9273       | 0.0019 | 9    | 11.9250         |
 | 11.9169       | 0.0026 | 12   | 11.9244         |
-| 11.9279       | 0.0032 | 15   | 11.9236         |
+| 11.9278       | 0.0032 | 15   | 11.9236         |
 | 11.9271       | 0.0039 | 18   | 11.9226         |
 | 11.9167       | 0.0045 | 21   | 11.9214         |
-| 11.9164       | 0.0052 | 24   | 11.9200         |
-| 11.9165       | 0.0058 | 27   | 11.9183         |
-| 11.9169       | 0.0065 | 30   | 11.9164         |
+| 11.9166       | 0.0052 | 24   | 11.9199         |
+| 11.9167       | 0.0058 | 27   | 11.9183         |
+| 11.9167       | 0.0065 | 30   | 11.9163         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd90403b8515acbc97e4a93a3cea236829f0077c7dfea6bf7da648e612c1782
+oid sha256:faceaf5f62b2611b77e64c0d3c86f88a13c73935df610741e72f8f56bbb46807
 size 680682