Add results for test.

examples/entailment/entailment_multinli_transformers.ipynb

@@ -60,7 +60,12 @@
    "outputs": [],
    "source": [
     "import sys, os\n",
-    "    \n",
+    "nlp_path = os.path.abspath('../../')\n",
+    "if nlp_path not in sys.path:\n",
+    "    sys.path.insert(0, nlp_path)\n",
+    "\n",
+    "import scrapbook as sb\n",
+    "\n",
     "from tempfile import TemporaryDirectory\n",
     "\n",
     "import numpy as np\n",
@@ -384,6 +389,22 @@
     "|xlnet-large-cased|5.15 hrs|0.11 hrs|0.887|0.890|\n",
     "|bert-large-cased|4.01 hrs|0.08 hrs|0.867|0.867|"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result_matched_dict = classification_report(dev_df_matched[LABEL_COL], predictions_matched, digits=3, output_dict=True)\n",
+    "result_mismatched_dict = classification_report(dev_df_mismatched[LABEL_COL], predictions_mismatched, digits=3, output_dict=True)\n",
+    "sb.glue(\"matched_precision\", result_matched_dict[\"weighted avg\"][\"precision\"])\n",
+    "sb.glue(\"matched_recall\", result_matched_dict[\"weighted avg\"][\"recall\"])\n",
+    "sb.glue(\"matched_f1\", result_matched_dict[\"weighted avg\"][\"f1-score\"])\n",
+    "sb.glue(\"mismatched_precision\", result_mismatched_dict[\"weighted avg\"][\"precision\"])\n",
+    "sb.glue(\"mismatched_recall\", result_mismatched_dict[\"weighted avg\"][\"recall\"])\n",
+    "sb.glue(\"mismatched_f1\", result_mismatched_dict[\"weighted avg\"][\"f1-score\"])"
+   ]
   }
  ],
  "metadata": {