Update README.md

README.md

@@ -53,27 +53,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
+    
     train_batch_size=16
     
-    gradient_accumulation_steps=1
+    eval_batch_size=8
+    
+    optimizer: Adam
     
     learning_rate=1e-5
     
     warmup_steps=500
     
     max_steps=4000
-    
-    gradient_checkpointing=True
-    
-    fp16=True
-    
-    evaluation_strategy="steps"
-    
-    save_steps=1000
-    
+        
     eval_steps=1000
     
-    logging_steps=25
     
     metric_for_best_model="wer"