dev

app.py

@@ -64,8 +64,8 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             per_device_eval_batch_size=int(batch_size), 
             num_train_epochs=int(num_epochs),
             weight_decay=0.01,
-            #gradient_accumulation_steps=int(grad),
-            #max_grad_norm = 1.0, 
+            gradient_accumulation_steps=int(grad),
+            max_grad_norm = 3.0, 
             load_best_model_at_end=True,
             metric_for_best_model="accuracy",
             greater_is_better=True,
@@ -190,8 +190,8 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             return 'RUN AGAIN TO LOAD REST OF DATA'
 
         # 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)
+        #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!")