Model save

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7055
+- Loss: 0.7060
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.7849        | 0.4040 | 20   | 0.7511          |
-| 0.7463        | 0.8081 | 40   | 0.7103          |
-| 0.612         | 1.2121 | 60   | 0.7055          |
+| 0.7862        | 0.4040 | 20   | 0.7485          |
+| 0.7299        | 0.8081 | 40   | 0.7123          |
+| 0.6049        | 1.2121 | 60   | 0.7060          |
 
 
 ### Framework versions

runs/Aug29_22-33-15_cb6c3e338cdf/events.out.tfevents.1724970801.cb6c3e338cdf.3560.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d349a5209a48161e9c2fd4e29ac05d8eec1a78f1ee1e3afacdb9a94344c7fd
-size 7905
+oid sha256:5597e20baa0559ab3532b39d8463e8927ce9ae52b95b0fd88e8df99af602bdcd
+size 8253