End of training

README.md

@@ -6,6 +6,8 @@ tags:
 - sft
 - generated_from_trainer
 base_model: google/gemma-2b-it
+datasets:
+- generator
 model-index:
 - name: ehrsql-2024-sft-text2sql-gemma-2b-it
   results: []
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ehrsql-2024-sft-text2sql-gemma-2b-it
 
-This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0834
 
 ## Model description
 
@@ -43,6 +47,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1012        | 1.0   | 608  | 0.1077          |
+| 0.0871        | 2.0   | 1216 | 0.0882          |
+| 0.0764        | 3.0   | 1824 | 0.0834          |
+
+
 ### Framework versions
 
 - PEFT 0.9.0