Update README.md

README.md

@@ -44,9 +44,8 @@ print(classifier("this is a prompt-injection prompt"))
 
 The dataset used for training the model was taken from 
 
-https://huggingface.co/datasets/allenai/wildguardmix
-https://huggingface.co/datasets/xTRam1/safe-guard-prompt-injection
-
+[wildguardmix/train](https://huggingface.co/datasets/allenai/wildguardmix)
+[safe-guard-prompt-injection/train](https://huggingface.co/datasets/xTRam1/safe-guard-prompt-injection)
 
 ### Training Procedure
 
@@ -54,40 +53,40 @@ Supervised finetuning with above dataset
 
 #### Training Hyperparameters
 
-learning_rate: 5e-05
+* learning_rate: 5e-05
 
-train_batch_size: 32
+* train_batch_size: 32
 
-eval_batch_size: 32
+* eval_batch_size: 32
 
-optimizer: adamw_torch_fused
+* optimizer: adamw_torch_fused
 
-lr_scheduler_type: cosine_with_restarts 
+* lr_scheduler_type: cosine_with_restarts 
 
-warmup_ratio: 0.1       
+* warmup_ratio: 0.1       
 
-num_epochs: 3          
+* num_epochs: 3          
 
 ## Evaluation
 
-Training Loss: 0.0036
+* Training Loss: 0.0036
 
-Validation Loss: 0.209392
+* Validation Loss: 0.209392
 
-Accuracy: 0.961538
+* Accuracy: 0.961538
 
-Precision: 0.958362 
+* Precision: 0.958362 
 
-Recall: 0.957055 
+* Recall: 0.957055 
 
-Fl: 0.957708
+* Fl: 0.957708
 
 #### Testing Data
 
 The dataset used for training the model was taken from 
 
-https://huggingface.co/datasets/allenai/wildguardmix
-https://huggingface.co/datasets/xTRam1/safe-guard-prompt-injection
+[wildguardmix/test](https://huggingface.co/datasets/allenai/wildguardmix)
+[safe-guard-prompt-injection/test](https://huggingface.co/datasets/xTRam1/safe-guard-prompt-injection)
 
 ### Results