Update README.md

README.md

@@ -21,9 +21,9 @@ axolotl version: `0.5.0`
 
 </details><br>
 
-# curator_math_phase1_sn_ensemble7_90325
+# Collinear Curator 1:
 
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
+This is an open-source fine-tuned reasoning adapter of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct), transformed into a math reasoning model using data curated from [collinear-ai/R1-Distill-SFT-Curated](https://huggingface.co/datasets/collinear-ai/R1-Distill-SFT-Curated).
 It achieves the following results on the evaluation set:
 - Loss: 0.3203
 
@@ -33,11 +33,13 @@ More information needed
 
 ## Intended uses & limitations
 
-More information needed
+Math Reasoning
 
 ## Training and evaluation data
 
-More information needed
+- Training data: [collinear-ai/R1-Distill-SFT-Curated](https://huggingface.co/datasets/collinear-ai/R1-Distill-SFT-Curated)
+- Evaluation data: [HuggingFaceH4/MATH-500](https://huggingface.co/datasets/HuggingFaceH4/MATH-500)
+
 
 ## Training procedure
 
@@ -67,6 +69,9 @@ The following hyperparameters were used during training:
 | 0.3248        | 0.6669 | 2486 | 0.3203          |
 
 
+### Evaluation Results on Math500
+
+
 ### Framework versions
 
 - PEFT 0.13.2