Update app.py

app.py

@@ -21,31 +21,7 @@ def tokenize_function(examples):
     return tokenizer(examples["text"])
 
     
-#Funktion, die den gegebenen Text aus dem Datenset gruppiert
-def group_texts(examples):
-    # Concatenate all texts.
-    concatenated_examples = {k: sum(examples[k], []) for k in examples.keys()}
-    total_length = len(concatenated_examples[list(examples.keys())[0]])
-    # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
-    # customize this part to your needs.
-    total_length = (total_length // block_size) * block_size
-    # Split by chunks of max_len.
-    result = {
-        k: [t[i : i + block_size] for i in range(0, total_length, block_size)]
-        for k, t in concatenated_examples.items()
-    }
-    result["labels"] = result["input_ids"].copy()
-    return result
-
-#Funktion, die der trainer braucht, um das Training zu evaluieren - mit einer Metrik
-def compute_metrics(eval_pred):
-    #Metrik berechnen, um das training messen zu können - wird es besser???
-    metric = evaluate.load("accuracy")   #3 Arten von gegebener Metrik: f1  oder roc_auc  oder accuracy
-    logits, labels = eval_pred
-    predictions = np.argmax(logits, axis=-1)
-    #Call compute on metric to calculate the accuracy of your predictions. 
-    #Before passing your predictions to compute, you need to convert the predictions to logits (remember all Transformers models return logits):
-    return metric.compute(predictions=predictions, references=labels)
+
 
 #neues Model testen nach dem Training
 ########################################################################