From d82165f9ed2f94fe096cf95811088a9f9888f33d Mon Sep 17 00:00:00 2001 From: Emil Date: Sun, 5 Jul 2026 04:59:23 +0300 Subject: [PATCH] Practice linear regression. --- My_Experiments/pytorch.ipynb | 2 +- My_Experiments/pytorch3.ipynb | 1244 +++++++++++++++++++++++++++++---- 2 files changed, 1120 insertions(+), 126 deletions(-) diff --git a/My_Experiments/pytorch.ipynb b/My_Experiments/pytorch.ipynb index df197f3..dba0e77 100644 --- a/My_Experiments/pytorch.ipynb +++ b/My_Experiments/pytorch.ipynb @@ -133,7 +133,7 @@ ], "metadata": { "kernelspec": { - "display_name": ".venv (3.11.15.final.0)", + "display_name": ".venv (3.11.15)", "language": "python", "name": "python3" }, diff --git a/My_Experiments/pytorch3.ipynb b/My_Experiments/pytorch3.ipynb index d8237c2..e3735e0 100644 --- a/My_Experiments/pytorch3.ipynb +++ b/My_Experiments/pytorch3.ipynb @@ -10,7 +10,7 @@ }, { "cell_type": "code", - "execution_count": 58, + "execution_count": 105, "id": "3163fb75", "metadata": {}, "outputs": [], @@ -23,7 +23,7 @@ }, { "cell_type": "code", - "execution_count": 59, + "execution_count": 106, "id": "64a02514", "metadata": {}, "outputs": [], @@ -34,7 +34,7 @@ }, { "cell_type": "code", - "execution_count": 60, + "execution_count": 107, "id": "35200e59", "metadata": {}, "outputs": [ @@ -42,33 +42,33 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 0: Loss = 2051.0815\n", - "Epoch 400: Loss = 181.1680\n", - "Epoch 800: Loss = 106.3257\n", - "Epoch 1200: Loss = 62.4014\n", - "Epoch 1600: Loss = 36.6228\n", - "Epoch 2000: Loss = 21.4935\n", - "Epoch 2400: Loss = 12.6143\n", - "Epoch 2800: Loss = 7.4032\n", - "Epoch 3200: Loss = 4.3449\n", - "Epoch 3600: Loss = 2.5500\n", - "Epoch 4000: Loss = 1.4965\n", - "Epoch 4400: Loss = 0.8783\n", - "Epoch 4800: Loss = 0.5155\n", - "Epoch 5200: Loss = 0.3025\n", - "Epoch 5600: Loss = 0.1775\n", - "Epoch 6000: Loss = 0.1042\n", - "Epoch 6400: Loss = 0.0612\n", - "Epoch 6800: Loss = 0.0359\n", - "Epoch 7200: Loss = 0.0211\n", - "Epoch 7600: Loss = 0.0124\n", - "Epoch 8000: Loss = 0.0073\n", - "Epoch 8400: Loss = 0.0043\n", - "Epoch 8800: Loss = 0.0025\n", - "Epoch 9200: Loss = 0.0015\n", - "Epoch 9600: Loss = 0.0009\n", - "Epoch 10000: Loss = 0.0005\n", - "Epoch 10400: Loss = 0.0003\n", + "Epoch 0: Loss = 3445.2056\n", + "Epoch 400: Loss = 223.5457\n", + "Epoch 800: Loss = 131.1967\n", + "Epoch 1200: Loss = 76.9979\n", + "Epoch 1600: Loss = 45.1893\n", + "Epoch 2000: Loss = 26.5212\n", + "Epoch 2400: Loss = 15.5650\n", + "Epoch 2800: Loss = 9.1350\n", + "Epoch 3200: Loss = 5.3611\n", + "Epoch 3600: Loss = 3.1464\n", + "Epoch 4000: Loss = 1.8466\n", + "Epoch 4400: Loss = 1.0837\n", + "Epoch 4800: Loss = 0.6360\n", + "Epoch 5200: Loss = 0.3733\n", + "Epoch 5600: Loss = 0.2191\n", + "Epoch 6000: Loss = 0.1286\n", + "Epoch 6400: Loss = 0.0755\n", + "Epoch 6800: Loss = 0.0443\n", + "Epoch 7200: Loss = 0.0260\n", + "Epoch 7600: Loss = 0.0153\n", + "Epoch 8000: Loss = 0.0090\n", + "Epoch 8400: Loss = 0.0053\n", + "Epoch 8800: Loss = 0.0031\n", + "Epoch 9200: Loss = 0.0018\n", + "Epoch 9600: Loss = 0.0011\n", + "Epoch 10000: Loss = 0.0006\n", + "Epoch 10400: Loss = 0.0004\n", "Epoch 10800: Loss = 0.0002\n", "Epoch 11200: Loss = 0.0001\n", "Epoch 11600: Loss = 0.0001\n", @@ -117,7 +117,7 @@ }, { "cell_type": "code", - "execution_count": 61, + "execution_count": 108, "id": "be1eb1bd", "metadata": {}, "outputs": [ @@ -153,7 +153,7 @@ }, { "cell_type": "code", - "execution_count": 62, + "execution_count": 109, "id": "fa3c1e81", "metadata": {}, "outputs": [], @@ -168,7 +168,7 @@ }, { "cell_type": "code", - "execution_count": 63, + "execution_count": 110, "id": "8860a027", "metadata": {}, "outputs": [], @@ -178,7 +178,7 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 111, "id": "b1213a8a", "metadata": {}, "outputs": [], @@ -189,7 +189,7 @@ }, { "cell_type": "code", - "execution_count": 65, + "execution_count": 112, "id": "27d203c4", "metadata": {}, "outputs": [ @@ -197,11 +197,11 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 0: loss = 5002.43408203125\n", - "Epoch 400: loss = 189.92440795898438\n", - "Epoch 800: loss = 111.46468353271484\n", - "Epoch 1200: loss = 65.41755676269531\n", - "Epoch 1600: loss = 38.39296340942383\n" + "Epoch 0: loss = 6451.947265625\n", + "Epoch 400: loss = 210.3446502685547\n", + "Epoch 800: loss = 123.4490966796875\n", + "Epoch 1200: loss = 72.45099639892578\n", + "Epoch 1600: loss = 42.52076721191406\n" ] } ], @@ -223,7 +223,7 @@ }, { "cell_type": "code", - "execution_count": 66, + "execution_count": 113, "id": "024b4276", "metadata": {}, "outputs": [ @@ -233,9 +233,9 @@ "text": [ "\n", "--- Результаты обучения ---\n", - "Предсказание для 100°C: 231.20°F\n", - "Итоговый вес W: 2.0742\n", - "Итоговое смещение B: 23.7783\n" + "Предсказание для 100°C: 232.21°F\n", + "Итоговый вес W: 2.0886\n", + "Итоговое смещение B: 23.3475\n" ] } ], @@ -253,7 +253,7 @@ }, { "cell_type": "code", - "execution_count": 67, + "execution_count": 114, "id": "df8942cd", "metadata": {}, "outputs": [ @@ -268,11 +268,11 @@ ")\n", "\n", "--- Starting Training Simulation ---\n", - "Epoch [1/5], Loss: 2.3632\n", - "Epoch [2/5], Loss: 2.0220\n", - "Epoch [3/5], Loss: 1.7251\n", - "Epoch [4/5], Loss: 1.4678\n", - "Epoch [5/5], Loss: 1.2423\n", + "Epoch [1/5], Loss: 2.2789\n", + "Epoch [2/5], Loss: 1.9576\n", + "Epoch [3/5], Loss: 1.6794\n", + "Epoch [4/5], Loss: 1.4376\n", + "Epoch [5/5], Loss: 1.2265\n", "\n", "MLP Example successfully defined and simulated training steps.\n" ] @@ -344,7 +344,7 @@ }, { "cell_type": "code", - "execution_count": 68, + "execution_count": 115, "id": "98166324", "metadata": {}, "outputs": [], @@ -356,44 +356,21 @@ }, { "cell_type": "code", - "execution_count": 69, + "execution_count": 116, "id": "ef1351a0", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[]" - ] - }, - "execution_count": 69, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "w = 0.7\n", "b = 0.3\n", "\n", - "X = torch.arange(10, 100, 5).unsqueeze(dim=1)\n", - "y = X * w + b\n", - "\n", - "plt.plot(X, y)" + "X = torch.arange(0, 1, 0.02).unsqueeze(1)\n", + "y = w * X + b" ] }, { "cell_type": "code", - "execution_count": 70, + "execution_count": 117, "id": "e452da62", "metadata": {}, "outputs": [], @@ -405,76 +382,1093 @@ }, { "cell_type": "code", - "execution_count": 71, + "execution_count": 118, "id": "b9f7783b", "metadata": {}, "outputs": [], "source": [ - "\n", - "\n", "class Model(nn.Module):\n", " def __init__(self):\n", " super().__init__()\n", - " self.w = nn.Parameter(torch.randn(1))\n", - " self.b = nn.Parameter(torch.randn(1))\n", + " self.linear = nn.Linear(1, 1)\n", " def forward(self, x):\n", - " return x * self.w + self.b" + " return self.linear(x)\n" ] }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 133, "id": "90874c3d", "metadata": {}, - "outputs": [ - { - "ename": "RuntimeError", - "evalue": "Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.", - "output_type": "error", - "traceback": [ - "\u001b[31m---------------------------------------------------------------------------\u001b[39m", - "\u001b[31mRuntimeError\u001b[39m Traceback (most recent call last)", - "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[78]\u001b[39m\u001b[32m, line 17\u001b[39m\n\u001b[32m 13\u001b[39m optimizer.step()\n\u001b[32m 14\u001b[39m epochs.append(epoch)\n\u001b[32m 15\u001b[39m losses.append(loss.item())\n\u001b[32m 16\u001b[39m plt.plot(X, y)\n\u001b[32m---> \u001b[39m\u001b[32m17\u001b[39m plt.plot(X_train, y_pred)\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/pyplot.py:4043\u001b[39m, in \u001b[36mplot\u001b[39m\u001b[34m(scalex, scaley, data, *args, **kwargs)\u001b[39m\n\u001b[32m 4035\u001b[39m \u001b[38;5;129m@_copy_docstring_and_deprecators\u001b[39m(Axes.plot)\n\u001b[32m 4036\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mplot\u001b[39m(\n\u001b[32m 4037\u001b[39m *args: \u001b[38;5;28mfloat\u001b[39m | ArrayLike | \u001b[38;5;28mstr\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 4041\u001b[39m **kwargs,\n\u001b[32m 4042\u001b[39m ) -> \u001b[38;5;28mlist\u001b[39m[Line2D]:\n\u001b[32m-> \u001b[39m\u001b[32m4043\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[30;43mgca\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43m)\u001b[39;49m\u001b[30;43m.\u001b[39;49m\u001b[30;43mplot\u001b[39;49m\u001b[30;43m(\u001b[39;49m\n\u001b[32m 4044\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43margs\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 4045\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mscalex\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mscalex\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 4046\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mscaley\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mscaley\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 4047\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43m{\u001b[39;49m\u001b[30;43m\"\u001b[39;49m\u001b[30;43mdata\u001b[39;49m\u001b[30;43m\"\u001b[39;49m\u001b[30;43m:\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mdata\u001b[39;49m\u001b[30;43m}\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43;01mif\u001b[39;49;00m\u001b[30;43m \u001b[39;49m\u001b[30;43mdata\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43;01mis\u001b[39;49;00m\u001b[30;43m \u001b[39;49m\u001b[30;43;01mnot\u001b[39;49;00m\u001b[30;43m \u001b[39;49m\u001b[30;43;01mNone\u001b[39;49;00m\u001b[30;43m \u001b[39;49m\u001b[30;43;01melse\u001b[39;49;00m\u001b[30;43m \u001b[39;49m\u001b[30;43m{\u001b[39;49m\u001b[30;43m}\u001b[39;49m\u001b[30;43m)\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 4048\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43mkwargs\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 4049\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m)\u001b[39;49m\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/axes/_axes.py:1792\u001b[39m, in \u001b[36mAxes.plot\u001b[39m\u001b[34m(self, scalex, scaley, data, *args, **kwargs)\u001b[39m\n\u001b[32m 1549\u001b[39m \u001b[38;5;250m\u001b[39m\u001b[33;03m\"\"\"\u001b[39;00m\n\u001b[32m 1550\u001b[39m \u001b[33;03mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[32m 1551\u001b[39m \n\u001b[32m (...)\u001b[39m\u001b[32m 1789\u001b[39m \u001b[33;03m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[32m 1790\u001b[39m \u001b[33;03m\"\"\"\u001b[39;00m\n\u001b[32m 1791\u001b[39m kwargs = cbook.normalize_kwargs(kwargs, mlines.Line2D)\n\u001b[32m-> \u001b[39m\u001b[32m1792\u001b[39m lines = [*\u001b[38;5;28mself\u001b[39m._get_lines(\u001b[38;5;28mself\u001b[39m, *args, data=data, **kwargs)]\n\u001b[32m 1793\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m lines:\n\u001b[32m 1794\u001b[39m \u001b[38;5;28mself\u001b[39m.add_line(line)\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/axes/_base.py:331\u001b[39m, in \u001b[36m_process_plot_var_args.__call__\u001b[39m\u001b[34m(self, axes, data, return_kwargs, *args, **kwargs)\u001b[39m\n\u001b[32m 329\u001b[39m this += args[\u001b[32m0\u001b[39m],\n\u001b[32m 330\u001b[39m args = args[\u001b[32m1\u001b[39m:]\n\u001b[32m--> \u001b[39m\u001b[32m331\u001b[39m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[30;43mself\u001b[39;49m\u001b[30;43m.\u001b[39;49m\u001b[30;43m_plot_args\u001b[39;49m\u001b[30;43m(\u001b[39;49m\n\u001b[32m 332\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43maxes\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mthis\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mkwargs\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mambiguous_fmt_datakey\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mambiguous_fmt_datakey\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 333\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mreturn_kwargs\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mreturn_kwargs\u001b[39;49m\n\u001b[32m 334\u001b[39m \u001b[30;43m\u001b[39;49m\u001b[30;43m)\u001b[39;49m\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/axes/_base.py:499\u001b[39m, in \u001b[36m_process_plot_var_args._plot_args\u001b[39m\u001b[34m(self, axes, tup, kwargs, return_kwargs, ambiguous_fmt_datakey)\u001b[39m\n\u001b[32m 497\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(xy) == \u001b[32m2\u001b[39m:\n\u001b[32m 498\u001b[39m x = _check_1d(xy[\u001b[32m0\u001b[39m])\n\u001b[32m--> \u001b[39m\u001b[32m499\u001b[39m y = \u001b[30;43m_check_1d\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43mxy\u001b[39;49m\u001b[30;43m[\u001b[39;49m\u001b[30;43m1\u001b[39;49m\u001b[30;43m]\u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 500\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 501\u001b[39m x, y = index_of(xy[-\u001b[32m1\u001b[39m])\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/cbook.py:1413\u001b[39m, in \u001b[36m_check_1d\u001b[39m\u001b[34m(x)\u001b[39m\n\u001b[32m 1411\u001b[39m \u001b[38;5;250m\u001b[39m\u001b[33;03m\"\"\"Convert scalars to 1D arrays; pass-through arrays as is.\"\"\"\u001b[39;00m\n\u001b[32m 1412\u001b[39m \u001b[38;5;66;03m# Unpack in case of e.g. Pandas or xarray object\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1413\u001b[39m x = \u001b[30;43m_unpack_to_numpy\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43mx\u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 1414\u001b[39m \u001b[38;5;66;03m# plot requires `shape` and `ndim`. If passed an\u001b[39;00m\n\u001b[32m 1415\u001b[39m \u001b[38;5;66;03m# object that doesn't provide them, then force to numpy array.\u001b[39;00m\n\u001b[32m 1416\u001b[39m \u001b[38;5;66;03m# Note this will strip unit information.\u001b[39;00m\n\u001b[32m 1417\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(x, \u001b[33m'\u001b[39m\u001b[33mshape\u001b[39m\u001b[33m'\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[32m 1418\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(x, \u001b[33m'\u001b[39m\u001b[33mndim\u001b[39m\u001b[33m'\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[32m 1419\u001b[39m \u001b[38;5;28mlen\u001b[39m(x.shape) < \u001b[32m1\u001b[39m):\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/matplotlib/cbook.py:2517\u001b[39m, in \u001b[36m_unpack_to_numpy\u001b[39m\u001b[34m(x)\u001b[39m\n\u001b[32m 2508\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m xtmp\n\u001b[32m 2509\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m _is_torch_array(x) \\\n\u001b[32m 2510\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m _is_jax_array(x) \\\n\u001b[32m 2511\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m _is_tensorflow_array(x) \\\n\u001b[32m (...)\u001b[39m\u001b[32m 2515\u001b[39m \u001b[38;5;66;03m# https://numpy.org/devdocs/user/basics.interoperability.html#using-arbitrary-objects-in-numpy\u001b[39;00m\n\u001b[32m 2516\u001b[39m \u001b[38;5;66;03m# therefore, let arrays do better if they can\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m2517\u001b[39m xtmp = np.asarray(x)\n\u001b[32m 2519\u001b[39m \u001b[38;5;66;03m# In case np.asarray method does not return a numpy array in future\u001b[39;00m\n\u001b[32m 2520\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(xtmp, np.ndarray):\n", - "\u001b[36mFile \u001b[39m\u001b[32m~/Desktop/Karpathy_ZtH_Learning/.venv/lib/python3.11/site-packages/torch/_tensor.py:1253\u001b[39m, in \u001b[36mTensor.__array__\u001b[39m\u001b[34m(self, dtype)\u001b[39m\n\u001b[32m 1251\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m handle_torch_function(Tensor.__array__, (\u001b[38;5;28mself\u001b[39m,), \u001b[38;5;28mself\u001b[39m, dtype=dtype)\n\u001b[32m 1252\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m dtype \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m1253\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[30;43mself\u001b[39;49m\u001b[30;43m.\u001b[39;49m\u001b[30;43mnumpy\u001b[39;49m\u001b[30;43m(\u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 1254\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 1255\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m.numpy().astype(dtype, copy=\u001b[38;5;28;01mFalse\u001b[39;00m)\n", - "\u001b[31mRuntimeError\u001b[39m: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead." - ] - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAh8AAAGdCAYAAACyzRGfAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlcelbwAAAAlwSFlzAAAPYQAAD2EBqD+naQAAQetJREFUeJzt3Xd0VAX+///npE16QhIgQEIPLYEUAyrFLtIERGnxs7vuWlalKVbWtaCu6CIqCLrr+vmsNaCAKCgqoqI0UUmB0IuU0EOZ9GTK/f3hb/PdCGgCYe5M5vU4J+cw996ZeXFuknnlvu/csRiGYSAiIiLiJn5mBxARERHfovIhIiIibqXyISIiIm6l8iEiIiJupfIhIiIibqXyISIiIm6l8iEiIiJupfIhIiIibhVgdoAzcblcHDx4kIiICCwWi9lxREREpA4Mw6CkpISWLVvi53f24xseWT4OHjxIYmKi2TFERETkHOzfv5+EhISzrvfI8hEREQH8HD4yMtLkNCIiIlIXxcXFJCYm1ryOn41Hlo//jFoiIyNVPkRERLzMb50yoRNORURExK1UPkRERMStVD5ERETErVQ+RERExK1UPkRERMStVD5ERETErVQ+RERExK1UPkRERMStVD5ERETErVQ+RERExK1UPkRERMStVD5ERETErVQ+REREfMj6vSeYumQThmGYlsEjP9VWREREGpbLZfDayt1M/3wbTpdBSssobrwowZQsKh8iIiKN3PHSKu6bn8+KbccAGJbWkutS4k3Lo/IhIiLSiK3bfZyJ83I5UlyFNcCPJ4clMyozEYvFYlomlQ8REZFGyOkyeOXrnby4fDsuAzo2C2dOVgad4yPMjqbyISIi0tgcK6ni3vfyWLWzCIAbMxJ4angyoUGe8bLvGSlERESkQazZWcSk9/I4VlJFSKA/Tw1P4SaTTiw9G5UPERGRRsDpMpj55Q5e/moHhgGdm0cw5+Z0OjYzf8zySyofIiIiXu5IcSWT5uXy3e4TAIzpmcjj1ycTEuRvcrIzU/kQERHxYt9uP8a97+VxvKyasCB/nhnRnWFprcyO9atUPkRERLyQw+nixeXbeWXFLgwDuraIZE5WOu2bhpsd7TepfIiIiHiZQ7YKJs7N5Yc9JwH43SVteGRwV4IDPXPM8ksqHyIiIl7k661Hmfx+HifL7URYA3j2xh4M7tHC7Fj1ovIhIiLiBexOF89/vo1/frsbgO6topidlU6b2DCTk9WfyoeIiIiHKzxZzoS5ueTuOwXALb3bMmVQF6wB3jFm+SWVDxEREQ+2bNNhHliwAVuFncjgAKaPTOW6ZPM+FK4hqHyIiIh4oGqHi2mfbuHfq/cAkJYYzctj00mMCTU3WANQ+RAREfEw+46XM35uDhsKbQDc3q8dD1zXhaAAP5OTNQyVDxEREQ/y6cZDPLhgAyVVDqJDA5kxMpWruzY3O1aDUvkQERHxAJV2J88s3cJba/cCkNmmCbPGptMyOsTkZA1P5UNERMRkPxWVMT47h00HiwG4+4oO3HttJwL9G8eY5ZdUPkREREy0OP8gUxZuoKzaSUxYEC+OTuPyTk3NjnVBqXyIiIiYoNLuZOqSzcz9fh8AvdrFMGtMOvFRwSYnu/BUPkRERNxs59FSxmfnsPVwCRYLTLiyIxOvTiKgkY5ZfknlQ0RExI0+yCnkrx8WUF7tJC7cykuj0+ibFGd2LLdS+RAREXGD8moHj320iQXrCwHo0zGWF0en0Syi8Y9ZfknlQ0RE5ALbfqSEce/msONoKX4WuOeaToy7siP+fhazo5lC5UNEROQCMQyD+T8W8tjiAirtLppFWJk1Np1L2seaHc1UKh8iIiIXQFmVg0cWbeTDvIMAXNapKS+MSiUu3GpyMvOpfIiIiDSwzQeLGZ+dw+6iMvz9LNzXvxN3XtYBPx8ds/ySyoeIiEgDMQyD7O/3MXXJZqodLlpEBTNrbDo928aYHc2jqHyIiIg0gJJKOw9/sJFPNhwC4KouzZgxMpUmYUEmJ/M8Kh8iIiLnqeCAjXHZOew9Xk6An4WHBnTh1r7tNGY5C5UPERGRc2QYBm+t3cvfPtlCtdNFq+gQXs5KJ6N1E7OjeTSVDxERkXNgq7Dz0IINfLbpMAD9uzVn+k2pRIUGmpzM89W7fLhcLt555x2WLl2KxWIhKyuL66+/vtY227ZtY+bMmezdu5ekpCTuu+8+EhMTGyy0iIiImfL2n2J8dg6FJysI9Lfwl0FduaV3WywWjVnqol6fYON0Ohk6dChPPPEE11xzDWPGjOGNN95g8eLFNdts376dXr16UVZWxi233MJPP/1Er169OHz4cIOHFxERcSfDMHh95W5G/mMNhScraB0TysK7evPHPu1UPOrBYhiGUdeNX3nlFe6//342b95M27Zta5aXlpYSHh4OwP/8z/+wY8cO1q1bB4DdbicpKYmRI0cyffr0Oj1PcXExUVFR2Gw2IiMj6/HfERERuTBOlVdz//x8lm85CsCg7vE8e2MPIoM1ZvmPur5+1+vIxxtvvMHQoUNrFQ+gpngALFu2jGHDhtXcDgwMZMiQISxbtqw+TyUiIuIx1u89waCZK1m+5ShBAX48NTyFOVkZKh7nqF7nfBQUFDBy5EheeOEFvv76a5o1a8ZNN93EwIEDASgvL+fYsWMkJCTUul9CQgJ79uw56+NWVVVRVVVVc7u4uLg+sURERC4Il8vgtZW7mf75Npwug3ZxYczOSie5ZZTZ0bxanY98GIZBZWUlf//739m6dSu33XYbHTt2ZMSIEcycOROA6upqAEJCQmrdNzQ0tGbdmUybNo2oqKiaL52cKiIiZjteWsWf3vyBZz/ditNlMDS1JUsm9FXxaAB1PvJhsViIjo6mY8eOvPbaawAMGzaM4uJipk+fzqRJkwgPDycgIIATJ07Uuu/x48dp0uTs73meMmUKkydPrrldXFysAiIiIqZZt/s4E+flcqS4CmuAH08MTWZMz0SdVNpA6jV2ycjIIC4urtay1q1bc/z4cQzDICAggJSUFHJycmptk5OTQ1pa2lkf12q1YrXqU/5ERMRcTpfBK1/v5MXl23EZ0KFpGHNuzqBLvN780JDqdcLprbfeyvLly9m/fz8AlZWVzJ07l8suu6ymDd5yyy3Mnz+fnTt3AvDjjz+ybNkybrnlloZNLiIi0oCOlVTxh//7nhlf/Fw8RmS0YvH4vioeF0C9jnyMHTuW3NxckpOTSUlJYffu3bRt25Z33nmnZpvx48eTk5NDamoqXbp0YfPmzYwbN45Ro0Y1eHgREZGGsGZnEZPey+NYSRUhgf48OSyZkZka/18o9brOx38cPnyYnTt30qJFC9q3b3/GGdjevXvZt28fHTp0oGXLlvV6fF3nQ0RE3MHpMpj55Q5e/moHhgGdmoczJyuDpOYRZkfzSnV9/T6nz3aJj48nPj7+V7dp06YNbdq0OZeHFxERueCOFFcyaV4u3+3++U0SozMTeWJoMiFB/iYna/z0wXIiIuJzvt1+jHvfy+N4WTWhQf48c0N3hqe3MjuWz1D5EBERn+Fwunhx+XZeWbELw4CuLSKZk5VO+6bhv31naTAqHyIi4hMO2SqYODeXH/acBODmi1vz6JBuBAdqzOJuKh8iItLofb31KJPfz+NkuZ1wawDP3tidIT3q92YIaTgqHyIi0mjZnS6e/3wb//x2NwAprSKZPTaDtnFhJifzbSofIiLSKBWeLGfC3Fxy950C4JbebZkyqAvWAI1ZzKbyISIijc6yTYd5YMEGbBV2IoIDmH5TDwaktDA7lvz/VD5ERKTRqHa4mPbpFv69eg8AqQlRzM7KIDEm1NxgUovKh4iINAr7jpczfm4OGwptANzWtx0PDuhCUEC9PsZM3EDlQ0REvN7SjYd4aMEGSqocRIUEMmNkKtd0a252LDkLlQ8REfFalXYnf/tkC29/txeAjNbRvJyVQavoEJOTya9R+RAREa/0U1EZ47Nz2HSwGIA7L+/Aff07EeivMYunU/kQERGvszj/IFMWbqCs2klMWBAzRqVyZedmZseSOlL5EBERr1FpdzJ1yWbmfr8PgF5tY5g1Np34qGCTk0l9qHyIiIhX2Hm0lPHZOWw9XILFAuOu6Mg91yQRoDGL11H5EBERj/dBTiF//bCA8monceFBvDg6jX5JTc2OJedI5UNERDxWebWDxz/axPz1hQBc2j6WmWPSaBapMYs3U/kQERGPtP1ICePezWHH0VL8LDDp6k6Mv6oj/n4Ws6PJeVL5EBERj2IYBvN/LOSxxQVU2l00jbAya0w6l3aINTuaNBCVDxER8RhlVQ4eWbSRD/MOAtAvKY4XR6cRF241OZk0JJUPERHxCJsPFjM+O4fdRWX4WeC+/p256/IO+GnM0uiofIiIiKkMwyD7+31MXbKZaoeL+MhgZo1Np1e7GLOjyQWi8iEiIqYpqbQz5YONfLzhEABXdm7KjFFpxIQFmZxMLiSVDxERMUXBARvjsnPYe7ycAD8LD1zXmdv7tdeYxQeofIiIiFsZhsFba/fyt0+2UO100So6hFlj07moTROzo4mbqHyIiIjb2CrsPLRgA59tOgzANV2b8/zIHkSHasziS1Q+RETELfL2n2J8dg6FJysI9Lfw8MCu/KlPWywWjVl8jcqHiIhcUIZh8L+rfuK5z7ZidxokxoQwe2wGqYnRZkcTk6h8iIjIBXOqvJr7529g+ZYjAAxMiefZG3sQFRJocjIxk8qHiIhcEOv3nmRCdg4HbZUE+fvx1yFd+d0lbTRmEZUPERFpWC6XwWsrdzP98204XQZtY0OZnZVBSqsos6OJh1D5EBGRBnOirJrJ7+exYtsxAK5PbckzN6QQEawxi/w/Kh8iItIgvv/pBBPn5nK4uBJrgB+PX5/M2F6JGrPIaVQ+RETkvLhcBq+s2MkLX2zHZUD7pmHMycqga4tIs6OJh1L5EBGRc3aspIrJ7+exckcRADekt+Lp4SmEWfXyImen7w4RETkna3YVMWleHsdKqggO9OPJYSmMvChBYxb5TSofIiJSL06Xwctf7WDWlztwGZDULJw5N2fQqXmE2dHES6h8iIhInR0trmTSvDzW7j4OwKjMBKYOTSEkyN/kZOJNVD5ERKROVu44xr3v5VFUWk1okD9PD09hREaC2bHEC6l8iIjIr3I4Xby0fAdzVuzEMKBLfASzszLo2Czc7GjipVQ+RETkrA7ZKpg0N4/v95wAIOvi1jw2pBvBgRqzyLlT+RARkTP6eutRJr+fx8lyO+HWAJ4Z0Z2hqS3NjiWNgMqHiIjUYne6eP7zbfzz290AJLeMZE5WBm3jwkxOJo2FyoeIiNQ4cKqCCdk55Ow7BcAfLm3DlEFdNWaRBlWv8rFnzx527txZa1lgYCCXX375advu3buXffv20bFjR1q0aHF+KUVE5IL7YvMR7p+fj63CTkRwAH+/sQcDu+v3tzS8epWPd955h+nTp9OzZ8+aZeHh4bXKh9Pp5E9/+hMLFiygS5cubN68mbvvvpsZM2Y0XGoREWkw1Q4Xz322lf9d9RMAqQlRzM7KIDEm1ORk0ljVe+zStWtXli9fftb1s2fPZvHixeTn59OxY0d+/PFH+vTpw8UXX8yoUaPOK6yIiDSs/SfKGZ+dQ36hDYBb+7bjoQFdCArwMzmZNGb1/u6qrq5m3bp15OfnU1lZedr6N954g1GjRtGxY0cAMjMz6d+/P2+88cZ5hxURkYbzWcEhBs1aSX6hjaiQQP71+0weHdJNxUMuuHp/hxUUFHD33XczYsQI4uPjef3112vWORwOCgoKyMjIqHWfjIwM8vLyzvqYVVVVFBcX1/oSEZELo8rh5PGPCrjznRxKKh1ktI7mk4l9ubZbc7OjiY+o19jl0ksvZc+ePbRs+fP7vF999VXuuOMOunTpQt++fSktLcXhcBATE1PrfrGxsZw8efKsjztt2jSmTp16DvFFRKQ+9hSVMX5uDgUHfv4j78+Xt+f+/p0J9NfRDnGfen23XX311TXFA+Cuu+6ia9euLFy4EICgoCAAKioqat2vvLy8Zt2ZTJkyBZvNVvO1f//++sQSEZE6WJJ/kCEvr6LgQDFNQgP59y09mTKwq4qHuN15X+cjLi6OQ4cOARAaGkrTpk0pLCystU1hYSFt27Y962NYrVasVuv5RhERkTOotDt58uPNZK/bB0CvtjHMHJtGi6gQk5OJr6pX3bXZbLVuHz58mNzcXFJTU2uW9e/fn48++qjmtt1u5+OPP6Z///7nGVVEROpr17FShs9ZTfa6fVgsMP7KjmTffrGKh5jKYhiGUdeNe/XqxYABA0hPT6eoqIgZM2bg5+fHmjVriI6OBmDbtm306tWL4cOHM2TIEN59913WrVtHbm4u8fHxdXqe4uJioqKisNlsREZGntN/TETE1y3KLeSRRQWUVzuJCw/ixdFp9EtqanYsacTq+vpdryMfX375JREREbz77rusXLmS8ePHk5ubW1M8ADp37sy6desIDQ3ljTfeoG3btqxbt67OxUNERM5PRbWTBxfkc+97+ZRXO7m0fSxLJ/ZT8RCPUa8jH+6iIx8iIudmx5ESxmXnsP1IKRYLTLo6iQlXJeHvZzE7mviAur5+64PlREQaAcMwmL++kMc+KqDS7qJphJWZY9Lo3SHO7Ggip1H5EBHxcmVVDh79sIAPcg8A0C8pjhdHpxEXrncRimdS+RAR8WJbDhUzPjuHXcfK8LPAff07c9flHfDTmEU8mMqHiIgXMgyDud/vZ+qSTVQ5XMRHBjNrbDq92sX89p1FTKbyISLiZUoq7fxlUQFL8g8CcEXnprwwKo2YsLNfSVrEk6h8iIh4kYIDNsZn57DneDn+fhYevK4zt/drrzGLeBWVDxERL2AYBu98t5enPt5CtdNFq+gQZo1N56I2TcyOJlJvKh8iIh6uuNLOwws3sHTjYQCu6dqc50f2IDpUYxbxTiofIiIeLH//KcbPzWH/iQoC/S08PLArf+rTFotFYxbxXiofIiIeyDAM/r16D9M+3YLdaZDQJIQ5WRmkJkabHU3kvKl8iIh4mFPl1TywYANfbD4CwIDkeJ67qQdRIYEmJxNpGCofIiIeJGffSSZk53LgVAVB/n78dUhXfndJG41ZpFFR+RAR8QAul8Hrq3bz98+24XAZtIkNZU5WBimtosyOJtLgVD5EREx2oqya++fn89XWowAM6dGCaSO6ExGsMYs0TiofIiIm+mHPCSbOzeWQrZKgAD+euD6Zsb0SNWaRRk3lQ0TEBC6Xwavf7OKFL7bjdBm0jwtjzs0ZdG0RaXY0kQtO5UNExM2KSquY/H4+324/BsAN6a14engKYVb9ShbfoO90ERE3WrvrOJPm5XK0pIrgQD+eHJrCyMwEjVnEp6h8iIi4gdNlMPurncz8cjsuA5KahTM7K4PO8RFmRxNxO5UPEZEL7GhJJffMy2PNruMAjLwoganDkgkN0q9g8U36zhcRuYBW7SjinvdyKSqtJjTIn6eHpzAiI8HsWCKmUvkQEbkAHE4XM7/cweyvd2IY0CU+gtlZGXRsFm52NBHTqXyIiDSww7ZKJs7L5fufTgAwtldrHr++G8GB/iYnE/EMKh8iIg1oxbajTH4/nxNl1YQF+TPtxh4MTW1pdiwRj6LyISLSAOxOFzOWbecf3+wCILllJLOzMmgXF2ZyMhHPo/IhInKeDpyqYOLcXNbvPQnA7y9tw18GddWYReQsVD5ERM7D8s1HuH9BPqfK7UQEB/D3G3swsHsLs2OJeDSVDxGRc1DtcPH3z7by+qqfAEhNiOLlsRm0jg01OZmI51P5EBGpp/0nyhk/N5f8/acA+FOfdjw8sAtBAX7mBhPxEiofIiL18FnBIR5YsIGSSgeRwQE8PzKV/snxZscS8SoqHyIidVDlcPLMJ1t4c+1eANJbR/Py2HQSmmjMIlJfKh8iIr9hT1EZ4+fmUHCgGIA/X96e+/t3JtBfYxaRc6HyISLyKz7ecJCHF26ktMpBk9BAXhiVxpVdmpkdS8SrqXyIiJxBpd3JUx9v5t11+wDo2bYJs8am0yIqxORkIt5P5UNE5Bd2HStl3Ls5bD1cgsUCd1/RgXuv6USAxiwiDULlQ0Tkv3yYe4C/LNpIebWT2LAgXhydxmWdmpodS6RRUfkQEQEqqp08sXgT7/24H4BL2scwa0w6zSKDTU4m0viofIiIz9txpIRx2TlsP1KKxQITr0pi4tVJ+PtZzI4m0iipfIiIT5v/434e+2gTFXYnTSOszBydRu+OcWbHEmnUVD5ExCeVVTl49KMCPsg5AEC/pDheGJVG0wiryclEGj+VDxHxOVsPFzPu3Rx2HSvDzwKTr+3E3Vd0xE9jFhG3UPkQEZ9hGAbzftjPE4s3UeVw0TzSyqwx6VzcPtbsaCI+ReVDRHxCaZWDv3ywkcX5BwG4onNTZoxMJTZcYxYRd1P5EJFGr+CAjfHZOew5Xo6/n4UHruvMHf3aa8wiYhKVDxFptAzD4J3v9vLUJ1uodrhoGRXMy1npXNQmxuxoIj7tnK8V/Nlnn5GZmclDDz102rr169eTlZVFnz59uOWWW9i2bdt5hRQRqa/iSjvjsnN49KNNVDtcXNO1GUsn9VPxEPEA51Q+Dh06xB133EFJSQm7du2qtW7jxo3069ePuLg4nnjiCZxOJ71792b//v0NElhE5LdsKDzF4FkrWbrxMIH+Fv46uCv/+n0m0aFBZkcTEcBiGIZRnzu4XC6uvfZahg0bxrJlywgODmbBggU160eNGsXhw4f59ttva7bv3LkzgwYNYubMmXV6juLiYqKiorDZbERGRtYnnoj4MMMw+PfqPUz7dAt2p0FCkxBmZ2WQlhhtdjQRn1DX1+96H/mYNm0agYGBTJgw4Yzrv/zySwYPHvz/nsDPj0GDBvHll1/W96lEROrMVm7nz2+v58mPN2N3GgxIjueTif1UPEQ8UL1OOF2zZg2zZ88mJycHi+X0s8TLyso4ceIELVu2rLW8ZcuW7Nu376yPW1VVRVVVVc3t4uLi+sQSER+Xs+8kE7JzOXCqgiB/Px4Z3JXfX9rmjL+nRMR8dS4fJ0+eJCsri1dffZUWLVqccRu73Q6A1Vr7ffMhISE1685k2rRpTJ06ta5RREQAcLkMXl+1m79/tg2Hy6BNbCizx2bQPSHK7Ggi8ivqPHb55ptvOHToEE8//TSZmZlkZmayatUqvvrqKzIzMzl06BAREREEBgZy/PjxWvctKioiNvbsVxCcMmUKNput5ksnp4rIbzlZVs1tb/3IM0u34nAZDO7Rgo8n9FXxEPECdT7yccUVV7B69epay+69916CgoJ47rnniI2Nxd/fn9TUVH744Qfuuuuumu3WrVtHRkbGWR/barWedrRERORsfthzgolzczlkqyQowI/Hr+9GVq/WGrOIeIk6l4/o6GgyMzNrLYuKiiI4OLjW8ttuu40HHniAe++9l+7du/PNN9/w1VdfsXDhwoZLLSI+yeUyePWbXbzwxXacLoP2cWHMzsqgW0u9K07EmzT4FU7vuOMONm/eTGZmJgkJCRw4cIBHH32UoUOHNvRTiYgPKSqtYvL7+Xy7/RgAw9Na8vQN3Qm36kLNIt6m3tf5+G87d+7Ez8+P9u3bn7buxIkTHDhwgNatWxMVVb8ZrK7zISL/7bvdx5k4N5ejJVUEB/rx5NAURmYmaMwi4mHq+vp9Xn8ydOzY8azrYmJiiInRZYxF5Nw5XQazv9rJzC+34zKgY7Nw5mRl0Dk+wuxoInIedLxSRDzS0ZJK7n0vj9U7f3733E0XJfDksGRCg/RrS8Tb6adYRDzOqh1F3PNeHkWlVYQE+vO3G1IYkZFgdiwRaSAqHyLiMRxOFzO/3MHsr3diGNAlPoLZWRl0bBZudjQRaUAqHyLiEQ7bKpk4L5fvfzoBwNheiTx+fTLBgf4mJxORhqbyISKmW7HtKJPfz+dEWTVhQf48M6I7w9JamR1LRC4QlQ8RMY3d6eKFL7bz6opdAHRrEcmcmzNoFxdmcjIRuZBUPkTEFAdPVTBhbi7r954E4PeXtuEvg7pqzCLiA1Q+RMTtvtxyhPvm53Oq3E6ENYDnburBoO5n/rRsEWl8VD5ExG2qHS7+/tlWXl/1EwA9EqKYPTaD1rGhJicTEXdS+RARt9h/opzxc3PJ338KgD/1acdDAztjDdCYRcTXqHyIyAX3WcFhHlyQT3Glg8jgAJ4fmUr/5HizY4mISVQ+ROSCqXI4mbZ0K2+s2QNAeutoXh6bTkITjVlEfJnKh4hcEHuPlzE+O5eNB2wA/Pmy9tx/XWcC/f1MTiYiZlP5EJEG98mGQzy8cAMlVQ6ahAYyY1QqV3VpbnYsEfEQKh8i0mAq7U6e/mQz73y3D4CebZswa2w6LaJCTE4mIp5E5UNEGsTuY6WMy85ly6FiAO6+ogOTr+1EgMYsIvILKh8ict4+zD3AXxZtpLzaSWxYEC+MTuPyTk3NjiUiHkrlQ0TOWUW1kycWb+K9H/cDcEn7GGaOSad5ZLDJyUTEk6l8iMg52Xm0hHHv5rLtSAkWC0y8KomJVyfh72cxO5qIeDiVDxGptwXrC3n0wwIq7E6aRliZOTqN3h3jzI4lIl5C5UNE6qy82sFfPyzgg5wDAPTtGMeLo9NoGmE1OZmIeBOVDxGpk62Hixn3bg67jpXhZ4HJ13biris6aswiIvWm8iEiv8owDN77YT+PL95ElcNF80grs8akc3H7WLOjiYiXUvkQkbMqrXLwyKKNfJR3EIDLOzXlhVGpxIZrzCIi507lQ0TOaNNBG+Ozc/mpqAx/Pwv39+/Mny9rj5/GLCJynlQ+RKQWwzB4Z90+nvp4M9UOFy2jgnk5K52L2sSYHU1EGgmVDxGpUVxpZ8rCjXyy8RAA13RtxvSbUmkSFmRyMhFpTFQ+RASADYWnGJ+dy74T5QT4WXh4YBdu7dsOi0VjFhFpWCofIj7OMAzeWLOHZ5Zuwe40SGgSwuysDNISo82OJiKNlMqHiA+zldt5YEE+yzYfAeC65Ob8/aZUokICTU4mIo2ZyoeIj8rdd5Lx2bkcOFVBkL8fjwzuyu8vbaMxi4hccCofIj7GMAxeX/kTz322FYfLoE1sKLPHZtA9IcrsaCLiI1Q+RHzIybJq7p+fz5dbjwIwuEcLpo3oTmSwxiwi4j4qHyI+4sc9J5gwN5dDtkqCAvx4bEg3br64tcYsIuJ2Kh8ijZzLZfCPb3cxY9l2nC6D9nFhzM7KoFvLSLOjiYiPUvkQacSOl1Yx+f18vtl+DIDhaS15+obuhFv1oy8i5tFvIJFG6rvdx5k0L5cjxVUEB/oxdWgyozITNWYREdOpfIg0Mk6XwZyvd/LS8u24DOjYLJw5WRl0jo8wO5qICKDyIdKoHC2pZPJ7+azaWQTATRcl8OSwZEKD9KMuIp5Dv5FEGonVO4uYNC+PotIqQgL9eXp4CjdelGB2LBGR06h8iHg5p8tg5pc7ePmrHRgGdG4ewZyb0+nYTGMWEfFMKh8iXuxIcSUT5+ay7qcTAIztlcjj1ycTHOhvcjIRkbNT+RDxUt9sP8a97+VxoqyasCB/nhnRnWFprcyOJSLym1Q+RLyMw+lixhfbeXXFLgC6tohkTlY67ZuGm5xMRKRu6l0+7HY7+fn5FBUVkZSURIcOHc643YYNG9i7dy9JSUl06dLlvIOKCBw8VcHEubn8uPckAL+7pA2PDO6qMYuIeJV6lY8lS5Zw//33ExMTQ2RkJGvWrOHaa69l7ty5WK1WAKqrqxk1ahQrV64kLS2NH374gZEjR/L666/r4kYi5+GrrUeY/H4+p8rtRFgDePbGHgzu0cLsWCIi9VbvIx8rV66kWbNmAOzfv5/OnTvz73//mzvvvBOAl156idWrV5Ofn09CQgKbNm0iMzOTK664gt/97ncNm17EB1Q7XEz/fCv/WvkTAN1bRTE7K502sWEmJxMROTd+9dn4+uuvrykeAK1atSIqKgqbzVaz7O2332b06NEkJPx8fYHk5GQGDhzI22+/3UCRRXzH/hPljPrn2pri8cc+bVlw16UqHiLi1ep95KO4uJhly5ZRVlbGBx98QLt27bj99tsBcDgcbNmyhQkTJtS6T48ePfjHP/5x1sesqqqiqqqq1nOI+LrPNx3mgfn5FFc6iAwOYPrIVK5Ljjc7lojIeat3+bDZbMybN49Tp06Rl5fHrbfeSkTEzxczKi0txel00qRJk1r3iY2N5dSpU2d9zGnTpjF16tT6RhFplKocTqYt3coba/YAkJYYzctj00mMCTU3mIhIA6l3+UhMTGTBggXAz+d89OzZk9DQUB5//PGak07Ly8tr3ae0tJTg4OCzPuaUKVOYPHlyze3i4mISExPrG03E6+09Xsb47Fw2Hvh5lHl7v3Y8cF0XggLqNSEVEfFo53Wdj8TERK6++mq++eYbAEJCQoiPj2ffvn21ttu3bx/t27c/6+NYrdaa4iLiqz7ZcIiHF26gpMpBdGggM0amcnXX5mbHEhFpcPX6c+ro0aO1bjscDjZu3FhzcinAwIED+eCDD3C5XABUVlayZMkSBg4c2ABxRRqfSruTv364kXHZOZRUOchs04SlE/upeIhIo2UxDMOo68a9evWid+/epKamUlFRwXvvvceWLVv49ttvay4ktmfPHnr27Enfvn0ZNGgQ8+bNY9euXaxfv57Y2Ng6PU9xcXHNu2giIyPP7X8m4gV2HytlXHYuWw79fJL13Vd04N5rOxHorzGLiHifur5+1+s33MqVK0lOTmb16tVs3LiRkSNHsmvXrlpXMG3bti05OTl06dKFFStW0K9fP3744Yc6Fw8RX/FR3gGuf3kVWw4VExMWxJt/6sWDA7qoeIhIo1evIx/uoiMf0phVVDuZumQT837YD8DF7WKYNTad5pFnPylbRMQb1PX1Wx8sJ+JGO4+WMO7dXLYdKcFigQlXdmTi1UkE6GiHiPgQlQ8RN1mwvpBHPyygwu4kLtzKS6PT6JsUZ3YsERG3U/kQucDKqx08+uEmFuYUAtCnYywvjk6jWYTGLCLim1Q+RC6gbYdLuPvd9ew6VoafBe65phPjruyIv58+4VlEfJfKh8gFYBgG7/2wn8cXb6LK4aJZhJVZY9O5pL3e9SUiovIh0sBKqxw8smgjH+UdBOCyTk15YVQqceG6iq+ICKh8iDSoTQdtTMjOZXdRGf5+Fu7r34k7L+uAn8YsIiI1VD5EGoBhGLyzbh9PfbyZaoeLFlHBzBqbTs+2MWZHExHxOCofIuepuNLOlA828smGQwBc1aUZM0am0iQsyORkIiKeSeVD5DxsLLQxLjuHfSfKCfCz8NCALtzat53GLCIiv0LlQ+QcGIbBm2v28MzSrVQ7XbSKDuHlrHQyWjcxO5qIiMdT+RCpJ1u5nQcX5vP5piMA9O/WnOk3pRIVGmhyMhER76DyIVIPuftOMmFuLoUnKwj0t/CXQV25pXdbLBaNWURE6krlQ6QODMPgf1f9xLOfbsXhMmgdE8rsrHR6JESbHU1ExOuofIj8hpNl1dw/P58vtx4FYFD3eJ69sQeRwRqziIicC5UPkV+xfu8JJmTnctBWSVCAH48O6cb/XNxaYxYRkfOg8iFyBi6XwT+/3c3zy7bhdBm0iwtjdlY6yS2jzI4mIuL1VD5EfuF4aRWT38/nm+3HABia2pJnRnQn3KofFxGRhqDfpiL/Zd3u40ycl8uR4iqsAX5MHZrM6J6JGrOIiDQglQ8RwOkyeOXrnby4fDsuAzo0DWPOzRl0iY80O5qISKOj8iE+71hJFfe8l8vqnccBGJHRiqeGpRCmMYuIyAWh367i09bsLGLivDyKSqsICfTnyWHJjMxMNDuWiEijpvIhPsnpMpj55Q5e/moHhgGdmoczJyuDpOYRZkcTEWn0VD7E5xwprmTSvFy+230CgNGZiTwxNJmQIH+Tk4mI+AaVD/Ep32w/xuT38jheVk1okD/P3NCd4emtzI4lIuJTVD7EJzicLl74YjuvrNgFQNcWkczJSqd903CTk4mI+B6VD2n0DtkqmDg3lx/2nATg5otb8+iQbgQHaswiImIGlQ9p1L7aeoT73s/nZLmdcGsAz97YnSE9WpodS0TEp6l8SKNkd7qY/vk2Xvt2NwAprSKZPTaDtnFhJicTERGVD2l0Ck+WM2FuLrn7TgFwS++2TBnUBWuAxiwiIp5A5UMalWWbDnP//HyKKx1EBAcw/aYeDEhpYXYsERH5Lyof0ihUO1xM+3QL/169B4DUxGhmj00nMSbU3GAiInIalQ/xevuOlzN+bg4bCm0A3Na3HQ8O6EJQgJ/JyURE5ExUPsSrLd14iIcWbKCkykFUSCAzRqZyTbfmZscSEZFfofIhXqnS7uRvn2zh7e/2AnBRmybMGptOq+gQk5OJiMhvUfkQr/NTURnjs3PYdLAYgDsv78B9/TsR6K8xi4iIN1D5EK/yUd4B/vLBRsqqncSEBTFjVCpXdm5mdiwREakHlQ/xCpV2J1OXbGLu9/sB6NU2hllj04mPCjY5mYiI1JfKh3i8nUdLGZ+dw9bDJVgsMP7Kjky6OokAjVlERLySyod4tIXrC/nrhwVU2J3EhQfx4ug0+iU1NTuWiIicB5UP8Ujl1Q4e+2gTC9YXAnBp+1hmjkmjWaTGLCIi3k7lQzzO9iMljHs3hx1HS/GzwKSrOzH+qo74+1nMjiYiIg1A5UM8hmEYzP+xkMcWF1Bpd9E0wsqsMelc2iHW7GgiItKAVD7EI5RVOXhk0UY+zDsIQL+kOF4cnUZcuNXkZCIi0tBUPsR0mw8WMz47h91FZfj7WZh8bSfuurwDfhqziIg0SvV6r+KRI0d45JFH6Nu3LxdffDHjx4/nwIEDp233zTffMGjQIJKTkxk+fDg5OTkNFlgaD8MweHfdXoa/sprdRWXERwYz745LGHdlRxUPEZFGrF7l4/rrryc8PJxnn32Wl156iZ07d9KnTx9OnDhRs80PP/xA//79yczM5I033qBVq1ZcccUV7Nq1q8HDi/cqqbQzYW4ujywqoNrh4srOTVk6qR8928aYHU1ERC4wi2EYRl03ttvtBAYG1twuLi6mSZMmvP3222RlZQEwfPhwysrK+OKLL2q269atG5dffjmvvvpqnZ6nuLiYqKgobDYbkZGRdY0nXqLggI1x2TnsPV5OgJ+FBwd05ra+7XW0Q0TEy9X19bteRz7+u3jAz4fNLRYLFsv/e9FYsWIF1113Xa3tBg4cyIoVK+rzVNIIGYbBm2v2MOKVNew9Xk6r6BDev/NS7rhM53eIiPiS8zrh9IknniAyMpL+/fsDUFJSgs1mIz4+vtZ28fHxFBYWnvVxqqqqqKqqqrldXFx8PrHEA9kq7Dy0YAOfbToMwLXdmjP9ph5EhwaZnExERNztnMvH66+/zuzZs1m0aBGxsT9fh8HlcgGnHyEJCgrC6XSe9bGmTZvG1KlTzzWKeLi8/acYn51D4ckKAv0tTBnYlT/2aVvriJmIiPiOc/pkrjfffJO7776bd955hyFDhtQsj4iIwGq1cvz48VrbFxUVERcXd9bHmzJlCjabreZr//795xJLPIxhGLy+cjcj/7GGwpMVJMaEsODO3vypbzsVDxERH1bvIx9vv/02d9xxB2+99RajR4+utc7Pz4+MjAzWrl3L3XffXbN81apVZGZmnvUxrVYrVqsuJtWYnCqv5v75G1i+5QgAg7rH8+yNPYgMDvyNe4qISGNXryMf2dnZ3Hbbbbz55puMGTPmjNvceeedLFy4kDVr1gCwZMkSVq5cyV133XX+acUrrN97kkEzV7J8yxGC/P14algyc7IyVDxERASo51ttw8LCcLlctGrVqtbyiRMnMnHixJrbjz/+ONOnTyckJAS73c7TTz9da/1v0VttvZPLZfDayt1M/3wbTpdB29hQZmdlkNIqyuxoIiLiBnV9/a5X+di9e3fNSaX/LSYmhpiY2heHqqys5NixYzRv3pygoPq9o0Hlw/scL63ivvn5rNh2DIChqS15ZkR3wq26gr+IiK+o6+t3vV4Z2rdvX+dtg4ODSUxMrM/Di5f6/qcTTJibw5HiKqwBfjwxNJkxPRN1UqmIiJyR/iyVc+ZyGbyyYicvfLEdlwEdmoYx5+YMusTraJWIiJydyoeck2MlVUx+P4+VO4oAGJHRiqeGpRCmMYuIiPwGvVJIva3ZWcSk9/I4VlJFSKA/Tw5LZmSmRmwiIlI3Kh9SZ06XwawvdzDrqx0YBnRqHs6crAySmkeYHU1ERLyIyofUydHiSibNy2Pt7p+vXjumZyKPX59MSJC/yclERMTbqHzIb1q54xj3vpdHUWk1YUH+PDOiO8PSWv32HUVERM5A5UPOyuF08dLyHcxZsRPDgK4tIpmdlU6HpuFmRxMRES+m8iFndMhWwaS5eXy/5wQAN1/cmkeHdCM4UGMWERE5Pyofcpqvtx5l8vt5nCy3E24N4NkbuzOkR0uzY4mISCOh8iE17E4Xz3++jX9+uxuAlFaRzMnKoE1smMnJRESkMVH5EAAOnKpgQnYOOftOAXBL77ZMGdQFa4DGLCIi0rBUPoQvNh/h/vn52CrsRAQHMP2mHgxIaWF2LBERaaRUPnxYtcPFs59u5f9W/wRAamI0s8emkxgTanIyERFpzFQ+fNT+E+WMz84hv9AGwG192/HggC4EBfiZnExERBo7lQ8f9OnGQzy4cAMllQ6iQgKZMTKVa7o1NzuWiIj4CJUPH1Jpd/LM0i28tXYvABe1acKssem0ig4xOZmIiPgSlQ8fsaeojHHZOWw6WAzAnZd34L7+nQj015hFRETcS+XDByzOP8hfPthIaZWDmLAgXhiVyhWdm5kdS0REfJTKRyNWaXcydclm5n6/D4Be7WKYNSad+Khgk5OJiIgvU/lopHYeLWV8dg5bD5dgscD4Kzsy6eokAjRmERERk6l8NEIf5BTy1w8LKK92EhcexEuj0+mbFGd2LBEREUDlo1Epr3bw+EebmL++EIDeHWJ5aXQazSI1ZhEREc+h8tFIbD9Swrh3c9hxtBQ/C0y6uhPjr+qIv5/F7GgiIiK1qHx4OcMwmL++kMc+KqDS7qJZhJWZY9K5tEOs2dFERETOSOXDi5VVOfjrhwUsyj0AQL+kOF4cnUZcuNXkZCIiImen8uGlthwqZty7OewuKsPfz8Lkaztx1+Ud8NOYRUREPJzKh5cxDIPs7/cxdclmqh0u4iODeTkrnZ5tY8yOJiIiUicqH16kpNLOlA828vGGQwBc2bkpM0alERMWZHIyERGRulP58BIFB2yMz85hz/FyAvwsPDigM7f1ba8xi4iIeB2VDw9nGAZvrd3L3z7ZQrXTRavoEGaNTeeiNk3MjiYiInJOVD48mK3CzsMLN/BpwWEArunanOdH9iA6VGMWERHxXiofHipv/ynGZ+dQeLKCQH8LUwZ25Y992mKxaMwiIiLeTeXDwxiGwf+u+onnPtuK3WmQGBPC7LEZpCZGmx1NRESkQah8eJBT5dXcP38Dy7ccAWBgSjzP3tiDqJBAk5OJiIg0HJUPD7F+70kmZOdw0FZJkL8ffx3Sld9d0kZjFhERaXRUPkzmchm8tnI30z/fhtNl0DY2lNlZGaS0ijI7moiIyAWh8mGiE2XVTH4/jxXbjgFwfWpLnrkhhYhgjVlERKTxUvkwyfc/nWDi3FwOF1diDfDjiaHJjOmZqDGLiIg0eiofbuZyGbyyYicvfLEdlwHtm4YxJyuDri0izY4mIiLiFiofbnSspIrJ7+exckcRACPSW/HU8BTCrNoNIiLiO/Sq5yZrdhYx6b08jpVUERzox5PDUhh5UYLGLCIi4nNUPi4wp8tg1pc7mPXVDgwDkpqF88rNGSQ1jzA7moiIiClUPi6go8WVTJqXx9rdxwEYlZnA1KEphAT5m5xMRETEPCofF8jKHce49708ikqrCQ3y5283pHBDeoLZsUREREx3TuUjPz+f3NxcLrvsMtq3b3/aesMwWLt2LXv37iUpKYnMzMzzDuotHE4XLy7fzisrdmEY0CU+gtlZGXRsFm52NBEREY9Qr/Lx3Xffcd9991FcXExBQQFvv/32aeWjsrKS66+/noKCAnr16sWqVau45ppryM7Oxt+/cY8bDtkqmDQ3j+/3nABgbK/WPH59N4IDG/f/W0REpD7qVT6qqqp47rnn6Nu371nfpfH8889TUFBAXl4ezZs3Z8eOHaSlpfHGG29w6623NkhoT/T11qNMfj+Pk+V2wq0BPDOiO0NTW5odS0RExOPUq3xcfvnlv7lNdnY2o0ePpnnz5gAkJSUxaNAgsrOzG2X5sDtdPP/5Nv757W4AkltGMicrg7ZxYSYnExER8Ux+Dflgdrudbdu2kZycXGt5SkoKBQUFZ71fVVUVxcXFtb68wYFTFYz+59qa4vGHS9uw8K7eKh4iIiK/okHf7VJaWorL5SI6OrrW8piYGGw221nvN23aNKZOndqQUS64LzYf4f75+dgq7EQEB/D3G3swsHsLs2OJiIh4vAY98hESEgJAWVlZreUlJSU1685kypQp2Gy2mq/9+/c3ZKwGVe1w8eSSzdz+1o/YKuykJkTxyYR+Kh4iIiJ11KBHPoKDg2nZsiV79uyptXzPnj106NDhrPezWq1YrdaGjHJB7D9RzvjsHPILfz6Kc2vfdjw0oAtBAQ3a4URERBq1Bn/VHDJkCAsXLsThcAA/HwVZsmQJQ4YMaeincqtPNx5i0KyV5BfaiAoJ5F+/z+TRId1UPEREROqpXkc+Dh06xOeff15ze+XKlTgcDjp16kTv3r0BePTRR+nVqxeDBw9mwIABzJ8/n4iICO65554GDe4ulXYnzyzdwltr9wKQ0TqaWWPTSWgSanIyERER71Sv8nHy5ElWrFgBwB/+8AeqqqpYsWIFhmHUlI+EhARyc3N5/fXX2bp1KyNGjOD2228nKiqqwcNfaHuKyhiXncOmgz+/++bPl7fn/v6dCfTX0Q4REZFzZTEMwzA7xC8VFxcTFRWFzWYjMjLSlAyL8w/ylw82UlrloEloIC+MSuPKLs1MySIiIuIN6vr6rQ+W+4VKu5OpSzYz9/t9APRs24RZY9NpEXX2d+uIiIhI3al8/Jddx0oZ924OWw+XYLHAuCs6cs81SQRozCIiItJgVD7+f4tyC3lkUQHl1U5iw4J4aUwa/ZKamh1LRESk0fH58lFR7eSxjwqYv74QgEvbxzJzTBrNIoNNTiYiItI4+XT52H6khHHv5rDjaCkWC0y6OokJVyXh73fmT+wVERGR8+eT5cMwDOavL+SxjwqotLtoGmFl5pg0eneIMzuaiIhIo+dz5aOsysFfPyxgUe4BAPolxfHCqDSaRnj+5d1FREQaA58qH1sOFTMuO4fdx8rws8B9/Ttz1+Ud8NOYRURExG18pnxUVDv5n9fXcbysmvjIYGaNTadXuxizY4mIiPgcnykfIUH+PDqkGx/mHeCFUWnEhAWZHUlERMQn+Uz5ABie3ophaS2xWDRmERERMYvPXbpTxUNERMRcPlc+RERExFwqHyIiIuJWKh8iIiLiViofIiIi4lYqHyIiIuJWKh8iIiLiViofIiIi4lYqHyIiIuJWKh8iIiLiViofIiIi4lYqHyIiIuJWKh8iIiLiVh75qbaGYQBQXFxschIRERGpq/+8bv/ndfxsPLJ8lJSUAJCYmGhyEhEREamvkpISoqKizrreYvxWPTGBy+Xi4MGDREREYLFYzI7j0YqLi0lMTGT//v1ERkaaHUfOQvvJe2hfeQftJ89kGAYlJSW0bNkSP7+zn9nhkUc+/Pz8SEhIMDuGV4mMjNQPoBfQfvIe2lfeQfvJ8/zaEY//0AmnIiIi4lYqHyIiIuJWKh9ezmq18vjjj2O1Ws2OIr9C+8l7aF95B+0n7+aRJ5yKiIhI46UjHyIiIuJWKh8iIiLiViofIiIi4lYeeZ0POZ3T6WTDhg0cOHCADh060LVr1zNuV1hYyPr164mOjqZ3794EBga6Oan8x/LlyykqKmLEiBEEBQXVWnf06FG+++47wsLC6NOnD8HBwSal9G1bt25l27ZtdOvWjaSkpNPWnzp1itWrV+Pv70/fvn0JDw83IaVvO3z4MBs2bMDhcJCcnEybNm1O26asrIxVq1bhcDjo3bs3TZo0MSGp1IshHm/p0qVG586djfT0dGPIkCFGTEyMMWDAAKOsrKzWdi+99JIREhJiXHnllUb79u2NLl26GIWFhSal9m2fffaZYbVaDcA4duxYrXXvvPOOERYWZvTr18/o2rWrkZiYaGzevNmkpL7JZrMZgwcPNmJiYoyhQ4caaWlpxj333FNrm88//9yIiooyLr74YiM9Pd2IjY01Vq1aZVJi3zRt2jQjODjYuOqqq4wBAwYYISEhxrhx42pt8/333xvNmjUzUlNTjUsvvdSIiIgwlixZYlJiqSuVDy+wePFiY9euXTW3jxw5YrRo0cKYMmVKzbKCggLDz8/PmD9/vmEYhlFZWWn06tXLGD58uNvz+rpDhw4ZiYmJxtNPP31a+Th48KAREhJivPzyy4ZhGIbT6TQGDRpkXHLJJWbF9Uk33HCDkZycbBw/frxm2UcffVTz77KyMqNp06bGQw89VLPs1ltvNdq2bWvY7Xa3ZvVVR44cMQDj//7v/2qWffHFFwZgfP/994Zh/Pzzk5SUZPzhD3+o2eaRRx4xYmJijOLiYndHlnpQ+fBSI0eONAYOHFhz+5FHHjESExNrbfPWW28Z/v7+xqlTp9wdz2c5nU7jmmuuMZ5//nljyZIlp5WPl19+2QgPDzcqKytrli1btswAjB07dpgR2eds2bLFAIzFixefdZtFixYZFovFOHToUM2yzZs3G4CxYsUKd8T0efv27TMA46uvvqpZtmvXLgOoOQK1du1aAzDy8/Nrtjl69Kjh7+9vzJs3z+2Zpe50wqkXqqioYM2aNaSkpNQs27hxY63bAN27d8fpdLJlyxZ3R/RZzz77LIZhMHny5DOu37hxI0lJSbUujNS9e3cACgoK3JLR13377bf4+/tz5ZVXsnr1aj755BP27NlTa5uNGzcSFxdHfHx8zbKuXbsSGBjIxo0b3ZzYNyUmJjJ16lQmTJjA7Nmzee211xgzZgx33nknffr0AX7eTxaLheTk5Jr7NW3alPj4eO0nD6cTTr3Q3Xffjd1ur/UCZ7PZTvswvtjYWODnk+bkwlu7di0zZ84kJyfnrJ/GbLPZiImJqbVM+8m9jh49SkREBDfeeCM2m40mTZrwzTffcNtttzFr1izgzPsJoEmTJtpPbpSWlkZ2djYLFizAarVy7NgxevbsWbPeZrMRGRmJv79/rfvFxsZqP3k4lQ8v8+CDD7Jo0SKWL19e668yq9VKaWlprW3/c1vvpHCP22+/nf79+7Ny5UoAcnNzAVi0aBEXX3wxPXr00H7yAMHBwZw6dYo+ffrw2GOPAfDdd9/Ru3dvrrvuOgYPHnzG/QQ/7yvtJ/fYsmULI0aMYO7cuYwcORKAdevW0bt3b9q0acPVV1+N1WqlrKzstPtqP3k+jV28yJQpU/jnP//J559/TmZmZq11HTp0YN++fbWW7d27F4D27du7LaMv69u3L3a7nQ8//JAPP/yQtWvXAvDpp5+yadMmQPvJE3To0AGAG2+8sWbZJZdcQqtWrVi/fn3NNseOHaOysrJmm6KiIsrLy7Wf3GTVqlUAjBgxombZxRdfTGJiIl9//TXw835yOBwcPHiwZpvq6moOHz6s/eTpzD7pROpmypQpRmRkpLF27dozrl+yZIlhsViM7du31yy75ZZbjJSUFHdFlF840wmnP/zwQ60T5gzDMB5++GEjPj7ecDgcZsT0OTabzQgNDTUWLFhQs6yoqMiwWq0176zYv3+/ERAQUOukxdmzZxshISHGyZMn3R3ZJ3366acGYGzZsqVm2fHjx42QkBDj1VdfNQzDMEpKSozw8HDjpZdeqtlmwYIFhp+fX613CIrn0djFC7zwwgtMmzaNe+65hz179tScHNekSROuu+46AAYPHlxzyHjChAls27aNd955h6VLl5qYXH4pMzOT3//+94wePZr77ruPI0eOMGPGDN58883T5tZyYURGRvLcc89x5513snPnTqKjo3nttdfo0qULY8aMASAhIYEHH3yQP//5z/z000/Y7XamTZvGk08+SXR0tLn/AR9xzTXXcOmllzJ48GAmTpxIUFAQ//rXv2jZsiVZWVkAhIeH88wzz/Dggw9y8uRJQkNDefbZZ7n33nt15MPD6VNtvcCsWbNYs2bNacvbtm3Ls88+W3Pbbrfz+uuvs27dOqKjo/nDH/5Aenq6O6PKf8nNzeW5557jX//6FxERETXLXS4Xb7/9Nt988w2hoaGMGTOGvn37mpjUN3311VcsXLgQu91Oeno6f/zjH087T2DRokUsXboUPz8/hg8fzsCBA01K65uqq6t5++23ycnJweFwkJKSwh//+MfTrjS7bNkyPvjgAxwOB9ddd13NOSLiuVQ+RERExK10wqmIiIi4lcqHiIiIuJXKh4iIiLiVyoeIiIi4lcqHiIiIuJXKh4iIiLiVyoeIiIi4lcqHiIiIuJXKh4iIiLiVyoeIiIi4lcqHiIiIuJXKh4iIiLjV/wdVs+N0M7Q+1AAAAABJRU5ErkJggg==", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "model = Model()\n", "loss_fn = nn.L1Loss()\n", - "optimizer = torch.optim.SGD(model.parameters(), lr=0.0001)\n", - "epochs_num = 100\n", - "epochs = []\n", - "losses = []\n", - "for epoch in range(epochs_num):\n", + "optimizer = torch.optim.SGD(model.parameters(), lr=0.0001)" + ] + }, + { + "cell_type": "code", + "execution_count": 141, + "id": "ad664e99", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 0: Loss: 0.008045697584748268 Loss_test: 0.018803399056196213\n", + "Epoch 10: Loss: 0.008011357858777046 Loss_test: 0.01872417889535427\n", + "Epoch 20: Loss: 0.007976962253451347 Loss_test: 0.018648361787199974\n", + "Epoch 30: Loss: 0.007942652329802513 Loss_test: 0.018565673381090164\n", + "Epoch 40: Loss: 0.007908274419605732 Loss_test: 0.018482983112335205\n", + "Epoch 50: Loss: 0.007873939350247383 Loss_test: 0.01840377412736416\n", + "Epoch 60: Loss: 0.007839584723114967 Loss_test: 0.018324535340070724\n", + "Epoch 70: Loss: 0.007805197034031153 Loss_test: 0.018241852521896362\n", + "Epoch 80: Loss: 0.007770814001560211 Loss_test: 0.018166035413742065\n", + "Epoch 90: Loss: 0.007736505474895239 Loss_test: 0.018083352595567703\n", + "Epoch 100: Loss: 0.007702118717133999 Loss_test: 0.018004130572080612\n", + "Epoch 110: Loss: 0.007667776197195053 Loss_test: 0.017921436578035355\n", + "Epoch 120: Loss: 0.007633431814610958 Loss_test: 0.017842214554548264\n", + "Epoch 130: Loss: 0.007599038537591696 Loss_test: 0.01775953732430935\n", + "Epoch 140: Loss: 0.007564662490040064 Loss_test: 0.017683720216155052\n", + "Epoch 150: Loss: 0.007530292961746454 Loss_test: 0.017597621306777\n", + "Epoch 160: Loss: 0.007495974190533161 Loss_test: 0.017521798610687256\n", + "Epoch 170: Loss: 0.007461588829755783 Loss_test: 0.01744258962571621\n", + "Epoch 180: Loss: 0.007427276577800512 Loss_test: 0.0173599012196064\n", + "Epoch 190: Loss: 0.007392874453216791 Loss_test: 0.017277205362915993\n", + "Epoch 200: Loss: 0.007358507718890905 Loss_test: 0.017201393842697144\n", + "Epoch 210: Loss: 0.007324136793613434 Loss_test: 0.01711530052125454\n", + "Epoch 220: Loss: 0.007289794739335775 Loss_test: 0.017036069184541702\n", + "Epoch 230: Loss: 0.0072554415091872215 Loss_test: 0.016960252076387405\n", + "Epoch 240: Loss: 0.007221107371151447 Loss_test: 0.016877567395567894\n", + "Epoch 250: Loss: 0.007186715956777334 Loss_test: 0.016794884577393532\n", + "Epoch 260: Loss: 0.007152379956096411 Loss_test: 0.01671566441655159\n", + "Epoch 270: Loss: 0.007117978297173977 Loss_test: 0.01663643680512905\n", + "Epoch 280: Loss: 0.0070836408995091915 Loss_test: 0.016553759574890137\n", + "Epoch 290: Loss: 0.007049286272376776 Loss_test: 0.016477936878800392\n", + "Epoch 300: Loss: 0.007014954928308725 Loss_test: 0.016395259648561478\n", + "Epoch 310: Loss: 0.006980604026466608 Loss_test: 0.016316020861268044\n", + "Epoch 320: Loss: 0.006946216337382793 Loss_test: 0.01623334363102913\n", + "Epoch 330: Loss: 0.006911881268024445 Loss_test: 0.01615411601960659\n", + "Epoch 340: Loss: 0.006877475883811712 Loss_test: 0.016071433201432228\n", + "Epoch 350: Loss: 0.006843137554824352 Loss_test: 0.01599561609327793\n", + "Epoch 360: Loss: 0.00680879270657897 Loss_test: 0.01591293141245842\n", + "Epoch 370: Loss: 0.00677445437759161 Loss_test: 0.015833700075745583\n", + "Epoch 380: Loss: 0.006740066222846508 Loss_test: 0.01575447991490364\n", + "Epoch 390: Loss: 0.006705722771584988 Loss_test: 0.015671800822019577\n", + "Epoch 400: Loss: 0.006671322043985128 Loss_test: 0.015589112415909767\n", + "Epoch 410: Loss: 0.006636989302933216 Loss_test: 0.015513300895690918\n", + "Epoch 420: Loss: 0.006602602545171976 Loss_test: 0.015434074215590954\n", + "Epoch 430: Loss: 0.006568240933120251 Loss_test: 0.015347987413406372\n", + "Epoch 440: Loss: 0.006533913314342499 Loss_test: 0.015272158198058605\n", + "Epoch 450: Loss: 0.0064995489083230495 Loss_test: 0.01518948096781969\n", + "Epoch 460: Loss: 0.006465154234319925 Loss_test: 0.015106802806258202\n", + "Epoch 470: Loss: 0.00643081683665514 Loss_test: 0.015027564950287342\n", + "Epoch 480: Loss: 0.006396452896296978 Loss_test: 0.014951747842133045\n", + "Epoch 490: Loss: 0.00636207964271307 Loss_test: 0.014865648932754993\n", + "Epoch 500: Loss: 0.006327774375677109 Loss_test: 0.014789843931794167\n", + "Epoch 510: Loss: 0.006293395068496466 Loss_test: 0.01470716018229723\n", + "Epoch 520: Loss: 0.006258990615606308 Loss_test: 0.014627927914261818\n", + "Epoch 530: Loss: 0.0062246560119092464 Loss_test: 0.014545244164764881\n", + "Epoch 540: Loss: 0.006190317217260599 Loss_test: 0.014466023072600365\n", + "Epoch 550: Loss: 0.006155920680612326 Loss_test: 0.014390205964446068\n", + "Epoch 560: Loss: 0.006121611688286066 Loss_test: 0.014307516627013683\n", + "Epoch 570: Loss: 0.006087233312427998 Loss_test: 0.014224827289581299\n", + "Epoch 580: Loss: 0.006052898708730936 Loss_test: 0.014145618304610252\n", + "Epoch 590: Loss: 0.00601854408159852 Loss_test: 0.014066380448639393\n", + "Epoch 600: Loss: 0.005984155926853418 Loss_test: 0.013983696699142456\n", + "Epoch 610: Loss: 0.005949772894382477 Loss_test: 0.01390787959098816\n", + "Epoch 620: Loss: 0.0059154643677175045 Loss_test: 0.013825195841491222\n", + "Epoch 630: Loss: 0.0058810776099562645 Loss_test: 0.01374597568064928\n", + "Epoch 640: Loss: 0.005846735090017319 Loss_test: 0.013663279823958874\n", + "Epoch 650: Loss: 0.005812390707433224 Loss_test: 0.013584059663116932\n", + "Epoch 660: Loss: 0.005777997430413961 Loss_test: 0.013501381501555443\n", + "Epoch 670: Loss: 0.0057436213828623295 Loss_test: 0.013425564393401146\n", + "Epoch 680: Loss: 0.005709252320230007 Loss_test: 0.013339465484023094\n", + "Epoch 690: Loss: 0.005674933083355427 Loss_test: 0.01326364278793335\n", + "Epoch 700: Loss: 0.005640547722578049 Loss_test: 0.013184433802962303\n", + "Epoch 710: Loss: 0.005606235470622778 Loss_test: 0.013101744465529919\n", + "Epoch 720: Loss: 0.005571833346039057 Loss_test: 0.013019049540162086\n", + "Epoch 730: Loss: 0.005537466146051884 Loss_test: 0.01294323243200779\n", + "Epoch 740: Loss: 0.0055030956864356995 Loss_test: 0.012857144698500633\n", + "Epoch 750: Loss: 0.005468753632158041 Loss_test: 0.012777912430465221\n", + "Epoch 760: Loss: 0.005434400402009487 Loss_test: 0.012702095322310925\n", + "Epoch 770: Loss: 0.005400066263973713 Loss_test: 0.012619411572813988\n", + "Epoch 780: Loss: 0.0053656748495996 Loss_test: 0.012536728754639626\n", + "Epoch 790: Loss: 0.005331338848918676 Loss_test: 0.012457507662475109\n", + "Epoch 800: Loss: 0.005296936724334955 Loss_test: 0.012378280982375145\n", + "Epoch 810: Loss: 0.005262599792331457 Loss_test: 0.01229560375213623\n", + "Epoch 820: Loss: 0.005228245165199041 Loss_test: 0.012219781056046486\n", + "Epoch 830: Loss: 0.005193913821130991 Loss_test: 0.012137102894484997\n", + "Epoch 840: Loss: 0.005159562919288874 Loss_test: 0.012057865038514137\n", + "Epoch 850: Loss: 0.005125174764543772 Loss_test: 0.011975186876952648\n", + "Epoch 860: Loss: 0.00509084016084671 Loss_test: 0.011895960196852684\n", + "Epoch 870: Loss: 0.005056434776633978 Loss_test: 0.011813277378678322\n", + "Epoch 880: Loss: 0.005022096447646618 Loss_test: 0.011737460270524025\n", + "Epoch 890: Loss: 0.0049877529963850975 Loss_test: 0.011654776521027088\n", + "Epoch 900: Loss: 0.004953412804752588 Loss_test: 0.011575544252991676\n", + "Epoch 910: Loss: 0.004919025115668774 Loss_test: 0.01149632316082716\n", + "Epoch 920: Loss: 0.004884681198745966 Loss_test: 0.011413645930588245\n", + "Epoch 930: Loss: 0.004850282333791256 Loss_test: 0.011330956593155861\n", + "Epoch 940: Loss: 0.0048159463331103325 Loss_test: 0.011255145072937012\n", + "Epoch 950: Loss: 0.004781560506671667 Loss_test: 0.011175918392837048\n", + "Epoch 960: Loss: 0.004747199825942516 Loss_test: 0.011089831590652466\n", + "Epoch 970: Loss: 0.004712873604148626 Loss_test: 0.011014002375304699\n", + "Epoch 980: Loss: 0.004678507801145315 Loss_test: 0.010931325145065784\n", + "Epoch 990: Loss: 0.004644113127142191 Loss_test: 0.010848646983504295\n", + "Epoch 1000: Loss: 0.0046097757294774055 Loss_test: 0.010769409127533436\n", + "Epoch 1010: Loss: 0.004575411789119244 Loss_test: 0.010693592019379139\n", + "Epoch 1020: Loss: 0.004541038069874048 Loss_test: 0.010607493110001087\n", + "Epoch 1030: Loss: 0.004506733268499374 Loss_test: 0.01053168810904026\n", + "Epoch 1040: Loss: 0.004472356289625168 Loss_test: 0.010449004359543324\n", + "Epoch 1050: Loss: 0.004437948111444712 Loss_test: 0.010369772091507912\n", + "Epoch 1060: Loss: 0.00440361350774765 Loss_test: 0.010287088342010975\n", + "Epoch 1070: Loss: 0.00436927517876029 Loss_test: 0.010207867249846458\n", + "Epoch 1080: Loss: 0.004334879573434591 Loss_test: 0.010132050141692162\n", + "Epoch 1090: Loss: 0.004300569649785757 Loss_test: 0.010049360804259777\n", + "Epoch 1100: Loss: 0.004266192205250263 Loss_test: 0.009966671466827393\n", + "Epoch 1110: Loss: 0.004231857601553202 Loss_test: 0.009887462481856346\n", + "Epoch 1120: Loss: 0.004197502043098211 Loss_test: 0.009808224625885487\n", + "Epoch 1130: Loss: 0.004163114819675684 Loss_test: 0.00972554087638855\n", + "Epoch 1140: Loss: 0.004128732718527317 Loss_test: 0.009649723768234253\n", + "Epoch 1150: Loss: 0.004094424657523632 Loss_test: 0.009567040018737316\n", + "Epoch 1160: Loss: 0.004060038365423679 Loss_test: 0.009487813338637352\n", + "Epoch 1170: Loss: 0.004025692585855722 Loss_test: 0.009405124001204967\n", + "Epoch 1180: Loss: 0.003991351462900639 Loss_test: 0.009325903840363026\n", + "Epoch 1190: Loss: 0.003956956323236227 Loss_test: 0.009243225678801537\n", + "Epoch 1200: Loss: 0.003922580275684595 Loss_test: 0.00916740857064724\n", + "Epoch 1210: Loss: 0.003888209816068411 Loss_test: 0.009081309661269188\n", + "Epoch 1220: Loss: 0.0038538917433470488 Loss_test: 0.009005486965179443\n", + "Epoch 1230: Loss: 0.0038195066154003143 Loss_test: 0.008926277980208397\n", + "Epoch 1240: Loss: 0.0037851943634450436 Loss_test: 0.008843588642776012\n", + "Epoch 1250: Loss: 0.0037507922388613224 Loss_test: 0.00876089371740818\n", + "Epoch 1260: Loss: 0.0037164248060435057 Loss_test: 0.008685076609253883\n", + "Epoch 1270: Loss: 0.003682055976241827 Loss_test: 0.008598988875746727\n", + "Epoch 1280: Loss: 0.003647714154794812 Loss_test: 0.008519756607711315\n", + "Epoch 1290: Loss: 0.003613357897847891 Loss_test: 0.008443939499557018\n", + "Epoch 1300: Loss: 0.003579024923965335 Loss_test: 0.008361255750060081\n", + "Epoch 1310: Loss: 0.0035446337424218655 Loss_test: 0.00827857293188572\n", + "Epoch 1320: Loss: 0.003510297741740942 Loss_test: 0.008199351839721203\n", + "Epoch 1330: Loss: 0.003475895617157221 Loss_test: 0.008120125159621239\n", + "Epoch 1340: Loss: 0.0034415586851537228 Loss_test: 0.008037447929382324\n", + "Epoch 1350: Loss: 0.003407204058021307 Loss_test: 0.00796162523329258\n", + "Epoch 1360: Loss: 0.003372871084138751 Loss_test: 0.00787894707173109\n", + "Epoch 1370: Loss: 0.0033385218121111393 Loss_test: 0.007799708750098944\n", + "Epoch 1380: Loss: 0.0033041336573660374 Loss_test: 0.007717031054198742\n", + "Epoch 1390: Loss: 0.0032698004506528378 Loss_test: 0.007637804839760065\n", + "Epoch 1400: Loss: 0.0032353922724723816 Loss_test: 0.007555121090263128\n", + "Epoch 1410: Loss: 0.003201055573299527 Loss_test: 0.007479303982108831\n", + "Epoch 1420: Loss: 0.0031667121220380068 Loss_test: 0.007396620698273182\n", + "Epoch 1430: Loss: 0.003132371697574854 Loss_test: 0.007317387964576483\n", + "Epoch 1440: Loss: 0.003097984241321683 Loss_test: 0.007238167338073254\n", + "Epoch 1450: Loss: 0.0030636400915682316 Loss_test: 0.007155490107834339\n", + "Epoch 1460: Loss: 0.0030292414594441652 Loss_test: 0.007072800304740667\n", + "Epoch 1470: Loss: 0.0029949054587632418 Loss_test: 0.0069969892501831055\n", + "Epoch 1480: Loss: 0.0029605193994939327 Loss_test: 0.006917762570083141\n", + "Epoch 1490: Loss: 0.0029261589515954256 Loss_test: 0.00683167576789856\n", + "Epoch 1500: Loss: 0.002891832496970892 Loss_test: 0.006755846552550793\n", + "Epoch 1510: Loss: 0.002857466693967581 Loss_test: 0.006673169322311878\n", + "Epoch 1520: Loss: 0.0028230720199644566 Loss_test: 0.006590491626411676\n", + "Epoch 1530: Loss: 0.0027887343894690275 Loss_test: 0.00651125330477953\n", + "Epoch 1540: Loss: 0.002754370914772153 Loss_test: 0.006435436196625233\n", + "Epoch 1550: Loss: 0.002719996962696314 Loss_test: 0.006349331233650446\n", + "Epoch 1560: Loss: 0.00268569216132164 Loss_test: 0.006273531820625067\n", + "Epoch 1570: Loss: 0.0026513151824474335 Loss_test: 0.006190842483192682\n", + "Epoch 1580: Loss: 0.0026169070042669773 Loss_test: 0.006111615803092718\n", + "Epoch 1590: Loss: 0.0025825724005699158 Loss_test: 0.006028932519257069\n", + "Epoch 1600: Loss: 0.0025482340715825558 Loss_test: 0.0059497118927538395\n", + "Epoch 1610: Loss: 0.002513838466256857 Loss_test: 0.005873894784599543\n", + "Epoch 1620: Loss: 0.0024795285426080227 Loss_test: 0.005791204981505871\n", + "Epoch 1630: Loss: 0.002445150865241885 Loss_test: 0.005708515644073486\n", + "Epoch 1640: Loss: 0.0024108164943754673 Loss_test: 0.005629307124763727\n", + "Epoch 1650: Loss: 0.002376460935920477 Loss_test: 0.00555006880313158\n", + "Epoch 1660: Loss: 0.0023420737124979496 Loss_test: 0.0054673850536346436\n", + "Epoch 1670: Loss: 0.002307691378518939 Loss_test: 0.005391567945480347\n", + "Epoch 1680: Loss: 0.0022733837831765413 Loss_test: 0.00530888419598341\n", + "Epoch 1690: Loss: 0.0022389970254153013 Loss_test: 0.005229657981544733\n", + "Epoch 1700: Loss: 0.002204651478677988 Loss_test: 0.005146968178451061\n", + "Epoch 1710: Loss: 0.0021703101228922606 Loss_test: 0.005067748017609119\n", + "Epoch 1720: Loss: 0.0021359152160584927 Loss_test: 0.004985070321708918\n", + "Epoch 1730: Loss: 0.0021015391685068607 Loss_test: 0.004909253213554621\n", + "Epoch 1740: Loss: 0.0020671687088906765 Loss_test: 0.004823154304176569\n", + "Epoch 1750: Loss: 0.0020328506361693144 Loss_test: 0.004747331142425537\n", + "Epoch 1760: Loss: 0.00199846550822258 Loss_test: 0.004668122623115778\n", + "Epoch 1770: Loss: 0.001964153256267309 Loss_test: 0.004585432820022106\n", + "Epoch 1780: Loss: 0.0019297510152682662 Loss_test: 0.004502737428992987\n", + "Epoch 1790: Loss: 0.0018953836988657713 Loss_test: 0.00442692032083869\n", + "Epoch 1800: Loss: 0.0018610149854794145 Loss_test: 0.004340833518654108\n", + "Epoch 1810: Loss: 0.0018266730476170778 Loss_test: 0.004261600784957409\n", + "Epoch 1820: Loss: 0.0017923169070854783 Loss_test: 0.004185783676803112\n", + "Epoch 1830: Loss: 0.0017579838167876005 Loss_test: 0.0041031003929674625\n", + "Epoch 1840: Loss: 0.001723592751659453 Loss_test: 0.004020416643470526\n", + "Epoch 1850: Loss: 0.0016892567509785295 Loss_test: 0.003941196016967297\n", + "Epoch 1860: Loss: 0.0016548543935641646 Loss_test: 0.0038619698025286198\n", + "Epoch 1870: Loss: 0.0016205176943913102 Loss_test: 0.003779292106628418\n", + "Epoch 1880: Loss: 0.0015861630672588944 Loss_test: 0.003703468944877386\n", + "Epoch 1890: Loss: 0.0015518299769610167 Loss_test: 0.003620791481807828\n", + "Epoch 1900: Loss: 0.001517480588518083 Loss_test: 0.0035415529273450375\n", + "Epoch 1910: Loss: 0.0014830924337729812 Loss_test: 0.0034588754642754793\n", + "Epoch 1920: Loss: 0.0014487594598904252 Loss_test: 0.003379649017006159\n", + "Epoch 1930: Loss: 0.0014143511652946472 Loss_test: 0.003296965267509222\n", + "Epoch 1940: Loss: 0.0013800144661217928 Loss_test: 0.003221148159354925\n", + "Epoch 1950: Loss: 0.0013456710148602724 Loss_test: 0.003138464642688632\n", + "Epoch 1960: Loss: 0.0013113304739817977 Loss_test: 0.0030592321418225765\n", + "Epoch 1970: Loss: 0.0012769431341439486 Loss_test: 0.002980011748149991\n", + "Epoch 1980: Loss: 0.0012425988679751754 Loss_test: 0.0028973340522497892\n", + "Epoch 1990: Loss: 0.0012082003522664309 Loss_test: 0.002814644481986761\n", + "Epoch 2000: Loss: 0.0011738643515855074 Loss_test: 0.0027388334274291992\n", + "Epoch 2010: Loss: 0.0011394784087315202 Loss_test: 0.0026596069801598787\n", + "Epoch 2020: Loss: 0.0011051192414015532 Loss_test: 0.0025735199451446533\n", + "Epoch 2030: Loss: 0.0010707930196076632 Loss_test: 0.00249769096262753\n", + "Epoch 2040: Loss: 0.0010364264016970992 Loss_test: 0.0024150132667273283\n", + "Epoch 2050: Loss: 0.001002032309770584 Loss_test: 0.00233233580365777\n", + "Epoch 2060: Loss: 0.0009676933404989541 Loss_test: 0.0022530972491949797\n", + "Epoch 2070: Loss: 0.0009333305060863495 Loss_test: 0.002177280141040683\n", + "Epoch 2080: Loss: 0.0008989557391032577 Loss_test: 0.0020911754108965397\n", + "Epoch 2090: Loss: 0.0008646510541439056 Loss_test: 0.0020153759978711605\n", + "Epoch 2100: Loss: 0.0008302740752696991 Loss_test: 0.0019326865440234542\n", + "Epoch 2110: Loss: 0.0007958657806739211 Loss_test: 0.0018534600967541337\n", + "Epoch 2120: Loss: 0.0007615297799929976 Loss_test: 0.0017707764636725187\n", + "Epoch 2130: Loss: 0.0007271930808201432 Loss_test: 0.0016915559535846114\n", + "Epoch 2140: Loss: 0.0006927959620952606 Loss_test: 0.0016157388454303145\n", + "Epoch 2150: Loss: 0.0006584875518456101 Loss_test: 0.0015330493915826082\n", + "Epoch 2160: Loss: 0.000624108302872628 Loss_test: 0.00145035982131958\n", + "Epoch 2170: Loss: 0.0005897767841815948 Loss_test: 0.0013711511855944991\n", + "Epoch 2180: Loss: 0.0005554199451580644 Loss_test: 0.0012919127475470304\n", + "Epoch 2190: Loss: 0.0005210332456044853 Loss_test: 0.0012092292308807373\n", + "Epoch 2200: Loss: 0.00048665032954886556 Loss_test: 0.0011334121227264404\n", + "Epoch 2210: Loss: 0.00045234113349579275 Loss_test: 0.0010507286060601473\n", + "Epoch 2220: Loss: 0.00041795746074058115 Loss_test: 0.000971502042375505\n", + "Epoch 2230: Loss: 0.0003836102841887623 Loss_test: 0.0008888125303201377\n", + "Epoch 2240: Loss: 0.0003492705582175404 Loss_test: 0.0008095920202322304\n", + "Epoch 2250: Loss: 0.00031487419619224966 Loss_test: 0.0007269143825396895\n", + "Epoch 2260: Loss: 0.0002804987016133964 Loss_test: 0.0006510972743853927\n", + "Epoch 2270: Loss: 0.0002461276890244335 Loss_test: 0.0005649983650073409\n", + "Epoch 2280: Loss: 0.0002118095726473257 Loss_test: 0.0004891753196716309\n", + "Epoch 2290: Loss: 0.00017742365889716893 Loss_test: 0.00040996671305038035\n", + "Epoch 2300: Loss: 0.00014311223640106618 Loss_test: 0.00032727717189118266\n", + "Epoch 2310: Loss: 0.00010870843834709376 Loss_test: 0.0002445816935505718\n", + "Epoch 2320: Loss: 7.43426353437826e-05 Loss_test: 0.00016876458539627492\n", + "Epoch 2330: Loss: 3.997236490249634e-05 Loss_test: 8.267760131275281e-05\n", + "Epoch 2340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 2990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 3990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 4990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 5990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 6990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 7990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 8990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9000: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9010: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9020: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9030: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9040: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9050: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9060: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9070: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9080: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9090: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9100: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9110: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9120: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9130: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9140: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9150: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9160: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9170: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9180: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9190: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9200: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9210: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9220: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9230: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9240: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9250: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9260: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9270: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9280: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9290: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9300: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9310: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9320: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9330: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9340: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9350: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9360: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9370: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9380: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9390: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9400: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9410: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9420: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9430: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9440: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9450: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9460: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9470: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9480: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9490: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9500: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9510: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9520: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9530: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9540: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9550: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9560: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9570: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9580: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9590: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9600: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9610: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9620: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9630: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9640: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9650: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9660: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9670: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9680: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9690: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9700: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9710: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9720: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9730: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9740: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9750: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9760: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9770: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9780: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9790: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9800: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9810: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9820: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9830: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9840: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9850: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9860: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9870: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9880: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9890: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9900: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9910: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9920: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9930: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9940: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9950: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9960: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9970: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9980: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n", + "Epoch 9990: Loss: 6.502568430732936e-05 Loss_test: 3.3360720408381894e-05\n" + ] + } + ], + "source": [ + "epochs = 10000\n", + "\n", + "for epoch in range(epochs):\n", " model.train()\n", " y_pred = model(X_train)\n", " loss = loss_fn(y_pred, y_train)\n", " optimizer.zero_grad()\n", " loss.backward()\n", " optimizer.step()\n", - " epochs.append(epoch)\n", - " losses.append(loss.item())\n", - "plt.plot(X, y)\n", - "plt.plot(X_train, y_pred)" + " #print(f\"Epoch {epoch}: Loss: {loss}\")\n", + "\n", + " model.eval()\n", + " with torch.inference_mode():\n", + " test_pred = model(X_test)\n", + " test_loss = loss_fn(test_pred, y_test)\n", + " if epoch % 10 == 0:\n", + " print(f\"Epoch {epoch}: Loss: {loss} Loss_test: {test_loss}\") " ] + }, + { + "cell_type": "code", + "execution_count": 142, + "id": "9524c9c8", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "OrderedDict([('linear.weight', tensor([[0.6999]])),\n", + " ('linear.bias', tensor([0.3000]))])" + ] + }, + "execution_count": 142, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model.state_dict()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "afe93d3e", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": {