deve

app.py

@@ -84,12 +84,12 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             metric_for_best_model="loss",
             greater_is_better=True,
             logging_dir='/data/logs',
-            logging_steps=200,
+            logging_steps=210,
             #push_to_hub=True,
             hub_model_id=hub_id.strip(),
             fp16=True,
             #lr_scheduler_type='cosine',
-            save_steps=200,  # Save checkpoint every 500 steps
+            save_steps=210,  # Save checkpoint every 500 steps
             save_total_limit=3, 
         )
         # Check if a checkpoint exists and load it
@@ -234,10 +234,10 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
         #)    
     
         # Fine-tune the model
-        #if os.path.exists(training_args.output_dir) and os.listdir(training_args.output_dir):
-            #train_result = trainer.train(resume_from_checkpoint=True)
-        #else:
-        train_result = trainer.train()
+        if os.path.exists(training_args.output_dir) and os.listdir(training_args.output_dir):
+            train_result = trainer.train(resume_from_checkpoint=True)
+        else:
+            train_result = trainer.train()
         trainer.push_to_hub(commit_message="Training complete!")
     except Exception as e:
         return f"An error occurred: {str(e)}, TB: {traceback.format_exc()}"