fastNLP/tutorials/fastnlp_tutorial_6.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fdd7ff16",
   "metadata": {},
   "source": [
    "# T6. fastNLP 与 paddle 或 jittor 的结合\n",
    "\n",
    "  1   fastNLP 结合 paddle 训练模型\n",
    " \n",
    "    1.1   关于 paddle 的简单介绍\n",
    "\n",
    "    1.2   使用 paddle 搭建并训练模型\n",
    "\n",
    "  2   fastNLP 结合 jittor 训练模型\n",
    "\n",
    "    2.1   关于 jittor 的简单介绍\n",
    "\n",
    "    2.2   使用 jittor 搭建并训练模型\n",
    "\n",
    "<!-- &emsp; 3 &ensp; fastNLP 实现 paddle 与 pytorch 互转 -->"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "08752c5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Reusing dataset glue (/remote-home/xrliu/.cache/huggingface/datasets/glue/sst2/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6b13d42c39ba455eb370bf2caaa3a264",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/3 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "sst2data = load_dataset('glue', 'sst2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7e8cc210",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[38;5;2m[i 0604 21:01:38.510813 72 log.cc:351] Load log_sync: 1\u001b[m\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Processing:   0%|          | 0/6000 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'fastNLP.core.dataset.dataset.DataSet'> True\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "sys.path.append('..')\n",
    "\n",
    "from fastNLP import DataSet\n",
    "\n",
    "dataset = DataSet.from_pandas(sst2data['train'].to_pandas())[:6000]\n",
    "\n",
    "dataset.apply_more(lambda ins:{'words': ins['sentence'].lower().split(), 'target': ins['label']}, \n",
    "                   progress_bar=\"tqdm\")\n",
    "dataset.delete_field('sentence')\n",
    "dataset.delete_field('label')\n",
    "dataset.delete_field('idx')\n",
    "\n",
    "from fastNLP import Vocabulary\n",
    "\n",
    "vocab = Vocabulary()\n",
    "vocab.from_dataset(dataset, field_name='words')\n",
    "vocab.index_dataset(dataset, field_name='words')\n",
    "\n",
    "train_dataset, evaluate_dataset = dataset.split(ratio=0.85)\n",
    "print(type(train_dataset), isinstance(train_dataset, DataSet))\n",
    "\n",
    "from fastNLP.io import DataBundle\n",
    "\n",
    "data_bundle = DataBundle(datasets={'train': train_dataset, 'dev': evaluate_dataset})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "57a3272f",
   "metadata": {},
   "source": [
    "## 1. fastNLP 结合 paddle 训练模型\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e31b3198",
   "metadata": {},
   "outputs": [],
   "source": [
    "import paddle\n",
    "import paddle.nn as nn\n",
    "import paddle.nn.functional as F\n",
    "\n",
    "\n",
    "class ClsByPaddle(nn.Layer):\n",
    "    def __init__(self, vocab_size, embedding_dim, output_dim, hidden_dim=64, dropout=0.5):\n",
    "        nn.Layer.__init__(self)\n",
    "        self.hidden_dim = hidden_dim\n",
    "\n",
    "        self.embedding = nn.Embedding(num_embeddings=vocab_size, embedding_dim=embedding_dim)\n",
    "        \n",
    "        self.conv1 = nn.Sequential(nn.Conv1D(embedding_dim, 30, 1, padding=0), nn.ReLU())\n",
    "        self.conv2 = nn.Sequential(nn.Conv1D(embedding_dim, 40, 3, padding=1), nn.ReLU())\n",
    "        self.conv3 = nn.Sequential(nn.Conv1D(embedding_dim, 50, 5, padding=2), nn.ReLU())\n",
    "\n",
    "        self.mlp = nn.Sequential(('dropout', nn.Dropout(p=dropout)),\n",
    "                                 ('linear_1', nn.Linear(120, hidden_dim)),\n",
    "                                 ('activate', nn.ReLU()),\n",
    "                                 ('linear_2', nn.Linear(hidden_dim, output_dim)))\n",
    "        \n",
    "        self.loss_fn = nn.MSELoss()\n",
    "\n",
    "    def forward(self, words):\n",
    "        output = self.embedding(words).transpose([0, 2, 1])\n",
    "        conv1, conv2, conv3 = self.conv1(output), self.conv2(output), self.conv3(output)\n",
    "\n",
    "        pool1 = F.max_pool1d(conv1, conv1.shape[-1]).squeeze(2)\n",
    "        pool2 = F.max_pool1d(conv2, conv2.shape[-1]).squeeze(2)\n",
    "        pool3 = F.max_pool1d(conv3, conv3.shape[-1]).squeeze(2)\n",
    "\n",
    "        pool = paddle.concat([pool1, pool2, pool3], axis=1)\n",
    "        output = self.mlp(pool)\n",
    "        return output\n",
    "    \n",
    "    def train_step(self, words, target):\n",
    "        pred = self(words)\n",
    "        target = paddle.stack((1 - target, target), axis=1).cast(pred.dtype)\n",
    "        return {'loss': self.loss_fn(pred, target)}\n",
    "\n",
    "    def evaluate_step(self, words, target):\n",
    "        pred = self(words)\n",
    "        pred = paddle.argmax(pred, axis=-1)\n",
    "        return {'pred': pred, 'target': target}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c63b030f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "W0604 21:02:25.453869 19014 gpu_context.cc:278] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 11.1, Runtime API Version: 10.2\n",
      "W0604 21:02:26.061690 19014 gpu_context.cc:306] device: 0, cuDNN Version: 7.6.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "ClsByPaddle(\n",
       "  (embedding): Embedding(8458, 100, sparse=False)\n",
       "  (conv1): Sequential(\n",
       "    (0): Conv1D(100, 30, kernel_size=[1], data_format=NCL)\n",
       "    (1): ReLU()\n",
       "  )\n",
       "  (conv2): Sequential(\n",
       "    (0): Conv1D(100, 40, kernel_size=[3], padding=1, data_format=NCL)\n",
       "    (1): ReLU()\n",
       "  )\n",
       "  (conv3): Sequential(\n",
       "    (0): Conv1D(100, 50, kernel_size=[5], padding=2, data_format=NCL)\n",
       "    (1): ReLU()\n",
       "  )\n",
       "  (mlp): Sequential(\n",
       "    (dropout): Dropout(p=0.5, axis=None, mode=upscale_in_train)\n",
       "    (linear_1): Linear(in_features=120, out_features=64, dtype=float32)\n",
       "    (activate): ReLU()\n",
       "    (linear_2): Linear(in_features=64, out_features=2, dtype=float32)\n",
       "  )\n",
       "  (loss_fn): MSELoss()\n",
       ")"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = ClsByPaddle(vocab_size=len(vocab), embedding_dim=100, output_dim=2)\n",
    "\n",
    "model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2997c0aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from paddle.optimizer import AdamW\n",
    "\n",
    "optimizers = AdamW(parameters=model.parameters(), learning_rate=5e-4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ead35fb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import prepare_paddle_dataloader\n",
    "\n",
    "train_dataloader = prepare_paddle_dataloader(train_dataset, batch_size=16, shuffle=True)\n",
    "evaluate_dataloader = prepare_paddle_dataloader(evaluate_dataset, batch_size=16)\n",
    "\n",
    "# dl_bundle = prepare_paddle_dataloader(data_bundle, batch_size=16, shuffle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "25e8da83",
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import Trainer, Accuracy\n",
    "\n",
    "trainer = Trainer(\n",
    "    model=model,\n",
    "    driver='paddle',\n",
    "    device='gpu',                              # 'cpu', 'gpu', 'gpu:x'\n",
    "    n_epochs=10,\n",
    "    optimizers=optimizers,\n",
    "    train_dataloader=train_dataloader,         # dl_bundle['train'],\n",
    "    evaluate_dataloaders=evaluate_dataloader,  # dl_bundle['dev'], \n",
    "    metrics={'acc': Accuracy()}\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d63c5d74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7fbfbf; text-decoration-color: #7fbfbf\">[21:03:08] </span><span style=\"color: #000080; text-decoration-color: #000080\">INFO    </span> Running evaluator sanity check for <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span> batches.              <a href=\"file://../fastNLP/core/controllers/trainer.py\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">trainer.py</span></a><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">:</span><a href=\"file://../fastNLP/core/controllers/trainer.py#596\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">596</span></a>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[2;36m[21:03:08]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Running evaluator sanity check for \u001b[1;36m2\u001b[0m batches.              \u001b]8;id=894986;file://../fastNLP/core/controllers/trainer.py\u001b\\\u001b[2mtrainer.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=567751;file://../fastNLP/core/controllers/trainer.py#596\u001b\\\u001b[2m596\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/ipywidgets/widgets/widget_\n",
       "output.py:111: DeprecationWarning: Kernel._parent_header is deprecated in ipykernel 6. Use \n",
       ".get_parent()\n",
       "  if ip and hasattr(ip, 'kernel') and hasattr(ip.kernel, '_parent_header'):\n",
       "</pre>\n"
      ],
      "text/plain": [
       "/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/ipywidgets/widgets/widget_\n",
       "output.py:111: DeprecationWarning: Kernel._parent_header is deprecated in ipykernel 6. Use \n",
       ".get_parent()\n",
       "  if ip and hasattr(ip, 'kernel') and hasattr(ip.kernel, '_parent_header'):\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/ipywidgets/widgets/widget_\n",
       "output.py:112: DeprecationWarning: Kernel._parent_header is deprecated in ipykernel 6. Use \n",
       ".get_parent()\n",
       "  self.msg_id = ip.kernel._parent_header['header']['msg_id']\n",
       "</pre>\n"
      ],
      "text/plain": [
       "/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/ipywidgets/widgets/widget_\n",
       "output.py:112: DeprecationWarning: Kernel._parent_header is deprecated in ipykernel 6. Use \n",
       ".get_parent()\n",
       "  self.msg_id = ip.kernel._parent_header['header']['msg_id']\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/paddle/tensor/creation.py:\n",
       "125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To \n",
       "silence this warning, use `object` by itself. Doing this will not modify any behavior and is \n",
       "safe. \n",
       "Deprecated in NumPy 1.20; for more details and guidance: \n",
       "https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n",
       "  if data.dtype == np.object:\n",
       "</pre>\n"
      ],
      "text/plain": [
       "/remote-home/xrliu/anaconda3/envs/demo/lib/python3.7/site-packages/paddle/tensor/creation.py:\n",
       "125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To \n",
       "silence this warning, use `object` by itself. Doing this will not modify any behavior and is \n",
       "safe. \n",
       "Deprecated in NumPy 1.20; for more details and guidance: \n",
       "https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n",
       "  if data.dtype == np.object:\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m1\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.78125</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">125.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.78125\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m125.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m2\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7875</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">126.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.7875\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m126.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m3\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.8</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">128.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.8\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m128.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">4</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m4\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.79375</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">127.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.79375\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m127.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m5\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.81875</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">131.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.81875\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m131.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">6</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m6\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.8</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">128.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.8\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m128.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">7</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m7\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.80625</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">129.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.80625\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m129.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m8\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.79375</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">127.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.79375\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m127.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">9</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m9\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7875</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">126.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.7875\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m126.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">---------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">10</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "---------------------------- Eval. results on Epoch:\u001b[1;36m10\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.8</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.0</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">128.0</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.8\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160.0\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m128.0\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "trainer.run(num_eval_batch_per_dl=10) "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cb9a0b3c",
   "metadata": {},
   "source": [
    "## 2. fastNLP 结合 jittor 训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c600191d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import jittor\n",
    "import jittor.nn as nn\n",
    "\n",
    "from jittor import Module\n",
    "\n",
    "\n",
    "class ClsByJittor(Module):\n",
    "    def __init__(self, vocab_size, embedding_dim, output_dim, hidden_dim=64, num_layers=2, dropout=0.5):\n",
    "        Module.__init__(self)\n",
    "        self.hidden_dim = hidden_dim\n",
    "\n",
    "        self.embedding = nn.Embedding(num=vocab_size, dim=embedding_dim)\n",
    "        self.lstm = nn.LSTM(input_size=embedding_dim, hidden_size=hidden_dim, batch_first=True,  # 默认 batch_first=False\n",
    "                            num_layers=num_layers, bidirectional=True, dropout=dropout)\n",
    "        self.mlp = nn.Sequential([nn.Dropout(p=dropout),\n",
    "                                  nn.Linear(hidden_dim * 2, hidden_dim * 2),\n",
    "                                  nn.ReLU(),\n",
    "                                  nn.Linear(hidden_dim * 2, output_dim),\n",
    "                                  nn.Sigmoid(),])\n",
    "\n",
    "        self.loss_fn = nn.MSELoss()\n",
    "\n",
    "    def execute(self, words):\n",
    "        output = self.embedding(words)\n",
    "        output, (hidden, cell) = self.lstm(output)\n",
    "        output = self.mlp(jittor.concat((hidden[-1], hidden[-2]), dim=1))\n",
    "        return output\n",
    "    \n",
    "    def train_step(self, words, target):\n",
    "        pred = self(words)\n",
    "        target = jittor.stack((1 - target, target), dim=1)\n",
    "        return {'loss': self.loss_fn(pred, target)}\n",
    "\n",
    "    def evaluate_step(self, words, target):\n",
    "        pred = self(words)\n",
    "        pred = jittor.argmax(pred, dim=-1)[0]\n",
    "        return {'pred': pred, 'target': target}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a94ed8c4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ClsByJittor(\n",
       "    embedding: Embedding(8458, 100)\n",
       "    lstm: LSTM(100, 64, 2, bias=True, batch_first=True, dropout=0.5, bidirectional=True, proj_size=0)\n",
       "    mlp: Sequential(\n",
       "        0: Dropout(0.5, is_train=False)\n",
       "        1: Linear(128, 128, float32[128,], None)\n",
       "        2: relu()\n",
       "        3: Linear(128, 2, float32[2,], None)\n",
       "        4: Sigmoid()\n",
       "    )\n",
       "    loss_fn: MSELoss(mean)\n",
       ")"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = ClsByJittor(vocab_size=len(vocab), embedding_dim=100, output_dim=2)\n",
    "\n",
    "model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "6d15ebc1",
   "metadata": {},
   "outputs": [],
   "source": [
    "from jittor.optim import AdamW\n",
    "\n",
    "optimizers = AdamW(params=model.parameters(), lr=5e-3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "95d8d09e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import prepare_jittor_dataloader\n",
    "\n",
    "train_dataloader = prepare_jittor_dataloader(train_dataset, batch_size=16, shuffle=True)\n",
    "evaluate_dataloader = prepare_jittor_dataloader(evaluate_dataset, batch_size=16)\n",
    "\n",
    "# dl_bundle = prepare_jittor_dataloader(data_bundle, batch_size=16, shuffle=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "917eab81",
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastNLP import Trainer, Accuracy\n",
    "\n",
    "trainer = Trainer(\n",
    "    model=model,\n",
    "    driver='jittor',\n",
    "    device='gpu',                              # 'cpu', 'gpu', 'cuda'\n",
    "    n_epochs=10,\n",
    "    optimizers=optimizers,\n",
    "    train_dataloader=train_dataloader,         # dl_bundle['train'],\n",
    "    evaluate_dataloaders=evaluate_dataloader,  # dl_bundle['dev'],\n",
    "    metrics={'acc': Accuracy()}\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "f7c4ac5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7fbfbf; text-decoration-color: #7fbfbf\">[21:05:51] </span><span style=\"color: #000080; text-decoration-color: #000080\">INFO    </span> Running evaluator sanity check for <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span> batches.              <a href=\"file://../fastNLP/core/controllers/trainer.py\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">trainer.py</span></a><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">:</span><a href=\"file://../fastNLP/core/controllers/trainer.py#596\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">596</span></a>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[2;36m[21:05:51]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Running evaluator sanity check for \u001b[1;36m2\u001b[0m batches.              \u001b]8;id=69759;file://../fastNLP/core/controllers/trainer.py\u001b\\\u001b[2mtrainer.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=202322;file://../fastNLP/core/controllers/trainer.py#596\u001b\\\u001b[2m596\u001b[0m\u001b]8;;\u001b\\\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Compiling Operators(5/6) used: 8.31s eta: 1.66s 6/6) used: 9.33s eta:    0s \n",
      "\n",
      "Compiling Operators(31/31) used: 7.31s eta:    0s \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m1\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.61875</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">99</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.61875\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m99\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m2\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">112</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.7\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m112\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m3\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.725</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">116</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.725\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m116\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">4</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m4\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.74375</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">119</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.74375\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m119\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m5\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.75625</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">121</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.75625\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m121\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">6</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m6\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.75625</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">121</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.75625\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m121\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">7</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m7\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.73125</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">117</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.73125\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m117\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m8\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7625</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">122</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.7625\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m122\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">----------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">9</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "----------------------------- Eval. results on Epoch:\u001b[1;36m9\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.74375</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">119</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.74375\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m119\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">---------------------------- Eval. results on Epoch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">10</span>, Batch:<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0</span> -----------------------------\n",
       "</pre>\n"
      ],
      "text/plain": [
       "---------------------------- Eval. results on Epoch:\u001b[1;36m10\u001b[0m, Batch:\u001b[1;36m0\u001b[0m -----------------------------\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">{</span>\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"acc#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7625</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"total#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160</span>,\n",
       "  <span style=\"color: #000080; text-decoration-color: #000080; font-weight: bold\">\"correct#acc\"</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">122</span>\n",
       "<span style=\"font-weight: bold\">}</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m{\u001b[0m\n",
       "  \u001b[1;34m\"acc#acc\"\u001b[0m: \u001b[1;36m0.7625\u001b[0m,\n",
       "  \u001b[1;34m\"total#acc\"\u001b[0m: \u001b[1;36m160\u001b[0m,\n",
       "  \u001b[1;34m\"correct#acc\"\u001b[0m: \u001b[1;36m122\u001b[0m\n",
       "\u001b[1m}\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "trainer.run(num_eval_batch_per_dl=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3df5f425",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}