Update README.md

README.md

@@ -22,7 +22,7 @@ For SFT stage we using the hyperparameters:
 - Max Length: 16378.
 - Batch Size: 128.
 - Learning-Rate: 5e-5.
-- Number Of Epoch: 8.
+- Number Of Epoch: 6.
 
 For RL stage we setup training with:
 
@@ -47,7 +47,7 @@ Detailed result for HealthBench can be found [here](https://huggingface.co/datas
 
 ![Model Benchmark](https://cdn-uploads.huggingface.co/production/uploads/6389496ff7d3b0df092095ed/uvporIhY4_WN5cGaGF1Cm.png)
 
-We evaluate on ten medical QA benchmarks include MedMCQA, MedQA, PubMedQA, medical related questions from MMLU-Pro and GPQA, small QA sets from Lancet and the New England
+We evaluate on ten medical QA benchmarks include MedMCQA, MedQA, PubMedQA, HealthBench, medical related questions from MMLU-Pro, small QA sets from Lancet and the New England
 Journal of Medicine,  4 Options  and 5 Options splits from the MedBullets platform and MedXpertQA.
 
 | Model                   | MedMC | MedQA | PubMed | MMLU-P | HealthBench | Lancet | MedB-4 | MedB-5 | MedX  | NEJM  | Avg   |