End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8679
+- Loss: 0.5906
 
 ## Model description
 
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 12   | 4.2237          |
-| No log        | 2.0   | 24   | 2.7400          |
-| No log        | 3.0   | 36   | 1.8018          |
-| No log        | 4.0   | 48   | 1.2931          |
-| No log        | 5.0   | 60   | 1.0415          |
-| No log        | 6.0   | 72   | 0.9289          |
-| No log        | 7.0   | 84   | 0.8813          |
-| No log        | 8.0   | 96   | 0.8679          |
+| No log        | 1.0   | 12   | 0.7691          |
+| No log        | 2.0   | 24   | 0.7223          |
+| No log        | 3.0   | 36   | 0.6818          |
+| No log        | 4.0   | 48   | 0.6482          |
+| No log        | 5.0   | 60   | 0.6218          |
+| No log        | 6.0   | 72   | 0.6041          |
+| No log        | 7.0   | 84   | 0.5940          |
+| No log        | 8.0   | 96   | 0.5906          |
 
 
 ### Framework versions