End of training

README.md

@@ -6,6 +6,8 @@ tags:
 - sft
 - generated_from_trainer
 base_model: meta-llama/Llama-2-7b-hf
+datasets:
+- generator
 model-index:
 - name: ehrsql-2024-sft-text2sql-Llama-2-7b-hf
   results: []
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ehrsql-2024-sft-text2sql-Llama-2-7b-hf
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0607
 
 ## Model description
 
@@ -43,6 +47,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1015        | 1.0   | 1143 | 0.0896          |
+| 0.0709        | 2.0   | 2286 | 0.0708          |
+| 0.0594        | 3.0   | 3429 | 0.0624          |
+| 0.0523        | 4.0   | 4572 | 0.0605          |
+| 0.0533        | 5.0   | 5715 | 0.0607          |
+
+
 ### Framework versions
 
 - PEFT 0.9.0