Skip to content

Instantly share code, notes, and snippets.

@kenorb

kenorb/torch-relu-simple-sorting-example.ipynb

Created July 20, 2022 11:54
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kenorb/cdbcb87227fa231c16c50395f8ba4a4f to your computer and use it in GitHub Desktop.
Save kenorb/cdbcb87227fa231c16c50395f8ba4a4f to your computer and use it in GitHub Desktop.
Download ZIP
Torch-relu-simple-sorting-example.ipynb
Display the source blob
Display the rendered blob
Raw
torch-relu-simple-sorting-example.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Torch-relu-simple-sorting-example.ipynb",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/kenorb/cdbcb87227fa231c16c50395f8ba4a4f/torch-relu-simple-sorting-example.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "cpaF662AfBtk"
},
"source": [
"Modified Torch example from https://pytorch.org/tutorials/beginner/pytorch_with_examples.html"
]
},
{
"cell_type": "code",
"metadata": {
"id": "IaCW3PHZEAoo"
},
"source": [
"import matplotlib.pyplot as plt\n",
"import torch\n",
"import torch.nn as nn"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Im5vJ-ggF4aX",
"outputId": "5d9f1dd3-f9ab-4697-efa3-1bfd84a4c739",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"# N is batch size; D_in is input dimension;\n",
"# H is hidden dimension; D_out is output dimension.\n",
"N, D_in, H, D_out = 0, 5, 2, 5\n",
"\n",
"# Create random Tensors to hold inputs and outputs\n",
"x = torch.arange(D_in - 1, -1, -1, dtype=torch.float32).unsqueeze_(0)\n",
"y = torch.arange(D_in, dtype=torch.float32).unsqueeze_(0)\n",
"x, y"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(tensor([[4., 3., 2., 1., 0.]]), tensor([[0., 1., 2., 3., 4.]]))"
]
},
"metadata": {
"tags": []
},
"execution_count": 2
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "3Gct9qKKPsIC",
"outputId": "a590ad52-21c1-4a58-b209-fa91e2087d4e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 391
}
},
"source": [
"# Use the nn package to define our model as a sequence of layers. nn.Sequential\n",
"# is a Module which contains other Modules, and applies them in sequence to\n",
"# produce its output. Each Linear Module computes output from input using a\n",
"# linear function, and holds internal Tensors for its weight and bias.\n",
"model = torch.nn.Sequential(\n",
" torch.nn.Linear(D_in, H),\n",
" torch.nn.ReLU(),\n",
" torch.nn.Linear(H, D_out),\n",
")\n",
"#model[0].weight.data.fill_(1)\n",
"#model[2].weight.data.fill_(1)\n",
"torch.nn.init.eye_(model[0].weight.data) # Fill with Identity.\n",
"model[0].bias.data.zero_()\n",
"torch.nn.init.eye_(model[2].weight.data) # Fill with Identity.\n",
"model[2].bias.data.fill_(1)\n",
"\n",
"print(\"Model:\\n\", model)\n",
"print(model[0], model[0].weight, model[0].bias)\n",
"print(model[2], model[2].weight, model[2].bias)\n",
"\n",
"print(model.parameters())\n",
"for name, param in model.named_parameters():\n",
" if param.requires_grad:\n",
" print(name, param.size())\n",
" else:\n",
" print(name, \"(no grad)\", param.size())"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Model:\n",
" Sequential(\n",
" (0): Linear(in_features=5, out_features=2, bias=True)\n",
" (1): ReLU()\n",
" (2): Linear(in_features=2, out_features=5, bias=True)\n",
")\n",
"Linear(in_features=5, out_features=2, bias=True) Parameter containing:\n",
"tensor([[1., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0.]], requires_grad=True) Parameter containing:\n",
"tensor([0., 0.], requires_grad=True)\n",
"Linear(in_features=2, out_features=5, bias=True) Parameter containing:\n",
"tensor([[1., 0.],\n",
" [0., 1.],\n",
" [0., 0.],\n",
" [0., 0.],\n",
" [0., 0.]], requires_grad=True) Parameter containing:\n",
"tensor([1., 1., 1., 1., 1.], requires_grad=True)\n",
"<generator object Module.parameters at 0x7fc70e5d4830>\n",
"0.weight torch.Size([2, 5])\n",
"0.bias torch.Size([2])\n",
"2.weight torch.Size([5, 2])\n",
"2.bias torch.Size([5])\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "m6Ba_8vhE0WN",
"outputId": "a103cda5-68c2-48c0-979a-088cf396ad79",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"# Reset model weights before each run.\n",
"torch.nn.init.eye_(model[0].weight.data)\n",
"torch.nn.init.eye_(model[2].weight.data)\n",
"\n",
"# The nn package also contains definitions of popular loss functions; in this\n",
"# case we will use Mean Squared Error (MSE) as our loss function.\n",
"loss_fn = torch.nn.MSELoss(reduction='sum')\n",
"\n",
"learning_rate = 0.00001\n",
"for t in range(4000):\n",
" # Forward pass: compute predicted y by passing x to the model. Module objects\n",
" # override the __call__ operator so you can call them like functions. When\n",
" # doing so you pass a Tensor of input data to the Module and it produces\n",
" # a Tensor of output data.\n",
" y_pred = model(x)\n",
" #print(y_pred)\n",
"\n",
" # Compute and print loss. We pass Tensors containing the predicted and true\n",
" # values of y, and the loss function returns a Tensor containing the\n",
" # loss.\n",
" loss = loss_fn(y_pred, y)\n",
"\n",
" # Print predicted and loss.\n",
" if t % 10 == 0:\n",
" print(t, y_pred)\n",
" print(t, \"Loss: \", loss.item())\n",
"\n",
" # Print model weights for the first 10 interations.\n",
" if t < 10:\n",
" print(model[0].weight, model[2].weight)\n",
"\n",
" # Zero the gradients before running the backward pass.\n",
" # See: https://stackoverflow.com/questions/48001598/why-do-we-need-to-call-zero-grad-in-pytorch\n",
" model.zero_grad()\n",
"\n",
" # Backward pass: compute gradient of the loss with respect to all the learnable\n",
" # parameters of the model. Internally, the parameters of each Module are stored\n",
" # in Tensors with requires_grad=True, so this call will compute gradients for\n",
" # all learnable parameters in the model.\n",
" loss.backward()\n",
"\n",
" # Update the weights using gradient descent. Each parameter is a Tensor, so\n",
" # we can access its gradients like we did before.\n",
" with torch.no_grad():\n",
" for param in model.parameters():\n",
" param -= learning_rate * param.grad\n",
"\n",
"print(y_pred)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"0 tensor([[5., 4., 1., 1., 1.]], grad_fn=<AddmmBackward>)\n",
"0 Loss: 48.0\n",
"Parameter containing:\n",
"tensor([[1., 0., 0., 0., 0.],\n",
" [0., 1., 0., 0., 0.]], requires_grad=True) Parameter containing:\n",
"tensor([[1., 0.],\n",
" [0., 1.],\n",
" [0., 0.],\n",
" [0., 0.],\n",
" [0., 0.]], requires_grad=True)\n",
"1 Loss: 47.90800094604492\n",
"Parameter containing:\n",
"tensor([[ 9.9960e-01, -3.0000e-04, -2.0000e-04, -1.0000e-04, 0.0000e+00],\n",
" [-2.4000e-04, 9.9982e-01, -1.2000e-04, -6.0000e-05, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9960e-01, -3.0000e-04],\n",
" [-2.4000e-04, 9.9982e-01],\n",
" [ 8.0000e-05, 6.0000e-05],\n",
" [ 1.6000e-04, 1.2000e-04],\n",
" [ 2.4000e-04, 1.8000e-04]], requires_grad=True)\n",
"2 Loss: 47.81632995605469\n",
"Parameter containing:\n",
"tensor([[ 9.9920e-01, -5.9943e-04, -3.9962e-04, -1.9981e-04, 0.0000e+00],\n",
" [-4.7950e-04, 9.9964e-01, -2.3975e-04, -1.1987e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9920e-01, -5.9947e-04],\n",
" [-4.7954e-04, 9.9964e-01],\n",
" [ 1.5990e-04, 1.1993e-04],\n",
" [ 3.1979e-04, 2.3986e-04],\n",
" [ 4.7969e-04, 3.5979e-04]], requires_grad=True)\n",
"3 Loss: 47.72499465942383\n",
"Parameter containing:\n",
"tensor([[ 9.9880e-01, -8.9829e-04, -5.9886e-04, -2.9943e-04, 0.0000e+00],\n",
" [-7.1849e-04, 9.9946e-01, -3.5925e-04, -1.7962e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9880e-01, -8.9842e-04],\n",
" [-7.1862e-04, 9.9946e-01],\n",
" [ 2.3969e-04, 1.7980e-04],\n",
" [ 4.7938e-04, 3.5959e-04],\n",
" [ 7.1907e-04, 5.3939e-04]], requires_grad=True)\n",
"4 Loss: 47.63397216796875\n",
"Parameter containing:\n",
"tensor([[ 9.9840e-01, -1.1966e-03, -7.9772e-04, -3.9886e-04, 0.0000e+00],\n",
" [-9.5698e-04, 9.9928e-01, -4.7849e-04, -2.3925e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9840e-01, -1.1968e-03],\n",
" [-9.5725e-04, 9.9928e-01],\n",
" [ 3.1938e-04, 2.3959e-04],\n",
" [ 6.3876e-04, 4.7918e-04],\n",
" [ 9.5814e-04, 7.1877e-04]], requires_grad=True)\n",
"5 Loss: 47.54328536987305\n",
"Parameter containing:\n",
"tensor([[ 9.9801e-01, -1.4943e-03, -9.9620e-04, -4.9810e-04, 0.0000e+00],\n",
" [-1.1950e-03, 9.9910e-01, -5.9749e-04, -2.9874e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9801e-01, -1.4947e-03],\n",
" [-1.1954e-03, 9.9910e-01],\n",
" [ 3.9897e-04, 2.9932e-04],\n",
" [ 7.9793e-04, 5.9864e-04],\n",
" [ 1.1969e-03, 8.9796e-04]], requires_grad=True)\n",
"6 Loss: 47.452919006347656\n",
"Parameter containing:\n",
"tensor([[ 9.9761e-01, -1.7915e-03, -1.1943e-03, -5.9715e-04, 0.0000e+00],\n",
" [-1.4325e-03, 9.9893e-01, -7.1624e-04, -3.5812e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9761e-01, -1.7921e-03],\n",
" [-1.4331e-03, 9.9892e-01],\n",
" [ 4.7845e-04, 3.5898e-04],\n",
" [ 9.5691e-04, 7.1796e-04],\n",
" [ 1.4354e-03, 1.0769e-03]], requires_grad=True)\n",
"7 Loss: 47.36287307739258\n",
"Parameter containing:\n",
"tensor([[ 9.9722e-01, -2.0880e-03, -1.3920e-03, -6.9602e-04, 0.0000e+00],\n",
" [-1.6695e-03, 9.9875e-01, -8.3474e-04, -4.1737e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9722e-01, -2.0890e-03],\n",
" [-1.6704e-03, 9.9875e-01],\n",
" [ 5.5784e-04, 4.1857e-04],\n",
" [ 1.1157e-03, 8.3714e-04],\n",
" [ 1.6735e-03, 1.2557e-03]], requires_grad=True)\n",
"8 Loss: 47.27314758300781\n",
"Parameter containing:\n",
"tensor([[ 9.9682e-01, -2.3841e-03, -1.5894e-03, -7.9469e-04, 0.0000e+00],\n",
" [-1.9060e-03, 9.9857e-01, -9.5299e-04, -4.7650e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9682e-01, -2.3853e-03],\n",
" [-1.9072e-03, 9.9857e-01],\n",
" [ 6.3712e-04, 4.7810e-04],\n",
" [ 1.2742e-03, 9.5619e-04],\n",
" [ 1.9114e-03, 1.4343e-03]], requires_grad=True)\n",
"9 Loss: 47.18373489379883\n",
"Parameter containing:\n",
"tensor([[ 9.9643e-01, -2.6795e-03, -1.7864e-03, -8.9318e-04, 0.0000e+00],\n",
" [-2.1420e-03, 9.9839e-01, -1.0710e-03, -5.3550e-04, 0.0000e+00]],\n",
" requires_grad=True) Parameter containing:\n",
"tensor([[ 9.9643e-01, -2.6811e-03],\n",
" [-2.1436e-03, 9.9839e-01],\n",
" [ 7.1630e-04, 5.3756e-04],\n",
" [ 1.4326e-03, 1.0751e-03],\n",
" [ 2.1489e-03, 1.6127e-03]], requires_grad=True)\n",
"10 tensor([[4.9437, 3.9662, 1.0051, 1.0103, 1.0154]], grad_fn=<AddmmBackward>)\n",
"10 Loss: 47.094642639160156\n",
"11 Loss: 47.005859375\n",
"12 Loss: 46.917396545410156\n",
"13 Loss: 46.829246520996094\n",
"14 Loss: 46.74140930175781\n",
"15 Loss: 46.65387725830078\n",
"16 Loss: 46.566650390625\n",
"17 Loss: 46.47972869873047\n",
"18 Loss: 46.39311599731445\n",
"19 Loss: 46.30679702758789\n",
"20 tensor([[4.8887, 3.9333, 1.0101, 1.0203, 1.0304]], grad_fn=<AddmmBackward>)\n",
"20 Loss: 46.22079086303711\n",
"21 Loss: 46.13507843017578\n",
"22 Loss: 46.04966735839844\n",
"23 Loss: 45.96455001831055\n",
"24 Loss: 45.879737854003906\n",
"25 Loss: 45.79521179199219\n",
"26 Loss: 45.71098709106445\n",
"27 Loss: 45.627044677734375\n",
"28 Loss: 45.543392181396484\n",
"29 Loss: 45.46003723144531\n",
"30 tensor([[4.8350, 3.9012, 1.0150, 1.0300, 1.0451]], grad_fn=<AddmmBackward>)\n",
"30 Loss: 45.37697219848633\n",
"31 Loss: 45.294185638427734\n",
"32 Loss: 45.21168518066406\n",
"33 Loss: 45.12947463989258\n",
"34 Loss: 45.047542572021484\n",
"35 Loss: 44.96588897705078\n",
"36 Loss: 44.8845100402832\n",
"37 Loss: 44.80341339111328\n",
"38 Loss: 44.722599029541016\n",
"39 Loss: 44.64206314086914\n",
"40 tensor([[4.7827, 3.8699, 1.0198, 1.0396, 1.0594]], grad_fn=<AddmmBackward>)\n",
"40 Loss: 44.561798095703125\n",
"41 Loss: 44.4818000793457\n",
"42 Loss: 44.402076721191406\n",
"43 Loss: 44.322628021240234\n",
"44 Loss: 44.24345397949219\n",
"45 Loss: 44.16453170776367\n",
"46 Loss: 44.08589553833008\n",
"47 Loss: 44.00750732421875\n",
"48 Loss: 43.92939376831055\n",
"49 Loss: 43.85154342651367\n",
"50 tensor([[4.7316, 3.8393, 1.0244, 1.0489, 1.0733]], grad_fn=<AddmmBackward>)\n",
"50 Loss: 43.773956298828125\n",
"51 Loss: 43.69662094116211\n",
"52 Loss: 43.61955642700195\n",
"53 Loss: 43.542747497558594\n",
"54 Loss: 43.46619415283203\n",
"55 Loss: 43.389896392822266\n",
"56 Loss: 43.31385803222656\n",
"57 Loss: 43.238067626953125\n",
"58 Loss: 43.16252899169922\n",
"59 Loss: 43.087249755859375\n",
"60 tensor([[4.6816, 3.8096, 1.0290, 1.0579, 1.0869]], grad_fn=<AddmmBackward>)\n",
"60 Loss: 43.01220703125\n",
"61 Loss: 42.93742370605469\n",
"62 Loss: 42.862892150878906\n",
"63 Loss: 42.78860092163086\n",
"64 Loss: 42.71455383300781\n",
"65 Loss: 42.64076232910156\n",
"66 Loss: 42.56720733642578\n",
"67 Loss: 42.49388885498047\n",
"68 Loss: 42.42082214355469\n",
"69 Loss: 42.347991943359375\n",
"70 tensor([[4.6329, 3.7805, 1.0334, 1.0668, 1.1002]], grad_fn=<AddmmBackward>)\n",
"70 Loss: 42.275390625\n",
"71 Loss: 42.20304870605469\n",
"72 Loss: 42.13093566894531\n",
"73 Loss: 42.059051513671875\n",
"74 Loss: 41.98740768432617\n",
"75 Loss: 41.91599655151367\n",
"76 Loss: 41.844818115234375\n",
"77 Loss: 41.77387619018555\n",
"78 Loss: 41.703163146972656\n",
"79 Loss: 41.63267517089844\n",
"80 tensor([[4.5852, 3.7521, 1.0377, 1.0754, 1.1131]], grad_fn=<AddmmBackward>)\n",
"80 Loss: 41.562416076660156\n",
"81 Loss: 41.49238586425781\n",
"82 Loss: 41.42258834838867\n",
"83 Loss: 41.3530158996582\n",
"84 Loss: 41.283660888671875\n",
"85 Loss: 41.214542388916016\n",
"86 Loss: 41.14563751220703\n",
"87 Loss: 41.07695388793945\n",
"88 Loss: 41.00849151611328\n",
"89 Loss: 40.94025421142578\n",
"90 tensor([[4.5386, 3.7244, 1.0419, 1.0839, 1.1258]], grad_fn=<AddmmBackward>)\n",
"90 Loss: 40.872230529785156\n",
"91 Loss: 40.80442428588867\n",
"92 Loss: 40.73683547973633\n",
"93 Loss: 40.66946792602539\n",
"94 Loss: 40.60231018066406\n",
"95 Loss: 40.535362243652344\n",
"96 Loss: 40.46864318847656\n",
"97 Loss: 40.40212631225586\n",
"98 Loss: 40.3358154296875\n",
"99 Loss: 40.26972579956055\n",
"100 tensor([[4.4931, 3.6974, 1.0461, 1.0921, 1.1382]], grad_fn=<AddmmBackward>)\n",
"100 Loss: 40.20383834838867\n",
"101 Loss: 40.13816833496094\n",
"102 Loss: 40.072696685791016\n",
"103 Loss: 40.0074348449707\n",
"104 Loss: 39.942378997802734\n",
"105 Loss: 39.877532958984375\n",
"106 Loss: 39.812889099121094\n",
"107 Loss: 39.748443603515625\n",
"108 Loss: 39.684200286865234\n",
"109 Loss: 39.62016677856445\n",
"110 tensor([[4.4485, 3.6710, 1.0501, 1.1002, 1.1503]], grad_fn=<AddmmBackward>)\n",
"110 Loss: 39.55632781982422\n",
"111 Loss: 39.49269104003906\n",
"112 Loss: 39.42925262451172\n",
"113 Loss: 39.36601257324219\n",
"114 Loss: 39.30297088623047\n",
"115 Loss: 39.24012756347656\n",
"116 Loss: 39.177467346191406\n",
"117 Loss: 39.115013122558594\n",
"118 Loss: 39.052757263183594\n",
"119 Loss: 38.990684509277344\n",
"120 tensor([[4.4050, 3.6452, 1.0540, 1.1080, 1.1621]], grad_fn=<AddmmBackward>)\n",
"120 Loss: 38.92881393432617\n",
"121 Loss: 38.86712646484375\n",
"122 Loss: 38.80563735961914\n",
"123 Loss: 38.74433135986328\n",
"124 Loss: 38.6832160949707\n",
"125 Loss: 38.62228775024414\n",
"126 Loss: 38.561546325683594\n",
"127 Loss: 38.500999450683594\n",
"128 Loss: 38.44062805175781\n",
"129 Loss: 38.38044738769531\n",
"130 tensor([[4.3623, 3.6200, 1.0579, 1.1158, 1.1736]], grad_fn=<AddmmBackward>)\n",
"130 Loss: 38.32045364379883\n",
"131 Loss: 38.26063919067383\n",
"132 Loss: 38.201011657714844\n",
"133 Loss: 38.14155960083008\n",
"134 Loss: 38.08229446411133\n",
"135 Loss: 38.02320861816406\n",
"136 Loss: 37.96430587768555\n",
"137 Loss: 37.905574798583984\n",
"138 Loss: 37.84703063964844\n",
"139 Loss: 37.78865432739258\n",
"140 tensor([[4.3206, 3.5953, 1.0616, 1.1233, 1.1849]], grad_fn=<AddmmBackward>)\n",
"140 Loss: 37.730464935302734\n",
"141 Loss: 37.67244338989258\n",
"142 Loss: 37.614601135253906\n",
"143 Loss: 37.55693054199219\n",
"144 Loss: 37.49943542480469\n",
"145 Loss: 37.442115783691406\n",
"146 Loss: 37.38496780395508\n",
"147 Loss: 37.3279914855957\n",
"148 Loss: 37.271183013916016\n",
"149 Loss: 37.21454620361328\n",
"150 tensor([[4.2798, 3.5712, 1.0653, 1.1307, 1.1960]], grad_fn=<AddmmBackward>)\n",
"150 Loss: 37.1580810546875\n",
"151 Loss: 37.10179138183594\n",
"152 Loss: 37.04566192626953\n",
"153 Loss: 36.98970031738281\n",
"154 Loss: 36.933902740478516\n",
"155 Loss: 36.87828063964844\n",
"156 Loss: 36.822818756103516\n",
"157 Loss: 36.767520904541016\n",
"158 Loss: 36.71238708496094\n",
"159 Loss: 36.65742492675781\n",
"160 tensor([[4.2398, 3.5476, 1.0689, 1.1379, 1.2068]], grad_fn=<AddmmBackward>)\n",
"160 Loss: 36.60260772705078\n",
"161 Loss: 36.54796600341797\n",
"162 Loss: 36.49348831176758\n",
"163 Loss: 36.43915939331055\n",
"164 Loss: 36.385005950927734\n",
"165 Loss: 36.330997467041016\n",
"166 Loss: 36.27715301513672\n",
"167 Loss: 36.22346878051758\n",
"168 Loss: 36.16994094848633\n",
"169 Loss: 36.1165771484375\n",
"170 tensor([[4.2007, 3.5246, 1.0725, 1.1450, 1.2174]], grad_fn=<AddmmBackward>)\n",
"170 Loss: 36.0633544921875\n",
"171 Loss: 36.01030349731445\n",
"172 Loss: 35.95740509033203\n",
"173 Loss: 35.90465545654297\n",
"174 Loss: 35.8520622253418\n",
"175 Loss: 35.799617767333984\n",
"176 Loss: 35.74733352661133\n",
"177 Loss: 35.695194244384766\n",
"178 Loss: 35.64320755004883\n",
"179 Loss: 35.59137725830078\n",
"180 tensor([[4.1623, 3.5020, 1.0759, 1.1519, 1.2278]], grad_fn=<AddmmBackward>)\n",
"180 Loss: 35.53969955444336\n",
"181 Loss: 35.488162994384766\n",
"182 Loss: 35.43677520751953\n",
"183 Loss: 35.38554382324219\n",
"184 Loss: 35.33445739746094\n",
"185 Loss: 35.28351593017578\n",
"186 Loss: 35.232723236083984\n",
"187 Loss: 35.18207550048828\n",
"188 Loss: 35.131568908691406\n",
"189 Loss: 35.08121871948242\n",
"190 tensor([[4.1248, 3.4800, 1.0793, 1.1587, 1.2380]], grad_fn=<AddmmBackward>)\n",
"190 Loss: 35.03099822998047\n",
"191 Loss: 34.980934143066406\n",
"192 Loss: 34.931007385253906\n",
"193 Loss: 34.8812255859375\n",
"194 Loss: 34.83158874511719\n",
"195 Loss: 34.78208923339844\n",
"196 Loss: 34.732730865478516\n",
"197 Loss: 34.68351364135742\n",
"198 Loss: 34.63444137573242\n",
"199 Loss: 34.58549880981445\n",
"200 tensor([[4.0880, 3.4584, 1.0826, 1.1653, 1.2479]], grad_fn=<AddmmBackward>)\n",
"200 Loss: 34.53670120239258\n",
"201 Loss: 34.488037109375\n",
"202 Loss: 34.439517974853516\n",
"203 Loss: 34.39113235473633\n",
"204 Loss: 34.34288787841797\n",
"205 Loss: 34.294769287109375\n",
"206 Loss: 34.246788024902344\n",
"207 Loss: 34.19894790649414\n",
"208 Loss: 34.151241302490234\n",
"209 Loss: 34.103668212890625\n",
"210 tensor([[4.0519, 3.4373, 1.0859, 1.1718, 1.2577]], grad_fn=<AddmmBackward>)\n",
"210 Loss: 34.05622863769531\n",
"211 Loss: 34.00892639160156\n",
"212 Loss: 33.961753845214844\n",
"213 Loss: 33.91470718383789\n",
"214 Loss: 33.8677978515625\n",
"215 Loss: 33.82101821899414\n",
"216 Loss: 33.77436828613281\n",
"217 Loss: 33.72785568237305\n",
"218 Loss: 33.68146514892578\n",
"219 Loss: 33.63520050048828\n",
"220 tensor([[4.0166, 3.4166, 1.0891, 1.1782, 1.2673]], grad_fn=<AddmmBackward>)\n",
"220 Loss: 33.58906936645508\n",
"221 Loss: 33.54307556152344\n",
"222 Loss: 33.4971923828125\n",
"223 Loss: 33.45144271850586\n",
"224 Loss: 33.405818939208984\n",
"225 Loss: 33.360328674316406\n",
"226 Loss: 33.31495666503906\n",
"227 Loss: 33.269710540771484\n",
"228 Loss: 33.22459030151367\n",
"229 Loss: 33.179595947265625\n",
"230 tensor([[3.9819, 3.3963, 1.0922, 1.1844, 1.2767]], grad_fn=<AddmmBackward>)\n",
"230 Loss: 33.13471984863281\n",
"231 Loss: 33.08997344970703\n",
"232 Loss: 33.045345306396484\n",
"233 Loss: 33.00083923339844\n",
"234 Loss: 32.956459045410156\n",
"235 Loss: 32.912200927734375\n",
"236 Loss: 32.86805725097656\n",
"237 Loss: 32.82403564453125\n",
"238 Loss: 32.78013610839844\n",
"239 Loss: 32.736358642578125\n",
"240 tensor([[3.9479, 3.3765, 1.0953, 1.1906, 1.2859]], grad_fn=<AddmmBackward>)\n",
"240 Loss: 32.69269561767578\n",
"241 Loss: 32.64915084838867\n",
"242 Loss: 32.60573196411133\n",
"243 Loss: 32.56242370605469\n",
"244 Loss: 32.51923751831055\n",
"245 Loss: 32.476165771484375\n",
"246 Loss: 32.43320846557617\n",
"247 Loss: 32.39036560058594\n",
"248 Loss: 32.3476448059082\n",
"249 Loss: 32.30503845214844\n",
"250 tensor([[3.9146, 3.3570, 1.0983, 1.1966, 1.2949]], grad_fn=<AddmmBackward>)\n",
"250 Loss: 32.262542724609375\n",
"251 Loss: 32.22016906738281\n",
"252 Loss: 32.17790222167969\n",
"253 Loss: 32.13574981689453\n",
"254 Loss: 32.093711853027344\n",
"255 Loss: 32.05178451538086\n",
"256 Loss: 32.00997543334961\n",
"257 Loss: 31.968273162841797\n",
"258 Loss: 31.926677703857422\n",
"259 Loss: 31.88520050048828\n",
"260 tensor([[3.8819, 3.3380, 1.1012, 1.2025, 1.3037]], grad_fn=<AddmmBackward>)\n",
"260 Loss: 31.84383201599121\n",
"261 Loss: 31.802574157714844\n",
"262 Loss: 31.761425018310547\n",
"263 Loss: 31.72038459777832\n",
"264 Loss: 31.679458618164062\n",
"265 Loss: 31.63863754272461\n",
"266 Loss: 31.597923278808594\n",
"267 Loss: 31.557313919067383\n",
"268 Loss: 31.51681900024414\n",
"269 Loss: 31.47643280029297\n",
"270 tensor([[3.8498, 3.3194, 1.1041, 1.2083, 1.3124]], grad_fn=<AddmmBackward>)\n",
"270 Loss: 31.43614387512207\n",
"271 Loss: 31.395965576171875\n",
"272 Loss: 31.35589027404785\n",
"273 Loss: 31.3159236907959\n",
"274 Loss: 31.276065826416016\n",
"275 Loss: 31.23630714416504\n",
"276 Loss: 31.196651458740234\n",
"277 Loss: 31.1571044921875\n",
"278 Loss: 31.117660522460938\n",
"279 Loss: 31.07831382751465\n",
"280 tensor([[3.8183, 3.3011, 1.1070, 1.2140, 1.3209]], grad_fn=<AddmmBackward>)\n",
"280 Loss: 31.039077758789062\n",
"281 Loss: 30.99993896484375\n",
"282 Loss: 30.96090316772461\n",
"283 Loss: 30.921974182128906\n",
"284 Loss: 30.88313865661621\n",
"285 Loss: 30.84441566467285\n",
"286 Loss: 30.805782318115234\n",
"287 Loss: 30.767253875732422\n",
"288 Loss: 30.72882080078125\n",
"289 Loss: 30.690492630004883\n",
"290 tensor([[3.7874, 3.2832, 1.1098, 1.2195, 1.3293]], grad_fn=<AddmmBackward>)\n",
"290 Loss: 30.65225601196289\n",
"291 Loss: 30.61412811279297\n",
"292 Loss: 30.576091766357422\n",
"293 Loss: 30.53815460205078\n",
"294 Loss: 30.500316619873047\n",
"295 Loss: 30.462574005126953\n",
"296 Loss: 30.42493438720703\n",
"297 Loss: 30.387386322021484\n",
"298 Loss: 30.34992790222168\n",
"299 Loss: 30.312580108642578\n",
"300 tensor([[3.7571, 3.2656, 1.1125, 1.2250, 1.3375]], grad_fn=<AddmmBackward>)\n",
"300 Loss: 30.27531623840332\n",
"301 Loss: 30.238155364990234\n",
"302 Loss: 30.20108413696289\n",
"303 Loss: 30.164112091064453\n",
"304 Loss: 30.127235412597656\n",
"305 Loss: 30.090450286865234\n",
"306 Loss: 30.053760528564453\n",
"307 Loss: 30.01715850830078\n",
"308 Loss: 29.980655670166016\n",
"309 Loss: 29.94424057006836\n",
"310 tensor([[3.7273, 3.2484, 1.1152, 1.2304, 1.3456]], grad_fn=<AddmmBackward>)\n",
"310 Loss: 29.90792465209961\n",
"311 Loss: 29.871694564819336\n",
"312 Loss: 29.835559844970703\n",
"313 Loss: 29.799516677856445\n",
"314 Loss: 29.763565063476562\n",
"315 Loss: 29.727699279785156\n",
"316 Loss: 29.691926956176758\n",
"317 Loss: 29.656238555908203\n",
"318 Loss: 29.620651245117188\n",
"319 Loss: 29.585147857666016\n",
"320 tensor([[3.6980, 3.2315, 1.1178, 1.2357, 1.3535]], grad_fn=<AddmmBackward>)\n",
"320 Loss: 29.54973602294922\n",
"321 Loss: 29.5144100189209\n",
"322 Loss: 29.479171752929688\n",
"323 Loss: 29.444026947021484\n",
"324 Loss: 29.40896224975586\n",
"325 Loss: 29.37398910522461\n",
"326 Loss: 29.339107513427734\n",
"327 Loss: 29.304304122924805\n",
"328 Loss: 29.269594192504883\n",
"329 Loss: 29.234973907470703\n",
"330 tensor([[3.6693, 3.2150, 1.1204, 1.2409, 1.3613]], grad_fn=<AddmmBackward>)\n",
"330 Loss: 29.200429916381836\n",
"331 Loss: 29.165983200073242\n",
"332 Loss: 29.131610870361328\n",
"333 Loss: 29.097332000732422\n",
"334 Loss: 29.063135147094727\n",
"335 Loss: 29.029022216796875\n",
"336 Loss: 28.994997024536133\n",
"337 Loss: 28.96105194091797\n",
"338 Loss: 28.927188873291016\n",
"339 Loss: 28.893413543701172\n",
"340 tensor([[3.6411, 3.1987, 1.1230, 1.2460, 1.3690]], grad_fn=<AddmmBackward>)\n",
"340 Loss: 28.85972023010254\n",
"341 Loss: 28.82611083984375\n",
"342 Loss: 28.792583465576172\n",
"343 Loss: 28.759138107299805\n",
"344 Loss: 28.72577667236328\n",
"345 Loss: 28.692489624023438\n",
"346 Loss: 28.65929412841797\n",
"347 Loss: 28.62617301940918\n",
"348 Loss: 28.593135833740234\n",
"349 Loss: 28.560178756713867\n",
"350 tensor([[3.6134, 3.1828, 1.1255, 1.2510, 1.3765]], grad_fn=<AddmmBackward>)\n",
"350 Loss: 28.527301788330078\n",
"351 Loss: 28.494510650634766\n",
"352 Loss: 28.461788177490234\n",
"353 Loss: 28.429157257080078\n",
"354 Loss: 28.396595001220703\n",
"355 Loss: 28.364120483398438\n",
"356 Loss: 28.331722259521484\n",
"357 Loss: 28.29939842224121\n",
"358 Loss: 28.26715850830078\n",
"359 Loss: 28.23499298095703\n",
"360 tensor([[3.5862, 3.1672, 1.1280, 1.2560, 1.3839]], grad_fn=<AddmmBackward>)\n",
"360 Loss: 28.20290756225586\n",
"361 Loss: 28.170900344848633\n",
"362 Loss: 28.13897132873535\n",
"363 Loss: 28.107112884521484\n",
"364 Loss: 28.075336456298828\n",
"365 Loss: 28.04363250732422\n",
"366 Loss: 28.012008666992188\n",
"367 Loss: 27.980459213256836\n",
"368 Loss: 27.948984146118164\n",
"369 Loss: 27.917585372924805\n",
"370 tensor([[3.5594, 3.1518, 1.1304, 1.2608, 1.3912]], grad_fn=<AddmmBackward>)\n",
"370 Loss: 27.886262893676758\n",
"371 Loss: 27.855010986328125\n",
"372 Loss: 27.82383918762207\n",
"373 Loss: 27.792736053466797\n",
"374 Loss: 27.76171112060547\n",
"375 Loss: 27.730762481689453\n",
"376 Loss: 27.69988250732422\n",
"377 Loss: 27.66908073425293\n",
"378 Loss: 27.638347625732422\n",
"379 Loss: 27.607688903808594\n",
"380 tensor([[3.5331, 3.1368, 1.1328, 1.2656, 1.3984]], grad_fn=<AddmmBackward>)\n",
"380 Loss: 27.577106475830078\n",
"381 Loss: 27.546592712402344\n",
"382 Loss: 27.51615333557129\n",
"383 Loss: 27.48578643798828\n",
"384 Loss: 27.455490112304688\n",
"385 Loss: 27.425264358520508\n",
"386 Loss: 27.395112991333008\n",
"387 Loss: 27.365028381347656\n",
"388 Loss: 27.33501625061035\n",
"389 Loss: 27.305078506469727\n",
"390 tensor([[3.5072, 3.1220, 1.1352, 1.2703, 1.4055]], grad_fn=<AddmmBackward>)\n",
"390 Loss: 27.275203704833984\n",
"391 Loss: 27.245407104492188\n",
"392 Loss: 27.215675354003906\n",
"393 Loss: 27.186012268066406\n",
"394 Loss: 27.15642547607422\n",
"395 Loss: 27.12689971923828\n",
"396 Loss: 27.097444534301758\n",
"397 Loss: 27.06806182861328\n",
"398 Loss: 27.038742065429688\n",
"399 Loss: 27.00949478149414\n",
"400 tensor([[3.4818, 3.1075, 1.1375, 1.2749, 1.4124]], grad_fn=<AddmmBackward>)\n",
"400 Loss: 26.980314254760742\n",
"401 Loss: 26.951204299926758\n",
"402 Loss: 26.922161102294922\n",
"403 Loss: 26.893184661865234\n",
"404 Loss: 26.864274978637695\n",
"405 Loss: 26.835430145263672\n",
"406 Loss: 26.806655883789062\n",
"407 Loss: 26.77794647216797\n",
"408 Loss: 26.749305725097656\n",
"409 Loss: 26.72072982788086\n",
"410 tensor([[3.4568, 3.0933, 1.1397, 1.2795, 1.4192]], grad_fn=<AddmmBackward>)\n",
"410 Loss: 26.692218780517578\n",
"411 Loss: 26.663772583007812\n",
"412 Loss: 26.63539695739746\n",
"413 Loss: 26.607084274291992\n",
"414 Loss: 26.57883071899414\n",
"415 Loss: 26.550643920898438\n",
"416 Loss: 26.52252960205078\n",
"417 Loss: 26.494474411010742\n",
"418 Loss: 26.466487884521484\n",
"419 Loss: 26.43855857849121\n",
"420 tensor([[3.4323, 3.0793, 1.1420, 1.2840, 1.4260]], grad_fn=<AddmmBackward>)\n",
"420 Loss: 26.410696029663086\n",
"421 Loss: 26.382896423339844\n",
"422 Loss: 26.35515785217285\n",
"423 Loss: 26.327489852905273\n",
"424 Loss: 26.299880981445312\n",
"425 Loss: 26.272335052490234\n",
"426 Loss: 26.24484634399414\n",
"427 Loss: 26.217426300048828\n",
"428 Loss: 26.190067291259766\n",
"429 Loss: 26.162769317626953\n",
"430 tensor([[3.4081, 3.0656, 1.1442, 1.2884, 1.4326]], grad_fn=<AddmmBackward>)\n",
"430 Loss: 26.135536193847656\n",
"431 Loss: 26.108362197875977\n",
"432 Loss: 26.081253051757812\n",
"433 Loss: 26.054203033447266\n",
"434 Loss: 26.02720832824707\n",
"435 Loss: 26.000282287597656\n",
"436 Loss: 25.973411560058594\n",
"437 Loss: 25.946603775024414\n",
"438 Loss: 25.919857025146484\n",
"439 Loss: 25.893169403076172\n",
"440 tensor([[3.3843, 3.0521, 1.1464, 1.2927, 1.4391]], grad_fn=<AddmmBackward>)\n",
"440 Loss: 25.866540908813477\n",
"441 Loss: 25.839969635009766\n",
"442 Loss: 25.813467025756836\n",
"443 Loss: 25.787015914916992\n",
"444 Loss: 25.7606258392334\n",
"445 Loss: 25.734298706054688\n",
"446 Loss: 25.708023071289062\n",
"447 Loss: 25.681808471679688\n",
"448 Loss: 25.655656814575195\n",
"449 Loss: 25.629558563232422\n",
"450 tensor([[3.3610, 3.0389, 1.1485, 1.2970, 1.4455]], grad_fn=<AddmmBackward>)\n",
"450 Loss: 25.603519439697266\n",
"451 Loss: 25.577537536621094\n",
"452 Loss: 25.551612854003906\n",
"453 Loss: 25.5257511138916\n",
"454 Loss: 25.499942779541016\n",
"455 Loss: 25.47418975830078\n",
"456 Loss: 25.448495864868164\n",
"457 Loss: 25.42285919189453\n",
"458 Loss: 25.397279739379883\n",
"459 Loss: 25.371753692626953\n",
"460 tensor([[3.3379, 3.0259, 1.1506, 1.3012, 1.4519]], grad_fn=<AddmmBackward>)\n",
"460 Loss: 25.346288681030273\n",
"461 Loss: 25.320873260498047\n",
"462 Loss: 25.29551887512207\n",
"463 Loss: 25.270221710205078\n",
"464 Loss: 25.244976043701172\n",
"465 Loss: 25.219785690307617\n",
"466 Loss: 25.194650650024414\n",
"467 Loss: 25.169570922851562\n",
"468 Loss: 25.144546508789062\n",
"469 Loss: 25.119579315185547\n",
"470 tensor([[3.3153, 3.0131, 1.1527, 1.3054, 1.4581]], grad_fn=<AddmmBackward>)\n",
"470 Loss: 25.094663619995117\n",
"471 Loss: 25.069805145263672\n",
"472 Loss: 25.044994354248047\n",
"473 Loss: 25.020240783691406\n",
"474 Loss: 24.995546340942383\n",
"475 Loss: 24.970901489257812\n",
"476 Loss: 24.946308135986328\n",
"477 Loss: 24.921770095825195\n",
"478 Loss: 24.897287368774414\n",
"479 Loss: 24.872854232788086\n",
"480 tensor([[3.2930, 3.0005, 1.1547, 1.3095, 1.4642]], grad_fn=<AddmmBackward>)\n",
"480 Loss: 24.84847640991211\n",
"481 Loss: 24.824148178100586\n",
"482 Loss: 24.79987335205078\n",
"483 Loss: 24.775657653808594\n",
"484 Loss: 24.751483917236328\n",
"485 Loss: 24.727371215820312\n",
"486 Loss: 24.703306198120117\n",
"487 Loss: 24.679292678833008\n",
"488 Loss: 24.65533447265625\n",
"489 Loss: 24.63142204284668\n",
"490 tensor([[3.2711, 2.9882, 1.1568, 1.3135, 1.4703]], grad_fn=<AddmmBackward>)\n",
"490 Loss: 24.60756492614746\n",
"491 Loss: 24.583757400512695\n",
"492 Loss: 24.559999465942383\n",
"493 Loss: 24.536296844482422\n",
"494 Loss: 24.51263999938965\n",
"495 Loss: 24.48904037475586\n",
"496 Loss: 24.465484619140625\n",
"497 Loss: 24.441978454589844\n",
"498 Loss: 24.41852569580078\n",
"499 Loss: 24.395124435424805\n",
"500 tensor([[3.2495, 2.9761, 1.1588, 1.3175, 1.4763]], grad_fn=<AddmmBackward>)\n",
"500 Loss: 24.371768951416016\n",
"501 Loss: 24.348464965820312\n",
"502 Loss: 24.32520866394043\n",
"503 Loss: 24.302003860473633\n",
"504 Loss: 24.278846740722656\n",
"505 Loss: 24.255741119384766\n",
"506 Loss: 24.23267936706543\n",
"507 Loss: 24.209671020507812\n",
"508 Loss: 24.18671226501465\n",
"509 Loss: 24.163795471191406\n",
"510 tensor([[3.2283, 2.9642, 1.1607, 1.3215, 1.4822]], grad_fn=<AddmmBackward>)\n",
"510 Loss: 24.140932083129883\n",
"511 Loss: 24.11811637878418\n",
"512 Loss: 24.095348358154297\n",
"513 Loss: 24.072628021240234\n",
"514 Loss: 24.049951553344727\n",
"515 Loss: 24.027332305908203\n",
"516 Loss: 24.00475311279297\n",
"517 Loss: 23.982223510742188\n",
"518 Loss: 23.95973777770996\n",
"519 Loss: 23.937305450439453\n",
"520 tensor([[3.2074, 2.9525, 1.1627, 1.3253, 1.4880]], grad_fn=<AddmmBackward>)\n",
"520 Loss: 23.914915084838867\n",
"521 Loss: 23.8925724029541\n",
"522 Loss: 23.87027359008789\n",
"523 Loss: 23.848024368286133\n",
"524 Loss: 23.825824737548828\n",
"525 Loss: 23.803668975830078\n",
"526 Loss: 23.781557083129883\n",
"527 Loss: 23.759492874145508\n",
"528 Loss: 23.737476348876953\n",
"529 Loss: 23.715499877929688\n",
"530 tensor([[3.1868, 2.9410, 1.1646, 1.3292, 1.4938]], grad_fn=<AddmmBackward>)\n",
"530 Loss: 23.693574905395508\n",
"531 Loss: 23.67169189453125\n",
"532 Loss: 23.649850845336914\n",
"533 Loss: 23.628061294555664\n",
"534 Loss: 23.606313705444336\n",
"535 Loss: 23.584611892700195\n",
"536 Loss: 23.562952041625977\n",
"537 Loss: 23.54134178161621\n",
"538 Loss: 23.519771575927734\n",
"539 Loss: 23.498247146606445\n",
"540 tensor([[3.1665, 2.9296, 1.1665, 1.3329, 1.4994]], grad_fn=<AddmmBackward>)\n",
"540 Loss: 23.476764678955078\n",
"541 Loss: 23.45532989501953\n",
"542 Loss: 23.433937072753906\n",
"543 Loss: 23.41259002685547\n",
"544 Loss: 23.39128875732422\n",
"545 Loss: 23.370027542114258\n",
"546 Loss: 23.34880828857422\n",
"547 Loss: 23.327634811401367\n",
"548 Loss: 23.306503295898438\n",
"549 Loss: 23.28541374206543\n",
"550 tensor([[3.1465, 2.9185, 1.1683, 1.3367, 1.5050]], grad_fn=<AddmmBackward>)\n",
"550 Loss: 23.264373779296875\n",
"551 Loss: 23.243370056152344\n",
"552 Loss: 23.222408294677734\n",
"553 Loss: 23.201492309570312\n",
"554 Loss: 23.180614471435547\n",
"555 Loss: 23.159786224365234\n",
"556 Loss: 23.13899803161621\n",
"557 Loss: 23.118247985839844\n",
"558 Loss: 23.097537994384766\n",
"559 Loss: 23.07687759399414\n",
"560 tensor([[3.1268, 2.9076, 1.1702, 1.3404, 1.5105]], grad_fn=<AddmmBackward>)\n",
"560 Loss: 23.05625343322754\n",
"561 Loss: 23.03567123413086\n",
"562 Loss: 23.015132904052734\n",
"563 Loss: 22.9946346282959\n",
"564 Loss: 22.974180221557617\n",
"565 Loss: 22.953763961791992\n",
"566 Loss: 22.933391571044922\n",
"567 Loss: 22.913053512573242\n",
"568 Loss: 22.89276123046875\n",
"569 Loss: 22.872509002685547\n",
"570 tensor([[3.1074, 2.8968, 1.1720, 1.3440, 1.5160]], grad_fn=<AddmmBackward>)\n",
"570 Loss: 22.852294921875\n",
"571 Loss: 22.832122802734375\n",
"572 Loss: 22.81199073791504\n",
"573 Loss: 22.791900634765625\n",
"574 Loss: 22.771848678588867\n",
"575 Loss: 22.75183868408203\n",
"576 Loss: 22.73186683654785\n",
"577 Loss: 22.71193504333496\n",
"578 Loss: 22.69204330444336\n",
"579 Loss: 22.672189712524414\n",
"580 tensor([[3.0883, 2.8862, 1.1738, 1.3476, 1.5214]], grad_fn=<AddmmBackward>)\n",
"580 Loss: 22.65237808227539\n",
"581 Loss: 22.63260269165039\n",
"582 Loss: 22.61286735534668\n",
"583 Loss: 22.593172073364258\n",
"584 Loss: 22.573516845703125\n",
"585 Loss: 22.553895950317383\n",
"586 Loss: 22.53431510925293\n",
"587 Loss: 22.514772415161133\n",
"588 Loss: 22.495275497436523\n",
"589 Loss: 22.475807189941406\n",
"590 tensor([[3.0695, 2.8758, 1.1756, 1.3511, 1.5267]], grad_fn=<AddmmBackward>)\n",
"590 Loss: 22.456382751464844\n",
"591 Loss: 22.436992645263672\n",
"592 Loss: 22.417646408081055\n",
"593 Loss: 22.398330688476562\n",
"594 Loss: 22.379058837890625\n",
"595 Loss: 22.359825134277344\n",
"596 Loss: 22.340625762939453\n",
"597 Loss: 22.32146453857422\n",
"598 Loss: 22.30234146118164\n",
"599 Loss: 22.28325653076172\n",
"600 tensor([[3.0510, 2.8656, 1.1773, 1.3546, 1.5319]], grad_fn=<AddmmBackward>)\n",
"600 Loss: 22.264205932617188\n",
"601 Loss: 22.245193481445312\n",
"602 Loss: 22.22621726989746\n",
"603 Loss: 22.2072811126709\n",
"604 Loss: 22.18838119506836\n",
"605 Loss: 22.16951560974121\n",
"606 Loss: 22.150684356689453\n",
"607 Loss: 22.131893157958984\n",
"608 Loss: 22.113142013549805\n",
"609 Loss: 22.094423294067383\n",
"610 tensor([[3.0327, 2.8555, 1.1790, 1.3581, 1.5371]], grad_fn=<AddmmBackward>)\n",
"610 Loss: 22.07573699951172\n",
"611 Loss: 22.057092666625977\n",
"612 Loss: 22.038480758666992\n",
"613 Loss: 22.019908905029297\n",
"614 Loss: 22.001367568969727\n",
"615 Loss: 21.982864379882812\n",
"616 Loss: 21.964399337768555\n",
"617 Loss: 21.94596290588379\n",
"618 Loss: 21.92756462097168\n",
"619 Loss: 21.909204483032227\n",
"620 tensor([[3.0147, 2.8456, 1.1808, 1.3615, 1.5423]], grad_fn=<AddmmBackward>)\n",
"620 Loss: 21.89087677001953\n",
"621 Loss: 21.87258529663086\n",
"622 Loss: 21.85433006286621\n",
"623 Loss: 21.836109161376953\n",
"624 Loss: 21.817920684814453\n",
"625 Loss: 21.79977035522461\n",
"626 Loss: 21.78165054321289\n",
"627 Loss: 21.763568878173828\n",
"628 Loss: 21.745521545410156\n",
"629 Loss: 21.727506637573242\n",
"630 tensor([[2.9969, 2.8359, 1.1824, 1.3649, 1.5473]], grad_fn=<AddmmBackward>)\n",
"630 Loss: 21.70952606201172\n",
"631 Loss: 21.69158172607422\n",
"632 Loss: 21.67366600036621\n",
"633 Loss: 21.655792236328125\n",
"634 Loss: 21.63794708251953\n",
"635 Loss: 21.620136260986328\n",
"636 Loss: 21.602359771728516\n",
"637 Loss: 21.58461570739746\n",
"638 Loss: 21.566905975341797\n",
"639 Loss: 21.54922866821289\n",
"640 tensor([[2.9794, 2.8263, 1.1841, 1.3682, 1.5523]], grad_fn=<AddmmBackward>)\n",
"640 Loss: 21.531585693359375\n",
"641 Loss: 21.513973236083984\n",
"642 Loss: 21.49639892578125\n",
"643 Loss: 21.47885513305664\n",
"644 Loss: 21.461345672607422\n",
"645 Loss: 21.443866729736328\n",
"646 Loss: 21.426422119140625\n",
"647 Loss: 21.40900993347168\n",
"648 Loss: 21.39162826538086\n",
"649 Loss: 21.374282836914062\n",
"650 tensor([[2.9622, 2.8168, 1.1858, 1.3715, 1.5573]], grad_fn=<AddmmBackward>)\n",
"650 Loss: 21.35696792602539\n",
"651 Loss: 21.339683532714844\n",
"652 Loss: 21.322433471679688\n",
"653 Loss: 21.305213928222656\n",
"654 Loss: 21.28802490234375\n",
"655 Loss: 21.270870208740234\n",
"656 Loss: 21.25374984741211\n",
"657 Loss: 21.23666000366211\n",
"658 Loss: 21.219600677490234\n",
"659 Loss: 21.202571868896484\n",
"660 tensor([[2.9452, 2.8076, 1.1874, 1.3748, 1.5622]], grad_fn=<AddmmBackward>)\n",
"660 Loss: 21.185579299926758\n",
"661 Loss: 21.16861343383789\n",
"662 Loss: 21.15167999267578\n",
"663 Loss: 21.134777069091797\n",
"664 Loss: 21.11790657043457\n",
"665 Loss: 21.10106658935547\n",
"666 Loss: 21.084259033203125\n",
"667 Loss: 21.06747817993164\n",
"668 Loss: 21.050731658935547\n",
"669 Loss: 21.034015655517578\n",
"670 tensor([[2.9284, 2.7984, 1.1890, 1.3780, 1.5671]], grad_fn=<AddmmBackward>)\n",
"670 Loss: 21.017330169677734\n",
"671 Loss: 21.00067901611328\n",
"672 Loss: 20.984054565429688\n",
"673 Loss: 20.967458724975586\n",
"674 Loss: 20.950897216796875\n",
"675 Loss: 20.93436050415039\n",
"676 Loss: 20.91786003112793\n",
"677 Loss: 20.901386260986328\n",
"678 Loss: 20.884946823120117\n",
"679 Loss: 20.8685302734375\n",
"680 tensor([[2.9118, 2.7894, 1.1906, 1.3812, 1.5719]], grad_fn=<AddmmBackward>)\n",
"680 Loss: 20.852148056030273\n",
"681 Loss: 20.835790634155273\n",
"682 Loss: 20.81947135925293\n",
"683 Loss: 20.80317497253418\n",
"684 Loss: 20.78691291809082\n",
"685 Loss: 20.770675659179688\n",
"686 Loss: 20.754470825195312\n",
"687 Loss: 20.73829460144043\n",
"688 Loss: 20.722148895263672\n",
"689 Loss: 20.706031799316406\n",
"690 tensor([[2.8955, 2.7806, 1.1922, 1.3844, 1.5766]], grad_fn=<AddmmBackward>)\n",
"690 Loss: 20.68994140625\n",
"691 Loss: 20.67388343811035\n",
"692 Loss: 20.657848358154297\n",
"693 Loss: 20.641847610473633\n",
"694 Loss: 20.625877380371094\n",
"695 Loss: 20.60993194580078\n",
"696 Loss: 20.59401512145996\n",
"697 Loss: 20.578128814697266\n",
"698 Loss: 20.562267303466797\n",
"699 Loss: 20.54644012451172\n",
"700 tensor([[2.8794, 2.7718, 1.1938, 1.3875, 1.5813]], grad_fn=<AddmmBackward>)\n",
"700 Loss: 20.530637741088867\n",
"701 Loss: 20.51486587524414\n",
"702 Loss: 20.49911880493164\n",
"703 Loss: 20.483400344848633\n",
"704 Loss: 20.46771240234375\n",
"705 Loss: 20.452049255371094\n",
"706 Loss: 20.436416625976562\n",
"707 Loss: 20.42081069946289\n",
"708 Loss: 20.40523338317871\n",
"709 Loss: 20.38968276977539\n",
"710 tensor([[2.8636, 2.7633, 1.1953, 1.3906, 1.5860]], grad_fn=<AddmmBackward>)\n",
"710 Loss: 20.374160766601562\n",
"711 Loss: 20.358665466308594\n",
"712 Loss: 20.343198776245117\n",
"713 Loss: 20.3277587890625\n",
"714 Loss: 20.312345504760742\n",
"715 Loss: 20.296958923339844\n",
"716 Loss: 20.281597137451172\n",
"717 Loss: 20.266265869140625\n",
"718 Loss: 20.250965118408203\n",
"719 Loss: 20.235689163208008\n",
"720 tensor([[2.8479, 2.7548, 1.1969, 1.3937, 1.5906]], grad_fn=<AddmmBackward>)\n",
"720 Loss: 20.220434188842773\n",
"721 Loss: 20.205209732055664\n",
"722 Loss: 20.190013885498047\n",
"723 Loss: 20.174842834472656\n",
"724 Loss: 20.159696578979492\n",
"725 Loss: 20.14457893371582\n",
"726 Loss: 20.129487991333008\n",
"727 Loss: 20.114423751831055\n",
"728 Loss: 20.099384307861328\n",
"729 Loss: 20.084373474121094\n",
"730 tensor([[2.8325, 2.7465, 1.1984, 1.3968, 1.5951]], grad_fn=<AddmmBackward>)\n",
"730 Loss: 20.06938934326172\n",
"731 Loss: 20.054428100585938\n",
"732 Loss: 20.03949546813965\n",
"733 Loss: 20.024587631225586\n",
"734 Loss: 20.009706497192383\n",
"735 Loss: 19.994848251342773\n",
"736 Loss: 19.980018615722656\n",
"737 Loss: 19.965213775634766\n",
"738 Loss: 19.950435638427734\n",
"739 Loss: 19.935680389404297\n",
"740 tensor([[2.8172, 2.7383, 1.1999, 1.3998, 1.5997]], grad_fn=<AddmmBackward>)\n",
"740 Loss: 19.920955657958984\n",
"741 Loss: 19.906253814697266\n",
"742 Loss: 19.89157485961914\n",
"743 Loss: 19.87692642211914\n",
"744 Loss: 19.8622989654541\n",
"745 Loss: 19.847698211669922\n",
"746 Loss: 19.83312225341797\n",
"747 Loss: 19.818572998046875\n",
"748 Loss: 19.804046630859375\n",
"749 Loss: 19.789546966552734\n",
"750 tensor([[2.8022, 2.7302, 1.2014, 1.4028, 1.6041]], grad_fn=<AddmmBackward>)\n",
"750 Loss: 19.775070190429688\n",
"751 Loss: 19.7606201171875\n",
"752 Loss: 19.746192932128906\n",
"753 Loss: 19.731788635253906\n",
"754 Loss: 19.717411041259766\n",
"755 Loss: 19.703060150146484\n",
"756 Loss: 19.688732147216797\n",
"757 Loss: 19.674427032470703\n",
"758 Loss: 19.660146713256836\n",
"759 Loss: 19.645893096923828\n",
"760 tensor([[2.7873, 2.7223, 1.2029, 1.4057, 1.6086]], grad_fn=<AddmmBackward>)\n",
"760 Loss: 19.63166046142578\n",
"761 Loss: 19.61745834350586\n",
"762 Loss: 19.603275299072266\n",
"763 Loss: 19.589115142822266\n",
"764 Loss: 19.574981689453125\n",
"765 Loss: 19.560871124267578\n",
"766 Loss: 19.546783447265625\n",
"767 Loss: 19.53272247314453\n",
"768 Loss: 19.518680572509766\n",
"769 Loss: 19.50466537475586\n",
"770 tensor([[2.7727, 2.7145, 1.2043, 1.4086, 1.6130]], grad_fn=<AddmmBackward>)\n",
"770 Loss: 19.49067497253418\n",
"771 Loss: 19.476703643798828\n",
"772 Loss: 19.46276092529297\n",
"773 Loss: 19.448841094970703\n",
"774 Loss: 19.43494415283203\n",
"775 Loss: 19.42106819152832\n",
"776 Loss: 19.40721893310547\n",
"777 Loss: 19.393390655517578\n",
"778 Loss: 19.37958526611328\n",
"779 Loss: 19.36580467224121\n",
"780 tensor([[2.7582, 2.7067, 1.2058, 1.4115, 1.6173]], grad_fn=<AddmmBackward>)\n",
"780 Loss: 19.35204315185547\n",
"781 Loss: 19.33831024169922\n",
"782 Loss: 19.324596405029297\n",
"783 Loss: 19.31090545654297\n",
"784 Loss: 19.297239303588867\n",
"785 Loss: 19.283592224121094\n",
"786 Loss: 19.269973754882812\n",
"787 Loss: 19.256376266479492\n",
"788 Loss: 19.242799758911133\n",
"789 Loss: 19.229246139526367\n",
"790 tensor([[2.7440, 2.6992, 1.2072, 1.4144, 1.6216]], grad_fn=<AddmmBackward>)\n",
"790 Loss: 19.215715408325195\n",
"791 Loss: 19.202205657958984\n",
"792 Loss: 19.188720703125\n",
"793 Loss: 19.175254821777344\n",
"794 Loss: 19.161815643310547\n",
"795 Loss: 19.148395538330078\n",
"796 Loss: 19.13499641418457\n",
"797 Loss: 19.121620178222656\n",
"798 Loss: 19.108264923095703\n",
"799 Loss: 19.094932556152344\n",
"800 tensor([[2.7299, 2.6917, 1.2086, 1.4173, 1.6259]], grad_fn=<AddmmBackward>)\n",
"800 Loss: 19.08162498474121\n",
"801 Loss: 19.068336486816406\n",
"802 Loss: 19.055068969726562\n",
"803 Loss: 19.041826248168945\n",
"804 Loss: 19.02860450744629\n",
"805 Loss: 19.015403747558594\n",
"806 Loss: 19.00222396850586\n",
"807 Loss: 18.98906707763672\n",
"808 Loss: 18.975929260253906\n",
"809 Loss: 18.962814331054688\n",
"810 tensor([[2.7160, 2.6843, 1.2101, 1.4201, 1.6302]], grad_fn=<AddmmBackward>)\n",
"810 Loss: 18.94972038269043\n",
"811 Loss: 18.936647415161133\n",
"812 Loss: 18.92359733581543\n",
"813 Loss: 18.910568237304688\n",
"814 Loss: 18.897560119628906\n",
"815 Loss: 18.884572982788086\n",
"816 Loss: 18.87160873413086\n",
"817 Loss: 18.858659744262695\n",
"818 Loss: 18.84573745727539\n",
"819 Loss: 18.832836151123047\n",
"820 tensor([[2.7023, 2.6770, 1.2115, 1.4229, 1.6344]], grad_fn=<AddmmBackward>)\n",
"820 Loss: 18.8199520111084\n",
"821 Loss: 18.807090759277344\n",
"822 Loss: 18.79425048828125\n",
"823 Loss: 18.781431198120117\n",
"824 Loss: 18.768630981445312\n",
"825 Loss: 18.755849838256836\n",
"826 Loss: 18.743091583251953\n",
"827 Loss: 18.730356216430664\n",
"828 Loss: 18.71763801574707\n",
"829 Loss: 18.70494270324707\n",
"830 tensor([[2.6887, 2.6699, 1.2128, 1.4257, 1.6385]], grad_fn=<AddmmBackward>)\n",
"830 Loss: 18.692264556884766\n",
"831 Loss: 18.679609298706055\n",
"832 Loss: 18.666973114013672\n",
"833 Loss: 18.65435791015625\n",
"834 Loss: 18.641761779785156\n",
"835 Loss: 18.629186630249023\n",
"836 Loss: 18.61663055419922\n",
"837 Loss: 18.604095458984375\n",
"838 Loss: 18.591581344604492\n",
"839 Loss: 18.579084396362305\n",
"840 tensor([[2.6753, 2.6628, 1.2142, 1.4284, 1.6427]], grad_fn=<AddmmBackward>)\n",
"840 Loss: 18.566608428955078\n",
"841 Loss: 18.55415153503418\n",
"842 Loss: 18.541717529296875\n",
"843 Loss: 18.529298782348633\n",
"844 Loss: 18.516902923583984\n",
"845 Loss: 18.5045223236084\n",
"846 Loss: 18.49216651916504\n",
"847 Loss: 18.479827880859375\n",
"848 Loss: 18.467510223388672\n",
"849 Loss: 18.455211639404297\n",
"850 tensor([[2.6621, 2.6559, 1.2156, 1.4312, 1.6468]], grad_fn=<AddmmBackward>)\n",
"850 Loss: 18.442930221557617\n",
"851 Loss: 18.4306697845459\n",
"852 Loss: 18.418426513671875\n",
"853 Loss: 18.406206130981445\n",
"854 Loss: 18.39400291442871\n",
"855 Loss: 18.381816864013672\n",
"856 Loss: 18.369653701782227\n",
"857 Loss: 18.35750961303711\n",
"858 Loss: 18.345382690429688\n",
"859 Loss: 18.33327293395996\n",
"860 tensor([[2.6491, 2.6491, 1.2170, 1.4339, 1.6509]], grad_fn=<AddmmBackward>)\n",
"860 Loss: 18.32118797302246\n",
"861 Loss: 18.309114456176758\n",
"862 Loss: 18.29706573486328\n",
"863 Loss: 18.2850341796875\n",
"864 Loss: 18.27301597595215\n",
"865 Loss: 18.261024475097656\n",
"866 Loss: 18.249048233032227\n",
"867 Loss: 18.237091064453125\n",
"868 Loss: 18.22515106201172\n",
"869 Loss: 18.213232040405273\n",
"870 tensor([[2.6362, 2.6423, 1.2183, 1.4366, 1.6549]], grad_fn=<AddmmBackward>)\n",
"870 Loss: 18.20132827758789\n",
"871 Loss: 18.18944549560547\n",
"872 Loss: 18.177579879760742\n",
"873 Loss: 18.165733337402344\n",
"874 Loss: 18.15390396118164\n",
"875 Loss: 18.142093658447266\n",
"876 Loss: 18.13030242919922\n",
"877 Loss: 18.118528366088867\n",
"878 Loss: 18.106773376464844\n",
"879 Loss: 18.095035552978516\n",
"880 tensor([[2.6234, 2.6357, 1.2196, 1.4393, 1.6589]], grad_fn=<AddmmBackward>)\n",
"880 Loss: 18.08331298828125\n",
"881 Loss: 18.071613311767578\n",
"882 Loss: 18.059926986694336\n",
"883 Loss: 18.048261642456055\n",
"884 Loss: 18.03661346435547\n",
"885 Loss: 18.024982452392578\n",
"886 Loss: 18.013370513916016\n",
"887 Loss: 18.00177574157715\n",
"888 Loss: 17.990198135375977\n",
"889 Loss: 17.9786376953125\n",
"890 tensor([[2.6109, 2.6291, 1.2210, 1.4419, 1.6629]], grad_fn=<AddmmBackward>)\n",
"890 Loss: 17.96709632873535\n",
"891 Loss: 17.9555721282959\n",
"892 Loss: 17.94406509399414\n",
"893 Loss: 17.932575225830078\n",
"894 Loss: 17.921104431152344\n",
"895 Loss: 17.909650802612305\n",
"896 Loss: 17.898212432861328\n",
"897 Loss: 17.88679313659668\n",
"898 Loss: 17.875391006469727\n",
"899 Loss: 17.864004135131836\n",
"900 tensor([[2.5984, 2.6226, 1.2223, 1.4446, 1.6669]], grad_fn=<AddmmBackward>)\n",
"900 Loss: 17.852636337280273\n",
"901 Loss: 17.841285705566406\n",
"902 Loss: 17.829952239990234\n",
"903 Loss: 17.818635940551758\n",
"904 Loss: 17.80733871459961\n",
"905 Loss: 17.79605484008789\n",
"906 Loss: 17.784786224365234\n",
"907 Loss: 17.773536682128906\n",
"908 Loss: 17.762306213378906\n",
"909 Loss: 17.7510929107666\n",
"910 tensor([[2.5862, 2.6163, 1.2236, 1.4472, 1.6708]], grad_fn=<AddmmBackward>)\n",
"910 Loss: 17.739892959594727\n",
"911 Loss: 17.72871208190918\n",
"912 Loss: 17.717546463012695\n",
"913 Loss: 17.706398010253906\n",
"914 Loss: 17.695266723632812\n",
"915 Loss: 17.684152603149414\n",
"916 Loss: 17.673053741455078\n",
"917 Loss: 17.661972045898438\n",
"918 Loss: 17.650903701782227\n",
"919 Loss: 17.639856338500977\n",
"920 tensor([[2.5740, 2.6100, 1.2249, 1.4498, 1.6747]], grad_fn=<AddmmBackward>)\n",
"920 Loss: 17.628826141357422\n",
"921 Loss: 17.617809295654297\n",
"922 Loss: 17.606807708740234\n",
"923 Loss: 17.595823287963867\n",
"924 Loss: 17.584854125976562\n",
"925 Loss: 17.57390594482422\n",
"926 Loss: 17.562973022460938\n",
"927 Loss: 17.552051544189453\n",
"928 Loss: 17.541147232055664\n",
"929 Loss: 17.53026008605957\n",
"930 tensor([[2.5621, 2.6038, 1.2262, 1.4524, 1.6786]], grad_fn=<AddmmBackward>)\n",
"930 Loss: 17.519390106201172\n",
"931 Loss: 17.508533477783203\n",
"932 Loss: 17.497695922851562\n",
"933 Loss: 17.48687171936035\n",
"934 Loss: 17.476064682006836\n",
"935 Loss: 17.46527671813965\n",
"936 Loss: 17.454498291015625\n",
"937 Loss: 17.443740844726562\n",
"938 Loss: 17.43299674987793\n",
"939 Loss: 17.42226791381836\n",
"940 tensor([[2.5502, 2.5977, 1.2275, 1.4549, 1.6824]], grad_fn=<AddmmBackward>)\n",
"940 Loss: 17.41155433654785\n",
"941 Loss: 17.40085792541504\n",
"942 Loss: 17.39017677307129\n",
"943 Loss: 17.3795108795166\n",
"944 Loss: 17.368860244750977\n",
"945 Loss: 17.35822296142578\n",
"946 Loss: 17.347604751586914\n",
"947 Loss: 17.33700180053711\n",
"948 Loss: 17.326414108276367\n",
"949 Loss: 17.315839767456055\n",
"950 tensor([[2.5385, 2.5917, 1.2288, 1.4575, 1.6863]], grad_fn=<AddmmBackward>)\n",
"950 Loss: 17.305282592773438\n",
"951 Loss: 17.294740676879883\n",
"952 Loss: 17.28421401977539\n",
"953 Loss: 17.273698806762695\n",
"954 Loss: 17.263202667236328\n",
"955 Loss: 17.25271987915039\n",
"956 Loss: 17.242252349853516\n",
"957 Loss: 17.231800079345703\n",
"958 Loss: 17.221364974975586\n",
"959 Loss: 17.21094512939453\n",
"960 tensor([[2.5270, 2.5858, 1.2300, 1.4600, 1.6901]], grad_fn=<AddmmBackward>)\n",
"960 Loss: 17.200536727905273\n",
"961 Loss: 17.190143585205078\n",
"962 Loss: 17.179765701293945\n",
"963 Loss: 17.169404983520508\n",
"964 Loss: 17.1590576171875\n",
"965 Loss: 17.148723602294922\n",
"966 Loss: 17.138408660888672\n",
"967 Loss: 17.128103256225586\n",
"968 Loss: 17.117816925048828\n",
"969 Loss: 17.107542037963867\n",
"970 tensor([[2.5156, 2.5799, 1.2313, 1.4626, 1.6938]], grad_fn=<AddmmBackward>)\n",
"970 Loss: 17.0972843170166\n",
"971 Loss: 17.087038040161133\n",
"972 Loss: 17.076807022094727\n",
"973 Loss: 17.066591262817383\n",
"974 Loss: 17.05638885498047\n",
"975 Loss: 17.04620361328125\n",
"976 Loss: 17.036029815673828\n",
"977 Loss: 17.025869369506836\n",
"978 Loss: 17.015724182128906\n",
"979 Loss: 17.005596160888672\n",
"980 tensor([[2.5043, 2.5742, 1.2325, 1.4651, 1.6976]], grad_fn=<AddmmBackward>)\n",
"980 Loss: 16.9954833984375\n",
"981 Loss: 16.985380172729492\n",
"982 Loss: 16.975292205810547\n",
"983 Loss: 16.965221405029297\n",
"984 Loss: 16.955163955688477\n",
"985 Loss: 16.945119857788086\n",
"986 Loss: 16.935089111328125\n",
"987 Loss: 16.925073623657227\n",
"988 Loss: 16.915071487426758\n",
"989 Loss: 16.90508460998535\n",
"990 tensor([[2.4931, 2.5685, 1.2338, 1.4676, 1.7013]], grad_fn=<AddmmBackward>)\n",
"990 Loss: 16.89510726928711\n",
"991 Loss: 16.885149002075195\n",
"992 Loss: 16.875200271606445\n",
"993 Loss: 16.865266799926758\n",
"994 Loss: 16.855348587036133\n",
"995 Loss: 16.84544563293457\n",
"996 Loss: 16.835554122924805\n",
"997 Loss: 16.8256778717041\n",
"998 Loss: 16.815814971923828\n",
"999 Loss: 16.80596351623535\n",
"1000 tensor([[2.4821, 2.5629, 1.2350, 1.4700, 1.7050]], grad_fn=<AddmmBackward>)\n",
"1000 Loss: 16.796127319335938\n",
"1001 Loss: 16.786304473876953\n",
"1002 Loss: 16.77649688720703\n",
"1003 Loss: 16.766700744628906\n",
"1004 Loss: 16.75691795349121\n",
"1005 Loss: 16.747150421142578\n",
"1006 Loss: 16.737396240234375\n",
"1007 Loss: 16.7276554107666\n",
"1008 Loss: 16.717924118041992\n",
"1009 Loss: 16.708209991455078\n",
"1010 tensor([[2.4712, 2.5574, 1.2362, 1.4725, 1.7087]], grad_fn=<AddmmBackward>)\n",
"1010 Loss: 16.69850730895996\n",
"1011 Loss: 16.688819885253906\n",
"1012 Loss: 16.67914390563965\n",
"1013 Loss: 16.669485092163086\n",
"1014 Loss: 16.65983772277832\n",
"1015 Loss: 16.65020179748535\n",
"1016 Loss: 16.640581130981445\n",
"1017 Loss: 16.630970001220703\n",
"1018 Loss: 16.62137222290039\n",
"1019 Loss: 16.611791610717773\n",
"1020 tensor([[2.4604, 2.5519, 1.2375, 1.4749, 1.7124]], grad_fn=<AddmmBackward>)\n",
"1020 Loss: 16.602222442626953\n",
"1021 Loss: 16.59266471862793\n",
"1022 Loss: 16.58312225341797\n",
"1023 Loss: 16.573589324951172\n",
"1024 Loss: 16.56407356262207\n",
"1025 Loss: 16.554569244384766\n",
"1026 Loss: 16.545074462890625\n",
"1027 Loss: 16.535594940185547\n",
"1028 Loss: 16.526126861572266\n",
"1029 Loss: 16.51667594909668\n",
"1030 tensor([[2.4497, 2.5465, 1.2387, 1.4774, 1.7161]], grad_fn=<AddmmBackward>)\n",
"1030 Loss: 16.507232666015625\n",
"1031 Loss: 16.497806549072266\n",
"1032 Loss: 16.488391876220703\n",
"1033 Loss: 16.47899055480957\n",
"1034 Loss: 16.469600677490234\n",
"1035 Loss: 16.460220336914062\n",
"1036 Loss: 16.450855255126953\n",
"1037 Loss: 16.441505432128906\n",
"1038 Loss: 16.43216323852539\n",
"1039 Loss: 16.422836303710938\n",
"1040 tensor([[2.4392, 2.5412, 1.2399, 1.4798, 1.7197]], grad_fn=<AddmmBackward>)\n",
"1040 Loss: 16.41352081298828\n",
"1041 Loss: 16.404216766357422\n",
"1042 Loss: 16.394926071166992\n",
"1043 Loss: 16.38564682006836\n",
"1044 Loss: 16.376386642456055\n",
"1045 Loss: 16.36713409423828\n",
"1046 Loss: 16.357891082763672\n",
"1047 Loss: 16.348663330078125\n",
"1048 Loss: 16.339447021484375\n",
"1049 Loss: 16.330242156982422\n",
"1050 tensor([[2.4288, 2.5360, 1.2411, 1.4822, 1.7233]], grad_fn=<AddmmBackward>)\n",
"1050 Loss: 16.32105255126953\n",
"1051 Loss: 16.311872482299805\n",
"1052 Loss: 16.302703857421875\n",
"1053 Loss: 16.293546676635742\n",
"1054 Loss: 16.284404754638672\n",
"1055 Loss: 16.2752742767334\n",
"1056 Loss: 16.26615333557129\n",
"1057 Loss: 16.25704574584961\n",
"1058 Loss: 16.24795150756836\n",
"1059 Loss: 16.238868713378906\n",
"1060 tensor([[2.4185, 2.5308, 1.2423, 1.4846, 1.7269]], grad_fn=<AddmmBackward>)\n",
"1060 Loss: 16.22979736328125\n",
"1061 Loss: 16.22073745727539\n",
"1062 Loss: 16.211692810058594\n",
"1063 Loss: 16.202655792236328\n",
"1064 Loss: 16.19363021850586\n",
"1065 Loss: 16.184619903564453\n",
"1066 Loss: 16.175621032714844\n",
"1067 Loss: 16.166629791259766\n",
"1068 Loss: 16.157655715942383\n",
"1069 Loss: 16.148691177368164\n",
"1070 tensor([[2.4083, 2.5257, 1.2435, 1.4870, 1.7305]], grad_fn=<AddmmBackward>)\n",
"1070 Loss: 16.139738082885742\n",
"1071 Loss: 16.130796432495117\n",
"1072 Loss: 16.12186622619629\n",
"1073 Loss: 16.112947463989258\n",
"1074 Loss: 16.10403823852539\n",
"1075 Loss: 16.095142364501953\n",
"1076 Loss: 16.086257934570312\n",
"1077 Loss: 16.0773868560791\n",
"1078 Loss: 16.068525314331055\n",
"1079 Loss: 16.059677124023438\n",
"1080 tensor([[2.3982, 2.5207, 1.2447, 1.4894, 1.7341]], grad_fn=<AddmmBackward>)\n",
"1080 Loss: 16.050838470458984\n",
"1081 Loss: 16.042011260986328\n",
"1082 Loss: 16.03319549560547\n",
"1083 Loss: 16.024394989013672\n",
"1084 Loss: 16.01559829711914\n",
"1085 Loss: 16.006820678710938\n",
"1086 Loss: 15.998050689697266\n",
"1087 Loss: 15.989288330078125\n",
"1088 Loss: 15.980544090270996\n",
"1089 Loss: 15.971807479858398\n",
"1090 tensor([[2.3882, 2.5158, 1.2459, 1.4918, 1.7376]], grad_fn=<AddmmBackward>)\n",
"1090 Loss: 15.963081359863281\n",
"1091 Loss: 15.954368591308594\n",
"1092 Loss: 15.94566535949707\n",
"1093 Loss: 15.936971664428711\n",
"1094 Loss: 15.928290367126465\n",
"1095 Loss: 15.919622421264648\n",
"1096 Loss: 15.91096305847168\n",
"1097 Loss: 15.902318000793457\n",
"1098 Loss: 15.893680572509766\n",
"1099 Loss: 15.885053634643555\n",
"1100 tensor([[2.3784, 2.5109, 1.2471, 1.4941, 1.7412]], grad_fn=<AddmmBackward>)\n",
"1100 Loss: 15.876440048217773\n",
"1101 Loss: 15.867835998535156\n",
"1102 Loss: 15.859243392944336\n",
"1103 Loss: 15.85066032409668\n",
"1104 Loss: 15.84208869934082\n",
"1105 Loss: 15.833526611328125\n",
"1106 Loss: 15.824980735778809\n",
"1107 Loss: 15.816442489624023\n",
"1108 Loss: 15.807912826538086\n",
"1109 Loss: 15.799397468566895\n",
"1110 tensor([[2.3686, 2.5061, 1.2482, 1.4965, 1.7447]], grad_fn=<AddmmBackward>)\n",
"1110 Loss: 15.790891647338867\n",
"1111 Loss: 15.782394409179688\n",
"1112 Loss: 15.773909568786621\n",
"1113 Loss: 15.765434265136719\n",
"1114 Loss: 15.75697135925293\n",
"1115 Loss: 15.748517990112305\n",
"1116 Loss: 15.740076065063477\n",
"1117 Loss: 15.731642723083496\n",
"1118 Loss: 15.72321891784668\n",
"1119 Loss: 15.714808464050293\n",
"1120 tensor([[2.3590, 2.5013, 1.2494, 1.4988, 1.7482]], grad_fn=<AddmmBackward>)\n",
"1120 Loss: 15.706406593322754\n",
"1121 Loss: 15.698015213012695\n",
"1122 Loss: 15.68963623046875\n",
"1123 Loss: 15.681266784667969\n",
"1124 Loss: 15.672908782958984\n",
"1125 Loss: 15.664556503295898\n",
"1126 Loss: 15.656221389770508\n",
"1127 Loss: 15.647891998291016\n",
"1128 Loss: 15.63957405090332\n",
"1129 Loss: 15.631267547607422\n",
"1130 tensor([[2.3495, 2.4966, 1.2506, 1.5011, 1.7517]], grad_fn=<AddmmBackward>)\n",
"1130 Loss: 15.622969627380371\n",
"1131 Loss: 15.614681243896484\n",
"1132 Loss: 15.606407165527344\n",
"1133 Loss: 15.598138809204102\n",
"1134 Loss: 15.589883804321289\n",
"1135 Loss: 15.581636428833008\n",
"1136 Loss: 15.573399543762207\n",
"1137 Loss: 15.565174102783203\n",
"1138 Loss: 15.556957244873047\n",
"1139 Loss: 15.548751831054688\n",
"1140 tensor([[2.3400, 2.4920, 1.2517, 1.5034, 1.7552]], grad_fn=<AddmmBackward>)\n",
"1140 Loss: 15.540553092956543\n",
"1141 Loss: 15.532367706298828\n",
"1142 Loss: 15.524194717407227\n",
"1143 Loss: 15.516023635864258\n",
"1144 Loss: 15.507869720458984\n",
"1145 Loss: 15.499723434448242\n",
"1146 Loss: 15.491588592529297\n",
"1147 Loss: 15.483461380004883\n",
"1148 Loss: 15.47534465789795\n",
"1149 Loss: 15.467239379882812\n",
"1150 tensor([[2.3307, 2.4874, 1.2529, 1.5058, 1.7586]], grad_fn=<AddmmBackward>)\n",
"1150 Loss: 15.45914077758789\n",
"1151 Loss: 15.451053619384766\n",
"1152 Loss: 15.442977905273438\n",
"1153 Loss: 15.43490982055664\n",
"1154 Loss: 15.426851272583008\n",
"1155 Loss: 15.418803215026855\n",
"1156 Loss: 15.410764694213867\n",
"1157 Loss: 15.402738571166992\n",
"1158 Loss: 15.394716262817383\n",
"1159 Loss: 15.386709213256836\n",
"1160 tensor([[2.3214, 2.4829, 1.2540, 1.5081, 1.7621]], grad_fn=<AddmmBackward>)\n",
"1160 Loss: 15.378708839416504\n",
"1161 Loss: 15.370718002319336\n",
"1162 Loss: 15.362737655639648\n",
"1163 Loss: 15.354766845703125\n",
"1164 Loss: 15.346807479858398\n",
"1165 Loss: 15.33885383605957\n",
"1166 Loss: 15.330909729003906\n",
"1167 Loss: 15.322979927062988\n",
"1168 Loss: 15.315053939819336\n",
"1169 Loss: 15.307141304016113\n",
"1170 tensor([[2.3123, 2.4784, 1.2552, 1.5103, 1.7655]], grad_fn=<AddmmBackward>)\n",
"1170 Loss: 15.299237251281738\n",
"1171 Loss: 15.291343688964844\n",
"1172 Loss: 15.283454895019531\n",
"1173 Loss: 15.275579452514648\n",
"1174 Loss: 15.267709732055664\n",
"1175 Loss: 15.259851455688477\n",
"1176 Loss: 15.25200366973877\n",
"1177 Loss: 15.24416446685791\n",
"1178 Loss: 15.236333847045898\n",
"1179 Loss: 15.228513717651367\n",
"1180 tensor([[2.3033, 2.4740, 1.2563, 1.5126, 1.7690]], grad_fn=<AddmmBackward>)\n",
"1180 Loss: 15.220701217651367\n",
"1181 Loss: 15.212898254394531\n",
"1182 Loss: 15.205106735229492\n",
"1183 Loss: 15.1973237991333\n",
"1184 Loss: 15.18954849243164\n",
"1185 Loss: 15.181782722473145\n",
"1186 Loss: 15.17402458190918\n",
"1187 Loss: 15.166277885437012\n",
"1188 Loss: 15.158537864685059\n",
"1189 Loss: 15.150810241699219\n",
"1190 tensor([[2.2943, 2.4697, 1.2575, 1.5149, 1.7724]], grad_fn=<AddmmBackward>)\n",
"1190 Loss: 15.143089294433594\n",
"1191 Loss: 15.135376930236816\n",
"1192 Loss: 15.127676010131836\n",
"1193 Loss: 15.11998176574707\n",
"1194 Loss: 15.112297058105469\n",
"1195 Loss: 15.104618072509766\n",
"1196 Loss: 15.096953392028809\n",
"1197 Loss: 15.089295387268066\n",
"1198 Loss: 15.081645965576172\n",
"1199 Loss: 15.074007987976074\n",
"1200 tensor([[2.2855, 2.4654, 1.2586, 1.5172, 1.7758]], grad_fn=<AddmmBackward>)\n",
"1200 Loss: 15.066375732421875\n",
"1201 Loss: 15.05875301361084\n",
"1202 Loss: 15.051138877868652\n",
"1203 Loss: 15.043533325195312\n",
"1204 Loss: 15.03593635559082\n",
"1205 Loss: 15.028350830078125\n",
"1206 Loss: 15.020772933959961\n",
"1207 Loss: 15.013200759887695\n",
"1208 Loss: 15.005642890930176\n",
"1209 Loss: 14.998086929321289\n",
"1210 tensor([[2.2767, 2.4612, 1.2597, 1.5194, 1.7792]], grad_fn=<AddmmBackward>)\n",
"1210 Loss: 14.990543365478516\n",
"1211 Loss: 14.983007431030273\n",
"1212 Loss: 14.975481986999512\n",
"1213 Loss: 14.967966079711914\n",
"1214 Loss: 14.960456848144531\n",
"1215 Loss: 14.95295524597168\n",
"1216 Loss: 14.945465087890625\n",
"1217 Loss: 14.937978744506836\n",
"1218 Loss: 14.930503845214844\n",
"1219 Loss: 14.923038482666016\n",
"1220 tensor([[2.2680, 2.4570, 1.2609, 1.5217, 1.7826]], grad_fn=<AddmmBackward>)\n",
"1220 Loss: 14.915581703186035\n",
"1221 Loss: 14.908130645751953\n",
"1222 Loss: 14.900689125061035\n",
"1223 Loss: 14.893255233764648\n",
"1224 Loss: 14.885831832885742\n",
"1225 Loss: 14.878416061401367\n",
"1226 Loss: 14.871007919311523\n",
"1227 Loss: 14.863609313964844\n",
"1228 Loss: 14.856216430664062\n",
"1229 Loss: 14.848834037780762\n",
"1230 tensor([[2.2594, 2.4529, 1.2620, 1.5240, 1.7859]], grad_fn=<AddmmBackward>)\n",
"1230 Loss: 14.841459274291992\n",
"1231 Loss: 14.834094047546387\n",
"1232 Loss: 14.82673454284668\n",
"1233 Loss: 14.819385528564453\n",
"1234 Loss: 14.81204605102539\n",
"1235 Loss: 14.804712295532227\n",
"1236 Loss: 14.797388076782227\n",
"1237 Loss: 14.790068626403809\n",
"1238 Loss: 14.782760620117188\n",
"1239 Loss: 14.775461196899414\n",
"1240 tensor([[2.2509, 2.4488, 1.2631, 1.5262, 1.7893]], grad_fn=<AddmmBackward>)\n",
"1240 Loss: 14.768169403076172\n",
"1241 Loss: 14.760884284973145\n",
"1242 Loss: 14.753606796264648\n",
"1243 Loss: 14.746341705322266\n",
"1244 Loss: 14.739081382751465\n",
"1245 Loss: 14.731828689575195\n",
"1246 Loss: 14.724583625793457\n",
"1247 Loss: 14.717347145080566\n",
"1248 Loss: 14.710123062133789\n",
"1249 Loss: 14.702901840209961\n",
"1250 tensor([[2.2425, 2.4448, 1.2642, 1.5284, 1.7927]], grad_fn=<AddmmBackward>)\n",
"1250 Loss: 14.695690155029297\n",
"1251 Loss: 14.68848705291748\n",
"1252 Loss: 14.681291580200195\n",
"1253 Loss: 14.674102783203125\n",
"1254 Loss: 14.666923522949219\n",
"1255 Loss: 14.659751892089844\n",
"1256 Loss: 14.652585983276367\n",
"1257 Loss: 14.645429611206055\n",
"1258 Loss: 14.638280868530273\n",
"1259 Loss: 14.631139755249023\n",
"1260 tensor([[2.2342, 2.4409, 1.2653, 1.5307, 1.7960]], grad_fn=<AddmmBackward>)\n",
"1260 Loss: 14.624006271362305\n",
"1261 Loss: 14.616880416870117\n",
"1262 Loss: 14.609764099121094\n",
"1263 Loss: 14.602653503417969\n",
"1264 Loss: 14.595552444458008\n",
"1265 Loss: 14.588459014892578\n",
"1266 Loss: 14.581371307373047\n",
"1267 Loss: 14.57429313659668\n",
"1268 Loss: 14.567222595214844\n",
"1269 Loss: 14.560160636901855\n",
"1270 tensor([[2.2260, 2.4370, 1.2664, 1.5329, 1.7993]], grad_fn=<AddmmBackward>)\n",
"1270 Loss: 14.553106307983398\n",
"1271 Loss: 14.546058654785156\n",
"1272 Loss: 14.539017677307129\n",
"1273 Loss: 14.531984329223633\n",
"1274 Loss: 14.5249605178833\n",
"1275 Loss: 14.517942428588867\n",
"1276 Loss: 14.510932922363281\n",
"1277 Loss: 14.503929138183594\n",
"1278 Loss: 14.496936798095703\n",
"1279 Loss: 14.489947319030762\n",
"1280 tensor([[2.2178, 2.4331, 1.2676, 1.5351, 1.8027]], grad_fn=<AddmmBackward>)\n",
"1280 Loss: 14.482967376708984\n",
"1281 Loss: 14.475996017456055\n",
"1282 Loss: 14.46903133392334\n",
"1283 Loss: 14.462071418762207\n",
"1284 Loss: 14.455121994018555\n",
"1285 Loss: 14.44818115234375\n",
"1286 Loss: 14.441246032714844\n",
"1287 Loss: 14.434318542480469\n",
"1288 Loss: 14.42739486694336\n",
"1289 Loss: 14.420483589172363\n",
"1290 tensor([[2.2097, 2.4293, 1.2687, 1.5373, 1.8060]], grad_fn=<AddmmBackward>)\n",
"1290 Loss: 14.413578033447266\n",
"1291 Loss: 14.4066801071167\n",
"1292 Loss: 14.399789810180664\n",
"1293 Loss: 14.392904281616211\n",
"1294 Loss: 14.386028289794922\n",
"1295 Loss: 14.37916088104248\n",
"1296 Loss: 14.372297286987305\n",
"1297 Loss: 14.365442276000977\n",
"1298 Loss: 14.358592987060547\n",
"1299 Loss: 14.351753234863281\n",
"1300 tensor([[2.2017, 2.4255, 1.2698, 1.5395, 1.8093]], grad_fn=<AddmmBackward>)\n",
"1300 Loss: 14.344918251037598\n",
"1301 Loss: 14.338092803955078\n",
"1302 Loss: 14.331274032592773\n",
"1303 Loss: 14.324460983276367\n",
"1304 Loss: 14.317656517028809\n",
"1305 Loss: 14.310860633850098\n",
"1306 Loss: 14.304069519042969\n",
"1307 Loss: 14.297286987304688\n",
"1308 Loss: 14.290512084960938\n",
"1309 Loss: 14.283740997314453\n",
"1310 tensor([[2.1938, 2.4218, 1.2709, 1.5418, 1.8126]], grad_fn=<AddmmBackward>)\n",
"1310 Loss: 14.276981353759766\n",
"1311 Loss: 14.270223617553711\n",
"1312 Loss: 14.263477325439453\n",
"1313 Loss: 14.256736755371094\n",
"1314 Loss: 14.250001907348633\n",
"1315 Loss: 14.24327278137207\n",
"1316 Loss: 14.236554145812988\n",
"1317 Loss: 14.229842185974121\n",
"1318 Loss: 14.223136901855469\n",
"1319 Loss: 14.216436386108398\n",
"1320 tensor([[2.1859, 2.4181, 1.2720, 1.5440, 1.8159]], grad_fn=<AddmmBackward>)\n",
"1320 Loss: 14.209745407104492\n",
"1321 Loss: 14.203059196472168\n",
"1322 Loss: 14.196382522583008\n",
"1323 Loss: 14.18971061706543\n",
"1324 Loss: 14.183046340942383\n",
"1325 Loss: 14.176389694213867\n",
"1326 Loss: 14.169736862182617\n",
"1327 Loss: 14.163094520568848\n",
"1328 Loss: 14.156455993652344\n",
"1329 Loss: 14.14982795715332\n",
"1330 tensor([[2.1782, 2.4145, 1.2731, 1.5462, 1.8192]], grad_fn=<AddmmBackward>)\n",
"1330 Loss: 14.14320182800293\n",
"1331 Loss: 14.136585235595703\n",
"1332 Loss: 14.129974365234375\n",
"1333 Loss: 14.123371124267578\n",
"1334 Loss: 14.116774559020996\n",
"1335 Loss: 14.110185623168945\n",
"1336 Loss: 14.103601455688477\n",
"1337 Loss: 14.097023010253906\n",
"1338 Loss: 14.0904541015625\n",
"1339 Loss: 14.08388900756836\n",
"1340 tensor([[2.1705, 2.4109, 1.2742, 1.5483, 1.8225]], grad_fn=<AddmmBackward>)\n",
"1340 Loss: 14.077332496643066\n",
"1341 Loss: 14.070782661437988\n",
"1342 Loss: 14.064238548278809\n",
"1343 Loss: 14.057703018188477\n",
"1344 Loss: 14.051172256469727\n",
"1345 Loss: 14.044649124145508\n",
"1346 Loss: 14.03813362121582\n",
"1347 Loss: 14.031621932983398\n",
"1348 Loss: 14.025117874145508\n",
"1349 Loss: 14.018621444702148\n",
"1350 tensor([[2.1629, 2.4074, 1.2753, 1.5505, 1.8258]], grad_fn=<AddmmBackward>)\n",
"1350 Loss: 14.012128829956055\n",
"1351 Loss: 14.005644798278809\n",
"1352 Loss: 13.999168395996094\n",
"1353 Loss: 13.992694854736328\n",
"1354 Loss: 13.986228942871094\n",
"1355 Loss: 13.97977066040039\n",
"1356 Loss: 13.973318099975586\n",
"1357 Loss: 13.966873168945312\n",
"1358 Loss: 13.960433959960938\n",
"1359 Loss: 13.954002380371094\n",
"1360 tensor([[2.1553, 2.4039, 1.2764, 1.5527, 1.8291]], grad_fn=<AddmmBackward>)\n",
"1360 Loss: 13.9475736618042\n",
"1361 Loss: 13.941155433654785\n",
"1362 Loss: 13.93474006652832\n",
"1363 Loss: 13.928332328796387\n",
"1364 Loss: 13.921932220458984\n",
"1365 Loss: 13.91553783416748\n",
"1366 Loss: 13.909149169921875\n",
"1367 Loss: 13.902769088745117\n",
"1368 Loss: 13.896390914916992\n",
"1369 Loss: 13.890021324157715\n",
"1370 tensor([[2.1479, 2.4005, 1.2775, 1.5549, 1.8324]], grad_fn=<AddmmBackward>)\n",
"1370 Loss: 13.883657455444336\n",
"1371 Loss: 13.877301216125488\n",
"1372 Loss: 13.870950698852539\n",
"1373 Loss: 13.864606857299805\n",
"1374 Loss: 13.858266830444336\n",
"1375 Loss: 13.851934432983398\n",
"1376 Loss: 13.845609664916992\n",
"1377 Loss: 13.839288711547852\n",
"1378 Loss: 13.83297348022461\n",
"1379 Loss: 13.826667785644531\n",
"1380 tensor([[2.1405, 2.3971, 1.2785, 1.5571, 1.8356]], grad_fn=<AddmmBackward>)\n",
"1380 Loss: 13.820367813110352\n",
"1381 Loss: 13.814071655273438\n",
"1382 Loss: 13.807782173156738\n",
"1383 Loss: 13.801499366760254\n",
"1384 Loss: 13.795221328735352\n",
"1385 Loss: 13.788951873779297\n",
"1386 Loss: 13.782686233520508\n",
"1387 Loss: 13.77642822265625\n",
"1388 Loss: 13.770174026489258\n",
"1389 Loss: 13.76392936706543\n",
"1390 tensor([[2.1331, 2.3937, 1.2796, 1.5593, 1.8389]], grad_fn=<AddmmBackward>)\n",
"1390 Loss: 13.757686614990234\n",
"1391 Loss: 13.75145149230957\n",
"1392 Loss: 13.745222091674805\n",
"1393 Loss: 13.73900032043457\n",
"1394 Loss: 13.732784271240234\n",
"1395 Loss: 13.726572036743164\n",
"1396 Loss: 13.720367431640625\n",
"1397 Loss: 13.714168548583984\n",
"1398 Loss: 13.707975387573242\n",
"1399 Loss: 13.701787948608398\n",
"1400 tensor([[2.1259, 2.3904, 1.2807, 1.5614, 1.8421]], grad_fn=<AddmmBackward>)\n",
"1400 Loss: 13.69560718536377\n",
"1401 Loss: 13.689434051513672\n",
"1402 Loss: 13.683263778686523\n",
"1403 Loss: 13.677099227905273\n",
"1404 Loss: 13.670942306518555\n",
"1405 Loss: 13.664790153503418\n",
"1406 Loss: 13.658645629882812\n",
"1407 Loss: 13.65250301361084\n",
"1408 Loss: 13.646368980407715\n",
"1409 Loss: 13.640241622924805\n",
"1410 tensor([[2.1187, 2.3871, 1.2818, 1.5636, 1.8454]], grad_fn=<AddmmBackward>)\n",
"1410 Loss: 13.634119033813477\n",
"1411 Loss: 13.628000259399414\n",
"1412 Loss: 13.621891021728516\n",
"1413 Loss: 13.6157865524292\n",
"1414 Loss: 13.609685897827148\n",
"1415 Loss: 13.603592872619629\n",
"1416 Loss: 13.597505569458008\n",
"1417 Loss: 13.591421127319336\n",
"1418 Loss: 13.585345268249512\n",
"1419 Loss: 13.579275131225586\n",
"1420 tensor([[2.1115, 2.3839, 1.2829, 1.5658, 1.8487]], grad_fn=<AddmmBackward>)\n",
"1420 Loss: 13.573208808898926\n",
"1421 Loss: 13.567148208618164\n",
"1422 Loss: 13.561094284057617\n",
"1423 Loss: 13.555047035217285\n",
"1424 Loss: 13.549001693725586\n",
"1425 Loss: 13.542964935302734\n",
"1426 Loss: 13.536933898925781\n",
"1427 Loss: 13.530908584594727\n",
"1428 Loss: 13.524886131286621\n",
"1429 Loss: 13.518872261047363\n",
"1430 tensor([[2.1045, 2.3807, 1.2840, 1.5679, 1.8519]], grad_fn=<AddmmBackward>)\n",
"1430 Loss: 13.512864112854004\n",
"1431 Loss: 13.506860733032227\n",
"1432 Loss: 13.500863075256348\n",
"1433 Loss: 13.494869232177734\n",
"1434 Loss: 13.488882064819336\n",
"1435 Loss: 13.482902526855469\n",
"1436 Loss: 13.476926803588867\n",
"1437 Loss: 13.470954895019531\n",
"1438 Loss: 13.464988708496094\n",
"1439 Loss: 13.459029197692871\n",
"1440 tensor([[2.0975, 2.3775, 1.2851, 1.5701, 1.8552]], grad_fn=<AddmmBackward>)\n",
"1440 Loss: 13.453075408935547\n",
"1441 Loss: 13.447128295898438\n",
"1442 Loss: 13.441183090209961\n",
"1443 Loss: 13.4352445602417\n",
"1444 Loss: 13.429312705993652\n",
"1445 Loss: 13.423383712768555\n",
"1446 Loss: 13.417462348937988\n",
"1447 Loss: 13.411545753479004\n",
"1448 Loss: 13.405635833740234\n",
"1449 Loss: 13.39972972869873\n",
"1450 tensor([[2.0905, 2.3744, 1.2861, 1.5723, 1.8584]], grad_fn=<AddmmBackward>)\n",
"1450 Loss: 13.393831253051758\n",
"1451 Loss: 13.387935638427734\n",
"1452 Loss: 13.38204574584961\n",
"1453 Loss: 13.376163482666016\n",
"1454 Loss: 13.370285034179688\n",
"1455 Loss: 13.364409446716309\n",
"1456 Loss: 13.358542442321777\n",
"1457 Loss: 13.352680206298828\n",
"1458 Loss: 13.346822738647461\n",
"1459 Loss: 13.34096908569336\n",
"1460 tensor([[2.0837, 2.3713, 1.2872, 1.5744, 1.8616]], grad_fn=<AddmmBackward>)\n",
"1460 Loss: 13.335123062133789\n",
"1461 Loss: 13.329278945922852\n",
"1462 Loss: 13.323443412780762\n",
"1463 Loss: 13.317611694335938\n",
"1464 Loss: 13.311784744262695\n",
"1465 Loss: 13.305965423583984\n",
"1466 Loss: 13.300148963928223\n",
"1467 Loss: 13.29433822631836\n",
"1468 Loss: 13.288533210754395\n",
"1469 Loss: 13.282732009887695\n",
"1470 tensor([[2.0769, 2.3682, 1.2883, 1.5766, 1.8649]], grad_fn=<AddmmBackward>)\n",
"1470 Loss: 13.276937484741211\n",
"1471 Loss: 13.27114486694336\n",
"1472 Loss: 13.265363693237305\n",
"1473 Loss: 13.25958251953125\n",
"1474 Loss: 13.253807067871094\n",
"1475 Loss: 13.248039245605469\n",
"1476 Loss: 13.242273330688477\n",
"1477 Loss: 13.236513137817383\n",
"1478 Loss: 13.23076057434082\n",
"1479 Loss: 13.225011825561523\n",
"1480 tensor([[2.0701, 2.3652, 1.2894, 1.5787, 1.8681]], grad_fn=<AddmmBackward>)\n",
"1480 Loss: 13.219266891479492\n",
"1481 Loss: 13.21352767944336\n",
"1482 Loss: 13.207794189453125\n",
"1483 Loss: 13.202066421508789\n",
"1484 Loss: 13.196340560913086\n",
"1485 Loss: 13.190622329711914\n",
"1486 Loss: 13.18490982055664\n",
"1487 Loss: 13.179201126098633\n",
"1488 Loss: 13.173498153686523\n",
"1489 Loss: 13.167798042297363\n",
"1490 tensor([[2.0634, 2.3623, 1.2904, 1.5809, 1.8713]], grad_fn=<AddmmBackward>)\n",
"1490 Loss: 13.162103652954102\n",
"1491 Loss: 13.156414031982422\n",
"1492 Loss: 13.15073013305664\n",
"1493 Loss: 13.145051956176758\n",
"1494 Loss: 13.13937759399414\n",
"1495 Loss: 13.133707046508789\n",
"1496 Loss: 13.128042221069336\n",
"1497 Loss: 13.122384071350098\n",
"1498 Loss: 13.116729736328125\n",
"1499 Loss: 13.111078262329102\n",
"1500 tensor([[2.0568, 2.3593, 1.2915, 1.5830, 1.8746]], grad_fn=<AddmmBackward>)\n",
"1500 Loss: 13.10543441772461\n",
"1501 Loss: 13.09979248046875\n",
"1502 Loss: 13.094158172607422\n",
"1503 Loss: 13.088525772094727\n",
"1504 Loss: 13.082901954650879\n",
"1505 Loss: 13.077281951904297\n",
"1506 Loss: 13.071662902832031\n",
"1507 Loss: 13.06605339050293\n",
"1508 Loss: 13.060447692871094\n",
"1509 Loss: 13.054847717285156\n",
"1510 tensor([[2.0503, 2.3564, 1.2926, 1.5852, 1.8778]], grad_fn=<AddmmBackward>)\n",
"1510 Loss: 13.049249649047852\n",
"1511 Loss: 13.043657302856445\n",
"1512 Loss: 13.038068771362305\n",
"1513 Loss: 13.032487869262695\n",
"1514 Loss: 13.026910781860352\n",
"1515 Loss: 13.021336555480957\n",
"1516 Loss: 13.015766143798828\n",
"1517 Loss: 13.010204315185547\n",
"1518 Loss: 13.004644393920898\n",
"1519 Loss: 12.999091148376465\n",
"1520 tensor([[2.0438, 2.3535, 1.2937, 1.5873, 1.8810]], grad_fn=<AddmmBackward>)\n",
"1520 Loss: 12.993539810180664\n",
"1521 Loss: 12.987995147705078\n",
"1522 Loss: 12.982455253601074\n",
"1523 Loss: 12.976920127868652\n",
"1524 Loss: 12.97138786315918\n",
"1525 Loss: 12.965864181518555\n",
"1526 Loss: 12.96034049987793\n",
"1527 Loss: 12.954824447631836\n",
"1528 Loss: 12.949312210083008\n",
"1529 Loss: 12.943803787231445\n",
"1530 tensor([[2.0373, 2.3507, 1.2947, 1.5895, 1.8842]], grad_fn=<AddmmBackward>)\n",
"1530 Loss: 12.938301086425781\n",
"1531 Loss: 12.932802200317383\n",
"1532 Loss: 12.92730712890625\n",
"1533 Loss: 12.921819686889648\n",
"1534 Loss: 12.916333198547363\n",
"1535 Loss: 12.910852432250977\n",
"1536 Loss: 12.905377388000488\n",
"1537 Loss: 12.89990520477295\n",
"1538 Loss: 12.894437789916992\n",
"1539 Loss: 12.888978004455566\n",
"1540 tensor([[2.0309, 2.3479, 1.2958, 1.5916, 1.8875]], grad_fn=<AddmmBackward>)\n",
"1540 Loss: 12.88351821899414\n",
"1541 Loss: 12.878067016601562\n",
"1542 Loss: 12.872618675231934\n",
"1543 Loss: 12.86717414855957\n",
"1544 Loss: 12.861735343933105\n",
"1545 Loss: 12.856300354003906\n",
"1546 Loss: 12.850870132446289\n",
"1547 Loss: 12.845443725585938\n",
"1548 Loss: 12.840022087097168\n",
"1549 Loss: 12.834604263305664\n",
"1550 tensor([[2.0246, 2.3451, 1.2969, 1.5938, 1.8907]], grad_fn=<AddmmBackward>)\n",
"1550 Loss: 12.829191207885742\n",
"1551 Loss: 12.823781967163086\n",
"1552 Loss: 12.818378448486328\n",
"1553 Loss: 12.812978744506836\n",
"1554 Loss: 12.80758285522461\n",
"1555 Loss: 12.802191734313965\n",
"1556 Loss: 12.796804428100586\n",
"1557 Loss: 12.791421890258789\n",
"1558 Loss: 12.786043167114258\n",
"1559 Loss: 12.780668258666992\n",
"1560 tensor([[2.0183, 2.3424, 1.2980, 1.5959, 1.8939]], grad_fn=<AddmmBackward>)\n",
"1560 Loss: 12.775300025939941\n",
"1561 Loss: 12.769935607910156\n",
"1562 Loss: 12.764575958251953\n",
"1563 Loss: 12.759218215942383\n",
"1564 Loss: 12.753868103027344\n",
"1565 Loss: 12.748518943786621\n",
"1566 Loss: 12.743175506591797\n",
"1567 Loss: 12.737838745117188\n",
"1568 Loss: 12.732501983642578\n",
"1569 Loss: 12.727170944213867\n",
"1570 tensor([[2.0121, 2.3397, 1.2990, 1.5981, 1.8971]], grad_fn=<AddmmBackward>)\n",
"1570 Loss: 12.721846580505371\n",
"1571 Loss: 12.716524124145508\n",
"1572 Loss: 12.711206436157227\n",
"1573 Loss: 12.705892562866211\n",
"1574 Loss: 12.700584411621094\n",
"1575 Loss: 12.69527816772461\n",
"1576 Loss: 12.689977645874023\n",
"1577 Loss: 12.68467903137207\n",
"1578 Loss: 12.679388046264648\n",
"1579 Loss: 12.674100875854492\n",
"1580 tensor([[2.0059, 2.3370, 1.3001, 1.6002, 1.9004]], grad_fn=<AddmmBackward>)\n",
"1580 Loss: 12.668816566467285\n",
"1581 Loss: 12.663536071777344\n",
"1582 Loss: 12.658260345458984\n",
"1583 Loss: 12.65298843383789\n",
"1584 Loss: 12.647722244262695\n",
"1585 Loss: 12.64245891571045\n",
"1586 Loss: 12.637200355529785\n",
"1587 Loss: 12.63194465637207\n",
"1588 Loss: 12.626693725585938\n",
"1589 Loss: 12.62144660949707\n",
"1590 tensor([[1.9998, 2.3344, 1.3012, 1.6024, 1.9036]], grad_fn=<AddmmBackward>)\n",
"1590 Loss: 12.616203308105469\n",
"1591 Loss: 12.610965728759766\n",
"1592 Loss: 12.605730056762695\n",
"1593 Loss: 12.60050106048584\n",
"1594 Loss: 12.595273971557617\n",
"1595 Loss: 12.590051651000977\n",
"1596 Loss: 12.584835052490234\n",
"1597 Loss: 12.579620361328125\n",
"1598 Loss: 12.574410438537598\n",
"1599 Loss: 12.569207191467285\n",
"1600 tensor([[1.9937, 2.3317, 1.3023, 1.6045, 1.9068]], grad_fn=<AddmmBackward>)\n",
"1600 Loss: 12.564002990722656\n",
"1601 Loss: 12.558806419372559\n",
"1602 Loss: 12.553613662719727\n",
"1603 Loss: 12.548423767089844\n",
"1604 Loss: 12.543237686157227\n",
"1605 Loss: 12.538055419921875\n",
"1606 Loss: 12.532877922058105\n",
"1607 Loss: 12.527702331542969\n",
"1608 Loss: 12.522533416748047\n",
"1609 Loss: 12.517366409301758\n",
"1610 tensor([[1.9877, 2.3292, 1.3033, 1.6067, 1.9100]], grad_fn=<AddmmBackward>)\n",
"1610 Loss: 12.512205123901367\n",
"1611 Loss: 12.507046699523926\n",
"1612 Loss: 12.501893043518066\n",
"1613 Loss: 12.496742248535156\n",
"1614 Loss: 12.491596221923828\n",
"1615 Loss: 12.486454010009766\n",
"1616 Loss: 12.481314659118652\n",
"1617 Loss: 12.476181030273438\n",
"1618 Loss: 12.471048355102539\n",
"1619 Loss: 12.465921401977539\n",
"1620 tensor([[1.9817, 2.3266, 1.3044, 1.6088, 1.9133]], grad_fn=<AddmmBackward>)\n",
"1620 Loss: 12.460801124572754\n",
"1621 Loss: 12.455680847167969\n",
"1622 Loss: 12.450567245483398\n",
"1623 Loss: 12.445455551147461\n",
"1624 Loss: 12.440348625183105\n",
"1625 Loss: 12.435243606567383\n",
"1626 Loss: 12.430146217346191\n",
"1627 Loss: 12.425048828125\n",
"1628 Loss: 12.419958114624023\n",
"1629 Loss: 12.414868354797363\n",
"1630 tensor([[1.9758, 2.3241, 1.3055, 1.6110, 1.9165]], grad_fn=<AddmmBackward>)\n",
"1630 Loss: 12.409784317016602\n",
"1631 Loss: 12.404704093933105\n",
"1632 Loss: 12.399626731872559\n",
"1633 Loss: 12.39455509185791\n",
"1634 Loss: 12.389485359191895\n",
"1635 Loss: 12.384420394897461\n",
"1636 Loss: 12.37936019897461\n",
"1637 Loss: 12.37430191040039\n",
"1638 Loss: 12.36924934387207\n",
"1639 Loss: 12.364197731018066\n",
"1640 tensor([[1.9699, 2.3216, 1.3066, 1.6131, 1.9197]], grad_fn=<AddmmBackward>)\n",
"1640 Loss: 12.359149932861328\n",
"1641 Loss: 12.354108810424805\n",
"1642 Loss: 12.349067687988281\n",
"1643 Loss: 12.344034194946289\n",
"1644 Loss: 12.339000701904297\n",
"1645 Loss: 12.333972930908203\n",
"1646 Loss: 12.328948974609375\n",
"1647 Loss: 12.32392692565918\n",
"1648 Loss: 12.318912506103516\n",
"1649 Loss: 12.313899040222168\n",
"1650 tensor([[1.9641, 2.3191, 1.3076, 1.6153, 1.9229]], grad_fn=<AddmmBackward>)\n",
"1650 Loss: 12.308891296386719\n",
"1651 Loss: 12.303884506225586\n",
"1652 Loss: 12.298881530761719\n",
"1653 Loss: 12.293885231018066\n",
"1654 Loss: 12.288888931274414\n",
"1655 Loss: 12.283899307250977\n",
"1656 Loss: 12.278912544250488\n",
"1657 Loss: 12.273927688598633\n",
"1658 Loss: 12.26894760131836\n",
"1659 Loss: 12.263971328735352\n",
"1660 tensor([[1.9583, 2.3167, 1.3087, 1.6174, 1.9261]], grad_fn=<AddmmBackward>)\n",
"1660 Loss: 12.258997917175293\n",
"1661 Loss: 12.2540283203125\n",
"1662 Loss: 12.249063491821289\n",
"1663 Loss: 12.244099617004395\n",
"1664 Loss: 12.239141464233398\n",
"1665 Loss: 12.234186172485352\n",
"1666 Loss: 12.22923469543457\n",
"1667 Loss: 12.224286079406738\n",
"1668 Loss: 12.219341278076172\n",
"1669 Loss: 12.214399337768555\n",
"1670 tensor([[1.9526, 2.3143, 1.3098, 1.6196, 1.9294]], grad_fn=<AddmmBackward>)\n",
"1670 Loss: 12.209463119506836\n",
"1671 Loss: 12.20452880859375\n",
"1672 Loss: 12.199600219726562\n",
"1673 Loss: 12.194671630859375\n",
"1674 Loss: 12.189750671386719\n",
"1675 Loss: 12.184829711914062\n",
"1676 Loss: 12.179915428161621\n",
"1677 Loss: 12.175003051757812\n",
"1678 Loss: 12.170093536376953\n",
"1679 Loss: 12.165188789367676\n",
"1680 tensor([[1.9469, 2.3119, 1.3109, 1.6217, 1.9326]], grad_fn=<AddmmBackward>)\n",
"1680 Loss: 12.160285949707031\n",
"1681 Loss: 12.155386924743652\n",
"1682 Loss: 12.150492668151855\n",
"1683 Loss: 12.145601272583008\n",
"1684 Loss: 12.140711784362793\n",
"1685 Loss: 12.135826110839844\n",
"1686 Loss: 12.130945205688477\n",
"1687 Loss: 12.126066207885742\n",
"1688 Loss: 12.12119197845459\n",
"1689 Loss: 12.116321563720703\n",
"1690 tensor([[1.9413, 2.3095, 1.3119, 1.6239, 1.9358]], grad_fn=<AddmmBackward>)\n",
"1690 Loss: 12.111454010009766\n",
"1691 Loss: 12.106590270996094\n",
"1692 Loss: 12.101729393005371\n",
"1693 Loss: 12.096872329711914\n",
"1694 Loss: 12.092019081115723\n",
"1695 Loss: 12.087167739868164\n",
"1696 Loss: 12.082319259643555\n",
"1697 Loss: 12.077475547790527\n",
"1698 Loss: 12.072635650634766\n",
"1699 Loss: 12.06779670715332\n",
"1700 tensor([[1.9357, 2.3072, 1.3130, 1.6260, 1.9391]], grad_fn=<AddmmBackward>)\n",
"1700 Loss: 12.062963485717773\n",
"1701 Loss: 12.058133125305176\n",
"1702 Loss: 12.053305625915527\n",
"1703 Loss: 12.048482894897461\n",
"1704 Loss: 12.043663024902344\n",
"1705 Loss: 12.038843154907227\n",
"1706 Loss: 12.034029960632324\n",
"1707 Loss: 12.029219627380371\n",
"1708 Loss: 12.0244140625\n",
"1709 Loss: 12.019609451293945\n",
"1710 tensor([[1.9302, 2.3049, 1.3141, 1.6282, 1.9423]], grad_fn=<AddmmBackward>)\n",
"1710 Loss: 12.014808654785156\n",
"1711 Loss: 12.010011672973633\n",
"1712 Loss: 12.005218505859375\n",
"1713 Loss: 12.000426292419434\n",
"1714 Loss: 11.99563980102539\n",
"1715 Loss: 11.990854263305664\n",
"1716 Loss: 11.986074447631836\n",
"1717 Loss: 11.98129653930664\n",
"1718 Loss: 11.976522445678711\n",
"1719 Loss: 11.971750259399414\n",
"1720 tensor([[1.9247, 2.3026, 1.3152, 1.6304, 1.9455]], grad_fn=<AddmmBackward>)\n",
"1720 Loss: 11.966981887817383\n",
"1721 Loss: 11.9622163772583\n",
"1722 Loss: 11.9574556350708\n",
"1723 Loss: 11.952695846557617\n",
"1724 Loss: 11.947940826416016\n",
"1725 Loss: 11.943187713623047\n",
"1726 Loss: 11.938440322875977\n",
"1727 Loss: 11.933692932128906\n",
"1728 Loss: 11.92895221710205\n",
"1729 Loss: 11.924213409423828\n",
"1730 tensor([[1.9192, 2.3004, 1.3163, 1.6325, 1.9488]], grad_fn=<AddmmBackward>)\n",
"1730 Loss: 11.919477462768555\n",
"1731 Loss: 11.914745330810547\n",
"1732 Loss: 11.910017013549805\n",
"1733 Loss: 11.905289649963379\n",
"1734 Loss: 11.900566101074219\n",
"1735 Loss: 11.89584732055664\n",
"1736 Loss: 11.891129493713379\n",
"1737 Loss: 11.886415481567383\n",
"1738 Loss: 11.881705284118652\n",
"1739 Loss: 11.876998901367188\n",
"1740 tensor([[1.9138, 2.2981, 1.3173, 1.6347, 1.9520]], grad_fn=<AddmmBackward>)\n",
"1740 Loss: 11.872292518615723\n",
"1741 Loss: 11.867591857910156\n",
"1742 Loss: 11.862892150878906\n",
"1743 Loss: 11.858198165893555\n",
"1744 Loss: 11.853507041931152\n",
"1745 Loss: 11.848817825317383\n",
"1746 Loss: 11.844131469726562\n",
"1747 Loss: 11.83945083618164\n",
"1748 Loss: 11.834771156311035\n",
"1749 Loss: 11.830093383789062\n",
"1750 tensor([[1.9085, 2.2959, 1.3184, 1.6368, 1.9553]], grad_fn=<AddmmBackward>)\n",
"1750 Loss: 11.825420379638672\n",
"1751 Loss: 11.820751190185547\n",
"1752 Loss: 11.816083908081055\n",
"1753 Loss: 11.811419486999512\n",
"1754 Loss: 11.806756973266602\n",
"1755 Loss: 11.802099227905273\n",
"1756 Loss: 11.797445297241211\n",
"1757 Loss: 11.792791366577148\n",
"1758 Loss: 11.788143157958984\n",
"1759 Loss: 11.783496856689453\n",
"1760 tensor([[1.9032, 2.2937, 1.3195, 1.6390, 1.9585]], grad_fn=<AddmmBackward>)\n",
"1760 Loss: 11.778852462768555\n",
"1761 Loss: 11.774212837219238\n",
"1762 Loss: 11.769577026367188\n",
"1763 Loss: 11.764942169189453\n",
"1764 Loss: 11.760313034057617\n",
"1765 Loss: 11.755683898925781\n",
"1766 Loss: 11.751060485839844\n",
"1767 Loss: 11.746438026428223\n",
"1768 Loss: 11.74181842803955\n",
"1769 Loss: 11.737202644348145\n",
"1770 tensor([[1.8979, 2.2916, 1.3206, 1.6412, 1.9617]], grad_fn=<AddmmBackward>)\n",
"1770 Loss: 11.732589721679688\n",
"1771 Loss: 11.72797966003418\n",
"1772 Loss: 11.723372459411621\n",
"1773 Loss: 11.718767166137695\n",
"1774 Loss: 11.714164733886719\n",
"1775 Loss: 11.70956802368164\n",
"1776 Loss: 11.704972267150879\n",
"1777 Loss: 11.70037841796875\n",
"1778 Loss: 11.695789337158203\n",
"1779 Loss: 11.691202163696289\n",
"1780 tensor([[1.8926, 2.2894, 1.3217, 1.6433, 1.9650]], grad_fn=<AddmmBackward>)\n",
"1780 Loss: 11.686617851257324\n",
"1781 Loss: 11.682036399841309\n",
"1782 Loss: 11.677457809448242\n",
"1783 Loss: 11.672883033752441\n",
"1784 Loss: 11.66831111907959\n",
"1785 Loss: 11.663741111755371\n",
"1786 Loss: 11.659175872802734\n",
"1787 Loss: 11.654611587524414\n",
"1788 Loss: 11.65005111694336\n",
"1789 Loss: 11.645492553710938\n",
"1790 tensor([[1.8874, 2.2873, 1.3227, 1.6455, 1.9682]], grad_fn=<AddmmBackward>)\n",
"1790 Loss: 11.640937805175781\n",
"1791 Loss: 11.636384963989258\n",
"1792 Loss: 11.6318359375\n",
"1793 Loss: 11.627288818359375\n",
"1794 Loss: 11.622745513916016\n",
"1795 Loss: 11.618206024169922\n",
"1796 Loss: 11.613666534423828\n",
"1797 Loss: 11.609132766723633\n",
"1798 Loss: 11.60460090637207\n",
"1799 Loss: 11.60007095336914\n",
"1800 tensor([[1.8823, 2.2852, 1.3238, 1.6477, 1.9715]], grad_fn=<AddmmBackward>)\n",
"1800 Loss: 11.59554386138916\n",
"1801 Loss: 11.591020584106445\n",
"1802 Loss: 11.58650016784668\n",
"1803 Loss: 11.581981658935547\n",
"1804 Loss: 11.57746696472168\n",
"1805 Loss: 11.572953224182129\n",
"1806 Loss: 11.568443298339844\n",
"1807 Loss: 11.563937187194824\n",
"1808 Loss: 11.559432983398438\n",
"1809 Loss: 11.554929733276367\n",
"1810 tensor([[1.8771, 2.2832, 1.3249, 1.6498, 1.9748]], grad_fn=<AddmmBackward>)\n",
"1810 Loss: 11.550431251525879\n",
"1811 Loss: 11.545934677124023\n",
"1812 Loss: 11.54144287109375\n",
"1813 Loss: 11.53695011138916\n",
"1814 Loss: 11.532463073730469\n",
"1815 Loss: 11.52797794342041\n",
"1816 Loss: 11.5234956741333\n",
"1817 Loss: 11.519018173217773\n",
"1818 Loss: 11.51453971862793\n",
"1819 Loss: 11.510066986083984\n",
"1820 tensor([[1.8721, 2.2811, 1.3260, 1.6520, 1.9780]], grad_fn=<AddmmBackward>)\n",
"1820 Loss: 11.505594253540039\n",
"1821 Loss: 11.501127243041992\n",
"1822 Loss: 11.496660232543945\n",
"1823 Loss: 11.492195129394531\n",
"1824 Loss: 11.487735748291016\n",
"1825 Loss: 11.483277320861816\n",
"1826 Loss: 11.47882080078125\n",
"1827 Loss: 11.474369049072266\n",
"1828 Loss: 11.469918251037598\n",
"1829 Loss: 11.465471267700195\n",
"1830 tensor([[1.8670, 2.2791, 1.3271, 1.6542, 1.9813]], grad_fn=<AddmmBackward>)\n",
"1830 Loss: 11.461027145385742\n",
"1831 Loss: 11.456583023071289\n",
"1832 Loss: 11.452144622802734\n",
"1833 Loss: 11.44770622253418\n",
"1834 Loss: 11.443273544311523\n",
"1835 Loss: 11.438840866088867\n",
"1836 Loss: 11.434412002563477\n",
"1837 Loss: 11.429986000061035\n",
"1838 Loss: 11.425561904907227\n",
"1839 Loss: 11.421142578125\n",
"1840 tensor([[1.8620, 2.2771, 1.3282, 1.6564, 1.9846]], grad_fn=<AddmmBackward>)\n",
"1840 Loss: 11.41672420501709\n",
"1841 Loss: 11.412307739257812\n",
"1842 Loss: 11.407896041870117\n",
"1843 Loss: 11.403484344482422\n",
"1844 Loss: 11.399076461791992\n",
"1845 Loss: 11.394672393798828\n",
"1846 Loss: 11.390268325805664\n",
"1847 Loss: 11.385869979858398\n",
"1848 Loss: 11.381473541259766\n",
"1849 Loss: 11.377076148986816\n",
"1850 tensor([[1.8570, 2.2751, 1.3293, 1.6586, 1.9878]], grad_fn=<AddmmBackward>)\n",
"1850 Loss: 11.372684478759766\n",
"1851 Loss: 11.368293762207031\n",
"1852 Loss: 11.36390495300293\n",
"1853 Loss: 11.359521865844727\n",
"1854 Loss: 11.355138778686523\n",
"1855 Loss: 11.350759506225586\n",
"1856 Loss: 11.346383094787598\n",
"1857 Loss: 11.342008590698242\n",
"1858 Loss: 11.337636947631836\n",
"1859 Loss: 11.333267211914062\n",
"1860 tensor([[1.8521, 2.2731, 1.3304, 1.6607, 1.9911]], grad_fn=<AddmmBackward>)\n",
"1860 Loss: 11.328901290893555\n",
"1861 Loss: 11.324536323547363\n",
"1862 Loss: 11.320175170898438\n",
"1863 Loss: 11.315814971923828\n",
"1864 Loss: 11.311458587646484\n",
"1865 Loss: 11.307103157043457\n",
"1866 Loss: 11.302751541137695\n",
"1867 Loss: 11.298402786254883\n",
"1868 Loss: 11.29405403137207\n",
"1869 Loss: 11.28971004486084\n",
"1870 tensor([[1.8472, 2.2712, 1.3315, 1.6629, 1.9944]], grad_fn=<AddmmBackward>)\n",
"1870 Loss: 11.285367965698242\n",
"1871 Loss: 11.281028747558594\n",
"1872 Loss: 11.276693344116211\n",
"1873 Loss: 11.272357940673828\n",
"1874 Loss: 11.268028259277344\n",
"1875 Loss: 11.263696670532227\n",
"1876 Loss: 11.259371757507324\n",
"1877 Loss: 11.255044937133789\n",
"1878 Loss: 11.250724792480469\n",
"1879 Loss: 11.246404647827148\n",
"1880 tensor([[1.8424, 2.2693, 1.3326, 1.6651, 1.9977]], grad_fn=<AddmmBackward>)\n",
"1880 Loss: 11.242086410522461\n",
"1881 Loss: 11.237771987915039\n",
"1882 Loss: 11.23345947265625\n",
"1883 Loss: 11.229148864746094\n",
"1884 Loss: 11.224841117858887\n",
"1885 Loss: 11.220535278320312\n",
"1886 Loss: 11.216233253479004\n",
"1887 Loss: 11.211932182312012\n",
"1888 Loss: 11.207633972167969\n",
"1889 Loss: 11.203338623046875\n",
"1890 tensor([[1.8375, 2.2674, 1.3337, 1.6673, 2.0010]], grad_fn=<AddmmBackward>)\n",
"1890 Loss: 11.199045181274414\n",
"1891 Loss: 11.194754600524902\n",
"1892 Loss: 11.19046688079834\n",
"1893 Loss: 11.18618106842041\n",
"1894 Loss: 11.18189811706543\n",
"1895 Loss: 11.177616119384766\n",
"1896 Loss: 11.173337936401367\n",
"1897 Loss: 11.169062614440918\n",
"1898 Loss: 11.164787292480469\n",
"1899 Loss: 11.160515785217285\n",
"1900 tensor([[1.8327, 2.2655, 1.3348, 1.6695, 2.0042]], grad_fn=<AddmmBackward>)\n",
"1900 Loss: 11.15624713897705\n",
"1901 Loss: 11.15198040008545\n",
"1902 Loss: 11.147714614868164\n",
"1903 Loss: 11.143452644348145\n",
"1904 Loss: 11.139192581176758\n",
"1905 Loss: 11.13493537902832\n",
"1906 Loss: 11.130680084228516\n",
"1907 Loss: 11.126426696777344\n",
"1908 Loss: 11.122176170349121\n",
"1909 Loss: 11.117928504943848\n",
"1910 tensor([[1.8280, 2.2636, 1.3358, 1.6717, 2.0075]], grad_fn=<AddmmBackward>)\n",
"1910 Loss: 11.113683700561523\n",
"1911 Loss: 11.109439849853516\n",
"1912 Loss: 11.10519790649414\n",
"1913 Loss: 11.100959777832031\n",
"1914 Loss: 11.096723556518555\n",
"1915 Loss: 11.092488288879395\n",
"1916 Loss: 11.088255882263184\n",
"1917 Loss: 11.084026336669922\n",
"1918 Loss: 11.079797744750977\n",
"1919 Loss: 11.075572967529297\n",
"1920 tensor([[1.8233, 2.2618, 1.3369, 1.6739, 2.0108]], grad_fn=<AddmmBackward>)\n",
"1920 Loss: 11.071351051330566\n",
"1921 Loss: 11.067129135131836\n",
"1922 Loss: 11.062911033630371\n",
"1923 Loss: 11.058695793151855\n",
"1924 Loss: 11.054481506347656\n",
"1925 Loss: 11.05026912689209\n",
"1926 Loss: 11.046060562133789\n",
"1927 Loss: 11.041853904724121\n",
"1928 Loss: 11.037650108337402\n",
"1929 Loss: 11.033447265625\n",
"1930 tensor([[1.8186, 2.2600, 1.3380, 1.6761, 2.0141]], grad_fn=<AddmmBackward>)\n",
"1930 Loss: 11.029247283935547\n",
"1931 Loss: 11.02504825592041\n",
"1932 Loss: 11.020853042602539\n",
"1933 Loss: 11.016658782958984\n",
"1934 Loss: 11.012467384338379\n",
"1935 Loss: 11.00827693939209\n",
"1936 Loss: 11.004091262817383\n",
"1937 Loss: 10.999906539916992\n",
"1938 Loss: 10.995723724365234\n",
"1939 Loss: 10.99154281616211\n",
"1940 tensor([[1.8139, 2.2582, 1.3392, 1.6783, 2.0175]], grad_fn=<AddmmBackward>)\n",
"1940 Loss: 10.987363815307617\n",
"1941 Loss: 10.983187675476074\n",
"1942 Loss: 10.97901439666748\n",
"1943 Loss: 10.974842071533203\n",
"1944 Loss: 10.970672607421875\n",
"1945 Loss: 10.966506004333496\n",
"1946 Loss: 10.962340354919434\n",
"1947 Loss: 10.95817756652832\n",
"1948 Loss: 10.954017639160156\n",
"1949 Loss: 10.949859619140625\n",
"1950 tensor([[1.8093, 2.2564, 1.3403, 1.6805, 2.0208]], grad_fn=<AddmmBackward>)\n",
"1950 Loss: 10.945703506469727\n",
"1951 Loss: 10.941549301147461\n",
"1952 Loss: 10.937397003173828\n",
"1953 Loss: 10.933246612548828\n",
"1954 Loss: 10.929100036621094\n",
"1955 Loss: 10.92495346069336\n",
"1956 Loss: 10.92081069946289\n",
"1957 Loss: 10.916668891906738\n",
"1958 Loss: 10.912528991699219\n",
"1959 Loss: 10.908392906188965\n",
"1960 tensor([[1.8047, 2.2546, 1.3414, 1.6827, 2.0241]], grad_fn=<AddmmBackward>)\n",
"1960 Loss: 10.904256820678711\n",
"1961 Loss: 10.900123596191406\n",
"1962 Loss: 10.895994186401367\n",
"1963 Loss: 10.891865730285645\n",
"1964 Loss: 10.887739181518555\n",
"1965 Loss: 10.883614540100098\n",
"1966 Loss: 10.879493713378906\n",
"1967 Loss: 10.875373840332031\n",
"1968 Loss: 10.871253967285156\n",
"1969 Loss: 10.867138862609863\n",
"1970 tensor([[1.8002, 2.2528, 1.3425, 1.6849, 2.0274]], grad_fn=<AddmmBackward>)\n",
"1970 Loss: 10.863025665283203\n",
"1971 Loss: 10.858915328979492\n",
"1972 Loss: 10.854804039001465\n",
"1973 Loss: 10.850696563720703\n",
"1974 Loss: 10.846590995788574\n",
"1975 Loss: 10.842488288879395\n",
"1976 Loss: 10.838386535644531\n",
"1977 Loss: 10.834287643432617\n",
"1978 Loss: 10.830190658569336\n",
"1979 Loss: 10.826094627380371\n",
"1980 tensor([[1.7956, 2.2511, 1.3436, 1.6872, 2.0307]], grad_fn=<AddmmBackward>)\n",
"1980 Loss: 10.822002410888672\n",
"1981 Loss: 10.817912101745605\n",
"1982 Loss: 10.813823699951172\n",
"1983 Loss: 10.809736251831055\n",
"1984 Loss: 10.805651664733887\n",
"1985 Loss: 10.801569938659668\n",
"1986 Loss: 10.79748821258545\n",
"1987 Loss: 10.793411254882812\n",
"1988 Loss: 10.78933334350586\n",
"1989 Loss: 10.785260200500488\n",
"1990 tensor([[1.7911, 2.2494, 1.3447, 1.6894, 2.0341]], grad_fn=<AddmmBackward>)\n",
"1990 Loss: 10.781187057495117\n",
"1991 Loss: 10.777115821838379\n",
"1992 Loss: 10.773046493530273\n",
"1993 Loss: 10.768980026245117\n",
"1994 Loss: 10.76491641998291\n",
"1995 Loss: 10.760852813720703\n",
"1996 Loss: 10.756793022155762\n",
"1997 Loss: 10.75273323059082\n",
"1998 Loss: 10.748679161071777\n",
"1999 Loss: 10.744623184204102\n",
"2000 tensor([[1.7867, 2.2477, 1.3458, 1.6916, 2.0374]], grad_fn=<AddmmBackward>)\n",
"2000 Loss: 10.740570068359375\n",
"2001 Loss: 10.736518859863281\n",
"2002 Loss: 10.732471466064453\n",
"2003 Loss: 10.728425025939941\n",
"2004 Loss: 10.724379539489746\n",
"2005 Loss: 10.720338821411133\n",
"2006 Loss: 10.716297149658203\n",
"2007 Loss: 10.712259292602539\n",
"2008 Loss: 10.708221435546875\n",
"2009 Loss: 10.704187393188477\n",
"2010 tensor([[1.7822, 2.2460, 1.3469, 1.6938, 2.0407]], grad_fn=<AddmmBackward>)\n",
"2010 Loss: 10.700155258178711\n",
"2011 Loss: 10.696123123168945\n",
"2012 Loss: 10.692094802856445\n",
"2013 Loss: 10.688067436218262\n",
"2014 Loss: 10.684041976928711\n",
"2015 Loss: 10.68001937866211\n",
"2016 Loss: 10.67599868774414\n",
"2017 Loss: 10.671978950500488\n",
"2018 Loss: 10.667962074279785\n",
"2019 Loss: 10.663947105407715\n",
"2020 tensor([[1.7778, 2.2443, 1.3480, 1.6961, 2.0441]], grad_fn=<AddmmBackward>)\n",
"2020 Loss: 10.659934997558594\n",
"2021 Loss: 10.655921936035156\n",
"2022 Loss: 10.651912689208984\n",
"2023 Loss: 10.647905349731445\n",
"2024 Loss: 10.643899917602539\n",
"2025 Loss: 10.63989543914795\n",
"2026 Loss: 10.635894775390625\n",
"2027 Loss: 10.6318941116333\n",
"2028 Loss: 10.62789535522461\n",
"2029 Loss: 10.623900413513184\n",
"2030 tensor([[1.7735, 2.2427, 1.3491, 1.6983, 2.0474]], grad_fn=<AddmmBackward>)\n",
"2030 Loss: 10.619906425476074\n",
"2031 Loss: 10.615912437438965\n",
"2032 Loss: 10.611922264099121\n",
"2033 Loss: 10.60793399810791\n",
"2034 Loss: 10.603946685791016\n",
"2035 Loss: 10.59996223449707\n",
"2036 Loss: 10.595980644226074\n",
"2037 Loss: 10.591999053955078\n",
"2038 Loss: 10.588020324707031\n",
"2039 Loss: 10.5840425491333\n",
"2040 tensor([[1.7691, 2.2410, 1.3503, 1.7005, 2.0508]], grad_fn=<AddmmBackward>)\n",
"2040 Loss: 10.58006763458252\n",
"2041 Loss: 10.576093673706055\n",
"2042 Loss: 10.572121620178223\n",
"2043 Loss: 10.568151473999023\n",
"2044 Loss: 10.564184188842773\n",
"2045 Loss: 10.560218811035156\n",
"2046 Loss: 10.556253433227539\n",
"2047 Loss: 10.552289962768555\n",
"2048 Loss: 10.54832935333252\n",
"2049 Loss: 10.544370651245117\n",
"2050 tensor([[1.7648, 2.2394, 1.3514, 1.7028, 2.0542]], grad_fn=<AddmmBackward>)\n",
"2050 Loss: 10.540412902832031\n",
"2051 Loss: 10.536458015441895\n",
"2052 Loss: 10.532504081726074\n",
"2053 Loss: 10.528552055358887\n",
"2054 Loss: 10.524601936340332\n",
"2055 Loss: 10.520654678344727\n",
"2056 Loss: 10.516708374023438\n",
"2057 Loss: 10.512765884399414\n",
"2058 Loss: 10.508821487426758\n",
"2059 Loss: 10.504881858825684\n",
"2060 tensor([[1.7605, 2.2378, 1.3525, 1.7050, 2.0575]], grad_fn=<AddmmBackward>)\n",
"2060 Loss: 10.50094223022461\n",
"2061 Loss: 10.497007369995117\n",
"2062 Loss: 10.493070602416992\n",
"2063 Loss: 10.489137649536133\n",
"2064 Loss: 10.48520565032959\n",
"2065 Loss: 10.48127555847168\n",
"2066 Loss: 10.477346420288086\n",
"2067 Loss: 10.473420143127441\n",
"2068 Loss: 10.46949577331543\n",
"2069 Loss: 10.465575218200684\n",
"2070 tensor([[1.7562, 2.2362, 1.3536, 1.7073, 2.0609]], grad_fn=<AddmmBackward>)\n",
"2070 Loss: 10.461652755737305\n",
"2071 Loss: 10.457735061645508\n",
"2072 Loss: 10.453817367553711\n",
"2073 Loss: 10.449901580810547\n",
"2074 Loss: 10.445987701416016\n",
"2075 Loss: 10.442076683044434\n",
"2076 Loss: 10.438164710998535\n",
"2077 Loss: 10.434256553649902\n",
"2078 Loss: 10.430349349975586\n",
"2079 Loss: 10.426445007324219\n",
"2080 tensor([[1.7520, 2.2346, 1.3548, 1.7095, 2.0643]], grad_fn=<AddmmBackward>)\n",
"2080 Loss: 10.422542572021484\n",
"2081 Loss: 10.418638229370117\n",
"2082 Loss: 10.414739608764648\n",
"2083 Loss: 10.41084098815918\n",
"2084 Loss: 10.40694522857666\n",
"2085 Loss: 10.403050422668457\n",
"2086 Loss: 10.399158477783203\n",
"2087 Loss: 10.395267486572266\n",
"2088 Loss: 10.391378402709961\n",
"2089 Loss: 10.387490272521973\n",
"2090 tensor([[1.7478, 2.2331, 1.3559, 1.7118, 2.0677]], grad_fn=<AddmmBackward>)\n",
"2090 Loss: 10.383604049682617\n",
"2091 Loss: 10.379718780517578\n",
"2092 Loss: 10.375838279724121\n",
"2093 Loss: 10.371956825256348\n",
"2094 Loss: 10.368078231811523\n",
"2095 Loss: 10.364200592041016\n",
"2096 Loss: 10.36032485961914\n",
"2097 Loss: 10.356450080871582\n",
"2098 Loss: 10.352577209472656\n",
"2099 Loss: 10.34870719909668\n",
"2100 tensor([[1.7436, 2.2315, 1.3570, 1.7140, 2.0710]], grad_fn=<AddmmBackward>)\n",
"2100 Loss: 10.34483814239502\n",
"2101 Loss: 10.340970039367676\n",
"2102 Loss: 10.337104797363281\n",
"2103 Loss: 10.33323860168457\n",
"2104 Loss: 10.329378128051758\n",
"2105 Loss: 10.325516700744629\n",
"2106 Loss: 10.321657180786133\n",
"2107 Loss: 10.317801475524902\n",
"2108 Loss: 10.313944816589355\n",
"2109 Loss: 10.310091018676758\n",
"2110 tensor([[1.7395, 2.2300, 1.3581, 1.7163, 2.0744]], grad_fn=<AddmmBackward>)\n",
"2110 Loss: 10.30624008178711\n",
"2111 Loss: 10.302388191223145\n",
"2112 Loss: 10.298540115356445\n",
"2113 Loss: 10.29469108581543\n",
"2114 Loss: 10.290846824645996\n",
"2115 Loss: 10.287001609802246\n",
"2116 Loss: 10.283159255981445\n",
"2117 Loss: 10.279319763183594\n",
"2118 Loss: 10.275480270385742\n",
"2119 Loss: 10.271641731262207\n",
"2120 tensor([[1.7354, 2.2284, 1.3593, 1.7186, 2.0778]], grad_fn=<AddmmBackward>)\n",
"2120 Loss: 10.267807006835938\n",
"2121 Loss: 10.263973236083984\n",
"2122 Loss: 10.260141372680664\n",
"2123 Loss: 10.256311416625977\n",
"2124 Loss: 10.252482414245605\n",
"2125 Loss: 10.24865436553955\n",
"2126 Loss: 10.244829177856445\n",
"2127 Loss: 10.241004943847656\n",
"2128 Loss: 10.237180709838867\n",
"2129 Loss: 10.233360290527344\n",
"2130 tensor([[1.7313, 2.2269, 1.3604, 1.7208, 2.0812]], grad_fn=<AddmmBackward>)\n",
"2130 Loss: 10.22954273223877\n",
"2131 Loss: 10.225723266601562\n",
"2132 Loss: 10.221906661987305\n",
"2133 Loss: 10.21809196472168\n",
"2134 Loss: 10.214279174804688\n",
"2135 Loss: 10.210466384887695\n",
"2136 Loss: 10.206658363342285\n",
"2137 Loss: 10.202850341796875\n",
"2138 Loss: 10.199042320251465\n",
"2139 Loss: 10.19523811340332\n",
"2140 tensor([[1.7272, 2.2254, 1.3616, 1.7231, 2.0847]], grad_fn=<AddmmBackward>)\n",
"2140 Loss: 10.191434860229492\n",
"2141 Loss: 10.187631607055664\n",
"2142 Loss: 10.183832168579102\n",
"2143 Loss: 10.180034637451172\n",
"2144 Loss: 10.176237106323242\n",
"2145 Loss: 10.172441482543945\n",
"2146 Loss: 10.168647766113281\n",
"2147 Loss: 10.16485595703125\n",
"2148 Loss: 10.161062240600586\n",
"2149 Loss: 10.157275199890137\n",
"2150 tensor([[1.7231, 2.2240, 1.3627, 1.7254, 2.0881]], grad_fn=<AddmmBackward>)\n",
"2150 Loss: 10.153487205505371\n",
"2151 Loss: 10.149701118469238\n",
"2152 Loss: 10.145915985107422\n",
"2153 Loss: 10.142131805419922\n",
"2154 Loss: 10.138351440429688\n",
"2155 Loss: 10.134570121765137\n",
"2156 Loss: 10.130791664123535\n",
"2157 Loss: 10.127015113830566\n",
"2158 Loss: 10.12324047088623\n",
"2159 Loss: 10.119464874267578\n",
"2160 tensor([[1.7191, 2.2225, 1.3638, 1.7277, 2.0915]], grad_fn=<AddmmBackward>)\n",
"2160 Loss: 10.115693092346191\n",
"2161 Loss: 10.11192512512207\n",
"2162 Loss: 10.108154296875\n",
"2163 Loss: 10.104387283325195\n",
"2164 Loss: 10.100621223449707\n",
"2165 Loss: 10.096857070922852\n",
"2166 Loss: 10.093094825744629\n",
"2167 Loss: 10.08933162689209\n",
"2168 Loss: 10.085570335388184\n",
"2169 Loss: 10.081812858581543\n",
"2170 tensor([[1.7151, 2.2210, 1.3650, 1.7300, 2.0949]], grad_fn=<AddmmBackward>)\n",
"2170 Loss: 10.078054428100586\n",
"2171 Loss: 10.074298858642578\n",
"2172 Loss: 10.070544242858887\n",
"2173 Loss: 10.066792488098145\n",
"2174 Loss: 10.063040733337402\n",
"2175 Loss: 10.05929183959961\n",
"2176 Loss: 10.055543899536133\n",
"2177 Loss: 10.051797866821289\n",
"2178 Loss: 10.048053741455078\n",
"2179 Loss: 10.044309616088867\n",
"2180 tensor([[1.7111, 2.2196, 1.3661, 1.7322, 2.0984]], grad_fn=<AddmmBackward>)\n",
"2180 Loss: 10.040567398071289\n",
"2181 Loss: 10.036827087402344\n",
"2182 Loss: 10.033087730407715\n",
"2183 Loss: 10.029350280761719\n",
"2184 Loss: 10.025613784790039\n",
"2185 Loss: 10.021879196166992\n",
"2186 Loss: 10.018145561218262\n",
"2187 Loss: 10.014413833618164\n",
"2188 Loss: 10.0106840133667\n",
"2189 Loss: 10.00695514678955\n",
"2190 tensor([[1.7072, 2.2181, 1.3673, 1.7345, 2.1018]], grad_fn=<AddmmBackward>)\n",
"2190 Loss: 10.003227233886719\n",
"2191 Loss: 9.999503135681152\n",
"2192 Loss: 9.99577808380127\n",
"2193 Loss: 9.992056846618652\n",
"2194 Loss: 9.988333702087402\n",
"2195 Loss: 9.984615325927734\n",
"2196 Loss: 9.98089599609375\n",
"2197 Loss: 9.977178573608398\n",
"2198 Loss: 9.973462104797363\n",
"2199 Loss: 9.969748497009277\n",
"2200 tensor([[1.7033, 2.2167, 1.3684, 1.7368, 2.1052]], grad_fn=<AddmmBackward>)\n",
"2200 Loss: 9.966036796569824\n",
"2201 Loss: 9.962325096130371\n",
"2202 Loss: 9.958616256713867\n",
"2203 Loss: 9.954906463623047\n",
"2204 Loss: 9.951199531555176\n",
"2205 Loss: 9.947494506835938\n",
"2206 Loss: 9.9437894821167\n",
"2207 Loss: 9.94008731842041\n",
"2208 Loss: 9.936385154724121\n",
"2209 Loss: 9.932686805725098\n",
"2210 tensor([[1.6993, 2.2153, 1.3696, 1.7391, 2.1087]], grad_fn=<AddmmBackward>)\n",
"2210 Loss: 9.928987503051758\n",
"2211 Loss: 9.92529010772705\n",
"2212 Loss: 9.921594619750977\n",
"2213 Loss: 9.917900085449219\n",
"2214 Loss: 9.914207458496094\n",
"2215 Loss: 9.910515785217285\n",
"2216 Loss: 9.906826972961426\n",
"2217 Loss: 9.903139114379883\n",
"2218 Loss: 9.899452209472656\n",
"2219 Loss: 9.895766258239746\n",
"2220 tensor([[1.6955, 2.2139, 1.3707, 1.7414, 2.1122]], grad_fn=<AddmmBackward>)\n",
"2220 Loss: 9.892082214355469\n",
"2221 Loss: 9.888399124145508\n",
"2222 Loss: 9.884716987609863\n",
"2223 Loss: 9.881036758422852\n",
"2224 Loss: 9.877359390258789\n",
"2225 Loss: 9.873682022094727\n",
"2226 Loss: 9.87000560760498\n",
"2227 Loss: 9.866331100463867\n",
"2228 Loss: 9.862659454345703\n",
"2229 Loss: 9.858987808227539\n",
"2230 tensor([[1.6916, 2.2125, 1.3719, 1.7437, 2.1156]], grad_fn=<AddmmBackward>)\n",
"2230 Loss: 9.855316162109375\n",
"2231 Loss: 9.851646423339844\n",
"2232 Loss: 9.847978591918945\n",
"2233 Loss: 9.844313621520996\n",
"2234 Loss: 9.840648651123047\n",
"2235 Loss: 9.836984634399414\n",
"2236 Loss: 9.83332347869873\n",
"2237 Loss: 9.829662322998047\n",
"2238 Loss: 9.82600212097168\n",
"2239 Loss: 9.822343826293945\n",
"2240 tensor([[1.6878, 2.2111, 1.3730, 1.7461, 2.1191]], grad_fn=<AddmmBackward>)\n",
"2240 Loss: 9.818687438964844\n",
"2241 Loss: 9.815032958984375\n",
"2242 Loss: 9.811379432678223\n",
"2243 Loss: 9.807726860046387\n",
"2244 Loss: 9.804075241088867\n",
"2245 Loss: 9.800424575805664\n",
"2246 Loss: 9.79677677154541\n",
"2247 Loss: 9.793129920959473\n",
"2248 Loss: 9.789484024047852\n",
"2249 Loss: 9.785839080810547\n",
"2250 tensor([[1.6840, 2.2098, 1.3742, 1.7484, 2.1226]], grad_fn=<AddmmBackward>)\n",
"2250 Loss: 9.782196044921875\n",
"2251 Loss: 9.778554916381836\n",
"2252 Loss: 9.774913787841797\n",
"2253 Loss: 9.771276473999023\n",
"2254 Loss: 9.767637252807617\n",
"2255 Loss: 9.764001846313477\n",
"2256 Loss: 9.76036548614502\n",
"2257 Loss: 9.756731033325195\n",
"2258 Loss: 9.753098487854004\n",
"2259 Loss: 9.749466896057129\n",
"2260 tensor([[1.6802, 2.2084, 1.3754, 1.7507, 2.1261]], grad_fn=<AddmmBackward>)\n",
"2260 Loss: 9.745838165283203\n",
"2261 Loss: 9.742208480834961\n",
"2262 Loss: 9.738581657409668\n",
"2263 Loss: 9.734954833984375\n",
"2264 Loss: 9.731330871582031\n",
"2265 Loss: 9.727707862854004\n",
"2266 Loss: 9.72408676147461\n",
"2267 Loss: 9.720464706420898\n",
"2268 Loss: 9.716846466064453\n",
"2269 Loss: 9.713229179382324\n",
"2270 tensor([[1.6764, 2.2071, 1.3765, 1.7530, 2.1295]], grad_fn=<AddmmBackward>)\n",
"2270 Loss: 9.709611892700195\n",
"2271 Loss: 9.705995559692383\n",
"2272 Loss: 9.702381134033203\n",
"2273 Loss: 9.698768615722656\n",
"2274 Loss: 9.69515609741211\n",
"2275 Loss: 9.691545486450195\n",
"2276 Loss: 9.687936782836914\n",
"2277 Loss: 9.684328079223633\n",
"2278 Loss: 9.680723190307617\n",
"2279 Loss: 9.677118301391602\n",
"2280 tensor([[1.6726, 2.2057, 1.3777, 1.7554, 2.1330]], grad_fn=<AddmmBackward>)\n",
"2280 Loss: 9.673513412475586\n",
"2281 Loss: 9.66991138458252\n",
"2282 Loss: 9.66631031036377\n",
"2283 Loss: 9.66270923614502\n",
"2284 Loss: 9.659111022949219\n",
"2285 Loss: 9.655512809753418\n",
"2286 Loss: 9.65191650390625\n",
"2287 Loss: 9.648323059082031\n",
"2288 Loss: 9.644728660583496\n",
"2289 Loss: 9.641136169433594\n",
"2290 tensor([[1.6689, 2.2044, 1.3788, 1.7577, 2.1365]], grad_fn=<AddmmBackward>)\n",
"2290 Loss: 9.637544631958008\n",
"2291 Loss: 9.633955001831055\n",
"2292 Loss: 9.630367279052734\n",
"2293 Loss: 9.626779556274414\n",
"2294 Loss: 9.623191833496094\n",
"2295 Loss: 9.619607925415039\n",
"2296 Loss: 9.6160249710083\n",
"2297 Loss: 9.612443923950195\n",
"2298 Loss: 9.608861923217773\n",
"2299 Loss: 9.6052827835083\n",
"2300 tensor([[1.6652, 2.2031, 1.3800, 1.7600, 2.1400]], grad_fn=<AddmmBackward>)\n",
"2300 Loss: 9.601703643798828\n",
"2301 Loss: 9.598126411437988\n",
"2302 Loss: 9.594549179077148\n",
"2303 Loss: 9.590972900390625\n",
"2304 Loss: 9.587400436401367\n",
"2305 Loss: 9.58382797241211\n",
"2306 Loss: 9.580256462097168\n",
"2307 Loss: 9.57668685913086\n",
"2308 Loss: 9.57311725616455\n",
"2309 Loss: 9.569549560546875\n",
"2310 tensor([[1.6615, 2.2018, 1.3812, 1.7624, 2.1436]], grad_fn=<AddmmBackward>)\n",
"2310 Loss: 9.565982818603516\n",
"2311 Loss: 9.562417984008789\n",
"2312 Loss: 9.558854103088379\n",
"2313 Loss: 9.555291175842285\n",
"2314 Loss: 9.55173110961914\n",
"2315 Loss: 9.54817008972168\n",
"2316 Loss: 9.544611930847168\n",
"2317 Loss: 9.541053771972656\n",
"2318 Loss: 9.537497520446777\n",
"2319 Loss: 9.533942222595215\n",
"2320 tensor([[1.6579, 2.2005, 1.3824, 1.7647, 2.1471]], grad_fn=<AddmmBackward>)\n",
"2320 Loss: 9.530387878417969\n",
"2321 Loss: 9.526834487915039\n",
"2322 Loss: 9.523283004760742\n",
"2323 Loss: 9.519732475280762\n",
"2324 Loss: 9.516182899475098\n",
"2325 Loss: 9.51263427734375\n",
"2326 Loss: 9.509086608886719\n",
"2327 Loss: 9.505539894104004\n",
"2328 Loss: 9.501996040344238\n",
"2329 Loss: 9.498454093933105\n",
"2330 tensor([[1.6542, 2.1992, 1.3835, 1.7671, 2.1506]], grad_fn=<AddmmBackward>)\n",
"2330 Loss: 9.494912147521973\n",
"2331 Loss: 9.491371154785156\n",
"2332 Loss: 9.487832069396973\n",
"2333 Loss: 9.484292030334473\n",
"2334 Loss: 9.480756759643555\n",
"2335 Loss: 9.477219581604004\n",
"2336 Loss: 9.473684310913086\n",
"2337 Loss: 9.4701509475708\n",
"2338 Loss: 9.466618537902832\n",
"2339 Loss: 9.46308708190918\n",
"2340 tensor([[1.6506, 2.1979, 1.3847, 1.7694, 2.1541]], grad_fn=<AddmmBackward>)\n",
"2340 Loss: 9.459556579589844\n",
"2341 Loss: 9.456026077270508\n",
"2342 Loss: 9.452498435974121\n",
"2343 Loss: 9.448970794677734\n",
"2344 Loss: 9.44544506072998\n",
"2345 Loss: 9.441922187805176\n",
"2346 Loss: 9.438399314880371\n",
"2347 Loss: 9.434877395629883\n",
"2348 Loss: 9.431356430053711\n",
"2349 Loss: 9.427837371826172\n",
"2350 tensor([[1.6470, 2.1967, 1.3859, 1.7718, 2.1577]], grad_fn=<AddmmBackward>)\n",
"2350 Loss: 9.42431926727295\n",
"2351 Loss: 9.420801162719727\n",
"2352 Loss: 9.41728401184082\n",
"2353 Loss: 9.413768768310547\n",
"2354 Loss: 9.410255432128906\n",
"2355 Loss: 9.406743049621582\n",
"2356 Loss: 9.403230667114258\n",
"2357 Loss: 9.399720191955566\n",
"2358 Loss: 9.396211624145508\n",
"2359 Loss: 9.392701148986816\n",
"2360 tensor([[1.6434, 2.1954, 1.3871, 1.7741, 2.1612]], grad_fn=<AddmmBackward>)\n",
"2360 Loss: 9.38919448852539\n",
"2361 Loss: 9.385687828063965\n",
"2362 Loss: 9.382183074951172\n",
"2363 Loss: 9.378680229187012\n",
"2364 Loss: 9.375176429748535\n",
"2365 Loss: 9.371675491333008\n",
"2366 Loss: 9.368175506591797\n",
"2367 Loss: 9.36467456817627\n",
"2368 Loss: 9.361177444458008\n",
"2369 Loss: 9.357680320739746\n",
"2370 tensor([[1.6398, 2.1942, 1.3883, 1.7765, 2.1648]], grad_fn=<AddmmBackward>)\n",
"2370 Loss: 9.354185104370117\n",
"2371 Loss: 9.350690841674805\n",
"2372 Loss: 9.347197532653809\n",
"2373 Loss: 9.343706130981445\n",
"2374 Loss: 9.34021282196045\n",
"2375 Loss: 9.336723327636719\n",
"2376 Loss: 9.333233833312988\n",
"2377 Loss: 9.32974624633789\n",
"2378 Loss: 9.32625961303711\n",
"2379 Loss: 9.322774887084961\n",
"2380 tensor([[1.6363, 2.1929, 1.3894, 1.7789, 2.1683]], grad_fn=<AddmmBackward>)\n",
"2380 Loss: 9.319289207458496\n",
"2381 Loss: 9.31580638885498\n",
"2382 Loss: 9.312325477600098\n",
"2383 Loss: 9.308842658996582\n",
"2384 Loss: 9.305362701416016\n",
"2385 Loss: 9.301883697509766\n",
"2386 Loss: 9.298404693603516\n",
"2387 Loss: 9.294928550720215\n",
"2388 Loss: 9.291452407836914\n",
"2389 Loss: 9.28797721862793\n",
"2390 tensor([[1.6327, 2.1917, 1.3906, 1.7813, 2.1719]], grad_fn=<AddmmBackward>)\n",
"2390 Loss: 9.284503936767578\n",
"2391 Loss: 9.281031608581543\n",
"2392 Loss: 9.277559280395508\n",
"2393 Loss: 9.274089813232422\n",
"2394 Loss: 9.27061939239502\n",
"2395 Loss: 9.267152786254883\n",
"2396 Loss: 9.263686180114746\n",
"2397 Loss: 9.26021957397461\n",
"2398 Loss: 9.256754875183105\n",
"2399 Loss: 9.253291130065918\n",
"2400 tensor([[1.6292, 2.1904, 1.3918, 1.7836, 2.1755]], grad_fn=<AddmmBackward>)\n",
"2400 Loss: 9.249829292297363\n",
"2401 Loss: 9.246367454528809\n",
"2402 Loss: 9.242907524108887\n",
"2403 Loss: 9.239447593688965\n",
"2404 Loss: 9.235989570617676\n",
"2405 Loss: 9.232532501220703\n",
"2406 Loss: 9.22907543182373\n",
"2407 Loss: 9.225621223449707\n",
"2408 Loss: 9.222167015075684\n",
"2409 Loss: 9.218713760375977\n",
"2410 tensor([[1.6257, 2.1892, 1.3930, 1.7860, 2.1790]], grad_fn=<AddmmBackward>)\n",
"2410 Loss: 9.215261459350586\n",
"2411 Loss: 9.211810111999512\n",
"2412 Loss: 9.208361625671387\n",
"2413 Loss: 9.204913139343262\n",
"2414 Loss: 9.20146369934082\n",
"2415 Loss: 9.198017120361328\n",
"2416 Loss: 9.194570541381836\n",
"2417 Loss: 9.191125869750977\n",
"2418 Loss: 9.18768310546875\n",
"2419 Loss: 9.18424129486084\n",
"2420 tensor([[1.6222, 2.1880, 1.3942, 1.7884, 2.1826]], grad_fn=<AddmmBackward>)\n",
"2420 Loss: 9.180800437927246\n",
"2421 Loss: 9.177360534667969\n",
"2422 Loss: 9.173921585083008\n",
"2423 Loss: 9.17048168182373\n",
"2424 Loss: 9.167045593261719\n",
"2425 Loss: 9.163609504699707\n",
"2426 Loss: 9.160174369812012\n",
"2427 Loss: 9.156740188598633\n",
"2428 Loss: 9.15330696105957\n",
"2429 Loss: 9.14987564086914\n",
"2430 tensor([[1.6188, 2.1868, 1.3954, 1.7908, 2.1862]], grad_fn=<AddmmBackward>)\n",
"2430 Loss: 9.146444320678711\n",
"2431 Loss: 9.14301586151123\n",
"2432 Loss: 9.139586448669434\n",
"2433 Loss: 9.13615894317627\n",
"2434 Loss: 9.132732391357422\n",
"2435 Loss: 9.12930679321289\n",
"2436 Loss: 9.125882148742676\n",
"2437 Loss: 9.122457504272461\n",
"2438 Loss: 9.119034767150879\n",
"2439 Loss: 9.115612030029297\n",
"2440 tensor([[1.6153, 2.1856, 1.3966, 1.7932, 2.1898]], grad_fn=<AddmmBackward>)\n",
"2440 Loss: 9.11219310760498\n",
"2441 Loss: 9.108772277832031\n",
"2442 Loss: 9.105354309082031\n",
"2443 Loss: 9.101935386657715\n",
"2444 Loss: 9.098519325256348\n",
"2445 Loss: 9.09510326385498\n",
"2446 Loss: 9.091691017150879\n",
"2447 Loss: 9.088275909423828\n",
"2448 Loss: 9.08486557006836\n",
"2449 Loss: 9.081454277038574\n",
"2450 tensor([[1.6119, 2.1844, 1.3978, 1.7956, 2.1934]], grad_fn=<AddmmBackward>)\n",
"2450 Loss: 9.078042030334473\n",
"2451 Loss: 9.074634552001953\n",
"2452 Loss: 9.071226119995117\n",
"2453 Loss: 9.067818641662598\n",
"2454 Loss: 9.064413070678711\n",
"2455 Loss: 9.061007499694824\n",
"2456 Loss: 9.057601928710938\n",
"2457 Loss: 9.05419921875\n",
"2458 Loss: 9.050797462463379\n",
"2459 Loss: 9.047395706176758\n",
"2460 tensor([[1.6085, 2.1833, 1.3990, 1.7980, 2.1970]], grad_fn=<AddmmBackward>)\n",
"2460 Loss: 9.043993949890137\n",
"2461 Loss: 9.040595054626465\n",
"2462 Loss: 9.037196159362793\n",
"2463 Loss: 9.03380012512207\n",
"2464 Loss: 9.030403137207031\n",
"2465 Loss: 9.027008056640625\n",
"2466 Loss: 9.023612976074219\n",
"2467 Loss: 9.020220756530762\n",
"2468 Loss: 9.016828536987305\n",
"2469 Loss: 9.013436317443848\n",
"2470 tensor([[1.6051, 2.1821, 1.4002, 1.8004, 2.2006]], grad_fn=<AddmmBackward>)\n",
"2470 Loss: 9.010045051574707\n",
"2471 Loss: 9.006656646728516\n",
"2472 Loss: 9.003268241882324\n",
"2473 Loss: 8.999879837036133\n",
"2474 Loss: 8.996492385864258\n",
"2475 Loss: 8.993108749389648\n",
"2476 Loss: 8.989725112915039\n",
"2477 Loss: 8.986339569091797\n",
"2478 Loss: 8.982956886291504\n",
"2479 Loss: 8.97957706451416\n",
"2480 tensor([[1.6017, 2.1809, 1.4014, 1.8028, 2.2043]], grad_fn=<AddmmBackward>)\n",
"2480 Loss: 8.9761962890625\n",
"2481 Loss: 8.972816467285156\n",
"2482 Loss: 8.969438552856445\n",
"2483 Loss: 8.966060638427734\n",
"2484 Loss: 8.962684631347656\n",
"2485 Loss: 8.959308624267578\n",
"2486 Loss: 8.955933570861816\n",
"2487 Loss: 8.952559471130371\n",
"2488 Loss: 8.949186325073242\n",
"2489 Loss: 8.945815086364746\n",
"2490 tensor([[1.5984, 2.1798, 1.4026, 1.8053, 2.2079]], grad_fn=<AddmmBackward>)\n",
"2490 Loss: 8.94244384765625\n",
"2491 Loss: 8.939075469970703\n",
"2492 Loss: 8.935705184936523\n",
"2493 Loss: 8.932336807250977\n",
"2494 Loss: 8.928970336914062\n",
"2495 Loss: 8.925605773925781\n",
"2496 Loss: 8.9222412109375\n",
"2497 Loss: 8.918875694274902\n",
"2498 Loss: 8.915513038635254\n",
"2499 Loss: 8.912149429321289\n",
"2500 tensor([[1.5950, 2.1786, 1.4038, 1.8077, 2.2115]], grad_fn=<AddmmBackward>)\n",
"2500 Loss: 8.908788681030273\n",
"2501 Loss: 8.905427932739258\n",
"2502 Loss: 8.902069091796875\n",
"2503 Loss: 8.898710250854492\n",
"2504 Loss: 8.895353317260742\n",
"2505 Loss: 8.891996383666992\n",
"2506 Loss: 8.888640403747559\n",
"2507 Loss: 8.885284423828125\n",
"2508 Loss: 8.88193130493164\n",
"2509 Loss: 8.878580093383789\n",
"2510 tensor([[1.5917, 2.1775, 1.4051, 1.8101, 2.2152]], grad_fn=<AddmmBackward>)\n",
"2510 Loss: 8.875226974487305\n",
"2511 Loss: 8.871875762939453\n",
"2512 Loss: 8.868526458740234\n",
"2513 Loss: 8.8651762008667\n",
"2514 Loss: 8.86182975769043\n",
"2515 Loss: 8.858482360839844\n",
"2516 Loss: 8.855134963989258\n",
"2517 Loss: 8.851791381835938\n",
"2518 Loss: 8.8484468460083\n",
"2519 Loss: 8.845104217529297\n",
"2520 tensor([[1.5884, 2.1763, 1.4063, 1.8126, 2.2188]], grad_fn=<AddmmBackward>)\n",
"2520 Loss: 8.841760635375977\n",
"2521 Loss: 8.838419914245605\n",
"2522 Loss: 8.835079193115234\n",
"2523 Loss: 8.83173942565918\n",
"2524 Loss: 8.828398704528809\n",
"2525 Loss: 8.82505989074707\n",
"2526 Loss: 8.821723937988281\n",
"2527 Loss: 8.818387985229492\n",
"2528 Loss: 8.815053939819336\n",
"2529 Loss: 8.811718940734863\n",
"2530 tensor([[1.5851, 2.1752, 1.4075, 1.8150, 2.2225]], grad_fn=<AddmmBackward>)\n",
"2530 Loss: 8.808385848999023\n",
"2531 Loss: 8.8050537109375\n",
"2532 Loss: 8.801721572875977\n",
"2533 Loss: 8.798391342163086\n",
"2534 Loss: 8.795062065124512\n",
"2535 Loss: 8.791733741760254\n",
"2536 Loss: 8.78840446472168\n",
"2537 Loss: 8.785079002380371\n",
"2538 Loss: 8.781752586364746\n",
"2539 Loss: 8.778427124023438\n",
"2540 tensor([[1.5818, 2.1741, 1.4087, 1.8174, 2.2261]], grad_fn=<AddmmBackward>)\n",
"2540 Loss: 8.775102615356445\n",
"2541 Loss: 8.77177906036377\n",
"2542 Loss: 8.76845645904541\n",
"2543 Loss: 8.765135765075684\n",
"2544 Loss: 8.76181411743164\n",
"2545 Loss: 8.75849437713623\n",
"2546 Loss: 8.755176544189453\n",
"2547 Loss: 8.751859664916992\n",
"2548 Loss: 8.748542785644531\n",
"2549 Loss: 8.74522590637207\n",
"2550 tensor([[1.5785, 2.1729, 1.4099, 1.8199, 2.2298]], grad_fn=<AddmmBackward>)\n",
"2550 Loss: 8.741910934448242\n",
"2551 Loss: 8.73859691619873\n",
"2552 Loss: 8.735282897949219\n",
"2553 Loss: 8.73197078704834\n",
"2554 Loss: 8.728659629821777\n",
"2555 Loss: 8.725348472595215\n",
"2556 Loss: 8.722039222717285\n",
"2557 Loss: 8.718729019165039\n",
"2558 Loss: 8.715421676635742\n",
"2559 Loss: 8.712114334106445\n",
"2560 tensor([[1.5753, 2.1718, 1.4112, 1.8223, 2.2335]], grad_fn=<AddmmBackward>)\n",
"2560 Loss: 8.708808898925781\n",
"2561 Loss: 8.705503463745117\n",
"2562 Loss: 8.702198028564453\n",
"2563 Loss: 8.698895454406738\n",
"2564 Loss: 8.695592880249023\n",
"2565 Loss: 8.692291259765625\n",
"2566 Loss: 8.688990592956543\n",
"2567 Loss: 8.685689926147461\n",
"2568 Loss: 8.682390213012695\n",
"2569 Loss: 8.679093360900879\n",
"2570 tensor([[1.5720, 2.1707, 1.4124, 1.8248, 2.2372]], grad_fn=<AddmmBackward>)\n",
"2570 Loss: 8.67579460144043\n",
"2571 Loss: 8.67249870300293\n",
"2572 Loss: 8.669200897216797\n",
"2573 Loss: 8.66590690612793\n",
"2574 Loss: 8.662612915039062\n",
"2575 Loss: 8.659318923950195\n",
"2576 Loss: 8.656026840209961\n",
"2577 Loss: 8.65273666381836\n",
"2578 Loss: 8.649445533752441\n",
"2579 Loss: 8.646156311035156\n",
"2580 tensor([[1.5688, 2.1696, 1.4136, 1.8272, 2.2409]], grad_fn=<AddmmBackward>)\n",
"2580 Loss: 8.642867088317871\n",
"2581 Loss: 8.639579772949219\n",
"2582 Loss: 8.63629150390625\n",
"2583 Loss: 8.633005142211914\n",
"2584 Loss: 8.629720687866211\n",
"2585 Loss: 8.626436233520508\n",
"2586 Loss: 8.623151779174805\n",
"2587 Loss: 8.619867324829102\n",
"2588 Loss: 8.61658763885498\n",
"2589 Loss: 8.613306045532227\n",
"2590 tensor([[1.5656, 2.1685, 1.4148, 1.8297, 2.2445]], grad_fn=<AddmmBackward>)\n",
"2590 Loss: 8.610027313232422\n",
"2591 Loss: 8.606748580932617\n",
"2592 Loss: 8.603469848632812\n",
"2593 Loss: 8.600192070007324\n",
"2594 Loss: 8.596917152404785\n",
"2595 Loss: 8.593640327453613\n",
"2596 Loss: 8.590365409851074\n",
"2597 Loss: 8.587090492248535\n",
"2598 Loss: 8.583819389343262\n",
"2599 Loss: 8.580545425415039\n",
"2600 tensor([[1.5624, 2.1674, 1.4161, 1.8322, 2.2483]], grad_fn=<AddmmBackward>)\n",
"2600 Loss: 8.577275276184082\n",
"2601 Loss: 8.574003219604492\n",
"2602 Loss: 8.570734024047852\n",
"2603 Loss: 8.567464828491211\n",
"2604 Loss: 8.56419563293457\n",
"2605 Loss: 8.560928344726562\n",
"2606 Loss: 8.557661056518555\n",
"2607 Loss: 8.55439567565918\n",
"2608 Loss: 8.551132202148438\n",
"2609 Loss: 8.547866821289062\n",
"2610 tensor([[1.5592, 2.1663, 1.4173, 1.8346, 2.2520]], grad_fn=<AddmmBackward>)\n",
"2610 Loss: 8.54460334777832\n",
"2611 Loss: 8.541340827941895\n",
"2612 Loss: 8.538079261779785\n",
"2613 Loss: 8.534819602966309\n",
"2614 Loss: 8.531559944152832\n",
"2615 Loss: 8.528301239013672\n",
"2616 Loss: 8.525041580200195\n",
"2617 Loss: 8.521784782409668\n",
"2618 Loss: 8.518528938293457\n",
"2619 Loss: 8.515274047851562\n",
"2620 tensor([[1.5560, 2.1652, 1.4186, 1.8371, 2.2557]], grad_fn=<AddmmBackward>)\n",
"2620 Loss: 8.512018203735352\n",
"2621 Loss: 8.508764266967773\n",
"2622 Loss: 8.505510330200195\n",
"2623 Loss: 8.50225830078125\n",
"2624 Loss: 8.499006271362305\n",
"2625 Loss: 8.495755195617676\n",
"2626 Loss: 8.49250602722168\n",
"2627 Loss: 8.489256858825684\n",
"2628 Loss: 8.486008644104004\n",
"2629 Loss: 8.48276138305664\n",
"2630 tensor([[1.5529, 2.1641, 1.4198, 1.8396, 2.2594]], grad_fn=<AddmmBackward>)\n",
"2630 Loss: 8.479514122009277\n",
"2631 Loss: 8.47626781463623\n",
"2632 Loss: 8.473023414611816\n",
"2633 Loss: 8.469779014587402\n",
"2634 Loss: 8.466534614562988\n",
"2635 Loss: 8.463293075561523\n",
"2636 Loss: 8.460050582885742\n",
"2637 Loss: 8.456809997558594\n",
"2638 Loss: 8.453571319580078\n",
"2639 Loss: 8.450331687927246\n",
"2640 tensor([[1.5497, 2.1631, 1.4210, 1.8421, 2.2631]], grad_fn=<AddmmBackward>)\n",
"2640 Loss: 8.44709300994873\n",
"2641 Loss: 8.443856239318848\n",
"2642 Loss: 8.440619468688965\n",
"2643 Loss: 8.437383651733398\n",
"2644 Loss: 8.434148788452148\n",
"2645 Loss: 8.430914878845215\n",
"2646 Loss: 8.427680969238281\n",
"2647 Loss: 8.424448013305664\n",
"2648 Loss: 8.42121696472168\n",
"2649 Loss: 8.417985916137695\n",
"2650 tensor([[1.5466, 2.1620, 1.4223, 1.8446, 2.2668]], grad_fn=<AddmmBackward>)\n",
"2650 Loss: 8.414755821228027\n",
"2651 Loss: 8.41152572631836\n",
"2652 Loss: 8.408297538757324\n",
"2653 Loss: 8.405068397521973\n",
"2654 Loss: 8.40184211730957\n",
"2655 Loss: 8.398614883422852\n",
"2656 Loss: 8.395389556884766\n",
"2657 Loss: 8.39216423034668\n",
"2658 Loss: 8.388940811157227\n",
"2659 Loss: 8.385717391967773\n",
"2660 tensor([[1.5435, 2.1609, 1.4235, 1.8471, 2.2706]], grad_fn=<AddmmBackward>)\n",
"2660 Loss: 8.382494926452637\n",
"2661 Loss: 8.379274368286133\n",
"2662 Loss: 8.376053810119629\n",
"2663 Loss: 8.372832298278809\n",
"2664 Loss: 8.369613647460938\n",
"2665 Loss: 8.366395950317383\n",
"2666 Loss: 8.363178253173828\n",
"2667 Loss: 8.359960556030273\n",
"2668 Loss: 8.356745719909668\n",
"2669 Loss: 8.353529930114746\n",
"2670 tensor([[1.5404, 2.1599, 1.4248, 1.8496, 2.2743]], grad_fn=<AddmmBackward>)\n",
"2670 Loss: 8.35031509399414\n",
"2671 Loss: 8.347101211547852\n",
"2672 Loss: 8.343889236450195\n",
"2673 Loss: 8.340677261352539\n",
"2674 Loss: 8.337465286254883\n",
"2675 Loss: 8.334256172180176\n",
"2676 Loss: 8.331046104431152\n",
"2677 Loss: 8.327836990356445\n",
"2678 Loss: 8.324628829956055\n",
"2679 Loss: 8.321420669555664\n",
"2680 tensor([[1.5373, 2.1588, 1.4260, 1.8521, 2.2781]], grad_fn=<AddmmBackward>)\n",
"2680 Loss: 8.318214416503906\n",
"2681 Loss: 8.315008163452148\n",
"2682 Loss: 8.311803817749023\n",
"2683 Loss: 8.308597564697266\n",
"2684 Loss: 8.305395126342773\n",
"2685 Loss: 8.302191734313965\n",
"2686 Loss: 8.298990249633789\n",
"2687 Loss: 8.295787811279297\n",
"2688 Loss: 8.292588233947754\n",
"2689 Loss: 8.289388656616211\n",
"2690 tensor([[1.5342, 2.1577, 1.4273, 1.8546, 2.2818]], grad_fn=<AddmmBackward>)\n",
"2690 Loss: 8.286190032958984\n",
"2691 Loss: 8.282992362976074\n",
"2692 Loss: 8.279793739318848\n",
"2693 Loss: 8.27659797668457\n",
"2694 Loss: 8.273404121398926\n",
"2695 Loss: 8.270208358764648\n",
"2696 Loss: 8.267013549804688\n",
"2697 Loss: 8.26382064819336\n",
"2698 Loss: 8.260628700256348\n",
"2699 Loss: 8.257436752319336\n",
"2700 tensor([[1.5311, 2.1567, 1.4285, 1.8571, 2.2856]], grad_fn=<AddmmBackward>)\n",
"2700 Loss: 8.25424575805664\n",
"2701 Loss: 8.251052856445312\n",
"2702 Loss: 8.247864723205566\n",
"2703 Loss: 8.24467658996582\n",
"2704 Loss: 8.241488456726074\n",
"2705 Loss: 8.238301277160645\n",
"2706 Loss: 8.235114097595215\n",
"2707 Loss: 8.231929779052734\n",
"2708 Loss: 8.228744506835938\n",
"2709 Loss: 8.225560188293457\n",
"2710 tensor([[1.5281, 2.1556, 1.4298, 1.8596, 2.2894]], grad_fn=<AddmmBackward>)\n",
"2710 Loss: 8.222375869750977\n",
"2711 Loss: 8.219194412231445\n",
"2712 Loss: 8.216012001037598\n",
"2713 Loss: 8.212830543518066\n",
"2714 Loss: 8.209650039672852\n",
"2715 Loss: 8.206470489501953\n",
"2716 Loss: 8.203292846679688\n",
"2717 Loss: 8.200113296508789\n",
"2718 Loss: 8.196935653686523\n",
"2719 Loss: 8.193758964538574\n",
"2720 tensor([[1.5250, 2.1546, 1.4311, 1.8621, 2.2932]], grad_fn=<AddmmBackward>)\n",
"2720 Loss: 8.190583229064941\n",
"2721 Loss: 8.187408447265625\n",
"2722 Loss: 8.184234619140625\n",
"2723 Loss: 8.181060791015625\n",
"2724 Loss: 8.177887916564941\n",
"2725 Loss: 8.174715042114258\n",
"2726 Loss: 8.171544075012207\n",
"2727 Loss: 8.168374061584473\n",
"2728 Loss: 8.165204048156738\n",
"2729 Loss: 8.162034034729004\n",
"2730 tensor([[1.5220, 2.1535, 1.4323, 1.8646, 2.2969]], grad_fn=<AddmmBackward>)\n",
"2730 Loss: 8.158864974975586\n",
"2731 Loss: 8.155698776245117\n",
"2732 Loss: 8.152532577514648\n",
"2733 Loss: 8.149364471435547\n",
"2734 Loss: 8.146200180053711\n",
"2735 Loss: 8.143033981323242\n",
"2736 Loss: 8.139871597290039\n",
"2737 Loss: 8.136709213256836\n",
"2738 Loss: 8.133545875549316\n",
"2739 Loss: 8.13038444519043\n",
"2740 tensor([[1.5190, 2.1525, 1.4336, 1.8672, 2.3007]], grad_fn=<AddmmBackward>)\n",
"2740 Loss: 8.127222061157227\n",
"2741 Loss: 8.124062538146973\n",
"2742 Loss: 8.120903015136719\n",
"2743 Loss: 8.117744445800781\n",
"2744 Loss: 8.11458683013916\n",
"2745 Loss: 8.111429214477539\n",
"2746 Loss: 8.108272552490234\n",
"2747 Loss: 8.10511589050293\n",
"2748 Loss: 8.101961135864258\n",
"2749 Loss: 8.098806381225586\n",
"2750 tensor([[1.5159, 2.1515, 1.4348, 1.8697, 2.3045]], grad_fn=<AddmmBackward>)\n",
"2750 Loss: 8.09565258026123\n",
"2751 Loss: 8.092498779296875\n",
"2752 Loss: 8.089347839355469\n",
"2753 Loss: 8.086195945739746\n",
"2754 Loss: 8.083044052124023\n",
"2755 Loss: 8.079895973205566\n",
"2756 Loss: 8.07674503326416\n",
"2757 Loss: 8.073596954345703\n",
"2758 Loss: 8.070448875427246\n",
"2759 Loss: 8.067301750183105\n",
"2760 tensor([[1.5129, 2.1504, 1.4361, 1.8722, 2.3083]], grad_fn=<AddmmBackward>)\n",
"2760 Loss: 8.064156532287598\n",
"2761 Loss: 8.061009407043457\n",
"2762 Loss: 8.05786418914795\n",
"2763 Loss: 8.054719924926758\n",
"2764 Loss: 8.0515775680542\n",
"2765 Loss: 8.048434257507324\n",
"2766 Loss: 8.045291900634766\n",
"2767 Loss: 8.042150497436523\n",
"2768 Loss: 8.039009094238281\n",
"2769 Loss: 8.035871505737305\n",
"2770 tensor([[1.5100, 2.1494, 1.4374, 1.8748, 2.3121]], grad_fn=<AddmmBackward>)\n",
"2770 Loss: 8.032732963562012\n",
"2771 Loss: 8.029594421386719\n",
"2772 Loss: 8.026455879211426\n",
"2773 Loss: 8.023319244384766\n",
"2774 Loss: 8.020182609558105\n",
"2775 Loss: 8.017047882080078\n",
"2776 Loss: 8.013914108276367\n",
"2777 Loss: 8.010778427124023\n",
"2778 Loss: 8.007645606994629\n",
"2779 Loss: 8.00451374053955\n",
"2780 tensor([[1.5070, 2.1484, 1.4386, 1.8773, 2.3159]], grad_fn=<AddmmBackward>)\n",
"2780 Loss: 8.001380920410156\n",
"2781 Loss: 7.998250484466553\n",
"2782 Loss: 7.995121002197266\n",
"2783 Loss: 7.991990089416504\n",
"2784 Loss: 7.988862037658691\n",
"2785 Loss: 7.985733985900879\n",
"2786 Loss: 7.982607364654541\n",
"2787 Loss: 7.979480266571045\n",
"2788 Loss: 7.976353645324707\n",
"2789 Loss: 7.973229885101318\n",
"2790 tensor([[1.5040, 2.1474, 1.4399, 1.8798, 2.3198]], grad_fn=<AddmmBackward>)\n",
"2790 Loss: 7.970104217529297\n",
"2791 Loss: 7.96697998046875\n",
"2792 Loss: 7.963855743408203\n",
"2793 Loss: 7.960733413696289\n",
"2794 Loss: 7.957611560821533\n",
"2795 Loss: 7.954490661621094\n",
"2796 Loss: 7.951369285583496\n",
"2797 Loss: 7.948249340057373\n",
"2798 Loss: 7.945130348205566\n",
"2799 Loss: 7.942011833190918\n",
"2800 tensor([[1.5011, 2.1463, 1.4412, 1.8824, 2.3236]], grad_fn=<AddmmBackward>)\n",
"2800 Loss: 7.938894271850586\n",
"2801 Loss: 7.93577766418457\n",
"2802 Loss: 7.932661056518555\n",
"2803 Loss: 7.929544448852539\n",
"2804 Loss: 7.926430702209473\n",
"2805 Loss: 7.923316478729248\n",
"2806 Loss: 7.92020320892334\n",
"2807 Loss: 7.917089462280273\n",
"2808 Loss: 7.913978099822998\n",
"2809 Loss: 7.910866737365723\n",
"2810 tensor([[1.4981, 2.1453, 1.4425, 1.8849, 2.3274]], grad_fn=<AddmmBackward>)\n",
"2810 Loss: 7.907756805419922\n",
"2811 Loss: 7.904645919799805\n",
"2812 Loss: 7.901535987854004\n",
"2813 Loss: 7.8984270095825195\n",
"2814 Loss: 7.895321846008301\n",
"2815 Loss: 7.892214298248291\n",
"2816 Loss: 7.889106750488281\n",
"2817 Loss: 7.8860015869140625\n",
"2818 Loss: 7.882896423339844\n",
"2819 Loss: 7.879793167114258\n",
"2820 tensor([[1.4952, 2.1443, 1.4438, 1.8875, 2.3313]], grad_fn=<AddmmBackward>)\n",
"2820 Loss: 7.876688480377197\n",
"2821 Loss: 7.873584747314453\n",
"2822 Loss: 7.870482444763184\n",
"2823 Loss: 7.867380142211914\n",
"2824 Loss: 7.864278793334961\n",
"2825 Loss: 7.861178398132324\n",
"2826 Loss: 7.858080863952637\n",
"2827 Loss: 7.854981422424316\n",
"2828 Loss: 7.851882457733154\n",
"2829 Loss: 7.848785400390625\n",
"2830 tensor([[1.4922, 2.1433, 1.4450, 1.8901, 2.3351]], grad_fn=<AddmmBackward>)\n",
"2830 Loss: 7.845688343048096\n",
"2831 Loss: 7.842594146728516\n",
"2832 Loss: 7.8394975662231445\n",
"2833 Loss: 7.836402893066406\n",
"2834 Loss: 7.833309650421143\n",
"2835 Loss: 7.8302154541015625\n",
"2836 Loss: 7.827123641967773\n",
"2837 Loss: 7.824030876159668\n",
"2838 Loss: 7.820939064025879\n",
"2839 Loss: 7.817848205566406\n",
"2840 tensor([[1.4893, 2.1423, 1.4463, 1.8926, 2.3390]], grad_fn=<AddmmBackward>)\n",
"2840 Loss: 7.814757347106934\n",
"2841 Loss: 7.81166934967041\n",
"2842 Loss: 7.80858039855957\n",
"2843 Loss: 7.805492877960205\n",
"2844 Loss: 7.80240535736084\n",
"2845 Loss: 7.799318313598633\n",
"2846 Loss: 7.796233177185059\n",
"2847 Loss: 7.793147563934326\n",
"2848 Loss: 7.790063858032227\n",
"2849 Loss: 7.786979675292969\n",
"2850 tensor([[1.4864, 2.1413, 1.4476, 1.8952, 2.3428]], grad_fn=<AddmmBackward>)\n",
"2850 Loss: 7.783897399902344\n",
"2851 Loss: 7.780814170837402\n",
"2852 Loss: 7.777731895446777\n",
"2853 Loss: 7.774651527404785\n",
"2854 Loss: 7.771570682525635\n",
"2855 Loss: 7.768490791320801\n",
"2856 Loss: 7.765412330627441\n",
"2857 Loss: 7.762332439422607\n",
"2858 Loss: 7.759254455566406\n",
"2859 Loss: 7.756176948547363\n",
"2860 tensor([[1.4835, 2.1403, 1.4489, 1.8978, 2.3467]], grad_fn=<AddmmBackward>)\n",
"2860 Loss: 7.753101348876953\n",
"2861 Loss: 7.750024795532227\n",
"2862 Loss: 7.746951103210449\n",
"2863 Loss: 7.743875980377197\n",
"2864 Loss: 7.740802764892578\n",
"2865 Loss: 7.737730026245117\n",
"2866 Loss: 7.73465633392334\n",
"2867 Loss: 7.731585502624512\n",
"2868 Loss: 7.728515148162842\n",
"2869 Loss: 7.7254438400268555\n",
"2870 tensor([[1.4806, 2.1393, 1.4502, 1.9004, 2.3505]], grad_fn=<AddmmBackward>)\n",
"2870 Loss: 7.722373962402344\n",
"2871 Loss: 7.719305038452148\n",
"2872 Loss: 7.7162370681762695\n",
"2873 Loss: 7.713168621063232\n",
"2874 Loss: 7.710102081298828\n",
"2875 Loss: 7.707036972045898\n",
"2876 Loss: 7.703970909118652\n",
"2877 Loss: 7.700906276702881\n",
"2878 Loss: 7.697842597961426\n",
"2879 Loss: 7.6947784423828125\n",
"2880 tensor([[1.4777, 2.1382, 1.4515, 1.9029, 2.3544]], grad_fn=<AddmmBackward>)\n",
"2880 Loss: 7.691715717315674\n",
"2881 Loss: 7.68865442276001\n",
"2882 Loss: 7.6855926513671875\n",
"2883 Loss: 7.682530879974365\n",
"2884 Loss: 7.679470062255859\n",
"2885 Loss: 7.676410675048828\n",
"2886 Loss: 7.673353672027588\n",
"2887 Loss: 7.670294284820557\n",
"2888 Loss: 7.667236328125\n",
"2889 Loss: 7.664180278778076\n",
"2890 tensor([[1.4749, 2.1372, 1.4528, 1.9055, 2.3583]], grad_fn=<AddmmBackward>)\n",
"2890 Loss: 7.661123275756836\n",
"2891 Loss: 7.658066749572754\n",
"2892 Loss: 7.655013084411621\n",
"2893 Loss: 7.65195894241333\n",
"2894 Loss: 7.6489057540893555\n",
"2895 Loss: 7.645853519439697\n",
"2896 Loss: 7.642800331115723\n",
"2897 Loss: 7.639750003814697\n",
"2898 Loss: 7.636699199676514\n",
"2899 Loss: 7.633649826049805\n",
"2900 tensor([[1.4720, 2.1362, 1.4541, 1.9081, 2.3622]], grad_fn=<AddmmBackward>)\n",
"2900 Loss: 7.630599021911621\n",
"2901 Loss: 7.62755012512207\n",
"2902 Loss: 7.624502182006836\n",
"2903 Loss: 7.621453285217285\n",
"2904 Loss: 7.618407249450684\n",
"2905 Loss: 7.615361213684082\n",
"2906 Loss: 7.6123151779174805\n",
"2907 Loss: 7.609271049499512\n",
"2908 Loss: 7.606226921081543\n",
"2909 Loss: 7.603182792663574\n",
"2910 tensor([[1.4692, 2.1352, 1.4554, 1.9107, 2.3661]], grad_fn=<AddmmBackward>)\n",
"2910 Loss: 7.600139617919922\n",
"2911 Loss: 7.597097396850586\n",
"2912 Loss: 7.594055652618408\n",
"2913 Loss: 7.5910162925720215\n",
"2914 Loss: 7.587975025177002\n",
"2915 Loss: 7.584934711456299\n",
"2916 Loss: 7.581895351409912\n",
"2917 Loss: 7.578857421875\n",
"2918 Loss: 7.575819969177246\n",
"2919 Loss: 7.572783470153809\n",
"2920 tensor([[1.4663, 2.1342, 1.4567, 1.9133, 2.3700]], grad_fn=<AddmmBackward>)\n",
"2920 Loss: 7.569746017456055\n",
"2921 Loss: 7.566710472106934\n",
"2922 Loss: 7.563675880432129\n",
"2923 Loss: 7.560641288757324\n",
"2924 Loss: 7.5576066970825195\n",
"2925 Loss: 7.554574012756348\n",
"2926 Loss: 7.551542282104492\n",
"2927 Loss: 7.5485100746154785\n",
"2928 Loss: 7.545479774475098\n",
"2929 Loss: 7.542448997497559\n",
"2930 tensor([[1.4635, 2.1333, 1.4580, 1.9159, 2.3739]], grad_fn=<AddmmBackward>)\n",
"2930 Loss: 7.5394182205200195\n",
"2931 Loss: 7.536388874053955\n",
"2932 Loss: 7.533359527587891\n",
"2933 Loss: 7.530331611633301\n",
"2934 Loss: 7.5273051261901855\n",
"2935 Loss: 7.52427864074707\n",
"2936 Loss: 7.521252155303955\n",
"2937 Loss: 7.518226623535156\n",
"2938 Loss: 7.515202522277832\n",
"2939 Loss: 7.512177467346191\n",
"2940 tensor([[1.4606, 2.1323, 1.4593, 1.9185, 2.3778]], grad_fn=<AddmmBackward>)\n",
"2940 Loss: 7.509154319763184\n",
"2941 Loss: 7.506133079528809\n",
"2942 Loss: 7.503109455108643\n",
"2943 Loss: 7.500088214874268\n",
"2944 Loss: 7.497067451477051\n",
"2945 Loss: 7.494046688079834\n",
"2946 Loss: 7.491026878356934\n",
"2947 Loss: 7.488007545471191\n",
"2948 Loss: 7.484989166259766\n",
"2949 Loss: 7.481971740722656\n",
"2950 tensor([[1.4578, 2.1313, 1.4606, 1.9211, 2.3817]], grad_fn=<AddmmBackward>)\n",
"2950 Loss: 7.478953838348389\n",
"2951 Loss: 7.475937843322754\n",
"2952 Loss: 7.472922325134277\n",
"2953 Loss: 7.469906806945801\n",
"2954 Loss: 7.466892242431641\n",
"2955 Loss: 7.463878631591797\n",
"2956 Loss: 7.4608659744262695\n",
"2957 Loss: 7.457852840423584\n",
"2958 Loss: 7.454840660095215\n",
"2959 Loss: 7.451829433441162\n",
"2960 tensor([[1.4550, 2.1303, 1.4619, 1.9237, 2.3856]], grad_fn=<AddmmBackward>)\n",
"2960 Loss: 7.448818683624268\n",
"2961 Loss: 7.445809841156006\n",
"2962 Loss: 7.442798614501953\n",
"2963 Loss: 7.439790725708008\n",
"2964 Loss: 7.436781406402588\n",
"2965 Loss: 7.433774948120117\n",
"2966 Loss: 7.430768013000488\n",
"2967 Loss: 7.427762031555176\n",
"2968 Loss: 7.42475700378418\n",
"2969 Loss: 7.4217529296875\n",
"2970 tensor([[1.4522, 2.1293, 1.4632, 1.9263, 2.3895]], grad_fn=<AddmmBackward>)\n",
"2970 Loss: 7.418747901916504\n",
"2971 Loss: 7.415744304656982\n",
"2972 Loss: 7.412741661071777\n",
"2973 Loss: 7.409738540649414\n",
"2974 Loss: 7.406736850738525\n",
"2975 Loss: 7.403736114501953\n",
"2976 Loss: 7.400734901428223\n",
"2977 Loss: 7.397735595703125\n",
"2978 Loss: 7.394735336303711\n",
"2979 Loss: 7.39173698425293\n",
"2980 tensor([[1.4494, 2.1283, 1.4645, 1.9290, 2.3935]], grad_fn=<AddmmBackward>)\n",
"2980 Loss: 7.388737678527832\n",
"2981 Loss: 7.385741710662842\n",
"2982 Loss: 7.382743835449219\n",
"2983 Loss: 7.37974739074707\n",
"2984 Loss: 7.376753330230713\n",
"2985 Loss: 7.373757362365723\n",
"2986 Loss: 7.370762825012207\n",
"2987 Loss: 7.367770671844482\n",
"2988 Loss: 7.364777565002441\n",
"2989 Loss: 7.361784934997559\n",
"2990 tensor([[1.4466, 2.1273, 1.4658, 1.9316, 2.3974]], grad_fn=<AddmmBackward>)\n",
"2990 Loss: 7.358793258666992\n",
"2991 Loss: 7.3558030128479\n",
"2992 Loss: 7.352811813354492\n",
"2993 Loss: 7.349822998046875\n",
"2994 Loss: 7.3468337059021\n",
"2995 Loss: 7.343844413757324\n",
"2996 Loss: 7.340855598449707\n",
"2997 Loss: 7.337869644165039\n",
"2998 Loss: 7.334883689880371\n",
"2999 Loss: 7.331896781921387\n",
"3000 tensor([[1.4439, 2.1263, 1.4671, 1.9342, 2.4013]], grad_fn=<AddmmBackward>)\n",
"3000 Loss: 7.328910827636719\n",
"3001 Loss: 7.325926780700684\n",
"3002 Loss: 7.32294225692749\n",
"3003 Loss: 7.319960117340088\n",
"3004 Loss: 7.316976070404053\n",
"3005 Loss: 7.313994884490967\n",
"3006 Loss: 7.311012268066406\n",
"3007 Loss: 7.308032035827637\n",
"3008 Loss: 7.305050849914551\n",
"3009 Loss: 7.3020710945129395\n",
"3010 tensor([[1.4411, 2.1253, 1.4684, 1.9368, 2.4053]], grad_fn=<AddmmBackward>)\n",
"3010 Loss: 7.299091339111328\n",
"3011 Loss: 7.296113967895508\n",
"3012 Loss: 7.293135643005371\n",
"3013 Loss: 7.290158271789551\n",
"3014 Loss: 7.287181854248047\n",
"3015 Loss: 7.284206867218018\n",
"3016 Loss: 7.2812323570251465\n",
"3017 Loss: 7.278256416320801\n",
"3018 Loss: 7.275282859802246\n",
"3019 Loss: 7.272309303283691\n",
"3020 tensor([[1.4383, 2.1243, 1.4697, 1.9395, 2.4092]], grad_fn=<AddmmBackward>)\n",
"3020 Loss: 7.269335746765137\n",
"3021 Loss: 7.266364097595215\n",
"3022 Loss: 7.263391971588135\n",
"3023 Loss: 7.260420799255371\n",
"3024 Loss: 7.257450580596924\n",
"3025 Loss: 7.254480361938477\n",
"3026 Loss: 7.2515106201171875\n",
"3027 Loss: 7.2485432624816895\n",
"3028 Loss: 7.245574474334717\n",
"3029 Loss: 7.242608070373535\n",
"3030 tensor([[1.4356, 2.1233, 1.4711, 1.9421, 2.4132]], grad_fn=<AddmmBackward>)\n",
"3030 Loss: 7.239642143249512\n",
"3031 Loss: 7.236674785614014\n",
"3032 Loss: 7.233709812164307\n",
"3033 Loss: 7.230745315551758\n",
"3034 Loss: 7.227779388427734\n",
"3035 Loss: 7.22481632232666\n",
"3036 Loss: 7.221854209899902\n",
"3037 Loss: 7.2188920974731445\n",
"3038 Loss: 7.215929985046387\n",
"3039 Loss: 7.212967872619629\n",
"3040 tensor([[1.4328, 2.1223, 1.4724, 1.9448, 2.4171]], grad_fn=<AddmmBackward>)\n",
"3040 Loss: 7.210007667541504\n",
"3041 Loss: 7.207047462463379\n",
"3042 Loss: 7.20408821105957\n",
"3043 Loss: 7.20112943649292\n",
"3044 Loss: 7.198172092437744\n",
"3045 Loss: 7.195215225219727\n",
"3046 Loss: 7.192258834838867\n",
"3047 Loss: 7.189301490783691\n",
"3048 Loss: 7.186347961425781\n",
"3049 Loss: 7.183392524719238\n",
"3050 tensor([[1.4301, 2.1214, 1.4737, 1.9474, 2.4211]], grad_fn=<AddmmBackward>)\n",
"3050 Loss: 7.1804375648498535\n",
"3051 Loss: 7.177484512329102\n",
"3052 Loss: 7.174530506134033\n",
"3053 Loss: 7.171578407287598\n",
"3054 Loss: 7.168626308441162\n",
"3055 Loss: 7.165675163269043\n",
"3056 Loss: 7.162724494934082\n",
"3057 Loss: 7.1597747802734375\n",
"3058 Loss: 7.156826019287109\n",
"3059 Loss: 7.153878211975098\n",
"3060 tensor([[1.4273, 2.1204, 1.4750, 1.9500, 2.4251]], grad_fn=<AddmmBackward>)\n",
"3060 Loss: 7.150928497314453\n",
"3061 Loss: 7.147981643676758\n",
"3062 Loss: 7.145035266876221\n",
"3063 Loss: 7.142087936401367\n",
"3064 Loss: 7.139142036437988\n",
"3065 Loss: 7.136196136474609\n",
"3066 Loss: 7.13325309753418\n",
"3067 Loss: 7.130309104919434\n",
"3068 Loss: 7.127365589141846\n",
"3069 Loss: 7.124422073364258\n",
"3070 tensor([[1.4246, 2.1194, 1.4763, 1.9527, 2.4290]], grad_fn=<AddmmBackward>)\n",
"3070 Loss: 7.121480464935303\n",
"3071 Loss: 7.118538856506348\n",
"3072 Loss: 7.115598201751709\n",
"3073 Loss: 7.112657070159912\n",
"3074 Loss: 7.10971736907959\n",
"3075 Loss: 7.1067795753479\n",
"3076 Loss: 7.1038408279418945\n",
"3077 Loss: 7.100903511047363\n",
"3078 Loss: 7.097965717315674\n",
"3079 Loss: 7.095028877258301\n",
"3080 tensor([[1.4219, 2.1184, 1.4777, 1.9553, 2.4330]], grad_fn=<AddmmBackward>)\n",
"3080 Loss: 7.092092990875244\n",
"3081 Loss: 7.089158058166504\n",
"3082 Loss: 7.08622407913208\n",
"3083 Loss: 7.08328914642334\n",
"3084 Loss: 7.080356597900391\n",
"3085 Loss: 7.077422618865967\n",
"3086 Loss: 7.074489593505859\n",
"3087 Loss: 7.071558952331543\n",
"3088 Loss: 7.068628311157227\n",
"3089 Loss: 7.065699100494385\n",
"3090 tensor([[1.4192, 2.1174, 1.4790, 1.9580, 2.4370]], grad_fn=<AddmmBackward>)\n",
"3090 Loss: 7.062769412994385\n",
"3091 Loss: 7.059840202331543\n",
"3092 Loss: 7.056910991668701\n",
"3093 Loss: 7.053982257843018\n",
"3094 Loss: 7.051055908203125\n",
"3095 Loss: 7.048129081726074\n",
"3096 Loss: 7.045202255249023\n",
"3097 Loss: 7.042276859283447\n",
"3098 Loss: 7.039351463317871\n",
"3099 Loss: 7.0364274978637695\n",
"3100 tensor([[1.4165, 2.1164, 1.4803, 1.9607, 2.4410]], grad_fn=<AddmmBackward>)\n",
"3100 Loss: 7.033502578735352\n",
"3101 Loss: 7.030580043792725\n",
"3102 Loss: 7.027657508850098\n",
"3103 Loss: 7.024735450744629\n",
"3104 Loss: 7.021814346313477\n",
"3105 Loss: 7.018893241882324\n",
"3106 Loss: 7.015974044799805\n",
"3107 Loss: 7.013054370880127\n",
"3108 Loss: 7.010135650634766\n",
"3109 Loss: 7.007216453552246\n",
"3110 tensor([[1.4138, 2.1154, 1.4817, 1.9633, 2.4450]], grad_fn=<AddmmBackward>)\n",
"3110 Loss: 7.004300117492676\n",
"3111 Loss: 7.001382827758789\n",
"3112 Loss: 6.998466491699219\n",
"3113 Loss: 6.995550155639648\n",
"3114 Loss: 6.9926347732543945\n",
"3115 Loss: 6.989720344543457\n",
"3116 Loss: 6.986804962158203\n",
"3117 Loss: 6.983892440795898\n",
"3118 Loss: 6.980978965759277\n",
"3119 Loss: 6.978067398071289\n",
"3120 tensor([[1.4111, 2.1144, 1.4830, 1.9660, 2.4490]], grad_fn=<AddmmBackward>)\n",
"3120 Loss: 6.975153923034668\n",
"3121 Loss: 6.972244739532471\n",
"3122 Loss: 6.969334125518799\n",
"3123 Loss: 6.966423988342285\n",
"3124 Loss: 6.963515281677246\n",
"3125 Loss: 6.960605621337891\n",
"3126 Loss: 6.957698822021484\n",
"3127 Loss: 6.954790115356445\n",
"3128 Loss: 6.951883316040039\n",
"3129 Loss: 6.948977947235107\n",
"3130 tensor([[1.4084, 2.1134, 1.4843, 1.9687, 2.4530]], grad_fn=<AddmmBackward>)\n",
"3130 Loss: 6.946071624755859\n",
"3131 Loss: 6.9431657791137695\n",
"3132 Loss: 6.9402618408203125\n",
"3133 Loss: 6.937358379364014\n",
"3134 Loss: 6.934455871582031\n",
"3135 Loss: 6.931552886962891\n",
"3136 Loss: 6.928652763366699\n",
"3137 Loss: 6.925749778747559\n",
"3138 Loss: 6.922849655151367\n",
"3139 Loss: 6.919949531555176\n",
"3140 tensor([[1.4057, 2.1124, 1.4857, 1.9713, 2.4570]], grad_fn=<AddmmBackward>)\n",
"3140 Loss: 6.917049407958984\n",
"3141 Loss: 6.914150238037109\n",
"3142 Loss: 6.911252975463867\n",
"3143 Loss: 6.90835428237915\n",
"3144 Loss: 6.905457496643066\n",
"3145 Loss: 6.902561187744141\n",
"3146 Loss: 6.899665832519531\n",
"3147 Loss: 6.8967695236206055\n",
"3148 Loss: 6.8938751220703125\n",
"3149 Loss: 6.8909807205200195\n",
"3150 tensor([[1.4030, 2.1115, 1.4870, 1.9740, 2.4610]], grad_fn=<AddmmBackward>)\n",
"3150 Loss: 6.888087272644043\n",
"3151 Loss: 6.885194778442383\n",
"3152 Loss: 6.882302761077881\n",
"3153 Loss: 6.8794097900390625\n",
"3154 Loss: 6.876519203186035\n",
"3155 Loss: 6.873629093170166\n",
"3156 Loss: 6.870737552642822\n",
"3157 Loss: 6.867849349975586\n",
"3158 Loss: 6.864960670471191\n",
"3159 Loss: 6.862071990966797\n",
"3160 tensor([[1.4003, 2.1105, 1.4883, 1.9767, 2.4650]], grad_fn=<AddmmBackward>)\n",
"3160 Loss: 6.859184265136719\n",
"3161 Loss: 6.856297016143799\n",
"3162 Loss: 6.853410720825195\n",
"3163 Loss: 6.850523948669434\n",
"3164 Loss: 6.84763765335083\n",
"3165 Loss: 6.844753265380859\n",
"3166 Loss: 6.841870307922363\n",
"3167 Loss: 6.838986396789551\n",
"3168 Loss: 6.8361053466796875\n",
"3169 Loss: 6.833223342895508\n",
"3170 tensor([[1.3977, 2.1095, 1.4897, 1.9794, 2.4691]], grad_fn=<AddmmBackward>)\n",
"3170 Loss: 6.830341339111328\n",
"3171 Loss: 6.827459812164307\n",
"3172 Loss: 6.824579238891602\n",
"3173 Loss: 6.821699619293213\n",
"3174 Loss: 6.818819999694824\n",
"3175 Loss: 6.815941333770752\n",
"3176 Loss: 6.813063621520996\n",
"3177 Loss: 6.810186386108398\n",
"3178 Loss: 6.807309150695801\n",
"3179 Loss: 6.8044328689575195\n",
"3180 tensor([[1.3950, 2.1085, 1.4910, 1.9821, 2.4731]], grad_fn=<AddmmBackward>)\n",
"3180 Loss: 6.801558017730713\n",
"3181 Loss: 6.798683166503906\n",
"3182 Loss: 6.795807838439941\n",
"3183 Loss: 6.792934417724609\n",
"3184 Loss: 6.790061950683594\n",
"3185 Loss: 6.787189960479736\n",
"3186 Loss: 6.784316062927246\n",
"3187 Loss: 6.781445026397705\n",
"3188 Loss: 6.7785749435424805\n",
"3189 Loss: 6.775704383850098\n",
"3190 tensor([[1.3924, 2.1075, 1.4924, 1.9847, 2.4771]], grad_fn=<AddmmBackward>)\n",
"3190 Loss: 6.772834300994873\n",
"3191 Loss: 6.769965648651123\n",
"3192 Loss: 6.767097473144531\n",
"3193 Loss: 6.764229774475098\n",
"3194 Loss: 6.761362075805664\n",
"3195 Loss: 6.758495807647705\n",
"3196 Loss: 6.755630016326904\n",
"3197 Loss: 6.752764701843262\n",
"3198 Loss: 6.749898910522461\n",
"3199 Loss: 6.747036457061768\n",
"3200 tensor([[1.3897, 2.1065, 1.4937, 1.9874, 2.4811]], grad_fn=<AddmmBackward>)\n",
"3200 Loss: 6.744173049926758\n",
"3201 Loss: 6.741309642791748\n",
"3202 Loss: 6.738447189331055\n",
"3203 Loss: 6.735584259033203\n",
"3204 Loss: 6.732723236083984\n",
"3205 Loss: 6.729862213134766\n",
"3206 Loss: 6.72700309753418\n",
"3207 Loss: 6.724143981933594\n",
"3208 Loss: 6.721284866333008\n",
"3209 Loss: 6.718425273895264\n",
"3210 tensor([[1.3871, 2.1055, 1.4951, 1.9901, 2.4852]], grad_fn=<AddmmBackward>)\n",
"3210 Loss: 6.715568542480469\n",
"3211 Loss: 6.712711334228516\n",
"3212 Loss: 6.7098541259765625\n",
"3213 Loss: 6.706998825073242\n",
"3214 Loss: 6.7041425704956055\n",
"3215 Loss: 6.701289653778076\n",
"3216 Loss: 6.698436260223389\n",
"3217 Loss: 6.695582389831543\n",
"3218 Loss: 6.692729949951172\n",
"3219 Loss: 6.689875602722168\n",
"3220 tensor([[1.3844, 2.1045, 1.4964, 1.9928, 2.4892]], grad_fn=<AddmmBackward>)\n",
"3220 Loss: 6.687024116516113\n",
"3221 Loss: 6.684173583984375\n",
"3222 Loss: 6.681323051452637\n",
"3223 Loss: 6.678473949432373\n",
"3224 Loss: 6.675623893737793\n",
"3225 Loss: 6.672776222229004\n",
"3226 Loss: 6.66992712020874\n",
"3227 Loss: 6.667079925537109\n",
"3228 Loss: 6.664233207702637\n",
"3229 Loss: 6.661386966705322\n",
"3230 tensor([[1.3818, 2.1035, 1.4978, 1.9955, 2.4933]], grad_fn=<AddmmBackward>)\n",
"3230 Loss: 6.658542156219482\n",
"3231 Loss: 6.655696392059326\n",
"3232 Loss: 6.652851104736328\n",
"3233 Loss: 6.650007247924805\n",
"3234 Loss: 6.647164344787598\n",
"3235 Loss: 6.644321441650391\n",
"3236 Loss: 6.6414794921875\n",
"3237 Loss: 6.638637542724609\n",
"3238 Loss: 6.635797500610352\n",
"3239 Loss: 6.632957458496094\n",
"3240 tensor([[1.3792, 2.1025, 1.4991, 1.9982, 2.4973]], grad_fn=<AddmmBackward>)\n",
"3240 Loss: 6.630117416381836\n",
"3241 Loss: 6.6272783279418945\n",
"3242 Loss: 6.624439716339111\n",
"3243 Loss: 6.621601104736328\n",
"3244 Loss: 6.6187639236450195\n",
"3245 Loss: 6.615926265716553\n",
"3246 Loss: 6.6130900382995605\n",
"3247 Loss: 6.61025333404541\n",
"3248 Loss: 6.607419967651367\n",
"3249 Loss: 6.604584693908691\n",
"3250 tensor([[1.3766, 2.1015, 1.5005, 2.0009, 2.5014]], grad_fn=<AddmmBackward>)\n",
"3250 Loss: 6.60175085067749\n",
"3251 Loss: 6.598917484283447\n",
"3252 Loss: 6.596085071563721\n",
"3253 Loss: 6.593252182006836\n",
"3254 Loss: 6.590419769287109\n",
"3255 Loss: 6.58759069442749\n",
"3256 Loss: 6.584760665893555\n",
"3257 Loss: 6.581931114196777\n",
"3258 Loss: 6.5791015625\n",
"3259 Loss: 6.5762739181518555\n",
"3260 tensor([[1.3739, 2.1005, 1.5018, 2.0036, 2.5054]], grad_fn=<AddmmBackward>)\n",
"3260 Loss: 6.573446273803711\n",
"3261 Loss: 6.57061767578125\n",
"3262 Loss: 6.567791938781738\n",
"3263 Loss: 6.564965724945068\n",
"3264 Loss: 6.562139511108398\n",
"3265 Loss: 6.559314727783203\n",
"3266 Loss: 6.556491374969482\n",
"3267 Loss: 6.5536675453186035\n",
"3268 Loss: 6.550842761993408\n",
"3269 Loss: 6.54802131652832\n",
"3270 tensor([[1.3713, 2.0995, 1.5032, 2.0063, 2.5095]], grad_fn=<AddmmBackward>)\n",
"3270 Loss: 6.545198917388916\n",
"3271 Loss: 6.542379379272461\n",
"3272 Loss: 6.539557456970215\n",
"3273 Loss: 6.536737442016602\n",
"3274 Loss: 6.533918380737305\n",
"3275 Loss: 6.531099319458008\n",
"3276 Loss: 6.528280735015869\n",
"3277 Loss: 6.5254621505737305\n",
"3278 Loss: 6.522644519805908\n",
"3279 Loss: 6.519826889038086\n",
"3280 tensor([[1.3687, 2.0985, 1.5045, 2.0090, 2.5136]], grad_fn=<AddmmBackward>)\n",
"3280 Loss: 6.517012119293213\n",
"3281 Loss: 6.514196395874023\n",
"3282 Loss: 6.51138162612915\n",
"3283 Loss: 6.50856876373291\n",
"3284 Loss: 6.5057549476623535\n",
"3285 Loss: 6.502941131591797\n",
"3286 Loss: 6.500129699707031\n",
"3287 Loss: 6.497317790985107\n",
"3288 Loss: 6.494505882263184\n",
"3289 Loss: 6.491695404052734\n",
"3290 tensor([[1.3661, 2.0974, 1.5059, 2.0118, 2.5176]], grad_fn=<AddmmBackward>)\n",
"3290 Loss: 6.488884925842285\n",
"3291 Loss: 6.486074447631836\n",
"3292 Loss: 6.483267307281494\n",
"3293 Loss: 6.4804582595825195\n",
"3294 Loss: 6.4776506423950195\n",
"3295 Loss: 6.4748430252075195\n",
"3296 Loss: 6.472036361694336\n",
"3297 Loss: 6.469231128692627\n",
"3298 Loss: 6.466425895690918\n",
"3299 Loss: 6.463621139526367\n",
"3300 tensor([[1.3635, 2.0964, 1.5072, 2.0145, 2.5217]], grad_fn=<AddmmBackward>)\n",
"3300 Loss: 6.460816860198975\n",
"3301 Loss: 6.458014011383057\n",
"3302 Loss: 6.455211639404297\n",
"3303 Loss: 6.4524102210998535\n",
"3304 Loss: 6.449607849121094\n",
"3305 Loss: 6.446806907653809\n",
"3306 Loss: 6.444005966186523\n",
"3307 Loss: 6.441206932067871\n",
"3308 Loss: 6.438407897949219\n",
"3309 Loss: 6.435608863830566\n",
"3310 tensor([[1.3609, 2.0954, 1.5086, 2.0172, 2.5258]], grad_fn=<AddmmBackward>)\n",
"3310 Loss: 6.4328107833862305\n",
"3311 Loss: 6.430014610290527\n",
"3312 Loss: 6.42721700668335\n",
"3313 Loss: 6.424421310424805\n",
"3314 Loss: 6.421626091003418\n",
"3315 Loss: 6.4188313484191895\n",
"3316 Loss: 6.416037559509277\n",
"3317 Loss: 6.413243293762207\n",
"3318 Loss: 6.410450458526611\n",
"3319 Loss: 6.407657623291016\n",
"3320 tensor([[1.3584, 2.0944, 1.5100, 2.0199, 2.5299]], grad_fn=<AddmmBackward>)\n",
"3320 Loss: 6.4048662185668945\n",
"3321 Loss: 6.402073860168457\n",
"3322 Loss: 6.399281978607178\n",
"3323 Loss: 6.396492004394531\n",
"3324 Loss: 6.393703937530518\n",
"3325 Loss: 6.3909149169921875\n",
"3326 Loss: 6.388127326965332\n",
"3327 Loss: 6.385338306427002\n",
"3328 Loss: 6.382552146911621\n",
"3329 Loss: 6.379765510559082\n",
"3330 tensor([[1.3558, 2.0934, 1.5113, 2.0226, 2.5340]], grad_fn=<AddmmBackward>)\n",
"3330 Loss: 6.376978397369385\n",
"3331 Loss: 6.374194145202637\n",
"3332 Loss: 6.371408939361572\n",
"3333 Loss: 6.368625164031982\n",
"3334 Loss: 6.365840911865234\n",
"3335 Loss: 6.363057613372803\n",
"3336 Loss: 6.3602752685546875\n",
"3337 Loss: 6.3574934005737305\n",
"3338 Loss: 6.354712009429932\n",
"3339 Loss: 6.351931571960449\n",
"3340 tensor([[1.3532, 2.0924, 1.5127, 2.0254, 2.5380]], grad_fn=<AddmmBackward>)\n",
"3340 Loss: 6.349151134490967\n",
"3341 Loss: 6.346371173858643\n",
"3342 Loss: 6.343592643737793\n",
"3343 Loss: 6.34081506729126\n",
"3344 Loss: 6.338037490844727\n",
"3345 Loss: 6.335259914398193\n",
"3346 Loss: 6.332483291625977\n",
"3347 Loss: 6.329707622528076\n",
"3348 Loss: 6.326931476593018\n",
"3349 Loss: 6.324157238006592\n",
"3350 tensor([[1.3506, 2.0914, 1.5140, 2.0281, 2.5421]], grad_fn=<AddmmBackward>)\n",
"3350 Loss: 6.321382522583008\n",
"3351 Loss: 6.318609237670898\n",
"3352 Loss: 6.3158369064331055\n",
"3353 Loss: 6.313063621520996\n",
"3354 Loss: 6.310293197631836\n",
"3355 Loss: 6.307521820068359\n",
"3356 Loss: 6.304751396179199\n",
"3357 Loss: 6.301980972290039\n",
"3358 Loss: 6.299211502075195\n",
"3359 Loss: 6.296442985534668\n",
"3360 tensor([[1.3480, 2.0903, 1.5154, 2.0308, 2.5462]], grad_fn=<AddmmBackward>)\n",
"3360 Loss: 6.293675422668457\n",
"3361 Loss: 6.29090690612793\n",
"3362 Loss: 6.288140296936035\n",
"3363 Loss: 6.285373210906982\n",
"3364 Loss: 6.282607555389404\n",
"3365 Loss: 6.279842853546143\n",
"3366 Loss: 6.2770771980285645\n",
"3367 Loss: 6.274313926696777\n",
"3368 Loss: 6.271551132202148\n",
"3369 Loss: 6.2687883377075195\n",
"3370 tensor([[1.3455, 2.0893, 1.5168, 2.0336, 2.5503]], grad_fn=<AddmmBackward>)\n",
"3370 Loss: 6.266026496887207\n",
"3371 Loss: 6.263265609741211\n",
"3372 Loss: 6.260503768920898\n",
"3373 Loss: 6.257744312286377\n",
"3374 Loss: 6.254983901977539\n",
"3375 Loss: 6.252224922180176\n",
"3376 Loss: 6.2494659423828125\n",
"3377 Loss: 6.246708393096924\n",
"3378 Loss: 6.243949890136719\n",
"3379 Loss: 6.2411932945251465\n",
"3380 tensor([[1.3429, 2.0883, 1.5181, 2.0363, 2.5544]], grad_fn=<AddmmBackward>)\n",
"3380 Loss: 6.238438129425049\n",
"3381 Loss: 6.235681056976318\n",
"3382 Loss: 6.2329254150390625\n",
"3383 Loss: 6.230171203613281\n",
"3384 Loss: 6.227417469024658\n",
"3385 Loss: 6.224664688110352\n",
"3386 Loss: 6.221912384033203\n",
"3387 Loss: 6.219160079956055\n",
"3388 Loss: 6.216408729553223\n",
"3389 Loss: 6.213657855987549\n",
"3390 tensor([[1.3404, 2.0873, 1.5195, 2.0390, 2.5585]], grad_fn=<AddmmBackward>)\n",
"3390 Loss: 6.210907936096191\n",
"3391 Loss: 6.208157539367676\n",
"3392 Loss: 6.205409049987793\n",
"3393 Loss: 6.20266056060791\n",
"3394 Loss: 6.1999125480651855\n",
"3395 Loss: 6.197165012359619\n",
"3396 Loss: 6.1944193840026855\n",
"3397 Loss: 6.191672325134277\n",
"3398 Loss: 6.18892765045166\n",
"3399 Loss: 6.186182022094727\n",
"3400 tensor([[1.3378, 2.0862, 1.5209, 2.0418, 2.5626]], grad_fn=<AddmmBackward>)\n",
"3400 Loss: 6.183437347412109\n",
"3401 Loss: 6.180693626403809\n",
"3402 Loss: 6.177950859069824\n",
"3403 Loss: 6.175209045410156\n",
"3404 Loss: 6.172467231750488\n",
"3405 Loss: 6.169726371765137\n",
"3406 Loss: 6.166984558105469\n",
"3407 Loss: 6.164244651794434\n",
"3408 Loss: 6.161504745483398\n",
"3409 Loss: 6.158766746520996\n",
"3410 tensor([[1.3353, 2.0852, 1.5222, 2.0445, 2.5667]], grad_fn=<AddmmBackward>)\n",
"3410 Loss: 6.1560282707214355\n",
"3411 Loss: 6.153290748596191\n",
"3412 Loss: 6.150554656982422\n",
"3413 Loss: 6.147817611694336\n",
"3414 Loss: 6.145082473754883\n",
"3415 Loss: 6.1423468589782715\n",
"3416 Loss: 6.139612197875977\n",
"3417 Loss: 6.136877059936523\n",
"3418 Loss: 6.134143829345703\n",
"3419 Loss: 6.131412029266357\n",
"3420 tensor([[1.3327, 2.0842, 1.5236, 2.0472, 2.5709]], grad_fn=<AddmmBackward>)\n",
"3420 Loss: 6.128679275512695\n",
"3421 Loss: 6.125946998596191\n",
"3422 Loss: 6.12321662902832\n",
"3423 Loss: 6.120485782623291\n",
"3424 Loss: 6.11775541305542\n",
"3425 Loss: 6.115026473999023\n",
"3426 Loss: 6.112298011779785\n",
"3427 Loss: 6.1095685958862305\n",
"3428 Loss: 6.106841087341309\n",
"3429 Loss: 6.104114532470703\n",
"3430 tensor([[1.3302, 2.0831, 1.5250, 2.0500, 2.5750]], grad_fn=<AddmmBackward>)\n",
"3430 Loss: 6.101388454437256\n",
"3431 Loss: 6.098661422729492\n",
"3432 Loss: 6.095937728881836\n",
"3433 Loss: 6.093213081359863\n",
"3434 Loss: 6.090488433837891\n",
"3435 Loss: 6.087765693664551\n",
"3436 Loss: 6.0850419998168945\n",
"3437 Loss: 6.082320213317871\n",
"3438 Loss: 6.079598426818848\n",
"3439 Loss: 6.076878547668457\n",
"3440 tensor([[1.3276, 2.0821, 1.5264, 2.0527, 2.5791]], grad_fn=<AddmmBackward>)\n",
"3440 Loss: 6.074158191680908\n",
"3441 Loss: 6.071438789367676\n",
"3442 Loss: 6.068719863891602\n",
"3443 Loss: 6.066001892089844\n",
"3444 Loss: 6.0632829666137695\n",
"3445 Loss: 6.060566425323486\n",
"3446 Loss: 6.057849884033203\n",
"3447 Loss: 6.055134296417236\n",
"3448 Loss: 6.052417755126953\n",
"3449 Loss: 6.0497026443481445\n",
"3450 tensor([[1.3251, 2.0811, 1.5277, 2.0555, 2.5832]], grad_fn=<AddmmBackward>)\n",
"3450 Loss: 6.046987533569336\n",
"3451 Loss: 6.04427433013916\n",
"3452 Loss: 6.041560173034668\n",
"3453 Loss: 6.038848876953125\n",
"3454 Loss: 6.036135673522949\n",
"3455 Loss: 6.033426284790039\n",
"3456 Loss: 6.030714988708496\n",
"3457 Loss: 6.028005123138428\n",
"3458 Loss: 6.025296211242676\n",
"3459 Loss: 6.022586822509766\n",
"3460 tensor([[1.3226, 2.0800, 1.5291, 2.0582, 2.5873]], grad_fn=<AddmmBackward>)\n",
"3460 Loss: 6.0198798179626465\n",
"3461 Loss: 6.017171859741211\n",
"3462 Loss: 6.014464378356934\n",
"3463 Loss: 6.011758804321289\n",
"3464 Loss: 6.009051322937012\n",
"3465 Loss: 6.006345272064209\n",
"3466 Loss: 6.003640174865723\n",
"3467 Loss: 6.000936985015869\n",
"3468 Loss: 5.998233318328857\n",
"3469 Loss: 5.995530128479004\n",
"3470 tensor([[1.3200, 2.0790, 1.5305, 2.0610, 2.5915]], grad_fn=<AddmmBackward>)\n",
"3470 Loss: 5.992828845977783\n",
"3471 Loss: 5.990126609802246\n",
"3472 Loss: 5.9874267578125\n",
"3473 Loss: 5.984726428985596\n",
"3474 Loss: 5.982025623321533\n",
"3475 Loss: 5.9793267250061035\n",
"3476 Loss: 5.976627349853516\n",
"3477 Loss: 5.973930358886719\n",
"3478 Loss: 5.971233367919922\n",
"3479 Loss: 5.968535900115967\n",
"3480 tensor([[1.3175, 2.0779, 1.5319, 2.0637, 2.5956]], grad_fn=<AddmmBackward>)\n",
"3480 Loss: 5.965839385986328\n",
"3481 Loss: 5.963144779205322\n",
"3482 Loss: 5.960448741912842\n",
"3483 Loss: 5.957754611968994\n",
"3484 Loss: 5.955060005187988\n",
"3485 Loss: 5.952366828918457\n",
"3486 Loss: 5.9496750831604\n",
"3487 Loss: 5.946982383728027\n",
"3488 Loss: 5.944292068481445\n",
"3489 Loss: 5.941600799560547\n",
"3490 tensor([[1.3150, 2.0769, 1.5332, 2.0665, 2.5997]], grad_fn=<AddmmBackward>)\n",
"3490 Loss: 5.938910961151123\n",
"3491 Loss: 5.936220169067383\n",
"3492 Loss: 5.933531761169434\n",
"3493 Loss: 5.930843353271484\n",
"3494 Loss: 5.928155899047852\n",
"3495 Loss: 5.925468444824219\n",
"3496 Loss: 5.922781944274902\n",
"3497 Loss: 5.920095920562744\n",
"3498 Loss: 5.9174113273620605\n",
"3499 Loss: 5.9147257804870605\n",
"3500 tensor([[1.3125, 2.0758, 1.5346, 2.0692, 2.6039]], grad_fn=<AddmmBackward>)\n",
"3500 Loss: 5.912042617797852\n",
"3501 Loss: 5.909358024597168\n",
"3502 Loss: 5.906675338745117\n",
"3503 Loss: 5.903993606567383\n",
"3504 Loss: 5.901311874389648\n",
"3505 Loss: 5.898631572723389\n",
"3506 Loss: 5.895950794219971\n",
"3507 Loss: 5.893270492553711\n",
"3508 Loss: 5.890591621398926\n",
"3509 Loss: 5.887912750244141\n",
"3510 tensor([[1.3100, 2.0747, 1.5360, 2.0720, 2.6080]], grad_fn=<AddmmBackward>)\n",
"3510 Loss: 5.8852338790893555\n",
"3511 Loss: 5.882556438446045\n",
"3512 Loss: 5.879878997802734\n",
"3513 Loss: 5.87720251083374\n",
"3514 Loss: 5.874527454376221\n",
"3515 Loss: 5.871851921081543\n",
"3516 Loss: 5.86917781829834\n",
"3517 Loss: 5.866504669189453\n",
"3518 Loss: 5.863830089569092\n",
"3519 Loss: 5.861158847808838\n",
"3520 tensor([[1.3074, 2.0737, 1.5374, 2.0748, 2.6121]], grad_fn=<AddmmBackward>)\n",
"3520 Loss: 5.858485221862793\n",
"3521 Loss: 5.855813980102539\n",
"3522 Loss: 5.853143692016602\n",
"3523 Loss: 5.850473403930664\n",
"3524 Loss: 5.847803592681885\n",
"3525 Loss: 5.845134735107422\n",
"3526 Loss: 5.842466354370117\n",
"3527 Loss: 5.839798927307129\n",
"3528 Loss: 5.837131977081299\n",
"3529 Loss: 5.834465980529785\n",
"3530 tensor([[1.3049, 2.0726, 1.5388, 2.0775, 2.6163]], grad_fn=<AddmmBackward>)\n",
"3530 Loss: 5.8317999839782715\n",
"3531 Loss: 5.829134941101074\n",
"3532 Loss: 5.826469898223877\n",
"3533 Loss: 5.823806285858154\n",
"3534 Loss: 5.821142196655273\n",
"3535 Loss: 5.818479537963867\n",
"3536 Loss: 5.815817832946777\n",
"3537 Loss: 5.813155174255371\n",
"3538 Loss: 5.810493469238281\n",
"3539 Loss: 5.807833671569824\n",
"3540 tensor([[1.3024, 2.0715, 1.5401, 2.0803, 2.6204]], grad_fn=<AddmmBackward>)\n",
"3540 Loss: 5.805173873901367\n",
"3541 Loss: 5.80251407623291\n",
"3542 Loss: 5.799856185913086\n",
"3543 Loss: 5.79719877243042\n",
"3544 Loss: 5.794541358947754\n",
"3545 Loss: 5.791884422302246\n",
"3546 Loss: 5.7892279624938965\n",
"3547 Loss: 5.78657341003418\n",
"3548 Loss: 5.783917427062988\n",
"3549 Loss: 5.781262397766113\n",
"3550 tensor([[1.2999, 2.0705, 1.5415, 2.0830, 2.6246]], grad_fn=<AddmmBackward>)\n",
"3550 Loss: 5.778609275817871\n",
"3551 Loss: 5.7759575843811035\n",
"3552 Loss: 5.773304462432861\n",
"3553 Loss: 5.770651817321777\n",
"3554 Loss: 5.76800012588501\n",
"3555 Loss: 5.765350341796875\n",
"3556 Loss: 5.762699604034424\n",
"3557 Loss: 5.7600507736206055\n",
"3558 Loss: 5.757402420043945\n",
"3559 Loss: 5.7547526359558105\n",
"3560 tensor([[1.2974, 2.0694, 1.5429, 2.0858, 2.6287]], grad_fn=<AddmmBackward>)\n",
"3560 Loss: 5.752106189727783\n",
"3561 Loss: 5.749459266662598\n",
"3562 Loss: 5.746812343597412\n",
"3563 Loss: 5.744166374206543\n",
"3564 Loss: 5.741521835327148\n",
"3565 Loss: 5.73887825012207\n",
"3566 Loss: 5.736233711242676\n",
"3567 Loss: 5.7335896492004395\n",
"3568 Loss: 5.7309465408325195\n",
"3569 Loss: 5.728303909301758\n",
"3570 tensor([[1.2949, 2.0683, 1.5443, 2.0886, 2.6329]], grad_fn=<AddmmBackward>)\n",
"3570 Loss: 5.725663661956787\n",
"3571 Loss: 5.723021984100342\n",
"3572 Loss: 5.7203826904296875\n",
"3573 Loss: 5.717743396759033\n",
"3574 Loss: 5.715103626251221\n",
"3575 Loss: 5.712465286254883\n",
"3576 Loss: 5.709827423095703\n",
"3577 Loss: 5.70719051361084\n",
"3578 Loss: 5.704553127288818\n",
"3579 Loss: 5.701918125152588\n",
"3580 tensor([[1.2924, 2.0672, 1.5457, 2.0913, 2.6370]], grad_fn=<AddmmBackward>)\n",
"3580 Loss: 5.699282646179199\n",
"3581 Loss: 5.696648120880127\n",
"3582 Loss: 5.694014072418213\n",
"3583 Loss: 5.691380023956299\n",
"3584 Loss: 5.688747406005859\n",
"3585 Loss: 5.686116695404053\n",
"3586 Loss: 5.6834845542907715\n",
"3587 Loss: 5.680854320526123\n",
"3588 Loss: 5.678224563598633\n",
"3589 Loss: 5.675594329833984\n",
"3590 tensor([[1.2900, 2.0662, 1.5471, 2.0941, 2.6412]], grad_fn=<AddmmBackward>)\n",
"3590 Loss: 5.672966003417969\n",
"3591 Loss: 5.670336723327637\n",
"3592 Loss: 5.667709827423096\n",
"3593 Loss: 5.665082931518555\n",
"3594 Loss: 5.66245698928833\n",
"3595 Loss: 5.659830093383789\n",
"3596 Loss: 5.657204627990723\n",
"3597 Loss: 5.654579162597656\n",
"3598 Loss: 5.651955604553223\n",
"3599 Loss: 5.649332046508789\n",
"3600 tensor([[1.2875, 2.0651, 1.5484, 2.0969, 2.6453]], grad_fn=<AddmmBackward>)\n",
"3600 Loss: 5.64670991897583\n",
"3601 Loss: 5.644087791442871\n",
"3602 Loss: 5.6414666175842285\n",
"3603 Loss: 5.638845920562744\n",
"3604 Loss: 5.636225700378418\n",
"3605 Loss: 5.63360595703125\n",
"3606 Loss: 5.630987644195557\n",
"3607 Loss: 5.628368377685547\n",
"3608 Loss: 5.62575101852417\n",
"3609 Loss: 5.623133659362793\n",
"3610 tensor([[1.2850, 2.0640, 1.5498, 2.0996, 2.6495]], grad_fn=<AddmmBackward>)\n",
"3610 Loss: 5.620516777038574\n",
"3611 Loss: 5.61790132522583\n",
"3612 Loss: 5.6152849197387695\n",
"3613 Loss: 5.6126708984375\n",
"3614 Loss: 5.610056400299072\n",
"3615 Loss: 5.607443332672119\n",
"3616 Loss: 5.604829788208008\n",
"3617 Loss: 5.6022186279296875\n",
"3618 Loss: 5.599606990814209\n",
"3619 Loss: 5.596996307373047\n",
"3620 tensor([[1.2825, 2.0629, 1.5512, 2.1024, 2.6536]], grad_fn=<AddmmBackward>)\n",
"3620 Loss: 5.594386577606201\n",
"3621 Loss: 5.591775894165039\n",
"3622 Loss: 5.589166641235352\n",
"3623 Loss: 5.5865583419799805\n",
"3624 Loss: 5.583950519561768\n",
"3625 Loss: 5.581343650817871\n",
"3626 Loss: 5.578736305236816\n",
"3627 Loss: 5.576131343841553\n",
"3628 Loss: 5.573525428771973\n",
"3629 Loss: 5.570920944213867\n",
"3630 tensor([[1.2800, 2.0618, 1.5526, 2.1052, 2.6578]], grad_fn=<AddmmBackward>)\n",
"3630 Loss: 5.568317413330078\n",
"3631 Loss: 5.565713882446289\n",
"3632 Loss: 5.5631103515625\n",
"3633 Loss: 5.560508728027344\n",
"3634 Loss: 5.557908058166504\n",
"3635 Loss: 5.5553059577941895\n",
"3636 Loss: 5.552704811096191\n",
"3637 Loss: 5.550105571746826\n",
"3638 Loss: 5.547506332397461\n",
"3639 Loss: 5.5449066162109375\n",
"3640 tensor([[1.2775, 2.0607, 1.5540, 2.1080, 2.6619]], grad_fn=<AddmmBackward>)\n",
"3640 Loss: 5.542308807373047\n",
"3641 Loss: 5.539710998535156\n",
"3642 Loss: 5.53711462020874\n",
"3643 Loss: 5.534518718719482\n",
"3644 Loss: 5.531923770904541\n",
"3645 Loss: 5.529328346252441\n",
"3646 Loss: 5.526734352111816\n",
"3647 Loss: 5.524141788482666\n",
"3648 Loss: 5.521547317504883\n",
"3649 Loss: 5.518957138061523\n",
"3650 tensor([[1.2751, 2.0596, 1.5554, 2.1107, 2.6661]], grad_fn=<AddmmBackward>)\n",
"3650 Loss: 5.516364574432373\n",
"3651 Loss: 5.513773441314697\n",
"3652 Loss: 5.511183738708496\n",
"3653 Loss: 5.50859260559082\n",
"3654 Loss: 5.506003379821777\n",
"3655 Loss: 5.503414154052734\n",
"3656 Loss: 5.500826358795166\n",
"3657 Loss: 5.498239517211914\n",
"3658 Loss: 5.49565315246582\n",
"3659 Loss: 5.493067741394043\n",
"3660 tensor([[1.2726, 2.0585, 1.5568, 2.1135, 2.6703]], grad_fn=<AddmmBackward>)\n",
"3660 Loss: 5.490481853485107\n",
"3661 Loss: 5.4878973960876465\n",
"3662 Loss: 5.4853129386901855\n",
"3663 Loss: 5.482729911804199\n",
"3664 Loss: 5.4801459312438965\n",
"3665 Loss: 5.47756290435791\n",
"3666 Loss: 5.474982261657715\n",
"3667 Loss: 5.472400665283203\n",
"3668 Loss: 5.469820976257324\n",
"3669 Loss: 5.467241287231445\n",
"3670 tensor([[1.2701, 2.0574, 1.5581, 2.1163, 2.6744]], grad_fn=<AddmmBackward>)\n",
"3670 Loss: 5.464661598205566\n",
"3671 Loss: 5.462083339691162\n",
"3672 Loss: 5.459506034851074\n",
"3673 Loss: 5.4569292068481445\n",
"3674 Loss: 5.454351902008057\n",
"3675 Loss: 5.451775074005127\n",
"3676 Loss: 5.44920015335083\n",
"3677 Loss: 5.446625232696533\n",
"3678 Loss: 5.4440507888793945\n",
"3679 Loss: 5.4414777755737305\n",
"3680 tensor([[1.2677, 2.0563, 1.5595, 2.1191, 2.6786]], grad_fn=<AddmmBackward>)\n",
"3680 Loss: 5.43890380859375\n",
"3681 Loss: 5.436331748962402\n",
"3682 Loss: 5.433760166168213\n",
"3683 Loss: 5.43118953704834\n",
"3684 Loss: 5.428618431091309\n",
"3685 Loss: 5.426050186157227\n",
"3686 Loss: 5.423480033874512\n",
"3687 Loss: 5.42091178894043\n",
"3688 Loss: 5.418343544006348\n",
"3689 Loss: 5.415777206420898\n",
"3690 tensor([[1.2652, 2.0552, 1.5609, 2.1218, 2.6827]], grad_fn=<AddmmBackward>)\n",
"3690 Loss: 5.413209915161133\n",
"3691 Loss: 5.41064453125\n",
"3692 Loss: 5.408078193664551\n",
"3693 Loss: 5.405514240264893\n",
"3694 Loss: 5.402949810028076\n",
"3695 Loss: 5.400386810302734\n",
"3696 Loss: 5.397823333740234\n",
"3697 Loss: 5.395261287689209\n",
"3698 Loss: 5.392699718475342\n",
"3699 Loss: 5.390140056610107\n",
"3700 tensor([[1.2627, 2.0540, 1.5623, 2.1246, 2.6869]], grad_fn=<AddmmBackward>)\n",
"3700 Loss: 5.387579917907715\n",
"3701 Loss: 5.3850202560424805\n",
"3702 Loss: 5.382462501525879\n",
"3703 Loss: 5.3799028396606445\n",
"3704 Loss: 5.377346038818359\n",
"3705 Loss: 5.374789714813232\n",
"3706 Loss: 5.372232913970947\n",
"3707 Loss: 5.3696770668029785\n",
"3708 Loss: 5.367122173309326\n",
"3709 Loss: 5.36456823348999\n",
"3710 tensor([[1.2603, 2.0529, 1.5637, 2.1274, 2.6911]], grad_fn=<AddmmBackward>)\n",
"3710 Loss: 5.362014293670654\n",
"3711 Loss: 5.359461307525635\n",
"3712 Loss: 5.356908798217773\n",
"3713 Loss: 5.3543572425842285\n",
"3714 Loss: 5.351805686950684\n",
"3715 Loss: 5.349255084991455\n",
"3716 Loss: 5.346706390380859\n",
"3717 Loss: 5.3441572189331055\n",
"3718 Loss: 5.34160852432251\n",
"3719 Loss: 5.3390607833862305\n",
"3720 tensor([[1.2578, 2.0518, 1.5651, 2.1302, 2.6952]], grad_fn=<AddmmBackward>)\n",
"3720 Loss: 5.336513519287109\n",
"3721 Loss: 5.33396577835083\n",
"3722 Loss: 5.331419944763184\n",
"3723 Loss: 5.328873634338379\n",
"3724 Loss: 5.326329231262207\n",
"3725 Loss: 5.323785305023193\n",
"3726 Loss: 5.32124137878418\n",
"3727 Loss: 5.318699359893799\n",
"3728 Loss: 5.31615686416626\n",
"3729 Loss: 5.313614845275879\n",
"3730 tensor([[1.2553, 2.0507, 1.5665, 2.1329, 2.6994]], grad_fn=<AddmmBackward>)\n",
"3730 Loss: 5.3110737800598145\n",
"3731 Loss: 5.308533668518066\n",
"3732 Loss: 5.305994033813477\n",
"3733 Loss: 5.303454399108887\n",
"3734 Loss: 5.300915718078613\n",
"3735 Loss: 5.298377990722656\n",
"3736 Loss: 5.295841217041016\n",
"3737 Loss: 5.293304443359375\n",
"3738 Loss: 5.290768623352051\n",
"3739 Loss: 5.288232803344727\n",
"3740 tensor([[1.2529, 2.0495, 1.5679, 2.1357, 2.7036]], grad_fn=<AddmmBackward>)\n",
"3740 Loss: 5.285698890686035\n",
"3741 Loss: 5.283164978027344\n",
"3742 Loss: 5.280630588531494\n",
"3743 Loss: 5.278098106384277\n",
"3744 Loss: 5.275567054748535\n",
"3745 Loss: 5.273036003112793\n",
"3746 Loss: 5.270505428314209\n",
"3747 Loss: 5.267974853515625\n",
"3748 Loss: 5.265444278717041\n",
"3749 Loss: 5.26291561126709\n",
"3750 tensor([[1.2504, 2.0484, 1.5692, 2.1385, 2.7077]], grad_fn=<AddmmBackward>)\n",
"3750 Loss: 5.260386943817139\n",
"3751 Loss: 5.257859230041504\n",
"3752 Loss: 5.255332946777344\n",
"3753 Loss: 5.252805709838867\n",
"3754 Loss: 5.250280380249023\n",
"3755 Loss: 5.2477545738220215\n",
"3756 Loss: 5.245230674743652\n",
"3757 Loss: 5.242707252502441\n",
"3758 Loss: 5.240184307098389\n",
"3759 Loss: 5.237662315368652\n",
"3760 tensor([[1.2480, 2.0472, 1.5706, 2.1413, 2.7119]], grad_fn=<AddmmBackward>)\n",
"3760 Loss: 5.235139846801758\n",
"3761 Loss: 5.23261833190918\n",
"3762 Loss: 5.230098247528076\n",
"3763 Loss: 5.227577209472656\n",
"3764 Loss: 5.2250590324401855\n",
"3765 Loss: 5.222539901733398\n",
"3766 Loss: 5.220022201538086\n",
"3767 Loss: 5.217504978179932\n",
"3768 Loss: 5.214987754821777\n",
"3769 Loss: 5.2124714851379395\n",
"3770 tensor([[1.2455, 2.0461, 1.5720, 2.1441, 2.7161]], grad_fn=<AddmmBackward>)\n",
"3770 Loss: 5.20995569229126\n",
"3771 Loss: 5.207440376281738\n",
"3772 Loss: 5.204927444458008\n",
"3773 Loss: 5.202411651611328\n",
"3774 Loss: 5.199899673461914\n",
"3775 Loss: 5.1973876953125\n",
"3776 Loss: 5.194876670837402\n",
"3777 Loss: 5.192366600036621\n",
"3778 Loss: 5.18985652923584\n",
"3779 Loss: 5.187346458435059\n",
"3780 tensor([[1.2431, 2.0449, 1.5734, 2.1468, 2.7202]], grad_fn=<AddmmBackward>)\n",
"3780 Loss: 5.1848368644714355\n",
"3781 Loss: 5.182329177856445\n",
"3782 Loss: 5.179821491241455\n",
"3783 Loss: 5.177314758300781\n",
"3784 Loss: 5.174808502197266\n",
"3785 Loss: 5.172303199768066\n",
"3786 Loss: 5.169798851013184\n",
"3787 Loss: 5.167293548583984\n",
"3788 Loss: 5.164791107177734\n",
"3789 Loss: 5.162287712097168\n",
"3790 tensor([[1.2406, 2.0438, 1.5748, 2.1496, 2.7244]], grad_fn=<AddmmBackward>)\n",
"3790 Loss: 5.15978479385376\n",
"3791 Loss: 5.157284259796143\n",
"3792 Loss: 5.154783248901367\n",
"3793 Loss: 5.15228271484375\n",
"3794 Loss: 5.149783134460449\n",
"3795 Loss: 5.147283554077148\n",
"3796 Loss: 5.1447858810424805\n",
"3797 Loss: 5.142287731170654\n",
"3798 Loss: 5.139791488647461\n",
"3799 Loss: 5.137293815612793\n",
"3800 tensor([[1.2382, 2.0426, 1.5762, 2.1524, 2.7286]], grad_fn=<AddmmBackward>)\n",
"3800 Loss: 5.134799003601074\n",
"3801 Loss: 5.1323041915893555\n",
"3802 Loss: 5.1298089027404785\n",
"3803 Loss: 5.127315521240234\n",
"3804 Loss: 5.124822616577148\n",
"3805 Loss: 5.122329235076904\n",
"3806 Loss: 5.119837760925293\n",
"3807 Loss: 5.11734676361084\n",
"3808 Loss: 5.114855766296387\n",
"3809 Loss: 5.112365245819092\n",
"3810 tensor([[1.2358, 2.0415, 1.5776, 2.1552, 2.7327]], grad_fn=<AddmmBackward>)\n",
"3810 Loss: 5.109875679016113\n",
"3811 Loss: 5.107386112213135\n",
"3812 Loss: 5.104898929595947\n",
"3813 Loss: 5.102410793304443\n",
"3814 Loss: 5.099923610687256\n",
"3815 Loss: 5.097438335418701\n",
"3816 Loss: 5.0949530601501465\n",
"3817 Loss: 5.09246826171875\n",
"3818 Loss: 5.089983940124512\n",
"3819 Loss: 5.08750057220459\n",
"3820 tensor([[1.2333, 2.0403, 1.5790, 2.1579, 2.7369]], grad_fn=<AddmmBackward>)\n",
"3820 Loss: 5.085017204284668\n",
"3821 Loss: 5.0825347900390625\n",
"3822 Loss: 5.080053329467773\n",
"3823 Loss: 5.077571392059326\n",
"3824 Loss: 5.0750908851623535\n",
"3825 Loss: 5.0726118087768555\n",
"3826 Loss: 5.070132255554199\n",
"3827 Loss: 5.067654609680176\n",
"3828 Loss: 5.0651774406433105\n",
"3829 Loss: 5.0627007484436035\n",
"3830 tensor([[1.2309, 2.0391, 1.5804, 2.1607, 2.7411]], grad_fn=<AddmmBackward>)\n",
"3830 Loss: 5.06022310256958\n",
"3831 Loss: 5.0577473640441895\n",
"3832 Loss: 5.055272579193115\n",
"3833 Loss: 5.052798748016357\n",
"3834 Loss: 5.0503249168396\n",
"3835 Loss: 5.047852039337158\n",
"3836 Loss: 5.045379638671875\n",
"3837 Loss: 5.042906761169434\n",
"3838 Loss: 5.040435791015625\n",
"3839 Loss: 5.037966251373291\n",
"3840 tensor([[1.2284, 2.0380, 1.5818, 2.1635, 2.7453]], grad_fn=<AddmmBackward>)\n",
"3840 Loss: 5.035495281219482\n",
"3841 Loss: 5.033026218414307\n",
"3842 Loss: 5.030557632446289\n",
"3843 Loss: 5.028090953826904\n",
"3844 Loss: 5.025622844696045\n",
"3845 Loss: 5.023158073425293\n",
"3846 Loss: 5.020692825317383\n",
"3847 Loss: 5.018227577209473\n",
"3848 Loss: 5.015761852264404\n",
"3849 Loss: 5.013298034667969\n",
"3850 tensor([[1.2260, 2.0368, 1.5831, 2.1663, 2.7494]], grad_fn=<AddmmBackward>)\n",
"3850 Loss: 5.01083517074585\n",
"3851 Loss: 5.008373260498047\n",
"3852 Loss: 5.005911827087402\n",
"3853 Loss: 5.003450393676758\n",
"3854 Loss: 5.00098991394043\n",
"3855 Loss: 4.99852991104126\n",
"3856 Loss: 4.996070861816406\n",
"3857 Loss: 4.993613243103027\n",
"3858 Loss: 4.991154670715332\n",
"3859 Loss: 4.988698482513428\n",
"3860 tensor([[1.2236, 2.0356, 1.5845, 2.1691, 2.7536]], grad_fn=<AddmmBackward>)\n",
"3860 Loss: 4.986240386962891\n",
"3861 Loss: 4.983785152435303\n",
"3862 Loss: 4.981330871582031\n",
"3863 Loss: 4.978876113891602\n",
"3864 Loss: 4.976421356201172\n",
"3865 Loss: 4.973969459533691\n",
"3866 Loss: 4.971516132354736\n",
"3867 Loss: 4.969064235687256\n",
"3868 Loss: 4.966613292694092\n",
"3869 Loss: 4.964162826538086\n",
"3870 tensor([[1.2212, 2.0344, 1.5859, 2.1718, 2.7578]], grad_fn=<AddmmBackward>)\n",
"3870 Loss: 4.9617133140563965\n",
"3871 Loss: 4.959263801574707\n",
"3872 Loss: 4.95681619644165\n",
"3873 Loss: 4.954367637634277\n",
"3874 Loss: 4.951920986175537\n",
"3875 Loss: 4.949473857879639\n",
"3876 Loss: 4.947028160095215\n",
"3877 Loss: 4.944582939147949\n",
"3878 Loss: 4.942138671875\n",
"3879 Loss: 4.939694404602051\n",
"3880 tensor([[1.2187, 2.0332, 1.5873, 2.1746, 2.7619]], grad_fn=<AddmmBackward>)\n",
"3880 Loss: 4.937250137329102\n",
"3881 Loss: 4.934808731079102\n",
"3882 Loss: 4.932366371154785\n",
"3883 Loss: 4.929924488067627\n",
"3884 Loss: 4.927484512329102\n",
"3885 Loss: 4.925044059753418\n",
"3886 Loss: 4.922605037689209\n",
"3887 Loss: 4.920166015625\n",
"3888 Loss: 4.917728900909424\n",
"3889 Loss: 4.915291786193848\n",
"3890 tensor([[1.2163, 2.0320, 1.5887, 2.1774, 2.7661]], grad_fn=<AddmmBackward>)\n",
"3890 Loss: 4.91285514831543\n",
"3891 Loss: 4.910418510437012\n",
"3892 Loss: 4.90798282623291\n",
"3893 Loss: 4.905549049377441\n",
"3894 Loss: 4.9031147956848145\n",
"3895 Loss: 4.900681495666504\n",
"3896 Loss: 4.89824914932251\n",
"3897 Loss: 4.895816326141357\n",
"3898 Loss: 4.893383979797363\n",
"3899 Loss: 4.89095401763916\n",
"3900 tensor([[1.2139, 2.0308, 1.5901, 2.1802, 2.7703]], grad_fn=<AddmmBackward>)\n",
"3900 Loss: 4.888524532318115\n",
"3901 Loss: 4.886096000671387\n",
"3902 Loss: 4.8836669921875\n",
"3903 Loss: 4.881239891052246\n",
"3904 Loss: 4.878812789916992\n",
"3905 Loss: 4.876386642456055\n",
"3906 Loss: 4.873960971832275\n",
"3907 Loss: 4.871535778045654\n",
"3908 Loss: 4.869111061096191\n",
"3909 Loss: 4.866687774658203\n",
"3910 tensor([[1.2114, 2.0296, 1.5915, 2.1829, 2.7744]], grad_fn=<AddmmBackward>)\n",
"3910 Loss: 4.864263534545898\n",
"3911 Loss: 4.861840724945068\n",
"3912 Loss: 4.859419345855713\n",
"3913 Loss: 4.856998443603516\n",
"3914 Loss: 4.854578495025635\n",
"3915 Loss: 4.852159023284912\n",
"3916 Loss: 4.849740028381348\n",
"3917 Loss: 4.847322463989258\n",
"3918 Loss: 4.84490442276001\n",
"3919 Loss: 4.842486381530762\n",
"3920 tensor([[1.2090, 2.0284, 1.5929, 2.1857, 2.7786]], grad_fn=<AddmmBackward>)\n",
"3920 Loss: 4.840070724487305\n",
"3921 Loss: 4.837654113769531\n",
"3922 Loss: 4.835238456726074\n",
"3923 Loss: 4.832824230194092\n",
"3924 Loss: 4.830410957336426\n",
"3925 Loss: 4.82799768447876\n",
"3926 Loss: 4.825585842132568\n",
"3927 Loss: 4.8231730461120605\n",
"3928 Loss: 4.820763111114502\n",
"3929 Loss: 4.818352222442627\n",
"3930 tensor([[1.2066, 2.0272, 1.5942, 2.1885, 2.7827]], grad_fn=<AddmmBackward>)\n",
"3930 Loss: 4.815942764282227\n",
"3931 Loss: 4.813533306121826\n",
"3932 Loss: 4.811124324798584\n",
"3933 Loss: 4.808716773986816\n",
"3934 Loss: 4.806309700012207\n",
"3935 Loss: 4.803903579711914\n",
"3936 Loss: 4.801497459411621\n",
"3937 Loss: 4.799093246459961\n",
"3938 Loss: 4.796688079833984\n",
"3939 Loss: 4.794284820556641\n",
"3940 tensor([[1.2042, 2.0260, 1.5956, 2.1913, 2.7869]], grad_fn=<AddmmBackward>)\n",
"3940 Loss: 4.791882514953613\n",
"3941 Loss: 4.789478778839111\n",
"3942 Loss: 4.787076950073242\n",
"3943 Loss: 4.7846760749816895\n",
"3944 Loss: 4.782275199890137\n",
"3945 Loss: 4.779876232147217\n",
"3946 Loss: 4.777476787567139\n",
"3947 Loss: 4.775079250335693\n",
"3948 Loss: 4.772682189941406\n",
"3949 Loss: 4.770284175872803\n",
"3950 tensor([[1.2018, 2.0248, 1.5970, 2.1940, 2.7911]], grad_fn=<AddmmBackward>)\n",
"3950 Loss: 4.76788854598999\n",
"3951 Loss: 4.765493392944336\n",
"3952 Loss: 4.763098239898682\n",
"3953 Loss: 4.760704040527344\n",
"3954 Loss: 4.758310317993164\n",
"3955 Loss: 4.755916595458984\n",
"3956 Loss: 4.753525733947754\n",
"3957 Loss: 4.751133918762207\n",
"3958 Loss: 4.748743534088135\n",
"3959 Loss: 4.7463531494140625\n",
"3960 tensor([[1.1993, 2.0236, 1.5984, 2.1968, 2.7952]], grad_fn=<AddmmBackward>)\n",
"3960 Loss: 4.743964195251465\n",
"3961 Loss: 4.741574287414551\n",
"3962 Loss: 4.739187240600586\n",
"3963 Loss: 4.736800193786621\n",
"3964 Loss: 4.734414100646973\n",
"3965 Loss: 4.732027053833008\n",
"3966 Loss: 4.729641437530518\n",
"3967 Loss: 4.72725772857666\n",
"3968 Loss: 4.724872589111328\n",
"3969 Loss: 4.722489356994629\n",
"3970 tensor([[1.1969, 2.0223, 1.5998, 2.1996, 2.7994]], grad_fn=<AddmmBackward>)\n",
"3970 Loss: 4.720107078552246\n",
"3971 Loss: 4.71772575378418\n",
"3972 Loss: 4.715343475341797\n",
"3973 Loss: 4.712962627410889\n",
"3974 Loss: 4.710583686828613\n",
"3975 Loss: 4.70820426940918\n",
"3976 Loss: 4.705825328826904\n",
"3977 Loss: 4.703447341918945\n",
"3978 Loss: 4.701070308685303\n",
"3979 Loss: 4.698693752288818\n",
"3980 tensor([[1.1945, 2.0211, 1.6012, 2.2024, 2.8035]], grad_fn=<AddmmBackward>)\n",
"3980 Loss: 4.696317195892334\n",
"3981 Loss: 4.693941593170166\n",
"3982 Loss: 4.691567420959473\n",
"3983 Loss: 4.689192771911621\n",
"3984 Loss: 4.686819076538086\n",
"3985 Loss: 4.684446811676025\n",
"3986 Loss: 4.682075500488281\n",
"3987 Loss: 4.679705619812012\n",
"3988 Loss: 4.677333354949951\n",
"3989 Loss: 4.674964427947998\n",
"3990 tensor([[1.1921, 2.0199, 1.6026, 2.2051, 2.8077]], grad_fn=<AddmmBackward>)\n",
"3990 Loss: 4.672595024108887\n",
"3991 Loss: 4.670226573944092\n",
"3992 Loss: 4.667859077453613\n",
"3993 Loss: 4.665492534637451\n",
"3994 Loss: 4.663126468658447\n",
"3995 Loss: 4.660760402679443\n",
"3996 Loss: 4.658395767211914\n",
"3997 Loss: 4.656031131744385\n",
"3998 Loss: 4.653668403625488\n",
"3999 Loss: 4.651305675506592\n",
"tensor([[1.1899, 2.0188, 1.6038, 2.2076, 2.8114]], grad_fn=<AddmmBackward>)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "lDex6PZVQgUi",
"outputId": "0fe22ee6-f9b6-439a-dae8-356b0aa5202d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
}
},
"source": [
"# Final weights.\n",
"print(model[0], model[0].weight, model[0].bias)\n",
"print(model[2], model[2].weight, model[2].bias)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Linear(in_features=5, out_features=2, bias=True) Parameter containing:\n",
"tensor([[ 0.9226, -0.0580, -0.0387, -0.0193, 0.0000],\n",
" [ 0.0478, 1.0358, 0.0239, 0.0119, 0.0000]], requires_grad=True) Parameter containing:\n",
"tensor([-0.0512, -0.0881], requires_grad=True)\n",
"Linear(in_features=2, out_features=5, bias=True) Parameter containing:\n",
"tensor([[ 0.6515, -0.3055],\n",
" [-0.1991, 0.8216],\n",
" [ 0.2570, 0.2262],\n",
" [ 0.3703, 0.3260],\n",
" [ 0.4370, 0.3847]], requires_grad=True) Parameter containing:\n",
"tensor([-0.6083, -0.5095, 0.0823, 0.2370, 0.7395], requires_grad=True)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "COntGcn9H2kb",
"outputId": "05723434-4957-4dd6-fcf5-d35357a1c626",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 68
}
},
"source": [
"Linear = nn.Linear(5, 2, bias=False)\n",
"Linear.weight.data.fill_(1)\n",
"print(Linear.weight.data)\n",
"input = torch.tensor([0., 1., 2., 3., 4.])\n",
"print(Linear(input))"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"tensor([[1., 1., 1., 1., 1.],\n",
" [1., 1., 1., 1., 1.]])\n",
"tensor([10., 10.], grad_fn=<SqueezeBackward3>)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "vzxU4-fRZP7X",
"outputId": "7307d8d5-5bc3-4e3d-fd5f-a722d62385b3",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 510
}
},
"source": [
"# Show the tensor.\n",
"def showTensor(aTensor):\n",
" plt.figure()\n",
" plt.imshow(aTensor.numpy())\n",
" plt.colorbar()\n",
" plt.show()\n",
"\n",
"showTensor(model[0].weight.data.detach())\n",
"showTensor(model[2].weight.data.detach())"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 2 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
},
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAKUAAAD8CAYAAAAWqmTlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAANSklEQVR4nO3db6xlV13G8e8z06FjoYXArbHSwTGxEptqgExA0xdUKFKqqS80hhJUzMR5o6YKaiQaIfoKjWhMCDrKpIharaMxEwVHqm0mmBaY0mbSdrROMOAIydDpUEtI25l7Hl/sc8fbydyz153Z+551zno+yU7un3PXWYVn1t5r7b3OT7aJqMm2eXcg4kIJZVQnoYzqJJRRnYQyqpNQRnUSyrhkkg5IOiXpsQ1+L0l/KOmEpGOS3lDSbkIZl+Nu4LYZv38HcMP02Ad8tKTRhDIume0jwNMzXvKjwJ+58xDwCknX9bV7xVAdXG/lldu9e9eOMZoe3JPHrpp3FzblWc48ZfvaS/37t//gS3366dWi1z587PnHgefW/Wi/7f2beLtXA/+97vuT0599ddYfjRLK3bt28LnDu8ZoenBv//bXzbsLm3KfD37pcv7+9NOrfO7wa4peu/26/3zO9p7Leb9LMUooo14GJky26u3+B1g/Ol0//dlMuaZsjDFnvVp0DOAQ8FPTWfj3A8/YnnnqhoyUTRpqpJR0D3ALsCLpJPABYAeA7T8CPgncDpwAvgn8TEm7CWVjjFkd6HFF23f2/N7Az2223YSyQRPqfoY2oWyMgdWEMmqTkTKqYuBs5VtgEsrGGOf0HZUxrNadyYSyNd0dnbollM0Rq2jenZgpoWxMN9FJKKMi3TplQhmVmWSkjJpkpIzqGLFa+ROLRb2TdJuk/5juSvu1sTsV45pYRce89I6UkrYDHwHeRrfH4vOSDtl+YuzOxfCMeMHb592NmUpGyjcCJ2x/0fYLwF/R7VKLBdQtnm8rOual5J032pH2IpL2SToq6ejXTg/yKH2MZHW6gN53zMtg/xxs77e9x/aea19V9+mhZbZY9baiY15KZt+XtCMt6jVZgiWhzwM3SPpOujC+E3jXqL2K0XQTnbpXAnt7Z/ucpJ8HDgPbgQO2Hx+9ZzGKtYlOzYr+ydj+JN12yVgCq7nNGDVZhDs6CWWDJnOcWZdIKBvTPZCRUEZFjDhb+W3GhLIxNnNdGC+RUDZHS7F4HkvEZKSMCmWiE1Ux832At0RC2Zhui23d/7fX3bsYQT6MICpjckcnKlT7SFn3P5kYnC0m3lZ0lOjb6SrpNZLul/TItD7j7X1tZqRsTDfRGeY2Y+FO198A7rX9UUk30j0CuXtWuwllczTk4vn5na4AktZ2uq4PpYFrpl+/HPhKX6OjhPLJY1ctTHm5w195dN5d2JTtveU2Z+smOsXXlCuSjq77/sLajBfb6fqmC9r4IPDPkn4BeClwa9+bZqRs0Cbu6Dw1QG3GO4G7bf+epB8APiHpJtsbfnZrQtmYge/olOx03cu0JrjtByXtBFaAUxs1mtl3gwb8hIzzO10lvYRup+uhC17zZeCtAJK+B9gJfG1WoxkpG2PD2ckwY9FGO10l/RZw1PYh4H3An0j6JbpL2vdMy+NtKKFsTHf6Hu4EebGdrrZ/c93XTwA3b6bNhLJBtd/RSSgbs8kloblIKJsz7Ol7DAllg7JHJ6rSzb6zxTYqku0QUaWcvqMqmX1HlTL7jqrY4lxCGbXJ6TuqsgjXlL3juKQDkk5JemwrOhTjq70MXsnFxd1MH9KMxbe2TllzKEuqQxyRtHv8rsRWyTplVMWGcwM95DuWwUIpaR+wD2AnVw3VbIyg9onOYKGcbr3cD3CNXjnzcfeYn9z7jiq58lCWLAndAzwIvFbSSUl7x+9WjGky/dzzvmNeSmbfd25FR2Jr2A1dU8aiEKutzL5jcdR+TZlQNmYR7n0nlK1xd11Zs4SyQbnNGFVxJjpRo5y+ozqZfUdV7IQyKpQloahOrimjKkZMMvuO2lQ+UOaD+JszneiUHCX6yuBNX/MTkp6Q9Likv+xrMyNliwYaKkvK4Em6AXg/cLPtM5K+ta/djJQNGnCkPF8Gz/YLwFoZvPV+FviI7TPde3vD+jlrmh8pF6Vc3/87cVl/bWAy2dIyeN8NIOnf6MqafND2P8160+ZD2RwD5euUQ5TBuwK4AbiFriLZEUnfa/vrG/1BTt8NssuOAiVl8E4Ch2yftf1fwJN0Id1QQtkiFx79Ssrg/T3dKImkFbrT+RdnNZrTd3PKl3v6FJbBOwz8kKQngFXgV2yfntVuQtmiAVfPC8rgGXjv9CiSULbG4PLZ91wklE1KKKM2ld/8TihblFBGVTa3eD4XCWWD8pBv1Cez76iNMlJGVcpvIc5NQtkcZaITFcpIGdWZzLsDsyWUrVmAdcqSD+LfJen+dbvR7tqKjsV45LJjXkpGynPA+2x/QdLVwMOSPr1+x1osmMqvKXtHSttftf2F6dfPAsfpNgxFjGJT15TTwqGvBz57kd+lDN6CWJrFc0kvA/4W+EXb/3vh71MGb0GY5bjNKGkHXSD/wvbfjdulGF3lQ0ZvKCUJ+Bhw3PaHx+9SjK3203fJFtubgZ8E3iLp0elx+8j9ijENt8V2FCW1GT9D7Zs6YnMqHylzR6cx814YL5FQtmgZZt+xXDJSRn0SyqhKrimjSgll1EaVP+Sbz6eM6mSkbFFO31GVTHSiSgllVCehjJqIzL6jNoU7GUuvO0tqM05f92OSLKm3Lk9C2aKBnqdcV5vxHcCNwJ2SbrzI664G7uIie7suJqFs0XAP+ZbUZgT4beBDwHMljSaUDdrE6XtF0tF1x74LmrpYbcYXbb+W9AZgl+1/LO1fJjotKp99X1ZtRknbgA8D79nM3yWUrfGgs+++2oxXAzcBD3T7D/k24JCkO2yvr477Iglli4Zbpzxfm5EujO8E3nX+bexngJW17yU9APzyrEBCrimbNNSSkO1zwFptxuPAvWu1GSXdcan9y0jZoi2szXjBz28paTOhbE0+8zxqI/KUUFQooYz6JJRRnYQyqpInz6NKCWXUpvaHfBPKBuX0HXXJ4nlUKaGMmizFHR1JO4EjwJXT1x+0/YGxOxbj0aTuVJaMlM8Db7H9jWnpks9I+pTth0buW4xhGa4pbRv4xvTbHdOj8v+smKX203fRQ76Stkt6FDgFfNp20VbJqFTlJUuKQml71fbr6PZgvFHSTRe+RtK+tV1vZ3l+6H7GgGovrbyp7RC2vw7cD9x2kd/tt73H9p4dXDlU/2IMiz5SSrpW0iumX38L8Dbg38fuWIxkupux5JiXktn3dcDHpx/RsY1uc9A/jNutGMtSrFPaPkZX4zuWhetOZe7oNGjhR8pYMsuweB7LJ89TRnUSyqiLyUQn6pOJTtQnoYyaLMXieSwZeyke8o1lU3cmE8oW5fQddTGQ03dUp+5M5jPPW7SVZfAkvVfSE5KOSfoXSd/R12ZC2SBNXHT0tlNWBu8RYI/t7wMOAr/T125C2ZrSrRADlcGzfb/tb06/fYhun9dMuaZsTLd4XnxRuSJpfc2b/bb3r/v+YmXw3jSjvb3Ap/reNKFsUflTQpdVBm89Se8G9gBv7nttQtmgTYyUffrK4HXvJ90K/DrwZtu9+69zTdmaYa8pz5fBk/QSujJ4h9a/QNLrgT8G7rB9qqTRjJTNGe7et+1zktbK4G0HDqyVwQOO2j4E/C7wMuBvpkVDv2x7Zom8hLJFAz7k21cGz/atm20zoWzNsKWVR5FQtijbIaI6dWcyoWyRJnWfvxPK1pjNLJ7PRULZGOEhF89HkVC2KKGM6iSUUZVcU0aNMvuOyjin76hMPuAqqlT32bv8ecppgadHJOVD+Bec7KJjXjYzUt4FHAeuGakvsVUqP32XlsG7Hvhh4E/H7U6MzobVSdkxJ6Uj5R8AvwpcvdELJO0D9gHs5KrL71mMZ9FHSkk/Apyy/fCs16UM3gKxy445KRkpbwbukHQ7sBO4RtKf2373uF2LUSzAB1z1jpS232/7etu76Xar/WsCucgMnpQdc5J1ytaYuU5iSmwqlLYfAB4YpSexdSqf6GSkbFFCGXXJAxlRGwN5dC2qk5Ey6uLlmn3HEjB4jmuQJRLKFlV+RyehbFGuKaMqdmbfUaGMlFEX49XVeXdipoSyNQvw6FpC2aLKl4RSHaIxBjxx0VGioDbjlZL+evr7z0ra3ddmQtkaD/eQb2Ftxr3AGdvfBfw+8KG+dhPKBnl1tego0Fubcfr9x6dfHwTeqmntko2Mck35LGeeus8HvzRwsyvAUwO3Oaax+ttbmniWZzlz+D4fXCl8+c4BajOef8207s4zwKuY8b/NKKG0fe3QbUo6OlSdwK1Qa39t3zbvPvTJ6TsuR0ltxvOvkXQF8HLg9KxGE8q4HL21Gaff//T06x+n2w07c2q/SOuU+/tfUpVF6++mFdZm/BjwCUkngKfpgjuTekIbseVy+o7qJJRRnYUIZd+trJpIOiDplKTH5t2XRVV9KAtvZdXkbqD6tcCaVR9Kym5lVcP2EbpZZlyiRQjlxW5lvXpOfYktsAihjMYsQihLbmXFElmEUJbcyoolUn0obZ8D1m5lHQfutf34fHu1MUn3AA8Cr5V0UtLeefdp0eQ2Y1Sn+pEy2pNQRnUSyqhOQhnVSSijOgllVCehjOr8H8LM+OD5m1aAAAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 432x288 with 2 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment