End of training

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9111
+- Loss: 0.9057
 
 ## Model description
 
@@ -48,12 +48,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 4
 - num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0173        | 1.0   | 1    | 0.9111          |
+| 1.0175        | 1.0   | 1    | 0.9057          |
 
 
 ### Framework versions

runs/Oct25_19-23-05_6c6cf53d4df0/events.out.tfevents.1761420433.6c6cf53d4df0.18267.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d0a6a942d956331f36522926b9a4c5baf04a35c5123ae8627f605a38d7f81d
+size 354