diff --git a/chapter10/Chapter 10 - Creating Text Embedding Models.ipynb b/chapter10/Chapter 10 - Creating Text Embedding Models.ipynb
index b4abfb6..53f46e6 100644
--- a/chapter10/Chapter 10 - Creating Text Embedding Models.ipynb	
+++ b/chapter10/Chapter 10 - Creating Text Embedding Models.ipynb	
@@ -269,21 +269,7 @@
     "id": "8uAAhNs0ocoV"
    },
    "outputs": [],
-   "source": [
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"base_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")"
-   ]
+   "source": "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"base_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)"
   },
   {
    "cell_type": "code",
@@ -837,189 +823,8 @@
     "id": "Ikky866vdseY",
     "outputId": "803f2abe-002a-481c-9403-8ce39dfa5b47"
    },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:sentence_transformers.SentenceTransformer:No sentence-transformers model found with name bert-base-uncased. Creating a new one with mean pooling.\n",
-      "/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='1563' max='1563' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1563/1563 06:04, Epoch 1/1]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>100</td>\n",
-       "      <td>0.231900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.168900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>300</td>\n",
-       "      <td>0.170900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.157800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>500</td>\n",
-       "      <td>0.152900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>600</td>\n",
-       "      <td>0.156100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>700</td>\n",
-       "      <td>0.149300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>800</td>\n",
-       "      <td>0.154500</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>900</td>\n",
-       "      <td>0.150900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1000</td>\n",
-       "      <td>0.145600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1100</td>\n",
-       "      <td>0.147800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1200</td>\n",
-       "      <td>0.145600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1300</td>\n",
-       "      <td>0.145100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1400</td>\n",
-       "      <td>0.142000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1500</td>\n",
-       "      <td>0.141600</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c16cc9c062f547ee938537a719d4f668",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "055c320e1c4540fb9f2b293dd28ed569",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "677333dacf8a41d08e0b7fc605da27f9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "TrainOutput(global_step=1563, training_loss=0.15676780793427353, metrics={'train_runtime': 364.4779, 'train_samples_per_second': 137.183, 'train_steps_per_second': 4.288, 'total_flos': 0.0, 'train_loss': 0.15676780793427353, 'epoch': 1.0})"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sentence_transformers import losses, SentenceTransformer\n",
-    "from sentence_transformers.trainer import SentenceTransformerTrainer\n",
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define model\n",
-    "embedding_model = SentenceTransformer('bert-base-uncased')\n",
-    "\n",
-    "# Loss function\n",
-    "train_loss = losses.CosineSimilarityLoss(model=embedding_model)\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"cosineloss_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "outputs": [],
+   "source": "from sentence_transformers import losses, SentenceTransformer\nfrom sentence_transformers.trainer import SentenceTransformerTrainer\nfrom sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define model\nembedding_model = SentenceTransformer('bert-base-uncased')\n\n# Loss function\ntrain_loss = losses.CosineSimilarityLoss(model=embedding_model)\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"cosineloss_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -1216,121 +1021,8 @@
     "id": "j-Q2m0yzkRvW",
     "outputId": "7f83f28d-79d1-4b1e-d70a-85f2cacee1c1"
    },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:sentence_transformers.SentenceTransformer:No sentence-transformers model found with name bert-base-uncased. Creating a new one with mean pooling.\n",
-      "/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='528' max='528' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [528/528 03:00, Epoch 1/1]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>100</td>\n",
-       "      <td>0.345200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.105500</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>300</td>\n",
-       "      <td>0.079000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.062200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>500</td>\n",
-       "      <td>0.069000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5913c2edc4de4e48990626d19af0ff2b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "TrainOutput(global_step=528, training_loss=0.12795479415041028, metrics={'train_runtime': 180.866, 'train_samples_per_second': 93.301, 'train_steps_per_second': 2.919, 'total_flos': 0.0, 'train_loss': 0.12795479415041028, 'epoch': 1.0})"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sentence_transformers import losses, SentenceTransformer\n",
-    "from sentence_transformers.trainer import SentenceTransformerTrainer\n",
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define model\n",
-    "embedding_model = SentenceTransformer('bert-base-uncased')\n",
-    "\n",
-    "# Loss function\n",
-    "train_loss = losses.MultipleNegativesRankingLoss(model=embedding_model)\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"mnrloss_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "outputs": [],
+   "source": "from sentence_transformers import losses, SentenceTransformer\nfrom sentence_transformers.trainer import SentenceTransformerTrainer\nfrom sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define model\nembedding_model = SentenceTransformer('bert-base-uncased')\n\n# Loss function\ntrain_loss = losses.MultipleNegativesRankingLoss(model=embedding_model)\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"mnrloss_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -1624,342 +1316,8 @@
     "id": "iQ3vW2VTA9dN",
     "outputId": "8772abf8-992c-4ec1-9e27-2f90cf1e4503"
    },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a3a94fe38f134761a6998fa7a057eb7e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "modules.json:   0%|          | 0.00/349 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "924aec3545864e3fb5fdcf962c21836a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config_sentence_transformers.json:   0%|          | 0.00/116 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cde32db4b98f41c9948c2f28c20a4c0a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "README.md:   0%|          | 0.00/10.7k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bbbb12d403fc4edc9f27e3ef9927ffd8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "sentence_bert_config.json:   0%|          | 0.00/53.0 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f8e627842b8c4342ac797c94121e83bf",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config.json:   0%|          | 0.00/612 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7a5a63ac37a94a009b7f6ba99f08e2da",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model.safetensors:   0%|          | 0.00/90.9M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "49d930971e0e4ef3a611eec49bf0f53e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer_config.json:   0%|          | 0.00/350 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6413d644285c47d08e2991171f2fedb6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aaf53993e3f1420b920b0afaf2919842",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.json:   0%|          | 0.00/466k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "22bad8429f9d4e4db13f79b7c36c79cb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "special_tokens_map.json:   0%|          | 0.00/112 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3d885279ea8f4e1dacca331fbc0a9d0a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "1_Pooling/config.json:   0%|          | 0.00/190 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='1563' max='1563' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1563/1563 01:57, Epoch 1/1]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>100</td>\n",
-       "      <td>0.155500</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.110000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>300</td>\n",
-       "      <td>0.118600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.115300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>500</td>\n",
-       "      <td>0.110700</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>600</td>\n",
-       "      <td>0.101000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>700</td>\n",
-       "      <td>0.113100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>800</td>\n",
-       "      <td>0.099800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>900</td>\n",
-       "      <td>0.109600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1000</td>\n",
-       "      <td>0.105800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1100</td>\n",
-       "      <td>0.094900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1200</td>\n",
-       "      <td>0.106400</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1300</td>\n",
-       "      <td>0.105300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1400</td>\n",
-       "      <td>0.105200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1500</td>\n",
-       "      <td>0.106600</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "511480884e6145cda98eac03e3eaa214",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dc3cccdae676461b991e6b375b482344",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "27bf3b15061241b5bc14c47e9713364e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Computing widget examples:   0%|          | 0/5 [00:00<?, ?example/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "TrainOutput(global_step=1563, training_loss=0.10982195932897176, metrics={'train_runtime': 117.3739, 'train_samples_per_second': 425.989, 'train_steps_per_second': 13.316, 'total_flos': 0.0, 'train_loss': 0.10982195932897176, 'epoch': 1.0})"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sentence_transformers import losses, SentenceTransformer\n",
-    "from sentence_transformers.trainer import SentenceTransformerTrainer\n",
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define model\n",
-    "embedding_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')\n",
-    "\n",
-    "# Loss function\n",
-    "train_loss = losses.MultipleNegativesRankingLoss(model=embedding_model)\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"finetuned_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "outputs": [],
+   "source": "from sentence_transformers import losses, SentenceTransformer\nfrom sentence_transformers.trainer import SentenceTransformerTrainer\nfrom sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define model\nembedding_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')\n\n# Loss function\ntrain_loss = losses.MultipleNegativesRankingLoss(model=embedding_model)\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"finetuned_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -2353,39 +1711,7 @@
     "id": "MK1KybOI_uIY"
    },
    "outputs": [],
-   "source": [
-    "from sentence_transformers import losses, SentenceTransformer\n",
-    "from sentence_transformers.trainer import SentenceTransformerTrainer\n",
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define model\n",
-    "embedding_model = SentenceTransformer('bert-base-uncased')\n",
-    "\n",
-    "# Loss function\n",
-    "train_loss = losses.CosineSimilarityLoss(model=embedding_model)\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"augmented_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "source": "from sentence_transformers import losses, SentenceTransformer\nfrom sentence_transformers.trainer import SentenceTransformerTrainer\nfrom sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define model\nembedding_model = SentenceTransformer('bert-base-uncased')\n\n# Loss function\ntrain_loss = losses.CosineSimilarityLoss(model=embedding_model)\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"augmented_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -2426,40 +1752,7 @@
     "id": "wyPBGfxp0D_7"
    },
    "outputs": [],
-   "source": [
-    "# Combine gold + silver\n",
-    "data = pd.concat([gold], ignore_index=True, axis=0)\n",
-    "data = data.drop_duplicates(subset=['sentence1', 'sentence2'], keep=\"first\")\n",
-    "train_dataset = Dataset.from_pandas(data, preserve_index=False)\n",
-    "\n",
-    "# Define model\n",
-    "embedding_model = SentenceTransformer('bert-base-uncased')\n",
-    "\n",
-    "# Loss function\n",
-    "train_loss = losses.CosineSimilarityLoss(model=embedding_model)\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"gold_only_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=32,\n",
-    "    per_device_eval_batch_size=32,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "source": "# Combine gold + silver\ndata = pd.concat([gold], ignore_index=True, axis=0)\ndata = data.drop_duplicates(subset=['sentence1', 'sentence2'], keep=\"first\")\ntrain_dataset = Dataset.from_pandas(data, preserve_index=False)\n\n# Define model\nembedding_model = SentenceTransformer('bert-base-uncased')\n\n# Loss function\ntrain_loss = losses.CosineSimilarityLoss(model=embedding_model)\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"gold_only_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=32,\n    per_device_eval_batch_size=32,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -2652,32 +1945,7 @@
     "id": "PYApurOS07x0"
    },
    "outputs": [],
-   "source": [
-    "from sentence_transformers.trainer import SentenceTransformerTrainer\n",
-    "from sentence_transformers.training_args import SentenceTransformerTrainingArguments\n",
-    "\n",
-    "# Define the training arguments\n",
-    "args = SentenceTransformerTrainingArguments(\n",
-    "    output_dir=\"tsdae_embedding_model\",\n",
-    "    num_train_epochs=1,\n",
-    "    per_device_train_batch_size=16,\n",
-    "    per_device_eval_batch_size=16,\n",
-    "    warmup_steps=100,\n",
-    "    fp16=True,\n",
-    "    eval_steps=100,\n",
-    "    logging_steps=100,\n",
-    ")\n",
-    "\n",
-    "# Train model\n",
-    "trainer = SentenceTransformerTrainer(\n",
-    "    model=embedding_model,\n",
-    "    args=args,\n",
-    "    train_dataset=train_dataset,\n",
-    "    loss=train_loss,\n",
-    "    evaluator=evaluator\n",
-    ")\n",
-    "trainer.train()"
-   ]
+   "source": "from sentence_transformers.trainer import SentenceTransformerTrainer\nfrom sentence_transformers.training_args import SentenceTransformerTrainingArguments\n\n# Define the training arguments\nargs = SentenceTransformerTrainingArguments(\n    output_dir=\"tsdae_embedding_model\",\n    num_train_epochs=1,\n    per_device_train_batch_size=16,\n    per_device_eval_batch_size=16,\n    warmup_steps=100,\n    fp16=True,\n    eval_steps=100,\n    logging_steps=100,\n    report_to=\"none\",\n)\n\n# Train model\ntrainer = SentenceTransformerTrainer(\n    model=embedding_model,\n    args=args,\n    train_dataset=train_dataset,\n    loss=train_loss,\n    evaluator=evaluator\n)\ntrainer.train()"
   },
   {
    "cell_type": "code",
@@ -2735,4 +2003,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}
\ No newline at end of file
diff --git a/chapter11/Chapter 11 - Fine-Tuning BERT.ipynb b/chapter11/Chapter 11 - Fine-Tuning BERT.ipynb
index c6879d3..c1a6420 100644
--- a/chapter11/Chapter 11 - Fine-Tuning BERT.ipynb	
+++ b/chapter11/Chapter 11 - Fine-Tuning BERT.ipynb	
@@ -2115,42 +2115,8 @@
     "id": "zZ10SpAXdNvC",
     "outputId": "f9930b86-e077-4233-f7d7-16c5ec1e640d"
    },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "630de7830edb4104938bef1c304129c0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/32 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from setfit import TrainingArguments as SetFitTrainingArguments\n",
-    "from setfit import Trainer as SetFitTrainer\n",
-    "\n",
-    "# Define training arguments\n",
-    "args = SetFitTrainingArguments(\n",
-    "    num_epochs=3, # The number of epochs to use for contrastive learning\n",
-    "    num_iterations=20  # The number of text pairs to generate\n",
-    ")\n",
-    "args.eval_strategy = args.evaluation_strategy\n",
-    "\n",
-    "# Create trainer\n",
-    "trainer = SetFitTrainer(\n",
-    "    model=model,\n",
-    "    args=args,\n",
-    "    train_dataset=sampled_train_data,\n",
-    "    eval_dataset=test_data,\n",
-    "    metric=\"f1\"\n",
-    ")"
-   ]
+   "outputs": [],
+   "source": "from setfit import TrainingArguments as SetFitTrainingArguments\nfrom setfit import Trainer as SetFitTrainer\n\n# Define training arguments\nargs = SetFitTrainingArguments(\n    num_epochs=3, # The number of epochs to use for contrastive learning\n    num_iterations=20,  # The number of text pairs to generate\n    report_to=\"none\",\n)\nargs.eval_strategy = args.evaluation_strategy\n\n# Create trainer\ntrainer = SetFitTrainer(\n    model=model,\n    args=args,\n    train_dataset=sampled_train_data,\n    eval_dataset=test_data,\n    metric=\"f1\"\n)"
   },
   {
    "cell_type": "code",
@@ -3624,4 +3590,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}
\ No newline at end of file