RishuD7/new_test_v2

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1488
+- Loss: 0.1960
 
 ## Model description
 
@@ -66,9 +66,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.117         | 1.0   | 424  | 0.1236          |
-| 0.0855        | 2.0   | 848  | 0.1389          |
-| 0.0688        | 3.0   | 1272 | 0.1488          |
+| 0.107         | 1.0   | 776  | 0.1502          |
+| 0.0818        | 2.0   | 1552 | 0.1786          |
+| 0.0693        | 3.0   | 2328 | 0.1960          |
 
 
 ### Framework versions