ruff run

Author: alexl-oai

examples/Fine_tuning_direct_preference_optimization_guide.ipynb

@@ -589,9 +589,9 @@
     "        \"type\": \"dpo\",\n",
     "        \"dpo\": {\n",
     "            \"hyperparameters\": {\n",
-    "                \"n_epochs\": 2,  \n",
-    "                \"beta\": 0.1,  \n",
-    "                \"batch_size\": 8,  \n",
+    "                \"n_epochs\": 2,\n",
+    "                \"beta\": 0.1,\n",
+    "                \"batch_size\": 8,\n",
     "            }\n",
     "        },\n",
     "    },\n",
@@ -610,7 +610,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -620,13 +620,13 @@
     "    responses = await generate_responses(testset, model=job.fine_tuned_model)\n",
     "\n",
     "    post_run = sync_client.evals.runs.create(\n",
-    "    name=ft.id,\n",
-    "    eval_id=logs_eval.id,\n",
-    "    data_source={\n",
-    "        \"type\": \"responses\",\n",
-    "        \"source\": {\"type\": \"responses\", \"limit\": len(test_pairs)},\n",
-    "    },\n",
-    ")"
+    "        name=ft.id,\n",
+    "        eval_id=logs_eval.id,\n",
+    "        data_source={\n",
+    "            \"type\": \"responses\",\n",
+    "            \"source\": {\"type\": \"responses\", \"limit\": len(test_pairs)},\n",
+    "        },\n",
+    "    )"
    ]
   },
   {
@@ -661,21 +661,16 @@
     ").data\n",
     "post_scores = [s.results[0][\"score\"] for s in post_data]\n",
     "\n",
+    "# print scores & a sample comparison from the test set for illustration\n",
     "print(\n",
     "    \"Δ mean:\",\n",
-    "    sum(t - b for b, t in zip(base_scores, post_scores))\n",
-    "    / len(base_scores),\n",
+    "    sum(t - b for b, t in zip(base_scores, post_scores)) / len(base_scores),\n",
     ")\n",
-    "# print a sample comparison from the test set for illustration\n",
     "print(\"\\n=== SAMPLE COMPARISON ===\")\n",
     "idx = 0\n",
     "print(f\"Prompt:\\n  {testset[idx]['item']['input']}\\n\")\n",
-    "print(\n",
-    "    f\"Base model reply: \\n {base_data[idx].sample.output[0].content} \\n\"\n",
-    ")\n",
-    "print(\n",
-    "    f\"DPO-tuned model reply \\n {post_data[idx].sample.output[0].content}\"\n",
-    ")"
+    "print(f\"Base model reply: \\n {base_data[idx].sample.output[0].content} \\n\")\n",
+    "print(f\"DPO-tuned model reply \\n {post_data[idx].sample.output[0].content}\")"
    ]
   }
  ],