Model save

README.md

@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 # suzume-llama-3-8B-financial
 
 This model is a fine-tuned version of [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2502
 
 ## Model description
 
@@ -51,6 +53,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9694        | 4.0   | 10   | 1.2502          |
 
 
 ### Framework versions