rft.ipynb: typo updates (#1903)

Author: theophile-oai

examples/Reinforcement_Fine_Tuning.ipynb

@@ -1339,8 +1339,8 @@
    "outputs": [],
    "source": [
     "# Set your training and test file paths\n",
-    "train_file = \"data/medical_01_verifiable_problem_train_with_prompt.jsonl\"\n",
-    "test_file = \"data/medical_01_verifiable_problem_val_with_prompt.jsonl\"\n",
+    "train_file = \"data/medical_01_verifiable_problem_train_simple_prompt.jsonl\"\n",
+    "test_file = \"data/medical_01_verifiable_problem_val_simple_prompt.jsonl\"\n",
     "\n",
     "def upload_file(file_path: str) -> str:\n",
     "    \"\"\"Upload a file to the OpenAI platform for fine-tuning.\"\"\"\n",
@@ -1389,7 +1389,7 @@
     "grader = model_grader_2\n",
     "response_format = None\n",
     "compute_multiplier = 1.0\n",
-    "etest_samples = 1\n",
+    "eval_samples = 1\n",
     "eval_interval = 5"
    ]
   },
@@ -1409,7 +1409,7 @@
     "# Launch the RFT job\n",
     "payload = dict(\n",
     "    training_file=train_file_id,\n",
-    "    test_file=test_file_id,\n",
+    "    validation_file=test_file_id,\n",
     "    model=model,\n",
     "    suffix=suffix,\n",
     "    method=dict(\n",
@@ -1419,7 +1419,7 @@
     "            response_format=response_format,\n",
     "            hyperparameters=dict(\n",
     "                compute_multiplier=compute_multiplier,\n",
-    "                etest_samples=etest_samples,\n",
+    "                eval_samples=eval_samples,\n",
     "                eval_interval=eval_interval,\n",
     "                n_epochs=n_epochs,\n",
     "                reasoning_effort=reasoning_effort,\n",
@@ -2116,7 +2116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.12.9"
   }
  },
  "nbformat": 4,