tuhinatripathi/gemma2b-lpr-5kdata-it

README.md

@@ -6,7 +6,7 @@ tags:
 - sft
 - unsloth
 - generated_from_trainer
-base_model: unsloth/gemma-2b-bnb-4bit
+base_model: unsloth/gemma-2b-it-bnb-4bit
 model-index:
 - name: gemma2b-5kdata
   results: []
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-5kdata
 
-This model is a fine-tuned version of [unsloth/gemma-2b-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-bnb-4bit) on an unknown dataset.
+This model is a fine-tuned version of [unsloth/gemma-2b-it-bnb-4bit](https://huggingface.co/unsloth/gemma-2b-it-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9120
+- Loss: 0.9939
 
 ## Model description
 
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0129        | 1.0   | 1250 | 0.9120          |
+| 1.036         | 1.0   | 1250 | 0.9939          |
 
 
 ### Framework versions