dev

app.py

@@ -69,12 +69,13 @@ def fine_tune_model(model_name, dataset_name, hub_id, api_key, num_epochs, batch
             output_dir='./results',
             eval_strategy="steps",  # Change this to steps
             save_strategy='steps',
-            learning_rate=lr*0.000001,
+            learning_rate=lr*0.00001,
             per_device_train_batch_size=int(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),
+            gradient_accumulation_steps=int(grad),
+            max_grad_norm = 1.0, 
             load_best_model_at_end=True,
             metric_for_best_model="accuracy",
             greater_is_better=True,