solution v2

.gitignore

@@ -1,149 +1,4 @@
-# ---> JupyterNotebooks
+.ipynb_checkpoints/
-# gitignore template for Jupyter Notebooks
+model/
-# website: http://jupyter.org/
-
-.ipynb_checkpoints
-*/.ipynb_checkpoints/*
-
-# IPython
-profile_default/
-ipython_config.py
-
-# Remove previous ipynb_checkpoints
-#   git rm -r .ipynb_checkpoints/
-
-# ---> Python
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
 geval
-
+processed_train.txt

run.ipynb

@@ -93,24 +93,11 @@
    "execution_count": 6,
    "id": "7a51f2b1",
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "ename": "NameError",
-     "evalue": "name 'SimpleBigramNeuralLanguageModel' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m/tmp/ipykernel_16179/3272155308.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mdevice\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'cuda'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mtrain_dataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBigrams\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'europarl.txt'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocab_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSimpleTrigramNeuralLanguageModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvocab_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membed_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataLoader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_dataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0moptimizer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mAdam\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/tmp/ipykernel_16179/1892442743.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, vocabulary_size, embedding_size)\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mclass\u001b[0m \u001b[0mSimpleTrigramNeuralLanguageModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModule\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocabulary_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membedding_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m         \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mSimpleBigramNeuralLanguageModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      7\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0membedding\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mEmbedding\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvocabulary_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0membedding_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinear\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0membedding_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvocabulary_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'SimpleBigramNeuralLanguageModel' is not defined"
-     ]
-    }
-   ],
    "source": [
     "from torch.utils.data import DataLoader\n",
     "\n",
-    "device = 'cuda'\n",
+    "device = 'cpu'\n",
     "train_dataset = Bigrams('europarl.txt', vocab_size)\n",
     "model = SimpleTrigramNeuralLanguageModel(vocab_size, embed_size).to(device)\n",
     "data = DataLoader(train_dataset, batch_size=2000)\n",
@@ -120,11 +107,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "474194ae",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0 tensor(10.0424, grad_fn=<NllLossBackward0>)\n",
+      "100 tensor(7.9016, grad_fn=<NllLossBackward0>)\n",
+      "200 tensor(7.1964, grad_fn=<NllLossBackward0>)\n",
+      "300 tensor(6.5661, grad_fn=<NllLossBackward0>)\n",
+      "400 tensor(6.4146, grad_fn=<NllLossBackward0>)\n",
+      "500 tensor(5.8718, grad_fn=<NllLossBackward0>)\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-8-06724a2e87a4>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      7\u001b[0m         \u001b[0my\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m         \u001b[0moptimizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 9\u001b[1;33m         \u001b[0moutputs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     10\u001b[0m         \u001b[0mloss\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcriterion\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mstep\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;36m100\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m   1108\u001b[0m         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks\n\u001b[0;32m   1109\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[1;32m-> 1110\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1111\u001b[0m         \u001b[1;31m# Do not call functions when jit is used\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1112\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m<ipython-input-2-4f6f391f0eb8>\u001b[0m in \u001b[0;36mforward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;32m     10\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m         \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0membedding\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m         \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     13\u001b[0m         \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msoftmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m   1108\u001b[0m         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks\n\u001b[0;32m   1109\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[1;32m-> 1110\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1111\u001b[0m         \u001b[1;31m# Do not call functions when jit is used\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1112\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\torch\\nn\\modules\\linear.py\u001b[0m in \u001b[0;36mforward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    101\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    102\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 103\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mF\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minput\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbias\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    105\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mextra_repr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
    "source": [
+    "step = 0\n",
+    "\n",
     "for epoch in range(1):\n",
     "    model.train()\n",
     "    for x, y in data:\n",
@@ -141,11 +158,19 @@
     "        \n",
     "torch.save(model.state_dict(), 'model/model1.bin')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "alpha-leonard",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -159,7 +184,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.9.2"
   }
  },
  "nbformat": 4,