Update app.py

app.py

@@ -103,6 +103,7 @@ tokenized_datasets = dataset_neu.map(tokenize_function, batched=True, num_proc=4
 #small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(1000))
 #small_eval_dataset = tokenized_datasets["test"].shuffle(seed=42).select(range(1000))
 
+#Probe ansehen - zum überprüfen...
 print (tokenized_datasets["train"][4])
 
 
@@ -134,19 +135,18 @@ metric = evaluate.load("accuracy")   # 3 Arten von gegebener Metrik: f1  oder ro
 ####################################################
 #Training
 ####################################################
-
+print ("training args")
 #Training Args
 batch_size = 2
 
 training_args = TrainingArguments(
-    #output_dir="alexkueck/test-tis-1",
-    output_dir="model",
+    output_dir="alexkueck/li-tis-tuned-1",
     overwrite_output_dir = 'True',
     per_device_train_batch_size=batch_size,  #batch_size = 2 for full training
     per_device_eval_batch_size=batch_size,
-    evaluation_strategy = "steps",  #oder  
-    logging_strategy="steps",   #oder epoch
-    logging_steps=10,
+    evaluation_strategy = "epoch",  #oder  steps
+    logging_strategy="epoch",   #oder steps
+    #logging_steps=10,
     logging_dir='logs',
     learning_rate=2e-5,
     weight_decay=0.01,
@@ -165,10 +165,11 @@ training_args = TrainingArguments(
     load_best_model_at_end=False,
     #push_to_hub=True,
 )
-print ("training args")
+
 ############################################
 #def trainieren_neu(name):
 #Trainer zusammenstellen
+print ("trainer")
 trainer = Trainer(
         model=model,
         args=training_args,
@@ -177,7 +178,25 @@ trainer = Trainer(
         #tokenizer=tokenizer,
         compute_metrics=compute_metrics,
 )
-print ("trainer")
+
+###############################################
+#Special QA Trainer...#
+'''
+trainer = QuestionAnsweringTrainer(
+        model=model,
+        args=training_args,
+        train_dataset=train_dataset if training_args.do_train else None,
+        eval_dataset=eval_dataset if training_args.do_eval else None,
+        eval_examples=eval_examples if training_args.do_eval else None,
+        tokenizer=tokenizer,
+        data_collator=data_collator,
+        post_process_function=post_processing_function,
+        compute_metrics=compute_metrics,
+    )
+'''
+#################################################
+
+
 #trainer ausführen
 trainer.train()
 #Wenn man vom letzten checkpoint aus weiter trainieren möchte: trainer.train(resume_from_checkpoint=True)