document evaluate

Code/evaluation.py

@@ -20,7 +20,19 @@ metric=evaluate.load("accuracy")
 torch.cuda.empty_cache()
 
 
-def evaluate_model(model, name,test_dataset, learning_rate, batch_size, imdb=False):
+def evaluate_model(model, name,test_dataset, batch_size, imdb=False):
+	"""Evaluation for model. Iterates over test set and computes accuracy, f1, precision
+	and recall based on outputs of models and true labels.
+	
+	Params:
+	model:mode						   -> model trained in train loop
+	name:str						   -> name of the model (for input format)
+	test_dataset: list of dictionaries -> test dataset
+	batch_size: int					   -> batch size for test dataset
+	imdb: bool 						   -> whether or not imdb dataset is used
+	
+	Returns: Accuracy, F1, Precision, Recall 
+	"""
 	torch.cuda.empty_cache()
 	print("eval swp")
 	metric=evaluate.combine(["accuracy", "f1", "precision", "recall"])
@@ -55,29 +67,28 @@ def evaluate_model(model, name,test_dataset, learning_rate, batch_size, imdb=Fal
 						  'end_position': batch[3],
 						  'labels': batch[4]}
 
-			outputs=model(**inputs)
-			print("len of outputs: ", len(outputs))
-			print("outputs 1: ", outputs[1].size())
-			print("labels size: ", batch[3].size())
-			prediction=torch.argmax(outputs[1], dim=-1)
-			print("prediciton sizes: ", prediction)
+			outputs=model(**inputs) #get logits
+			prediction=torch.argmax(outputs[1], dim=-1) #get predictions
 			if name[0] =="b":
 				if imdb==False:
 					metric.add_batch(predictions=prediction, references=batch[5])
 				else:
-					print("batch 3: ", batch[3])
 					metric.add_batch(predictions=prediction, references=batch[3])
 			if name[0] =="r":
 				metric.add_batch(predictions=prediction, references=batch[4])
 
-	res=metric.compute()
-	#print(f"learning rate {learning_rate}: ", res)
- 
+	res=metric.compute() 
 	return res
 
 
 def compute_metrics(eval_pred):
-	print("eval salami")
+	""""Compute metrics function to apply predictions and references to
+	accuracy, f1, precision and recall, also used in salami train loop.
+	
+	Params:
+	eval_pred: tuple ->(logits, labels)
+	
+	Returns: Accuracy, F1, Precision, Recall"""
 	metric=evaluate.combine(["accuracy", "f1", "precision", "recall"])
 	logits, labels=eval_pred
 	predictions=np.argmax(logits, axis=-1)