changes

openfl-tutorials/Federated_PyTorch_LLM.ipynb

@@ -4,14 +4,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Federated PyTorch TinyImageNet Tutorial"
+    "# Federated PyTorch LLM Tutorial"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook is an example of Transfer Learning \n",
+    "This notebook is an example of LLM fine-tuning\n",
     "\n",
     "Custom DataLoader is used with OpenFL Python API"
    ]
@@ -77,7 +77,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now we are ready to define our dataset and model to perform federated learning on. The dataset should be composed of a numpy arrayWe start with a simple fully connected model that is trained on the MNIST dataset. "
+    "Now we are ready to define our dataset and model to perform federated learning on. The dataset should be composed of a numpy arrayWe start with a simple Roberta model that is trained on the glue mrpc dataset. "
    ]
   },
   {
@@ -458,7 +458,7 @@
    "outputs": [],
    "source": [
     "#Run experiment, return trained FederatedModel\n",
-    "final_fl_model = fx.run_experiment(collaborators,{'aggregator.settings.rounds_to_train':1,\"tasks.train.kwargs.epochs\":10})"
+    "final_fl_model = fx.run_experiment(collaborators,{'aggregator.settings.rounds_to_train':10,\"tasks.train.kwargs.epochs\":2})"
    ]
   },
   {