diff --git a/test.ipynb b/test.ipynb
deleted file mode 100644
index f97326a..0000000
--- a/test.ipynb
+++ /dev/null
@@ -1,165 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\art\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
-   "source": [
-    "from torch.utils.data import Dataset\n",
-    "from transformers import BertGenerationEncoder, BertGenerationDecoder, EncoderDecoderModel, BertTokenizer\n",
-    "from tqdm import tqdm as progress_bar\n",
-    "import torch\n",
-    "import matplotlib"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "cuda\n"
-     ]
-    }
-   ],
-   "source": [
-    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
-    "print(device)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "You are using a model of type bert to instantiate a model of type bert-generation. This is not supported for all configurations of models and can yield errors.\n",
-      "You are using a model of type bert to instantiate a model of type bert-generation. This is not supported for all configurations of models and can yield errors.\n",
-      "Some weights of BertGenerationDecoder were not initialized from the model checkpoint at google-bert/bert-large-uncased and are newly initialized: ['bert.encoder.layer.0.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.0.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.0.crossattention.output.dense.bias', 'bert.encoder.layer.0.crossattention.output.dense.weight', 'bert.encoder.layer.0.crossattention.self.key.bias', 'bert.encoder.layer.0.crossattention.self.key.weight', 'bert.encoder.layer.0.crossattention.self.query.bias', 'bert.encoder.layer.0.crossattention.self.query.weight', 'bert.encoder.layer.0.crossattention.self.value.bias', 'bert.encoder.layer.0.crossattention.self.value.weight', 'bert.encoder.layer.1.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.1.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.1.crossattention.output.dense.bias', 'bert.encoder.layer.1.crossattention.output.dense.weight', 'bert.encoder.layer.1.crossattention.self.key.bias', 'bert.encoder.layer.1.crossattention.self.key.weight', 'bert.encoder.layer.1.crossattention.self.query.bias', 'bert.encoder.layer.1.crossattention.self.query.weight', 'bert.encoder.layer.1.crossattention.self.value.bias', 'bert.encoder.layer.1.crossattention.self.value.weight', 'bert.encoder.layer.10.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.10.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.10.crossattention.output.dense.bias', 'bert.encoder.layer.10.crossattention.output.dense.weight', 'bert.encoder.layer.10.crossattention.self.key.bias', 'bert.encoder.layer.10.crossattention.self.key.weight', 'bert.encoder.layer.10.crossattention.self.query.bias', 'bert.encoder.layer.10.crossattention.self.query.weight', 'bert.encoder.layer.10.crossattention.self.value.bias', 'bert.encoder.layer.10.crossattention.self.value.weight', 'bert.encoder.layer.11.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.11.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.11.crossattention.output.dense.bias', 'bert.encoder.layer.11.crossattention.output.dense.weight', 'bert.encoder.layer.11.crossattention.self.key.bias', 'bert.encoder.layer.11.crossattention.self.key.weight', 'bert.encoder.layer.11.crossattention.self.query.bias', 'bert.encoder.layer.11.crossattention.self.query.weight', 'bert.encoder.layer.11.crossattention.self.value.bias', 'bert.encoder.layer.11.crossattention.self.value.weight', 'bert.encoder.layer.12.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.12.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.12.crossattention.output.dense.bias', 'bert.encoder.layer.12.crossattention.output.dense.weight', 'bert.encoder.layer.12.crossattention.self.key.bias', 'bert.encoder.layer.12.crossattention.self.key.weight', 'bert.encoder.layer.12.crossattention.self.query.bias', 'bert.encoder.layer.12.crossattention.self.query.weight', 'bert.encoder.layer.12.crossattention.self.value.bias', 'bert.encoder.layer.12.crossattention.self.value.weight', 'bert.encoder.layer.13.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.13.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.13.crossattention.output.dense.bias', 'bert.encoder.layer.13.crossattention.output.dense.weight', 'bert.encoder.layer.13.crossattention.self.key.bias', 'bert.encoder.layer.13.crossattention.self.key.weight', 'bert.encoder.layer.13.crossattention.self.query.bias', 'bert.encoder.layer.13.crossattention.self.query.weight', 'bert.encoder.layer.13.crossattention.self.value.bias', 'bert.encoder.layer.13.crossattention.self.value.weight', 'bert.encoder.layer.14.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.14.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.14.crossattention.output.dense.bias', 'bert.encoder.layer.14.crossattention.output.dense.weight', 'bert.encoder.layer.14.crossattention.self.key.bias', 'bert.encoder.layer.14.crossattention.self.key.weight', 'bert.encoder.layer.14.crossattention.self.query.bias', 'bert.encoder.layer.14.crossattention.self.query.weight', 'bert.encoder.layer.14.crossattention.self.value.bias', 'bert.encoder.layer.14.crossattention.self.value.weight', 'bert.encoder.layer.15.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.15.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.15.crossattention.output.dense.bias', 'bert.encoder.layer.15.crossattention.output.dense.weight', 'bert.encoder.layer.15.crossattention.self.key.bias', 'bert.encoder.layer.15.crossattention.self.key.weight', 'bert.encoder.layer.15.crossattention.self.query.bias', 'bert.encoder.layer.15.crossattention.self.query.weight', 'bert.encoder.layer.15.crossattention.self.value.bias', 'bert.encoder.layer.15.crossattention.self.value.weight', 'bert.encoder.layer.16.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.16.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.16.crossattention.output.dense.bias', 'bert.encoder.layer.16.crossattention.output.dense.weight', 'bert.encoder.layer.16.crossattention.self.key.bias', 'bert.encoder.layer.16.crossattention.self.key.weight', 'bert.encoder.layer.16.crossattention.self.query.bias', 'bert.encoder.layer.16.crossattention.self.query.weight', 'bert.encoder.layer.16.crossattention.self.value.bias', 'bert.encoder.layer.16.crossattention.self.value.weight', 'bert.encoder.layer.17.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.17.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.17.crossattention.output.dense.bias', 'bert.encoder.layer.17.crossattention.output.dense.weight', 'bert.encoder.layer.17.crossattention.self.key.bias', 'bert.encoder.layer.17.crossattention.self.key.weight', 'bert.encoder.layer.17.crossattention.self.query.bias', 'bert.encoder.layer.17.crossattention.self.query.weight', 'bert.encoder.layer.17.crossattention.self.value.bias', 'bert.encoder.layer.17.crossattention.self.value.weight', 'bert.encoder.layer.18.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.18.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.18.crossattention.output.dense.bias', 'bert.encoder.layer.18.crossattention.output.dense.weight', 'bert.encoder.layer.18.crossattention.self.key.bias', 'bert.encoder.layer.18.crossattention.self.key.weight', 'bert.encoder.layer.18.crossattention.self.query.bias', 'bert.encoder.layer.18.crossattention.self.query.weight', 'bert.encoder.layer.18.crossattention.self.value.bias', 'bert.encoder.layer.18.crossattention.self.value.weight', 'bert.encoder.layer.19.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.19.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.19.crossattention.output.dense.bias', 'bert.encoder.layer.19.crossattention.output.dense.weight', 'bert.encoder.layer.19.crossattention.self.key.bias', 'bert.encoder.layer.19.crossattention.self.key.weight', 'bert.encoder.layer.19.crossattention.self.query.bias', 'bert.encoder.layer.19.crossattention.self.query.weight', 'bert.encoder.layer.19.crossattention.self.value.bias', 'bert.encoder.layer.19.crossattention.self.value.weight', 'bert.encoder.layer.2.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.2.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.2.crossattention.output.dense.bias', 'bert.encoder.layer.2.crossattention.output.dense.weight', 'bert.encoder.layer.2.crossattention.self.key.bias', 'bert.encoder.layer.2.crossattention.self.key.weight', 'bert.encoder.layer.2.crossattention.self.query.bias', 'bert.encoder.layer.2.crossattention.self.query.weight', 'bert.encoder.layer.2.crossattention.self.value.bias', 'bert.encoder.layer.2.crossattention.self.value.weight', 'bert.encoder.layer.20.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.20.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.20.crossattention.output.dense.bias', 'bert.encoder.layer.20.crossattention.output.dense.weight', 'bert.encoder.layer.20.crossattention.self.key.bias', 'bert.encoder.layer.20.crossattention.self.key.weight', 'bert.encoder.layer.20.crossattention.self.query.bias', 'bert.encoder.layer.20.crossattention.self.query.weight', 'bert.encoder.layer.20.crossattention.self.value.bias', 'bert.encoder.layer.20.crossattention.self.value.weight', 'bert.encoder.layer.21.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.21.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.21.crossattention.output.dense.bias', 'bert.encoder.layer.21.crossattention.output.dense.weight', 'bert.encoder.layer.21.crossattention.self.key.bias', 'bert.encoder.layer.21.crossattention.self.key.weight', 'bert.encoder.layer.21.crossattention.self.query.bias', 'bert.encoder.layer.21.crossattention.self.query.weight', 'bert.encoder.layer.21.crossattention.self.value.bias', 'bert.encoder.layer.21.crossattention.self.value.weight', 'bert.encoder.layer.22.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.22.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.22.crossattention.output.dense.bias', 'bert.encoder.layer.22.crossattention.output.dense.weight', 'bert.encoder.layer.22.crossattention.self.key.bias', 'bert.encoder.layer.22.crossattention.self.key.weight', 'bert.encoder.layer.22.crossattention.self.query.bias', 'bert.encoder.layer.22.crossattention.self.query.weight', 'bert.encoder.layer.22.crossattention.self.value.bias', 'bert.encoder.layer.22.crossattention.self.value.weight', 'bert.encoder.layer.23.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.23.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.23.crossattention.output.dense.bias', 'bert.encoder.layer.23.crossattention.output.dense.weight', 'bert.encoder.layer.23.crossattention.self.key.bias', 'bert.encoder.layer.23.crossattention.self.key.weight', 'bert.encoder.layer.23.crossattention.self.query.bias', 'bert.encoder.layer.23.crossattention.self.query.weight', 'bert.encoder.layer.23.crossattention.self.value.bias', 'bert.encoder.layer.23.crossattention.self.value.weight', 'bert.encoder.layer.3.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.3.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.3.crossattention.output.dense.bias', 'bert.encoder.layer.3.crossattention.output.dense.weight', 'bert.encoder.layer.3.crossattention.self.key.bias', 'bert.encoder.layer.3.crossattention.self.key.weight', 'bert.encoder.layer.3.crossattention.self.query.bias', 'bert.encoder.layer.3.crossattention.self.query.weight', 'bert.encoder.layer.3.crossattention.self.value.bias', 'bert.encoder.layer.3.crossattention.self.value.weight', 'bert.encoder.layer.4.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.4.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.4.crossattention.output.dense.bias', 'bert.encoder.layer.4.crossattention.output.dense.weight', 'bert.encoder.layer.4.crossattention.self.key.bias', 'bert.encoder.layer.4.crossattention.self.key.weight', 'bert.encoder.layer.4.crossattention.self.query.bias', 'bert.encoder.layer.4.crossattention.self.query.weight', 'bert.encoder.layer.4.crossattention.self.value.bias', 'bert.encoder.layer.4.crossattention.self.value.weight', 'bert.encoder.layer.5.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.5.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.5.crossattention.output.dense.bias', 'bert.encoder.layer.5.crossattention.output.dense.weight', 'bert.encoder.layer.5.crossattention.self.key.bias', 'bert.encoder.layer.5.crossattention.self.key.weight', 'bert.encoder.layer.5.crossattention.self.query.bias', 'bert.encoder.layer.5.crossattention.self.query.weight', 'bert.encoder.layer.5.crossattention.self.value.bias', 'bert.encoder.layer.5.crossattention.self.value.weight', 'bert.encoder.layer.6.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.6.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.6.crossattention.output.dense.bias', 'bert.encoder.layer.6.crossattention.output.dense.weight', 'bert.encoder.layer.6.crossattention.self.key.bias', 'bert.encoder.layer.6.crossattention.self.key.weight', 'bert.encoder.layer.6.crossattention.self.query.bias', 'bert.encoder.layer.6.crossattention.self.query.weight', 'bert.encoder.layer.6.crossattention.self.value.bias', 'bert.encoder.layer.6.crossattention.self.value.weight', 'bert.encoder.layer.7.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.7.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.7.crossattention.output.dense.bias', 'bert.encoder.layer.7.crossattention.output.dense.weight', 'bert.encoder.layer.7.crossattention.self.key.bias', 'bert.encoder.layer.7.crossattention.self.key.weight', 'bert.encoder.layer.7.crossattention.self.query.bias', 'bert.encoder.layer.7.crossattention.self.query.weight', 'bert.encoder.layer.7.crossattention.self.value.bias', 'bert.encoder.layer.7.crossattention.self.value.weight', 'bert.encoder.layer.8.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.8.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.8.crossattention.output.dense.bias', 'bert.encoder.layer.8.crossattention.output.dense.weight', 'bert.encoder.layer.8.crossattention.self.key.bias', 'bert.encoder.layer.8.crossattention.self.key.weight', 'bert.encoder.layer.8.crossattention.self.query.bias', 'bert.encoder.layer.8.crossattention.self.query.weight', 'bert.encoder.layer.8.crossattention.self.value.bias', 'bert.encoder.layer.8.crossattention.self.value.weight', 'bert.encoder.layer.9.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.9.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.9.crossattention.output.dense.bias', 'bert.encoder.layer.9.crossattention.output.dense.weight', 'bert.encoder.layer.9.crossattention.self.key.bias', 'bert.encoder.layer.9.crossattention.self.key.weight', 'bert.encoder.layer.9.crossattention.self.query.bias', 'bert.encoder.layer.9.crossattention.self.query.weight', 'bert.encoder.layer.9.crossattention.self.value.bias', 'bert.encoder.layer.9.crossattention.self.value.weight', 'lm_head.bias', 'lm_head.decoder.bias']\n",
-      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
-     ]
-    }
-   ],
-   "source": [
-    "encoder = BertGenerationEncoder.from_pretrained(\"google-bert/bert-large-uncased\", bos_token_id=101, eos_token_id=102)\n",
-    "# add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token\n",
-    "decoder = BertGenerationDecoder.from_pretrained(\"google-bert/bert-large-uncased\", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102)\n",
-    "model = EncoderDecoderModel(encoder=encoder, decoder=decoder)\n",
-    "\n",
-    "# create tokenizer...\n",
-    "tokenizer = BertTokenizer.from_pretrained(\"google-bert/bert-large-uncased\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "\n",
-    "class CodeDataset(Dataset):\n",
-    "    def __init__(self):\n",
-    "        with open(\"data/conala-train.json\") as f:\n",
-    "            self.data = json.load(f)\n",
-    "\n",
-    "    def __len__(self):\n",
-    "        return len(self.data)\n",
-    "\n",
-    "    def __getitem__(self, idx):\n",
-    "        return self.data[idx][\"rewritten_intent\"], self.data[idx][\"snippet\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "optimizer = torch.optim.AdamW(params=model.parameters(), lr=1e-3)\n",
-    "dataloader = CodeDataset()\n",
-    "model = model.to(device)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "  0%|          | 0/2379 [00:00<?, ?it/s]C:\\Users\\art\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\transformers\\models\\encoder_decoder\\modeling_encoder_decoder.py:636: FutureWarning: Version v4.12.0 introduces a better way to train encoder-decoder models by computing the loss inside the encoder-decoder framework rather than in the decoder itself. You may observe training discrepancies if fine-tuning a model trained with versions anterior to 4.12.0. The decoder_input_ids are now created based on the labels, no need to pass them yourself anymore.\n",
-      "  warnings.warn(DEPRECATION_WARNING, FutureWarning)\n",
-      "  0%|          | 3/2379 [01:18<16:16:50, 24.67s/it]"
-     ]
-    }
-   ],
-   "source": [
-    "losses = []\n",
-    "epochs = 10\n",
-    "for i in range(epochs):\n",
-    "\n",
-    "    epoch_loss = 0\n",
-    "\n",
-    "    for idx, (question, answer) in progress_bar(enumerate(dataloader), total=len(dataloader)):\n",
-    "\n",
-    "        print(questions)\n",
-    "        input_ids = tokenizer(question, add_special_tokens=False, return_tensors=\"pt\").input_ids.to(device)\n",
-    "        label_ids = tokenizer(answer, return_tensors=\"pt\").input_ids.to(device)\n",
-    "\n",
-    "        loss = model(input_ids=input_ids, decoder_input_ids=label_ids, labels=label_ids).loss\n",
-    "\n",
-    "        optimizer.zero_grad()\n",
-    "        loss.backward()\n",
-    "        optimizer.step()\n",
-    "\n",
-    "        epoch_loss += loss.item()\n",
-    "\n",
-    "    losses.append(epoch_loss)\n",
-    "\n",
-    "plt.plot(losses, color=\"green\", label=\"Training Loss\")\n",
-    "plt.legend(loc = 'upper left')\n",
-    "plt.show()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/test.py b/test.py
deleted file mode 100644
index ed9cd55..0000000
--- a/test.py
+++ /dev/null
@@ -1,61 +0,0 @@
-
-from torch.utils.data import Dataset
-from transformers import BertGenerationEncoder, BertGenerationDecoder, EncoderDecoderModel, BertTokenizer
-from tqdm import tqdm as progress_bar
-import torch
-import matplotlib
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(device)
-
-encoder = BertGenerationEncoder.from_pretrained("google-bert/bert-base-uncased", bos_token_id=101, eos_token_id=102)
-# add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token
-decoder = BertGenerationDecoder.from_pretrained("google-bert/bert-base-uncased", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102)
-model = EncoderDecoderModel(encoder=encoder, decoder=decoder)
-
-# create tokenizer...
-tokenizer = BertTokenizer.from_pretrained("google-bert/bert-large-uncased")
-
-import json
-
-class CodeDataset(Dataset):
-    def __init__(self):
-        with open("data/conala-train.json") as f:
-            self.data = json.load(f)
-
-    def __len__(self):
-        return len(self.data)
-
-    def __getitem__(self, idx):
-        intent = self.data[idx]["rewritten_intent"] if self.data[idx]["rewritten_intent"] else self.data[idx]["intent"]
-        return intent, self.data[idx]["snippet"]
-
-
-optimizer = torch.optim.AdamW(params=model.parameters(), lr=1e-3)
-dataloader = CodeDataset()
-model = model.to(device)
-
-losses = []
-epochs = 10
-for i in range(epochs):
-
-    epoch_loss = 0
-
-    for idx, (question, answer) in progress_bar(enumerate(dataloader), total=len(dataloader)):
-
-        input_ids = tokenizer(question, add_special_tokens=False, return_tensors="pt").input_ids.to(device)
-        label_ids = tokenizer(answer, return_tensors="pt").input_ids.to(device)
-
-        loss = model(input_ids=input_ids, decoder_input_ids=label_ids, labels=label_ids).loss
-
-        optimizer.zero_grad()
-        loss.backward()
-        optimizer.step()
-
-        epoch_loss += loss.item()
-
-    losses.append(epoch_loss)
-
-plt.plot(losses, color="green", label="Training Loss")
-plt.legend(loc = 'upper left')
-plt.savefig("plot.png")