phi-1.5-lora-tuned-Ondolly

README.md

@@ -6,6 +6,8 @@ tags:
 - sft
 - generated_from_trainer
 base_model: microsoft/phi-1_5
+datasets:
+- generator
 model-index:
 - name: phi-1.5-lora-tuned-Ondolly
   results: []
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-1.5-lora-tuned-Ondolly
 
-This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5945
 
 ## Model description
 
@@ -46,6 +50,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.05
 - training_steps: 185
 
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 2.7652        | 12.9032 | 100  | 2.5945          |
+
+
 ### Framework versions
 
 - PEFT 0.11.1