diff options
Diffstat (limited to 'transformer_shortest_paths.ipynb')
| -rw-r--r-- | transformer_shortest_paths.ipynb | 2303 |
1 files changed, 463 insertions, 1840 deletions
diff --git a/transformer_shortest_paths.ipynb b/transformer_shortest_paths.ipynb index 25fd2a7..1c45fe6 100644 --- a/transformer_shortest_paths.ipynb +++ b/transformer_shortest_paths.ipynb @@ -76,7 +76,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 158, "execution_state": "idle", "metadata": {}, "outputs": [], @@ -151,10 +151,12 @@ " break\n", " elif target == \"onpath\":\n", " path = SSSP(adj_list, 2, False)\n", - " if len(path) < 1:\n", + " dist = len(path) - 1\n", + " # Filter out some short distance graphs\n", + " if dist < 1 or (not large and dist < 4 and 3 * random.random() > 1 / (4 - dist)):\n", " continue\n", - " dist = random.randrange(1, len(path))\n", - " if largetarget or path[dist] <= MAX_TUNE_VTXS:\n", + " dist = random.choices(range(1, len(path)), weights=range(1, len(path)))[0]\n", + " if (largetarget or path[dist] <= MAX_TUNE_VTXS):\n", " edge_list[-1] = path[dist]\n", " break\n", " elif target == \"any\":\n", @@ -200,52 +202,13 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 48, "execution_state": "idle", "metadata": {}, "outputs": [ { "data": { - "text/plain": [ - "(tensor([[ 5, 11, 9, 10, 3, 4, 6, 13, 3, 9, 9, 13, 1, 10, 6, 8, 1, 2,\n", - " 6, 13, 4, 5, 1, 4, 2, 10, 0, 0, 0, 0, 2],\n", - " [ 4, 10, 1, 10, 2, 7, 6, 9, 4, 5, 4, 6, 5, 7, 3, 5, 0, 0,\n", - " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2],\n", - " [ 9, 10, 3, 7, 1, 3, 5, 6, 13, 14, 1, 15, 4, 6, 4, 11, 2, 11,\n", - " 6, 13, 9, 15, 7, 14, 10, 12, 3, 15, 0, 0, 2]]),\n", - " tensor([1., 5., 8.]),\n", - " tensor([[False, False, False, False, False, False, False, False, False, False,\n", - " False, False, False, False, False, False, False, False, False, False,\n", - " False, False, False, False, False, False, True, True, True, True,\n", - " False],\n", - " [False, False, False, False, False, False, False, False, False, False,\n", - " False, False, False, False, False, False, True, True, True, True,\n", - " True, True, True, True, True, True, True, True, True, True,\n", - " False],\n", - " [False, False, False, False, False, False, False, False, False, False,\n", - " False, False, False, False, False, False, False, False, False, False,\n", - " False, False, False, False, False, False, False, False, True, True,\n", - " False]]))" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "mkbatch(3)" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "execution_state": "idle", - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "<Figure size 640x480 with 1 Axes>" ] @@ -259,29 +222,20 @@ "plt.bar(range(len(bins)), bins)\n", "plt.xlabel(\"Label\")\n", "plt.ylabel(\"Count\")\n", + "plt.title(\"Pre-train Data Distribution\")\n", "with open(\"plots/train-dist.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 136, "execution_state": "idle", "metadata": {}, "outputs": [ { "data": { - "text/plain": [ - "Text(0, 0.5, 'Count')" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "<Figure size 640x480 with 1 Axes>" ] @@ -294,28 +248,21 @@ "bins = torch.bincount(mkbatch(2**15, large=False, target=\"onpath\")[1].to(torch.uint8).cpu())\n", "plt.bar(range(len(bins)), bins)\n", "plt.xlabel(\"Label\")\n", - "plt.ylabel(\"Count\")" + "plt.ylabel(\"Count\")\n", + "plt.title(\"Fine-tune Data Distribution\")\n", + "with open(\"plots/tune-dist.html\", \"w\") as f:\n", + " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 152, "execution_state": "idle", "metadata": {}, "outputs": [ { "data": { - "text/plain": [ - "Text(0, 0.5, 'Count')" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "<Figure size 640x480 with 1 Axes>" ] @@ -328,7 +275,10 @@ "bins = torch.bincount(mkbatch(2**15, large=True, target=\"onpath\", largetarget=False)[1].to(torch.uint8).cpu())\n", "plt.bar(range(len(bins)), bins)\n", "plt.xlabel(\"Label\")\n", - "plt.ylabel(\"Count\")" + "plt.ylabel(\"Count\")\n", + "plt.title(\"Test Data Distribution\")\n", + "with open(\"plots/test-dist.html\", \"w\") as f:\n", + " mpld3.save_html(plt.gcf(), f)" ] }, { @@ -342,7 +292,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 138, "execution_state": "idle", "metadata": { "id": "tLOWhg_CeWzH" @@ -379,7 +329,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 139, "execution_state": "idle", "metadata": { "colab": { @@ -393,7 +343,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Training data: 209715K\n", + "Training data: 314572K\n", "Trainable parameters in the model: 550433\n" ] } @@ -402,7 +352,7 @@ "# PARAMS\n", "VOCAB_SIZE = 1 + MAX_VTXS + 1 # pad plus max number of vertices plus target token\n", "MODEL_DIM = 64 # Dimension of model (embedding and transformer)\n", - "NEPOCHS = 200\n", + "NEPOCHS = 300\n", "BSZ = 2**15 # Batch size\n", "NHEADS = 2\n", "NLAYERS = 11\n", @@ -430,7 +380,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 140, "execution_state": "idle", "metadata": {}, "outputs": [], @@ -442,7 +392,7 @@ "# model = torch.compile(model)\n", "# model.load_state_dict(torch.load('model.pth', weights_only=True))\n", "\n", - "LR = 5e-4\n", + "LR = 1e-4\n", "\n", "criterion = nn.MSELoss()\n", "optimizer = torch.optim.Adam(model.parameters(), lr=LR)" @@ -459,49 +409,31 @@ }, { "cell_type": "code", - "execution_count": null, - "execution_state": "running", + "execution_count": 32, + "execution_state": "idle", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 486 }, "id": "pvTfzGmCeXU4", - "outputId": "0d3a20f3-23be-4c19-9eb6-46bfe11a48b1" + "outputId": "0d3a20f3-23be-4c19-9eb6-46bfe11a48b1", + "scrolled": true }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "/home/sipb/.venv/lib64/python3.12/site-packages/torch/nn/functional.py:6278: UserWarning: Memory Efficient attention on Navi31 GPU is still experimental. Enable it with TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1. (Triggered internally at ../aten/src/ATen/native/transformers/hip/sdp_utils.cpp:269.)\n", - " attn_output = scaled_dot_product_attention(\n", - "/tmp/torchinductor_sipb/lc/clcqc3ufbzrethiy77dmsu54kurxdmh4eji2f3msm347rhmfpf4j.py:1078: UserWarning: Attempting to use hipBLASLt on an unsupported architecture! Overriding blas backend to hipblas (Triggered internally at ../aten/src/ATen/Context.cpp:296.)\n", - " extern_kernels.mm(reinterpret_tensor(buf1, (524288, 64), (64, 1), 0), reinterpret_tensor(primals_5, (64, 192), (1, 64), 0), out=buf2)\n", "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:41<00:00, 1.31s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 0/200 \t Train Err: 29.90892779827118 11.204990872880444 6.002899471088313 2.7772275000461377 119.98257398605347\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 1/200 \t Train Err: 24.833097636699677 7.996231320299557 10.17519548535347 4.934848785400391 95.85787630081177\n" + "Epoch 200/300 \t Train Err: 0.009700538314064033 0.0010365489144987805 0.0014181289396901775 0.0025550971085976926 0.0037460410569565283\n" ] }, { @@ -516,7 +448,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 2/200 \t Train Err: 20.868117928504944 0.06162079039495438 9.863971814513206 5.750443048775196 84.68168807029724\n" + "Epoch 201/300 \t Train Err: 0.006831652077380568 7.503824454602182e-05 9.871918865655971e-05 0.0007692588069403428 0.004252040160537263\n" ] }, { @@ -531,7 +463,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 3/200 \t Train Err: 16.48520603775978 0.03265308297704905 2.906232228502631 4.825529254972935 70.63315153121948\n" + "Epoch 202/300 \t Train Err: 0.006540725109516643 2.3946865439938847e-05 4.20242082554978e-05 0.000602365005761385 0.002779622270679738\n" ] }, { @@ -546,22 +478,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 4/200 \t Train Err: 12.373839050531387 0.012339260501903482 1.0458019012585282 5.470552921295166 52.21906542778015\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 5/200 \t Train Err: 9.265015065670013 0.020387541531817988 0.6235579419881105 4.304356303066015 38.14229780435562\n" + "Epoch 203/300 \t Train Err: 0.006822258495958522 3.6414980883137105e-05 6.143140507219869e-05 0.0006219874312591855 0.003169983861084802\n" ] }, { @@ -569,14 +486,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 6/200 \t Train Err: 6.847102478146553 0.00765054406656418 0.34211935847997665 3.4029701724648476 27.37058013677597\n" + "Epoch 204/300 \t Train Err: 0.006038466963218525 2.4559519403055674e-05 3.5345615970072686e-05 0.0005455858222376264 0.0026163237602645495\n" ] }, { @@ -584,14 +501,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 7/200 \t Train Err: 5.120877355337143 0.006255884032725589 0.24545069271698594 2.8054168857634068 19.56860715150833\n" + "Epoch 205/300 \t Train Err: 0.006186740662087686 3.194489249835897e-05 4.294817205163781e-05 0.0005785539024145692 0.0024907126505127053\n" ] }, { @@ -606,7 +523,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 8/200 \t Train Err: 3.8786706030368805 0.01005001129124139 0.19835278647951782 2.2635713517665863 14.35572400689125\n" + "Epoch 206/300 \t Train Err: 0.005865870829438791 3.5813305146348284e-05 4.379174754376436e-05 0.0005817442843181198 0.0024162692638469707\n" ] }, { @@ -614,29 +531,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 9/200 \t Train Err: 3.386067658662796 0.06476508973355521 0.3309611896984279 2.269792005419731 11.835063099861145\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.07it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 10/200 \t Train Err: 2.6640610471367836 0.019311404510517605 0.15212045633234084 1.7280069142580032 9.439383015036583\n" + "Epoch 207/300 \t Train Err: 0.005545882100705057 3.600231397626885e-05 4.1314136637993215e-05 0.000594669256315683 0.0013424500369580983\n" ] }, { @@ -651,7 +553,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 11/200 \t Train Err: 2.271987594664097 0.004357099162007216 0.09561244037467986 1.4371714778244495 8.072030693292618\n" + "Epoch 208/300 \t Train Err: 0.005720494489651173 3.859014077534084e-05 4.535487767043378e-05 0.0006117928719504562 0.0023836229374580853\n" ] }, { @@ -666,7 +568,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 12/200 \t Train Err: 2.110176682472229 0.0037538947944995016 0.0762243423378095 1.3135331608355045 7.434565886855125\n" + "Epoch 209/300 \t Train Err: 0.0055108592205215245 4.586832275776942e-05 4.0804587058573816e-05 0.0005661740378855029 0.0030462031715501325\n" ] }, { @@ -681,7 +583,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 13/200 \t Train Err: 1.935215126723051 0.0025575611580279656 0.06788019218947738 1.1661983076483011 6.806286051869392\n" + "Epoch 210/300 \t Train Err: 0.005376759043429047 3.36051924136882e-05 2.9235137617433793e-05 0.0005097897928862949 0.002858400079929879\n" ] }, { @@ -689,14 +591,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 14/200 \t Train Err: 1.8060001619160175 0.0021859380358364433 0.05315158853773028 1.051108269020915 6.399133637547493\n" + "Epoch 211/300 \t Train Err: 0.005853716938872822 2.940421961739048e-05 3.749220735471681e-05 0.0004930990489810938 0.003736929087807539\n" ] }, { @@ -704,14 +606,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.07it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 15/200 \t Train Err: 1.7425284087657928 0.003451302447501803 0.042916826030705124 0.9607762675732374 6.2206505835056305\n" + "Epoch 212/300 \t Train Err: 0.005851926427567378 4.79271157871608e-05 6.914466911212003e-05 0.0006478189106928767 0.0024831123845956427\n" ] }, { @@ -726,7 +628,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 16/200 \t Train Err: 1.649382572621107 0.0032472783022967633 0.039788190391846 0.9184560999274254 5.846587151288986\n" + "Epoch 213/300 \t Train Err: 0.006799800234148279 5.7865587223204784e-05 9.293013340538891e-05 0.0007397326644422719 0.0039469943152141695\n" ] }, { @@ -741,7 +643,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 17/200 \t Train Err: 1.6013295575976372 0.0026137664608540945 0.03258192975772545 0.8397737592458725 5.709988132119179\n" + "Epoch 214/300 \t Train Err: 0.005759138788562268 3.775120410409727e-05 5.748265243710193e-05 0.0006046978646736534 0.004287633692598547\n" ] }, { @@ -756,7 +658,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 18/200 \t Train Err: 1.5462302453815937 0.002207836727393442 0.028909130429383367 0.7771711964160204 5.481079399585724\n" + "Epoch 215/300 \t Train Err: 0.005322410768712871 4.7106011834330275e-05 6.199689340746772e-05 0.0004951892847202544 0.001372809862331792\n" ] }, { @@ -764,14 +666,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 19/200 \t Train Err: 1.4744272604584694 0.002453724335282459 0.027229167113546282 0.7396254185587168 5.192027851939201\n" + "Epoch 216/300 \t Train Err: 0.00555990070279222 4.190891476696379e-05 5.821139978934298e-05 0.0005380580719247519 0.0035210271687731165\n" ] }, { @@ -786,7 +688,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 20/200 \t Train Err: 1.405750896781683 0.0035180113754904596 0.025897870946209878 0.7007174119353294 4.946545287966728\n" + "Epoch 217/300 \t Train Err: 0.004976086333044805 7.500407750171689e-05 7.286436925824091e-05 0.0004962704629178916 0.0015869929502514424\n" ] }, { @@ -801,7 +703,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 21/200 \t Train Err: 1.37083425745368 0.005473145276482683 0.026675976172555238 0.6762280324473977 4.781045973300934\n" + "Epoch 218/300 \t Train Err: 0.005077980022178963 4.628878488688315e-05 6.263833648745276e-05 0.0005214507327764295 0.0021321314072508812\n" ] }, { @@ -809,14 +711,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 22/200 \t Train Err: 1.3181258291006088 0.003216923019863316 0.02211966845788993 0.6302088163793087 4.611788898706436\n" + "Epoch 219/300 \t Train Err: 0.0049016569028026424 3.899440955024147e-05 3.9328363271806666e-05 0.0005199085585445573 0.0025905770780241255\n" ] }, { @@ -831,7 +733,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 23/200 \t Train Err: 1.270566176623106 0.0022422261081374018 0.019996988266939297 0.5934071252122521 4.4385934472084045\n" + "Epoch 220/300 \t Train Err: 0.005104515570565127 3.7041234861590056e-05 4.9192609594683745e-05 0.000491508646064176 0.002698791566103864\n" ] }, { @@ -839,14 +741,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 24/200 \t Train Err: 1.1932538747787476 0.004239499055984197 0.020018045412143692 0.552213310264051 4.133698016405106\n" + "Epoch 221/300 \t Train Err: 0.0053775256528751925 8.40174562881657e-05 8.321028616364856e-05 0.0006354096440190915 0.002188114008376374\n" ] }, { @@ -861,7 +763,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 25/200 \t Train Err: 1.173534195870161 0.00575368078352767 0.02177350874990225 0.5586085859686136 4.002377942204475\n" + "Epoch 222/300 \t Train Err: 0.005235390446614474 6.318601433008553e-05 0.00011316225950963599 0.0005508687736437423 0.003185757487855767\n" ] }, { @@ -876,22 +778,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 26/200 \t Train Err: 1.0854019112884998 0.003320175252156332 0.01748313583084382 0.5035764751955867 3.7186833322048187\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 27/200 \t Train Err: 1.0489223580807447 0.002155393432985875 0.014516596915200353 0.47800380270928144 3.589349642395973\n" + "Epoch 223/300 \t Train Err: 0.005300909557263367 7.39117677142076e-05 0.00011925572943027873 0.0005487319253916212 0.002978381860572199\n" ] }, { @@ -906,7 +793,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 28/200 \t Train Err: 1.0285752080380917 0.003717334211614798 0.01597064675297588 0.4826665371656418 3.4730969667434692\n" + "Epoch 224/300 \t Train Err: 0.004497841160628013 5.9339764732158073e-05 6.96952459975364e-05 0.0005027879551562364 0.001782914390517476\n" ] }, { @@ -921,7 +808,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 29/200 \t Train Err: 0.9720142241567373 0.004084829584826366 0.014119503815891221 0.43038015346974134 3.3248252645134926\n" + "Epoch 225/300 \t Train Err: 0.004688454842835199 7.675816877394936e-05 0.00010453435777435516 0.0005171399702703638 0.0028854877792241496\n" ] }, { @@ -929,14 +816,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 30/200 \t Train Err: 0.9608706310391426 0.002451939526508795 0.011319156386889517 0.4139528265222907 3.2747417390346527\n" + "Epoch 226/300 \t Train Err: 0.004642922693165019 7.117038816772947e-05 6.250007260177881e-05 0.00053063289669808 0.00242330242127764\n" ] }, { @@ -951,7 +838,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 31/200 \t Train Err: 0.9179007802158594 0.002311610933247721 0.01079355452384334 0.3930521896108985 3.1119269728660583\n" + "Epoch 227/300 \t Train Err: 0.004380291829875205 4.348535961185007e-05 6.43278998779806e-05 0.00042627666130101716 0.0024958747199974596\n" ] }, { @@ -966,22 +853,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 32/200 \t Train Err: 0.8977434728294611 0.0021589329044218175 0.00950733212812338 0.3691776511259377 3.040615402162075\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 33/200 \t Train Err: 0.881706677377224 0.0020159517880529165 0.009437998596695252 0.35962088825181127 2.982758790254593\n" + "Epoch 228/300 \t Train Err: 0.004652515672205482 4.8108470394936376e-05 6.366262556412039e-05 0.00046550729939554003 0.002803799277046437\n" ] }, { @@ -996,7 +868,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 34/200 \t Train Err: 0.8403967656195164 0.001898838694614824 0.00869621682795696 0.3381345858797431 2.8688452169299126\n" + "Epoch 229/300 \t Train Err: 0.004113680275622755 3.100523605326089e-05 4.310856323286316e-05 0.0004433248200257367 0.0022460650430957685\n" ] }, { @@ -1011,22 +883,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 35/200 \t Train Err: 0.8310248833149672 0.0013434199390758295 0.007526626766775735 0.32297050580382347 2.818771593272686\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 36/200 \t Train Err: 0.8045722767710686 0.0018811499339790316 0.0069304521166486666 0.30397533625364304 2.722321219742298\n" + "Epoch 230/300 \t Train Err: 0.004635281045921147 4.207487796747955e-05 6.043314004955391e-05 0.0005022242676204769 0.0024831719019289267\n" ] }, { @@ -1041,22 +898,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 37/200 \t Train Err: 0.807910643517971 0.0022051451851439197 0.007862750302592758 0.30017248587682843 2.739243097603321\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:29<00:00, 1.07it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 38/200 \t Train Err: 0.7853260803967714 0.005179399433473009 0.008613282887381501 0.2864332143217325 2.6513936147093773\n" + "Epoch 231/300 \t Train Err: 0.005110396894451696 0.0001983720651708154 0.0002375991614940176 0.0008774314223956026 0.002636964950681886\n" ] }, { @@ -1071,7 +913,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 39/200 \t Train Err: 0.7792632356286049 0.004665168027713662 0.009170589764835313 0.277913779951632 2.6232368499040604\n" + "Epoch 232/300 \t Train Err: 0.0049849917777464725 0.0001501558316192586 0.00024557938434099924 0.0007316948017432878 0.0021723491789202853\n" ] }, { @@ -1086,22 +928,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 40/200 \t Train Err: 0.7583489026874304 0.00292711379006505 0.007873743350501172 0.27461743634194136 2.522021509706974\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 41/200 \t Train Err: 0.7282119914889336 0.0017558942890900653 0.006133111986855511 0.23886349285021424 2.4373623058199883\n" + "Epoch 233/300 \t Train Err: 0.004696133633842692 0.00010220188283938114 0.00014721588598831659 0.0006821819579272415 0.0023902068645895724\n" ] }, { @@ -1116,37 +943,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 42/200 \t Train Err: 0.7180026862770319 0.0023761796346661868 0.006810532162489835 0.23614320810884237 2.375364724546671\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 43/200 \t Train Err: 0.7019325699657202 0.005046901515015634 0.008944688888732344 0.22622147155925632 2.30900501832366\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 44/200 \t Train Err: 0.6817822623997927 0.0017093055594159523 0.005646904020977672 0.21380048524588346 2.223499771207571\n" + "Epoch 234/300 \t Train Err: 0.004084704407432582 5.2511502758534334e-05 6.844933011507237e-05 0.00047021749242048827 0.002734669448628324\n" ] }, { @@ -1161,7 +958,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 45/200 \t Train Err: 0.6641208492219448 0.0038460963405668736 0.0067629652403411455 0.21014394168742 2.1612670943140984\n" + "Epoch 235/300 \t Train Err: 0.003639004957221914 5.903515790350866e-05 8.000035580835174e-05 0.0003796246064666775 0.001738929542312917\n" ] }, { @@ -1176,7 +973,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 46/200 \t Train Err: 0.6523595433682203 0.0018703954374359455 0.006019242704496719 0.20436032535508275 2.1252111680805683\n" + "Epoch 236/300 \t Train Err: 0.003710617238539271 2.977514947133386e-05 3.8898698477396465e-05 0.0003604722842283081 0.0009449759105422117\n" ] }, { @@ -1191,7 +988,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 47/200 \t Train Err: 0.617787566035986 0.0030503157668135827 0.0069770159825566225 0.1832384041044861 1.9817177206277847\n" + "Epoch 237/300 \t Train Err: 0.003989764125435613 3.9895228240993674e-05 5.16856140109212e-05 0.00045158102011555457 0.001674787971268188\n" ] }, { @@ -1206,52 +1003,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 48/200 \t Train Err: 0.600332060828805 0.002064528713162872 0.0051435344576020725 0.17475251341238618 1.9067389331758022\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 49/200 \t Train Err: 0.5904311630874872 0.004617106849764241 0.006938040380191524 0.16196146188303828 1.8893518187105656\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 50/200 \t Train Err: 0.5741921290755272 0.004996264638975845 0.007533758063800633 0.15988326235674322 1.8061449080705643\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 51/200 \t Train Err: 0.532125998288393 0.001918236821438768 0.0039053107029758394 0.1349696076940745 1.6755047999322414\n" + "Epoch 238/300 \t Train Err: 0.0052436307014431804 0.00013858247947950986 0.00022083272577333446 0.0008545901869183581 0.00233671873354524\n" ] }, { @@ -1266,37 +1018,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 52/200 \t Train Err: 0.5333235822618008 0.002287628563863109 0.005320303003827576 0.14349294803105295 1.6620671227574348\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 53/200 \t Train Err: 0.4952954547479749 0.0010008449244196527 0.003929206512111705 0.1226266548037529 1.5398627035319805\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 54/200 \t Train Err: 0.490776726976037 0.0021560709155892255 0.004821252721740166 0.12306429445743561 1.5102213434875011\n" + "Epoch 239/300 \t Train Err: 0.004502967931330204 0.00010209598895016825 9.616378500254541e-05 0.00048576207518635783 0.0015566766385006758\n" ] }, { @@ -1311,22 +1033,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 55/200 \t Train Err: 0.4630659334361553 0.002020925041506416 0.0043996189124300145 0.11745399446226656 1.4124069288372993\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 56/200 \t Train Err: 0.4430495109409094 0.0022180716405273415 0.004020084164949367 0.10757899098098278 1.3317870814353228\n" + "Epoch 240/300 \t Train Err: 0.00395154607394943 2.4841689480581408e-05 3.481786328052294e-05 0.0003626737070590025 0.002694538376630362\n" ] }, { @@ -1334,59 +1041,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 57/200 \t Train Err: 0.45779580902308226 0.007255890723172342 0.010569222271442413 0.1332057132385671 1.3446197882294655\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.07it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 58/200 \t Train Err: 0.40347473975270987 0.0013051820133114234 0.0031506957930105273 0.09731322806328535 1.1896578464657068\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 59/200 \t Train Err: 0.3944752989336848 0.0025091177740250714 0.005466303970024455 0.10591710731387138 1.1414270270615816\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 60/200 \t Train Err: 0.3850894244387746 0.0022618337816311396 0.00499681286237319 0.10177210683468729 1.1139366328716278\n" + "Epoch 241/300 \t Train Err: 0.004540074682154227 7.381854948107502e-05 9.893310834740987e-05 0.0005228228733358264 0.0026238594035135065\n" ] }, { @@ -1401,22 +1063,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 61/200 \t Train Err: 0.3536613713949919 0.0016294859724439448 0.003189665607351344 0.09225898724980652 1.0001246724277735\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 62/200 \t Train Err: 0.3431710870936513 0.0014996515783423092 0.0034722756390692666 0.09043321071658283 0.9589487668126822\n" + "Epoch 242/300 \t Train Err: 0.004094215779332444 5.668814941373057e-05 8.304187170438126e-05 0.00044306572590357973 0.002081132290115306\n" ] }, { @@ -1431,22 +1078,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 63/200 \t Train Err: 0.3311467822641134 0.001135409189373604 0.0031531365275441203 0.0849773638183251 0.9113363474607468\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 64/200 \t Train Err: 0.31347283348441124 0.0010190900329689612 0.003212062452803366 0.08056736667640507 0.8582371436059475\n" + "Epoch 243/300 \t Train Err: 0.003913102438673377 4.585197802953189e-05 5.789757997831657e-05 0.0013291612922330387 0.0020740707810062986\n" ] }, { @@ -1461,7 +1093,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 65/200 \t Train Err: 0.2970640519633889 0.0010584184110484784 0.002994029131514253 0.07881279999855906 0.8098555449396372\n" + "Epoch 244/300 \t Train Err: 0.004195565263216849 3.806313242193937e-05 5.340812001008999e-05 0.00041497633492326713 0.002989801170187434\n" ] }, { @@ -1476,7 +1108,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 66/200 \t Train Err: 0.2887888355180621 0.0012073961215719464 0.0033224597755179275 0.0822362134931609 0.7632680460810661\n" + "Epoch 245/300 \t Train Err: 0.004047608803375624 6.732485988436565e-05 9.67713261843528e-05 0.0005451126739899337 0.002438096437799686\n" ] }, { @@ -1491,7 +1123,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 67/200 \t Train Err: 0.27321118395775557 0.0009283916206186404 0.0024455750972265378 0.07351583207491785 0.7209800574928522\n" + "Epoch 246/300 \t Train Err: 0.004089277834282257 6.664293536573496e-05 9.393133385060537e-05 0.0004827346115234832 0.0017539746410619728\n" ] }, { @@ -1506,97 +1138,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 68/200 \t Train Err: 0.2642599456012249 0.0024096847391774645 0.004758599683555076 0.07438989775255322 0.6782895382493734\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 69/200 \t Train Err: 0.24411699920892715 0.0009143148763541831 0.002384097140748054 0.06588289514183998 0.637260627001524\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 70/200 \t Train Err: 0.2355448892340064 0.0011828851866084733 0.00317692070530029 0.07014255912508816 0.5985564198344946\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 71/200 \t Train Err: 0.22664254251867533 0.0011206458884771564 0.002485872115357779 0.06011384085286409 0.5786449136212468\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 72/200 \t Train Err: 0.21451926324516535 0.0008609092228653026 0.002164756482670782 0.0564098390750587 0.5476357256993651\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 73/200 \t Train Err: 0.2044255300424993 0.0010747715696197702 0.00229402982222382 0.05511317937634885 0.5015372652560472\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 74/200 \t Train Err: 0.200456322170794 0.001536047003355634 0.003252933354815468 0.05711311026243493 0.48181435000151396\n" + "Epoch 247/300 \t Train Err: 0.0035380944900680333 9.052370739937032e-05 0.00011764369932620866 0.0006084945985094237 0.0011799170262918324\n" ] }, { @@ -1611,7 +1153,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 75/200 \t Train Err: 0.19111737608909607 0.003518748955684714 0.004175829379164497 0.049318774370476604 0.45180629566311836\n" + "Epoch 248/300 \t Train Err: 0.0035020401555811986 3.0666821288605206e-05 4.465118504981547e-05 0.0003278196218161611 0.0018799946564627135\n" ] }, { @@ -1619,14 +1161,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 76/200 \t Train Err: 0.1808590106666088 0.0013624421417262056 0.002329483479115879 0.04611049557570368 0.4279420841485262\n" + "Epoch 249/300 \t Train Err: 0.004724001191789284 9.285189429419916e-05 0.00012808766365424162 0.0004897935516510188 0.00302792190994694\n" ] }, { @@ -1641,7 +1183,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 77/200 \t Train Err: 0.16973466146737337 0.0008994456393338623 0.00207517536728119 0.04326868336647749 0.3952533109113574\n" + "Epoch 250/300 \t Train Err: 0.004049119248520583 7.58403711529354e-05 9.593046939926353e-05 0.0004770750299485371 0.0026782418092778926\n" ] }, { @@ -1656,67 +1198,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 78/200 \t Train Err: 0.1702535841614008 0.0007078972075760248 0.0016872428823262453 0.04189401387702674 0.3984428942203522\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 79/200 \t Train Err: 0.16377683635801077 0.0013382542465478764 0.0027396336699894164 0.04209184244973585 0.3769973455928266\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 80/200 \t Train Err: 0.1497581924777478 0.0016949967903201468 0.0021530323319893796 0.03568895586067811 0.33177076652646065\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 81/200 \t Train Err: 0.14450395992025733 0.001401656336383894 0.002270640025017201 0.03478072857251391 0.317978051956743\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 82/200 \t Train Err: 0.1389398977626115 0.0033198261371580884 0.00435145793017 0.0375910610309802 0.28218549815937877\n" + "Epoch 251/300 \t Train Err: 0.003661572525743395 4.6462737600450055e-05 5.566726716210724e-05 0.0004296750569210417 0.002789238562314722\n" ] }, { @@ -1724,14 +1206,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 83/200 \t Train Err: 0.12944017979316413 0.0013174645964681986 0.0020839970657107187 0.033180530241224915 0.2718075602315366\n" + "Epoch 252/300 \t Train Err: 0.003436399820202496 4.064976889139871e-05 5.003276532988821e-05 0.00038082731816757587 0.002257287138661468\n" ] }, { @@ -1746,7 +1228,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 84/200 \t Train Err: 0.1269651602488011 0.001952557386175613 0.002797932973408024 0.030586290056817234 0.2562156552448869\n" + "Epoch 253/300 \t Train Err: 0.003201432766218204 3.2443880314758644e-05 3.860860113036324e-05 0.00032383076040787273 0.0012120022082626747\n" ] }, { @@ -1761,7 +1243,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 85/200 \t Train Err: 0.1262973020784557 0.0034579528983158525 0.004187718592220335 0.03295240050647408 0.26100850058719516\n" + "Epoch 254/300 \t Train Err: 0.003311082960863132 4.5200399654277135e-05 6.019428829517892e-05 0.00033768308026083105 0.0017057321817901538\n" ] }, { @@ -1776,22 +1258,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 86/200 \t Train Err: 0.11676973546855152 0.002271431191729789 0.0028272587187530007 0.029616059619002044 0.22773186769336462\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 87/200 \t Train Err: 0.11645400826819241 0.003942164817090088 0.004389651330711786 0.02888663241174072 0.22617254313081503\n" + "Epoch 255/300 \t Train Err: 0.003727161471033469 8.389212513293387e-05 0.00011534792562883922 0.00044301021353021497 0.0015780800986391341\n" ] }, { @@ -1806,7 +1273,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 88/200 \t Train Err: 0.1069438960403204 0.0007534859851148212 0.0015284864657587605 0.02535622369032353 0.20643022749572992\n" + "Epoch 256/300 \t Train Err: 0.003738447092473507 8.379092363952623e-05 0.00011557144276252984 0.00045860962654842297 0.002139192058905337\n" ] }, { @@ -1821,7 +1288,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 89/200 \t Train Err: 0.1019233949482441 0.0009516884665572434 0.001511421851319028 0.024724961316678673 0.18514555739238858\n" + "Epoch 257/300 \t Train Err: 0.0034996949252672493 7.875290160086479e-05 0.00010191635280420996 0.0010230293487438757 0.0011676927765904566\n" ] }, { @@ -1836,82 +1303,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 90/200 \t Train Err: 0.09508711867965758 0.0008840842388053716 0.0013085861846775515 0.022952270082896575 0.17402319004759192\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 91/200 \t Train Err: 0.09273395943455398 0.0008308457795465074 0.0014873276431899285 0.020763451553648338 0.1700441548600793\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 92/200 \t Train Err: 0.08730011875741184 0.000720000532510312 0.0011607171036303043 0.020305267593357712 0.15585350175388157\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 93/200 \t Train Err: 0.08319679484702647 0.0007787930949234578 0.0012370077938612667 0.018640907626831904 0.14242116385139525\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 94/200 \t Train Err: 0.08445112314075232 0.002024608746069134 0.0023303976749957656 0.0193185547250323 0.14395680534653366\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 95/200 \t Train Err: 0.0859984909184277 0.001967401332422014 0.002160638517125335 0.02076483884593472 0.14143188181333244\n" + "Epoch 258/300 \t Train Err: 0.0036751833540620282 4.3053820434124646e-05 5.797953258479538e-05 0.00033043701182577934 0.0026015445665450443\n" ] }, { @@ -1926,37 +1318,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 96/200 \t Train Err: 0.07500915951095521 0.0011493155893731455 0.0014125802363196271 0.019469743536319584 0.12187899858690798\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 97/200 \t Train Err: 0.07068800239358097 0.0006672579925179889 0.0009655766079958994 0.01619866766850464 0.11232927581295371\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 98/200 \t Train Err: 0.06899663107469678 0.0029092533500261197 0.002759141156275291 0.01706777891376987 0.10129301541019231\n" + "Epoch 259/300 \t Train Err: 0.0030066172403167 2.8544642134420428e-05 3.4369389794619565e-05 0.00030651216297883366 0.0010866159546480958\n" ] }, { @@ -1971,22 +1333,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 99/200 \t Train Err: 0.06587723165284842 0.0010087788145938248 0.0015239717367876437 0.015540250373305753 0.10049017099663615\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 100/200 \t Train Err: 0.06758000492118299 0.0019963337617809884 0.0021085088956169784 0.018880482559325173 0.10054084449075162\n" + "Epoch 260/300 \t Train Err: 0.003899131465004757 9.39390017435926e-05 0.00010894855989818097 0.000464337135781534 0.0015993566187972874\n" ] }, { @@ -2001,7 +1348,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 101/200 \t Train Err: 0.06307036883663386 0.0012753937157867767 0.0016400622589571867 0.015593403164530173 0.09352678328286856\n" + "Epoch 261/300 \t Train Err: 0.0027930525757255964 7.185203750736946e-05 9.880084232349873e-05 0.0003542822555573366 0.0008163415011068764\n" ] }, { @@ -2009,104 +1356,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 102/200 \t Train Err: 0.060316542629152536 0.0006818027850385988 0.0010231798241875367 0.013433107393211685 0.09090642654336989\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 103/200 \t Train Err: 0.060421090107411146 0.0027040049144488876 0.0027294684268781566 0.01441186985175591 0.0847808476537466\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 104/200 \t Train Err: 0.05678413005080074 0.001134833364176302 0.001431436577149725 0.012649833428440616 0.0780830224393867\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 105/200 \t Train Err: 0.05805800168309361 0.003231210850572097 0.003441706239755149 0.015121193689992651 0.0752038118080236\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 106/200 \t Train Err: 0.0547659246949479 0.002454680496839501 0.002737534454809065 0.013384125923039392 0.07274198567029089\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 107/200 \t Train Err: 0.04927568801213056 0.0005825197017657047 0.0007837470261620183 0.010716092379880138 0.05965513514820486\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 108/200 \t Train Err: 0.05318018130492419 0.0013841798254361493 0.0015562751477773418 0.01211979822255671 0.07018060437985696\n" + "Epoch 262/300 \t Train Err: 0.003117560874670744 0.00010307476776461044 0.00012391211180329265 0.00041415533542021876 0.0014386503646477422\n" ] }, { @@ -2121,67 +1378,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 109/200 \t Train Err: 0.051697830320335925 0.0010280100987074547 0.001098815353543614 0.010801961965626106 0.06942529141088016\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 110/200 \t Train Err: 0.04692836094181985 0.0008446434776487877 0.0008702427021489711 0.01032250898424536 0.05933116714004427\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 111/200 \t Train Err: 0.044668186688795686 0.0011062668152135302 0.0010394338919468282 0.009862772989436053 0.054550442087929696\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 112/200 \t Train Err: 0.0447915755212307 0.0014217505979559064 0.0016150277879205532 0.010183335049077868 0.05510500964010134\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 113/200 \t Train Err: 0.043250435031950474 0.002363460382412086 0.002828258522640681 0.00971244159154594 0.047139356975094415\n" + "Epoch 263/300 \t Train Err: 0.003268079031840898 9.003786195194152e-05 8.649396028204137e-05 0.0004168724274222768 0.00150578541718005\n" ] }, { @@ -2196,22 +1393,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 114/200 \t Train Err: 0.045086685102432966 0.0011699077874709474 0.0013979203313283506 0.010937912025838159 0.0543683817377314\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 115/200 \t Train Err: 0.0411334311356768 0.0013191173275117762 0.0011784266635004315 0.00858650918235071 0.04524634237168357\n" + "Epoch 264/300 \t Train Err: 0.0026079017552547157 2.246009304940344e-05 3.15551765197597e-05 0.0002907984498961014 0.0007710294869553991\n" ] }, { @@ -2226,7 +1408,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 116/200 \t Train Err: 0.039555212075356394 0.0005507277148808498 0.0005802504801977193 0.007789377530571073 0.04690207863677642\n" + "Epoch 265/300 \t Train Err: 0.0028374393659760244 2.585551322908941e-05 2.7533280416491834e-05 0.00028491684133769013 0.0010678084470185922\n" ] }, { @@ -2241,7 +1423,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 117/200 \t Train Err: 0.03692283679265529 0.00043711723651540524 0.0005214224675000878 0.007687705321586691 0.03813074165373109\n" + "Epoch 266/300 \t Train Err: 0.003345544362673536 4.9037233594617646e-05 6.386032035265998e-05 0.0003377324483153643 0.002303508839716528\n" ] }, { @@ -2249,14 +1431,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 118/200 \t Train Err: 0.03628927277168259 0.00044126920215603604 0.0005619980265691993 0.007773650635499507 0.0384644401492551\n" + "Epoch 267/300 \t Train Err: 0.0028792162775062025 6.944555900645355e-05 9.428040866055198e-05 0.00039187861466416507 0.0007993936363277498\n" ] }, { @@ -2271,7 +1453,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 119/200 \t Train Err: 0.03890394070185721 0.001729899499878229 0.001493205483257043 0.00798933092301013 0.041969388112192973\n" + "Epoch 268/300 \t Train Err: 0.0031112020296859555 4.3891389566397265e-05 4.875301172546642e-05 0.00027064218579653243 0.0017511903075018154\n" ] }, { @@ -2279,14 +1461,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 120/200 \t Train Err: 0.03712784848175943 0.0007071991701650404 0.0008030551111914974 0.007690385325986426 0.04134120314847678\n" + "Epoch 269/300 \t Train Err: 0.0030466990065178834 4.0109083158768044e-05 6.39344424371302e-05 0.0004256982326751313 0.0010282776493681922\n" ] }, { @@ -2301,7 +1483,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 121/200 \t Train Err: 0.03516055888030678 0.0004485433178160747 0.0006193339004312293 0.006722165890096221 0.03440287291596178\n" + "Epoch 270/300 \t Train Err: 0.0038976767973508686 0.00010299110641653897 0.0001073770393702489 0.0004656959667954652 0.001747739342135901\n" ] }, { @@ -2316,22 +1498,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 122/200 \t Train Err: 0.03431048977654427 0.0007996012898274785 0.000579838467274385 0.007459181011654437 0.03256209765095264\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 123/200 \t Train Err: 0.0351686873473227 0.0006591397341253469 0.0006555682361977233 0.006613661207666155 0.037333723666961305\n" + "Epoch 271/300 \t Train Err: 0.004126565829210449 0.00012952255988807337 0.00016465946305288526 0.0004091988171239791 0.002737868909463259\n" ] }, { @@ -2346,37 +1513,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 124/200 \t Train Err: 0.03355215600458905 0.0002945618743979139 0.0004387611575111805 0.006839323941676412 0.034134260716200515\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 125/200 \t Train Err: 0.029283913841936737 0.00046266792719507066 0.00058449966218177 0.0056224113504868 0.024552044065785594\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 126/200 \t Train Err: 0.03119118546601385 0.0005014674925405416 0.0007099974022821698 0.0060376596375135705 0.02815229452244239\n" + "Epoch 272/300 \t Train Err: 0.005586953229794744 0.00011988704233090175 8.92973938562136e-05 0.0008274920874100644 0.005225448500027596\n" ] }, { @@ -2391,67 +1528,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 127/200 \t Train Err: 0.031841877149417996 0.00027776491560871364 0.00046666834350617137 0.005703783383069094 0.03038091241910479\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 128/200 \t Train Err: 0.030603406310547143 0.0006404905841463915 0.0006846741659956024 0.006221181378350593 0.025205713599461887\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 129/200 \t Train Err: 0.029333731392398477 0.0005602014119858723 0.000642365913336107 0.006284213814069517 0.02611703903221496\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 130/200 \t Train Err: 0.028047623636666685 0.0008307177447477443 0.0007543345300291548 0.006256156790186651 0.02223676520952722\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.07it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 131/200 \t Train Err: 0.02852347370935604 0.0005703339811589103 0.0009201887021390576 0.005433428774267668 0.025521833274979144\n" + "Epoch 273/300 \t Train Err: 0.003360286595125217 4.9669066697788367e-05 7.549639843773548e-05 0.00040038250972429523 0.0017126402361498094\n" ] }, { @@ -2459,14 +1536,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 132/200 \t Train Err: 0.028580970887560397 0.0005810092270621681 0.0005398729952048598 0.005319414980476722 0.027794180728960782\n" + "Epoch 274/300 \t Train Err: 0.0037096842715982348 0.00010263273924238092 0.00010759665562432019 0.0004499732262956968 0.002582911283610656\n" ] }, { @@ -2481,22 +1558,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 133/200 \t Train Err: 0.02704069105675444 0.0003059067348658573 0.0003909187862518593 0.0050654686710913666 0.023506886311224662\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 134/200 \t Train Err: 0.024850417801644653 0.00024160909720194468 0.0003672063955946214 0.004596906874212436 0.01910146742920915\n" + "Epoch 275/300 \t Train Err: 0.003157066814310383 4.581558967231558e-05 9.948560264660955e-05 0.0004738382222058135 0.0019836488944235953\n" ] }, { @@ -2511,7 +1573,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 135/200 \t Train Err: 0.024681290611624718 0.00037400397729925317 0.000489667942019878 0.004580263695970643 0.019593202690884937\n" + "Epoch 276/300 \t Train Err: 0.003158892614010256 5.7304253459733445e-05 7.066275753686568e-05 0.0003324287613395427 0.0018403834514018058\n" ] }, { @@ -2519,74 +1581,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 136/200 \t Train Err: 0.027638425526674837 0.0004977623525519448 0.0005427452181265835 0.005582943878835067 0.02646890448522754\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 137/200 \t Train Err: 0.024757418257649988 0.0003685475935526483 0.0003517182428822707 0.004618304148607422 0.018053345412681665\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 138/200 \t Train Err: 0.02439499576576054 0.00027227840394061786 0.00036000374461764295 0.004171678388956934 0.020061984119138287\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 139/200 \t Train Err: 0.0229199705645442 0.00046586399253101263 0.0005068485352239804 0.004258882479916792 0.01709363247573492\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 140/200 \t Train Err: 0.024649846891406924 0.0006087151427891513 0.0007250320297771395 0.004237969173118472 0.022251372053233354\n" + "Epoch 277/300 \t Train Err: 0.002581501808890607 4.861700740832475e-05 6.541747751498406e-05 0.000284652207938052 0.0007380942764569909\n" ] }, { @@ -2601,232 +1603,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 141/200 \t Train Err: 0.023699990182649344 0.0006855616327356984 0.0008273822963928978 0.004291944787837565 0.01694076002422662\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 142/200 \t Train Err: 0.022072256018873304 0.00023243963084951247 0.0003913031405318179 0.0035956969295511954 0.019112591930934286\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 143/200 \t Train Err: 0.023525280528701842 0.00040764258983472246 0.0003686606121391378 0.00405594674157328 0.02093119484015915\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 144/200 \t Train Err: 0.02343721961369738 0.00033207295859938313 0.0005353521628421731 0.004094722855370492 0.020869585259788437\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 145/200 \t Train Err: 0.02064004127169028 0.00022399188014787796 0.0003062049111122178 0.004059467602928635 0.017480447175330482\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 146/200 \t Train Err: 0.020763279171660542 0.0004162326339383071 0.0003410943327253335 0.0032998187525663525 0.01631780587376852\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 147/200 \t Train Err: 0.020571442728396505 0.00044352215627441183 0.0005010924719499599 0.003667172095447313 0.014751498597888713\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 148/200 \t Train Err: 0.01997521542944014 0.00021835572067629982 0.000277048953648773 0.0034534092810645234 0.015434162895644477\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 149/200 \t Train Err: 0.021312509546987712 0.00030864444181588624 0.0005689966556019499 0.004085102085809922 0.01556764474753436\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 150/200 \t Train Err: 0.019479235576000065 0.0003387887146573121 0.000369657065903084 0.003481321306026075 0.01391503391016613\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 151/200 \t Train Err: 0.023493657063227147 0.0003406951947226844 0.0004765782725826284 0.003387280346942134 0.024297427552482986\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 152/200 \t Train Err: 0.020062169001903385 0.0001796720187030587 0.0002183982696806197 0.003409319913771469 0.013818501599416777\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 153/200 \t Train Err: 0.019131189765175804 0.00029574484346994723 0.0002947069822312187 0.002951359812868759 0.01664116706706409\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 154/200 \t Train Err: 0.017693023837637156 0.00024806520877973526 0.0002983832400786923 0.00312236421086709 0.010928787386546901\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.07it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 155/200 \t Train Err: 0.017173090571304783 0.00020240362800905132 0.0002837313263626129 0.0024838966492097825 0.01155280199873232\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 156/200 \t Train Err: 0.018064823234453797 0.00025287491257586225 0.00042023322453133005 0.0031510025983152445 0.013277582744422034\n" + "Epoch 278/300 \t Train Err: 0.0025860080822894815 2.174209052441256e-05 2.662913956896773e-05 0.00022730225418854388 0.0010037773529276706\n" ] }, { @@ -2841,67 +1618,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 157/200 \t Train Err: 0.01679313532076776 0.00016895983264930692 0.00023369373479908973 0.0025660492974566296 0.013730080009736412\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 158/200 \t Train Err: 0.018779858626658097 0.0006825042137279524 0.00039098577053664485 0.0030517936720571015 0.014663536599073268\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 159/200 \t Train Err: 0.020110780431423336 0.000910040460212258 0.000834133242506141 0.004305297403334407 0.013905958928830842\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 160/200 \t Train Err: 0.019773374748183414 0.0009348806023581346 0.0008922487559175352 0.003975474533945089 0.01617197653695257\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 161/200 \t Train Err: 0.017475509172072634 0.00046213520988658274 0.0005404102516877174 0.003040906784008257 0.014273262689584953\n" + "Epoch 279/300 \t Train Err: 0.002347265100979712 3.7067890659159275e-05 5.258349327164069e-05 0.00027653912843561557 0.0008076369083056534\n" ] }, { @@ -2916,22 +1633,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 162/200 \t Train Err: 0.015029630245408043 0.0001904235211895866 0.00021963075801068044 0.002168249424357782 0.010509091553103644\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 163/200 \t Train Err: 0.018164523935411125 0.0005775698982688482 0.0006741533361491747 0.0036203847994329408 0.011193782368536631\n" + "Epoch 280/300 \t Train Err: 0.0020991099227103405 4.95786165544132e-05 7.162138820149266e-05 0.00025381120440215454 0.00021227763140529987\n" ] }, { @@ -2946,7 +1648,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 164/200 \t Train Err: 0.01632957032416016 0.0003306799113715897 0.0003712935063049372 0.0029763625025225338 0.009990961348194105\n" + "Epoch 281/300 \t Train Err: 0.002149274954717839 4.502804105754876e-05 5.465928461489966e-05 0.00020037225408486847 0.0008008158908197061\n" ] }, { @@ -2961,37 +1663,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 165/200 \t Train Err: 0.0153682763047982 0.0002632132137705412 0.0003610171986565547 0.0023970418515091296 0.012086256845577736\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 166/200 \t Train Err: 0.013866374094504863 0.00012185312010615235 0.00018107489950125455 0.0018877797901950544 0.008829483279441774\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 167/200 \t Train Err: 0.015403825411340222 0.00034605842233759176 0.00046738405558244267 0.002471095247528865 0.009661761823792858\n" + "Epoch 282/300 \t Train Err: 0.002332294654479483 5.822195592486423e-05 7.976816402788245e-05 0.00027342953717379714 0.0011204043772465866\n" ] }, { @@ -3006,7 +1678,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 168/200 \t Train Err: 0.015333578106947243 0.0007963078196553397 0.0006389631322463174 0.0029809060470142867 0.009118859635066201\n" + "Epoch 283/300 \t Train Err: 0.002367243367189076 6.421889257524072e-05 7.192823628088263e-05 0.00027969777374892146 0.000926283852436427\n" ] }, { @@ -3014,44 +1686,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 169/200 \t Train Err: 0.01377101321122609 0.00028809423406528367 0.0002655940699014536 0.0022669341324217385 0.0077932964362616985\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 170/200 \t Train Err: 0.014377146551851183 0.0006095316629171066 0.000566291571203692 0.002504439868062036 0.007364666845887768\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 171/200 \t Train Err: 0.01476844641729258 0.0002849637266422178 0.00032093194135995873 0.002440014208332286 0.00954770603743782\n" + "Epoch 284/300 \t Train Err: 0.0024702023074496537 4.001182000479275e-05 5.6243611766149115e-05 0.00028294666503825283 0.001745262754937471\n" ] }, { @@ -3066,52 +1708,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 172/200 \t Train Err: 0.014352218277053908 0.0001346213794590767 0.0002298443192785271 0.0027853190676978556 0.011637392487727993\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 173/200 \t Train Err: 0.013293113705003634 0.0002518077910735883 0.00021664196594883833 0.0016753806212363997 0.008185207087933577\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 174/200 \t Train Err: 0.01469786892994307 0.0005061904257672722 0.0006176612511126223 0.0025409646332263947 0.009795411139066346\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 175/200 \t Train Err: 0.01577709667617455 0.0002547664359440205 0.0003405914605991711 0.0020204293869028334 0.013386641423039691\n" + "Epoch 285/300 \t Train Err: 0.00244181264861254 3.681690922974212e-05 4.3878520443740854e-05 0.0002598097414647782 0.0010403500756694939\n" ] }, { @@ -3126,7 +1723,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 176/200 \t Train Err: 0.014100697473622859 0.00036510653808363713 0.0004396585003405562 0.0022091059381637024 0.00978638644005514\n" + "Epoch 286/300 \t Train Err: 0.004294504986319225 0.0001190346050776725 0.00014606812183615148 0.0005992255282762926 0.0030846270542213006\n" ] }, { @@ -3134,14 +1731,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:31<00:00, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 177/200 \t Train Err: 0.014368639851454645 0.00044816699323746434 0.00045128344186196045 0.002814159254739934 0.008726180123630911\n" + "Epoch 287/300 \t Train Err: 0.002652545867022127 4.383792450823876e-05 5.175098229415198e-05 0.00022583443728763086 0.0010033834210929626\n" ] }, { @@ -3156,7 +1753,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 178/200 \t Train Err: 0.014014390297234058 0.0006206710049809772 0.00046763980253672344 0.002513490486308001 0.008434324339646082\n" + "Epoch 288/300 \t Train Err: 0.0024623927056381945 4.488101473043571e-05 5.153768390186997e-05 0.0002487341471351101 0.0007657397355842477\n" ] }, { @@ -3171,22 +1768,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 179/200 \t Train Err: 0.011972312582656741 0.00018721630084428398 0.00029149899171443394 0.0016975146063487045 0.007282969920481719\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 180/200 \t Train Err: 0.01289494353113696 0.00020095304734013553 0.000251299350793488 0.0017014556851790985 0.010998782015121833\n" + "Epoch 289/300 \t Train Err: 0.0020869168256467674 1.6691098323917686e-05 2.3564317743307583e-05 0.00022000102012498246 0.00045439355731957676\n" ] }, { @@ -3201,7 +1783,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 181/200 \t Train Err: 0.013175164320273325 0.000340911025944024 0.00035113496642225073 0.002221787386588403 0.008535892283987323\n" + "Epoch 290/300 \t Train Err: 0.0022730279415554833 3.0484697447263898e-05 4.219567442476091e-05 0.00016836693907862355 0.001119111784291249\n" ] }, { @@ -3216,7 +1798,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 182/200 \t Train Err: 0.012816024391213432 0.0003103266114408143 0.00028728846336889546 0.0020579011925292434 0.00718217800522325\n" + "Epoch 291/300 \t Train Err: 0.001991223918594187 2.1141308877759002e-05 3.04732807308028e-05 0.00020811638796658372 0.0003465958211279485\n" ] }, { @@ -3231,7 +1813,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 183/200 \t Train Err: 0.01449834939558059 0.0005017787769361348 0.0005829150882163958 0.002624640494104824 0.012894641169850729\n" + "Epoch 292/300 \t Train Err: 0.002292186658451101 3.154981907016463e-05 4.474536956422526e-05 0.00023634338492684037 0.0009605502598901694\n" ] }, { @@ -3246,7 +1828,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 184/200 \t Train Err: 0.01308623020304367 0.0003065749452275668 0.0002674301056231343 0.0018643831190274796 0.009087016163903172\n" + "Epoch 293/300 \t Train Err: 0.0026851176444324665 4.017607729167594e-05 5.052340833344715e-05 0.0002948304424990056 0.0016830961768476982\n" ] }, { @@ -3254,14 +1836,14 @@ "output_type": "stream", "text": [ "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" + "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 185/200 \t Train Err: 0.011409497121348977 0.00029326116043648653 0.0003596148741280558 0.001658103732552263 0.007742758548488382\n" + "Epoch 294/300 \t Train Err: 0.0034057760349242017 7.469349623079324e-05 8.74023012897851e-05 0.000339981324486871 0.003754490641924235\n" ] }, { @@ -3276,7 +1858,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 186/200 \t Train Err: 0.010975291283102706 0.00022339119993830536 0.00027696753636519134 0.0014451522856688825 0.0054481543454585335\n" + "Epoch 295/300 \t Train Err: 0.0030984806799096987 0.00010745276432544415 9.293096556461933e-05 0.00044971922284275934 0.001608260552785623\n" ] }, { @@ -3291,22 +1873,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 187/200 \t Train Err: 0.010257220594212413 0.00023113110682970728 0.0002813607433154175 0.001320708272032789 0.005819132793249082\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.06it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 188/200 \t Train Err: 0.012054045568220317 0.000388129293298789 0.0004733345151635149 0.001878096192740486 0.00747043985700202\n" + "Epoch 296/300 \t Train Err: 0.0046719673155166674 0.0002628431795983488 0.0001992497713558805 0.0007588743333144521 0.00447205124172001\n" ] }, { @@ -3321,7 +1888,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 189/200 \t Train Err: 0.012783893820596859 0.00031030693571665324 0.00032841233428371197 0.0017014134382407065 0.006328187721919676\n" + "Epoch 297/300 \t Train Err: 0.0029889549914514646 3.997794847521163e-05 5.749405914912131e-05 0.0002763791262623272 0.0008012855590209256\n" ] }, { @@ -3336,44 +1903,28 @@ "name": "stdout", "output_type": "stream", "text": [ - "Epoch 190/200 \t Train Err: 0.01047908267355524 0.000252351564199671 0.0003104653961827353 0.0015047969627630664 0.00647446524692441\n" + "Epoch 298/300 \t Train Err: 0.0024420233276032377 2.269027612555874e-05 2.9261659733492706e-05 0.0002353174338622921 0.001323332107006081\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" + "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 191/200 \t Train Err: 0.01059192547108978 0.00032810493928536744 0.00036611615337278636 0.0015751951596030267 0.005902428454646724\n" + "Epoch 299/300 \t Train Err: 0.0022801305785833392 5.704613654700097e-05 7.387786931190021e-05 0.0002796662083710544 0.0008495270817547862\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "\n", - "00%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:30<00:00, 1.04it/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 192/200 \t Train Err: 0.011238765117013827 0.0005425223790780365 0.0005242744022098123 0.0020095554464205634 0.006199448111232186\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 75%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 24/32 [00:22<00:07, 1.03it/s]" + "\n" ] } ], @@ -3412,7 +1963,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 85, "execution_state": "idle", "metadata": {}, "outputs": [], @@ -3426,40 +1977,33 @@ " loss = criterion(output.squeeze(1), batch_labels)\n", " return output.detach(), batch_labels.detach().to(torch.uint8), loss.item()\n", "\n", - "def mkhist(data):\n", + "def mkhist(data, title):\n", " y, x, loss = evaluate(data)\n", " print(loss)\n", " cnts = torch.bincount(x)\n", " weights = [1/cnts[i.item()].item() for i in x] # normalize by label count\n", " fig, ax = plt.subplots()\n", - " h = ax.hist2d(x.cpu().numpy().flatten(), y.cpu().numpy().flatten(), weights=weights, bins=[15,50], norm=mpl.colors.LogNorm())\n", + " h = ax.hist2d(x.cpu().numpy().flatten(), y.cpu().numpy().flatten(), weights=weights, bins=[cnts.shape[0] - 1, 50], norm=mpl.colors.LogNorm())\n", " ax.set_xlabel(\"Label\")\n", " ax.set_ylabel(\"Model Output\")\n", - " fig.colorbar(h[3], ax=ax)" + " ax.set_title(title)\n", + " fig.colorbar(h[3], ax=ax)\n", + " return fig" ] }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 141, + "execution_state": "idle", "metadata": {}, "outputs": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/sipb/.venv/lib64/python3.12/site-packages/torch/nn/modules/transformer.py:871: UserWarning: Memory Efficient attention on Navi31 GPU is still experimental. Enable it with TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1. (Triggered internally at ../aten/src/ATen/native/transformers/hip/sdp_utils.cpp:269.)\n", - " return torch._transformer_encoder_layer_fwd(\n", - "/home/sipb/.venv/lib64/python3.12/site-packages/torch/nn/modules/transformer.py:871: UserWarning: Attempting to use hipBLASLt on an unsupported architecture! Overriding blas backend to hipblas (Triggered internally at ../aten/src/ATen/Context.cpp:296.)\n", - " return torch._transformer_encoder_layer_fwd(\n" - ] - }, - { "data": { "text/plain": [ - "0.031184175983071327" + "0.0019329296192154288" ] }, - "execution_count": 13, + "execution_count": 141, "metadata": {}, "output_type": "execute_result" } @@ -3470,29 +2014,50 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 49, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 1 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "with open('loss') as f:\n", " losses = torch.tensor([list(map(float, l.split())) for l in f.readlines()])\n", "plt.plot(torch.log(losses[:, 0]), label='Train', color='blue')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Log MSE')\n", + "plt.title('Training Loss')\n", "with open(\"plots/train-loss.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 116, + "execution_state": "idle", "metadata": { "id": "LoGEmM5lH7_A" }, "outputs": [ { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.002062194049358368\n" + ] + }, + { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "<Figure size 640x480 with 2 Axes>" ] @@ -3502,32 +2067,75 @@ } ], "source": [ - "mkhist(mkbatch(BSZ))\n", - "plt.show()\n", + "fig = mkhist(mkbatch(BSZ), \"Train Output Distribution\")\n", "with open(\"plots/train-hist.html\", \"w\") as f:\n", - " mpld3.save_html(plt.gcf(), f)" + " mpld3.save_html(fig, f)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 1 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "plt.suptitle('Log MSE vs Epochs')\n", - "plt.plot(torch.log(torch.tensor(losses[:, 0])), label='Train', color='blue')\n", - "plt.plot(torch.log(torch.tensor(losses[:, 1])), label='Len 1', color='red')\n", - "plt.plot(torch.log(torch.tensor(losses[:, 2])), label='Len 2', color='green')\n", - "plt.plot(torch.log(torch.tensor(losses[:, 3])), label='Len 3', color='yellow')\n", - "plt.plot(torch.log(torch.tensor(losses[:, 4])), label='Len 15', color='magenta')\n", + "plt.plot(torch.log(losses[:300, 0]), label='Train', color='blue')\n", + "plt.plot(torch.log(losses[:300, 1]), label='Len 1', color='red')\n", + "plt.plot(torch.log(losses[:300, 2]), label='Len 2', color='green')\n", + "plt.plot(torch.log(losses[:300, 3]), label='Len 3', color='orange')\n", + "plt.plot(torch.log(losses[:300, 4]), label='Len 15', color='magenta')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Log MSE')\n", + "plt.title('Training Loss For Different Labels')\n", "plt.legend()\n", "with open(\"plots/train-lens.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { + "cell_type": "code", + "execution_count": 180, + "execution_state": "idle", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tensor([[ 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11,\n", + " 11, 12, 12, 13, 13, 14, 14, 15, 1, 15, 0, 0, 2]], device='cuda:0')\n" + ] + }, + { + "data": { + "text/plain": [ + "tensor([[7.1840]], device='cuda:0', grad_fn=<CompiledFunctionBackward>)" + ] + }, + "execution_count": 180, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Testing line graph\n", + "inp = torch.cat((torch.repeat_interleave(torch.arange(2, MAX_VTXS + 1), 2)[1:-1], torch.tensor([1, 15, 0, 0, 2]))).unsqueeze(0).to(device)\n", + "print(inp)\n", + "model(inp, inp == PAD_TOKEN)" + ] + }, + { "cell_type": "markdown", "metadata": { "id": "LC6Xv3YfC0Rm" @@ -3538,7 +2146,8 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 142, + "execution_state": "idle", "metadata": {}, "outputs": [], "source": [ @@ -3556,113 +2165,114 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 143, + "execution_state": "idle", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 0/100 \t Train Err: 0.4553\n", - "Epoch 1/100 \t Train Err: 0.2545\n", - "Epoch 2/100 \t Train Err: 0.2368\n", - "Epoch 3/100 \t Train Err: 0.2138\n", - "Epoch 4/100 \t Train Err: 0.1898\n", - "Epoch 5/100 \t Train Err: 0.1931\n", - "Epoch 6/100 \t Train Err: 0.1948\n", - "Epoch 7/100 \t Train Err: 0.1847\n", - "Epoch 8/100 \t Train Err: 0.1638\n", - "Epoch 9/100 \t Train Err: 0.1490\n", - "Epoch 10/100 \t Train Err: 0.1457\n", - "Epoch 11/100 \t Train Err: 0.1509\n", - "Epoch 12/100 \t Train Err: 0.1537\n", - "Epoch 13/100 \t Train Err: 0.1472\n", - "Epoch 14/100 \t Train Err: 0.1369\n", - "Epoch 15/100 \t Train Err: 0.1304\n", - "Epoch 16/100 \t Train Err: 0.1257\n", - "Epoch 17/100 \t Train Err: 0.1201\n", - "Epoch 18/100 \t Train Err: 0.1160\n", - "Epoch 19/100 \t Train Err: 0.1064\n", - "Epoch 20/100 \t Train Err: 0.1026\n", - "Epoch 21/100 \t Train Err: 0.0964\n", - "Epoch 22/100 \t Train Err: 0.1165\n", - "Epoch 23/100 \t Train Err: 0.0990\n", - "Epoch 24/100 \t Train Err: 0.0691\n", - "Epoch 25/100 \t Train Err: 0.0633\n", - "Epoch 26/100 \t Train Err: 0.0552\n", - "Epoch 27/100 \t Train Err: 0.0505\n", - "Epoch 28/100 \t Train Err: 0.0429\n", - "Epoch 29/100 \t Train Err: 0.0376\n", - "Epoch 30/100 \t Train Err: 0.0309\n", - "Epoch 31/100 \t Train Err: 0.0252\n", - "Epoch 32/100 \t Train Err: 0.0233\n", - "Epoch 33/100 \t Train Err: 0.0219\n", - "Epoch 34/100 \t Train Err: 0.0196\n", - "Epoch 35/100 \t Train Err: 0.0186\n", - "Epoch 36/100 \t Train Err: 0.0181\n", - "Epoch 37/100 \t Train Err: 0.0189\n", - "Epoch 38/100 \t Train Err: 0.0174\n", - "Epoch 39/100 \t Train Err: 0.0141\n", - "Epoch 40/100 \t Train Err: 0.0138\n", - "Epoch 41/100 \t Train Err: 0.0136\n", - "Epoch 42/100 \t Train Err: 0.0124\n", - "Epoch 43/100 \t Train Err: 0.0121\n", - "Epoch 44/100 \t Train Err: 0.0109\n", - "Epoch 45/100 \t Train Err: 0.0107\n", - "Epoch 46/100 \t Train Err: 0.0105\n", - "Epoch 47/100 \t Train Err: 0.0103\n", - "Epoch 48/100 \t Train Err: 0.0088\n", - "Epoch 49/100 \t Train Err: 0.0089\n", - "Epoch 50/100 \t Train Err: 0.0092\n", - "Epoch 51/100 \t Train Err: 0.0078\n", - "Epoch 52/100 \t Train Err: 0.0075\n", - "Epoch 53/100 \t Train Err: 0.0068\n", - "Epoch 54/100 \t Train Err: 0.0066\n", - "Epoch 55/100 \t Train Err: 0.0065\n", - "Epoch 56/100 \t Train Err: 0.0055\n", - "Epoch 57/100 \t Train Err: 0.0056\n", - "Epoch 58/100 \t Train Err: 0.0052\n", - "Epoch 59/100 \t Train Err: 0.0055\n", - "Epoch 60/100 \t Train Err: 0.0048\n", - "Epoch 61/100 \t Train Err: 0.0050\n", - "Epoch 62/100 \t Train Err: 0.0049\n", - "Epoch 63/100 \t Train Err: 0.0051\n", - "Epoch 64/100 \t Train Err: 0.0047\n", - "Epoch 65/100 \t Train Err: 0.0045\n", - "Epoch 66/100 \t Train Err: 0.0041\n", - "Epoch 67/100 \t Train Err: 0.0038\n", - "Epoch 68/100 \t Train Err: 0.0036\n", - "Epoch 69/100 \t Train Err: 0.0035\n", - "Epoch 70/100 \t Train Err: 0.0035\n", - "Epoch 71/100 \t Train Err: 0.0032\n", - "Epoch 72/100 \t Train Err: 0.0032\n", - "Epoch 73/100 \t Train Err: 0.0030\n", - "Epoch 74/100 \t Train Err: 0.0031\n", - "Epoch 75/100 \t Train Err: 0.0026\n", - "Epoch 76/100 \t Train Err: 0.0030\n", - "Epoch 77/100 \t Train Err: 0.0024\n", - "Epoch 78/100 \t Train Err: 0.0026\n", - "Epoch 79/100 \t Train Err: 0.0028\n", - "Epoch 80/100 \t Train Err: 0.0026\n", - "Epoch 81/100 \t Train Err: 0.0023\n", - "Epoch 82/100 \t Train Err: 0.0022\n", - "Epoch 83/100 \t Train Err: 0.0022\n", - "Epoch 84/100 \t Train Err: 0.0021\n", - "Epoch 85/100 \t Train Err: 0.0023\n", - "Epoch 86/100 \t Train Err: 0.0023\n", - "Epoch 87/100 \t Train Err: 0.0020\n", - "Epoch 88/100 \t Train Err: 0.0020\n", - "Epoch 89/100 \t Train Err: 0.0021\n", - "Epoch 90/100 \t Train Err: 0.0020\n", - "Epoch 91/100 \t Train Err: 0.0019\n", - "Epoch 92/100 \t Train Err: 0.0017\n", - "Epoch 93/100 \t Train Err: 0.0019\n", - "Epoch 94/100 \t Train Err: 0.0019\n", - "Epoch 95/100 \t Train Err: 0.0015\n", - "Epoch 96/100 \t Train Err: 0.0016\n", - "Epoch 97/100 \t Train Err: 0.0017\n", - "Epoch 98/100 \t Train Err: 0.0015\n", - "Epoch 99/100 \t Train Err: 0.0015\n" + "Epoch 0/100 \t Train Err: 0.5544188022613525\n", + "Epoch 1/100 \t Train Err: 0.3685164451599121\n", + "Epoch 2/100 \t Train Err: 0.3081561028957367\n", + "Epoch 3/100 \t Train Err: 0.34435540437698364\n", + "Epoch 4/100 \t Train Err: 0.34420037269592285\n", + "Epoch 5/100 \t Train Err: 0.3113354742527008\n", + "Epoch 6/100 \t Train Err: 0.2920008897781372\n", + "Epoch 7/100 \t Train Err: 0.29242873191833496\n", + "Epoch 8/100 \t Train Err: 0.29623904824256897\n", + "Epoch 9/100 \t Train Err: 0.289389967918396\n", + "Epoch 10/100 \t Train Err: 0.2864971160888672\n", + "Epoch 11/100 \t Train Err: 0.275798499584198\n", + "Epoch 12/100 \t Train Err: 0.26332974433898926\n", + "Epoch 13/100 \t Train Err: 0.24548597633838654\n", + "Epoch 14/100 \t Train Err: 0.23320920765399933\n", + "Epoch 15/100 \t Train Err: 0.21942488849163055\n", + "Epoch 16/100 \t Train Err: 0.2166539430618286\n", + "Epoch 17/100 \t Train Err: 0.199913889169693\n", + "Epoch 18/100 \t Train Err: 0.18155084550380707\n", + "Epoch 19/100 \t Train Err: 0.16955474019050598\n", + "Epoch 20/100 \t Train Err: 0.1510634422302246\n", + "Epoch 21/100 \t Train Err: 0.14870578050613403\n", + "Epoch 22/100 \t Train Err: 0.1314307153224945\n", + "Epoch 23/100 \t Train Err: 0.11984959244728088\n", + "Epoch 24/100 \t Train Err: 0.11021721363067627\n", + "Epoch 25/100 \t Train Err: 0.10518306493759155\n", + "Epoch 26/100 \t Train Err: 0.0979144424200058\n", + "Epoch 27/100 \t Train Err: 0.08785216510295868\n", + "Epoch 28/100 \t Train Err: 0.08054468035697937\n", + "Epoch 29/100 \t Train Err: 0.07370081543922424\n", + "Epoch 30/100 \t Train Err: 0.07197917997837067\n", + "Epoch 31/100 \t Train Err: 0.06865058839321136\n", + "Epoch 32/100 \t Train Err: 0.0573689229786396\n", + "Epoch 33/100 \t Train Err: 0.05383218824863434\n", + "Epoch 34/100 \t Train Err: 0.0517902597784996\n", + "Epoch 35/100 \t Train Err: 0.05098778009414673\n", + "Epoch 36/100 \t Train Err: 0.04457991570234299\n", + "Epoch 37/100 \t Train Err: 0.04348936304450035\n", + "Epoch 38/100 \t Train Err: 0.04035983979701996\n", + "Epoch 39/100 \t Train Err: 0.03779032826423645\n", + "Epoch 40/100 \t Train Err: 0.03429888188838959\n", + "Epoch 41/100 \t Train Err: 0.033257707953453064\n", + "Epoch 42/100 \t Train Err: 0.03203653544187546\n", + "Epoch 43/100 \t Train Err: 0.028432603925466537\n", + "Epoch 44/100 \t Train Err: 0.025738071650266647\n", + "Epoch 45/100 \t Train Err: 0.025591572746634483\n", + "Epoch 46/100 \t Train Err: 0.023587044328451157\n", + "Epoch 47/100 \t Train Err: 0.023489363491535187\n", + "Epoch 48/100 \t Train Err: 0.0216952133923769\n", + "Epoch 49/100 \t Train Err: 0.021158069372177124\n", + "Epoch 50/100 \t Train Err: 0.020110130310058594\n", + "Epoch 51/100 \t Train Err: 0.019414473325014114\n", + "Epoch 52/100 \t Train Err: 0.019276173785328865\n", + "Epoch 53/100 \t Train Err: 0.017750531435012817\n", + "Epoch 54/100 \t Train Err: 0.016304394230246544\n", + "Epoch 55/100 \t Train Err: 0.015181242488324642\n", + "Epoch 56/100 \t Train Err: 0.01471915002912283\n", + "Epoch 57/100 \t Train Err: 0.013883879408240318\n", + "Epoch 58/100 \t Train Err: 0.013605501502752304\n", + "Epoch 59/100 \t Train Err: 0.012538591399788857\n", + "Epoch 60/100 \t Train Err: 0.01240430399775505\n", + "Epoch 61/100 \t Train Err: 0.012169113382697105\n", + "Epoch 62/100 \t Train Err: 0.011674975976347923\n", + "Epoch 63/100 \t Train Err: 0.011418530717492104\n", + "Epoch 64/100 \t Train Err: 0.010362120345234871\n", + "Epoch 65/100 \t Train Err: 0.010559136047959328\n", + "Epoch 66/100 \t Train Err: 0.010620282962918282\n", + "Epoch 67/100 \t Train Err: 0.010126937180757523\n", + "Epoch 68/100 \t Train Err: 0.00937468558549881\n", + "Epoch 69/100 \t Train Err: 0.009250747971236706\n", + "Epoch 70/100 \t Train Err: 0.008886337280273438\n", + "Epoch 71/100 \t Train Err: 0.008759485557675362\n", + "Epoch 72/100 \t Train Err: 0.009314234368503094\n", + "Epoch 73/100 \t Train Err: 0.008515555411577225\n", + "Epoch 74/100 \t Train Err: 0.00820714607834816\n", + "Epoch 75/100 \t Train Err: 0.0083921505138278\n", + "Epoch 76/100 \t Train Err: 0.007950334809720516\n", + "Epoch 77/100 \t Train Err: 0.007480953820049763\n", + "Epoch 78/100 \t Train Err: 0.007860099896788597\n", + "Epoch 79/100 \t Train Err: 0.007678570691496134\n", + "Epoch 80/100 \t Train Err: 0.0071814958937466145\n", + "Epoch 81/100 \t Train Err: 0.0071525052189826965\n", + "Epoch 82/100 \t Train Err: 0.0072823925875127316\n", + "Epoch 83/100 \t Train Err: 0.006747257895767689\n", + "Epoch 84/100 \t Train Err: 0.006682292558252811\n", + "Epoch 85/100 \t Train Err: 0.00638470659032464\n", + "Epoch 86/100 \t Train Err: 0.006667225155979395\n", + "Epoch 87/100 \t Train Err: 0.0068595497868955135\n", + "Epoch 88/100 \t Train Err: 0.006241748109459877\n", + "Epoch 89/100 \t Train Err: 0.006172557361423969\n", + "Epoch 90/100 \t Train Err: 0.006007512100040913\n", + "Epoch 91/100 \t Train Err: 0.005983388051390648\n", + "Epoch 92/100 \t Train Err: 0.006069593131542206\n", + "Epoch 93/100 \t Train Err: 0.005962291732430458\n", + "Epoch 94/100 \t Train Err: 0.005884208716452122\n", + "Epoch 95/100 \t Train Err: 0.005678766407072544\n", + "Epoch 96/100 \t Train Err: 0.0055491309612989426\n", + "Epoch 97/100 \t Train Err: 0.005540946964174509\n", + "Epoch 98/100 \t Train Err: 0.005390995182096958\n", + "Epoch 99/100 \t Train Err: 0.005392617546021938\n" ] } ], @@ -3681,7 +2291,7 @@ " tune_train_err.append(train_loss)\n", " with open('tune_loss', 'a') as f:\n", " f.write(f\"{train_loss}\\n\")\n", - " print(f\"Epoch {epoch}/{N_TUNE_EPOCHS} \\t Train Err: {train_loss:.4f}\")\n", + " print(f\"Epoch {epoch}/{N_TUNE_EPOCHS} \\t Train Err: {train_loss}\")\n", "\n", " if epoch % 10 == 9:\n", " torch.save(model.state_dict(), f\"checkpoints/tune_model_weights_{epoch + 1}.pth\")" @@ -3689,16 +2299,17 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 144, + "execution_state": "idle", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "0.001733972690999508" + "0.00539579801261425" ] }, - "execution_count": 19, + "execution_count": 144, "metadata": {}, "output_type": "execute_result" } @@ -3709,12 +2320,13 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 145, + "execution_state": "idle", "metadata": {}, "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "<Figure size 640x480 with 1 Axes>" ] @@ -3724,61 +2336,32 @@ } ], "source": [ - "plt.suptitle('Log MSE vs Epochs')\n", - "plt.plot(torch.log(tune_train_err), label='Train', color='blue')\n", - "plt.xlabel('Epochs')\n", - "plt.ylabel('Log MSE')\n", - "plt.show()\n", + "plt.plot(torch.log(torch.tensor(tune_train_err)), label=\"Train\", color=\"blue\")\n", + "plt.xlabel(\"Epochs\")\n", + "plt.ylabel(\"Log MSE\")\n", + "plt.title(\"Fine-tune Loss\")\n", "with open(\"plots/tune-loss.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 146, + "execution_state": "idle", "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "(array([[6.0290e+03, 1.8597e+04, 8.4000e+01, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " ...,\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 1.0000e+00]]),\n", - " array([1. , 1.1 , 1.2 , 1.3 , 1.4 , 1.5 , 1.6 , 1.699, 1.8 ,\n", - " 1.9 , 2. , 2.1 , 2.2 , 2.3 , 2.398, 2.5 , 2.6 , 2.7 ,\n", - " 2.8 , 2.898, 3. , 3.1 , 3.2 , 3.299, 3.398, 3.5 , 3.6 ,\n", - " 3.7 , 3.799, 3.898, 4. , 4.1 , 4.2 , 4.297, 4.4 , 4.5 ,\n", - " 4.6 , 4.7 , 4.797, 4.9 , 5. , 5.098, 5.2 , 5.3 , 5.4 ,\n", - " 5.5 , 5.598, 5.7 , 5.797, 5.9 , 6. ], dtype=float16),\n", - " array([0.9014, 0.998 , 1.094 , 1.19 , 1.287 , 1.384 , 1.48 , 1.576 ,\n", - " 1.673 , 1.77 , 1.865 , 1.962 , 2.059 , 2.156 , 2.25 , 2.348 ,\n", - " 2.445 , 2.541 , 2.637 , 2.734 , 2.83 , 2.926 , 3.023 , 3.121 ,\n", - " 3.215 , 3.312 , 3.41 , 3.504 , 3.602 , 3.7 , 3.793 , 3.89 ,\n", - " 3.988 , 4.082 , 4.18 , 4.277 , 4.375 , 4.47 , 4.566 , 4.664 ,\n", - " 4.758 , 4.855 , 4.953 , 5.05 , 5.145 , 5.242 , 5.34 , 5.434 ,\n", - " 5.53 , 5.63 , 5.723 ], dtype=float16),\n", - " <matplotlib.collections.QuadMesh at 0x7f201dae35c0>)" - ] - }, - "execution_count": 21, - "metadata": {}, - "output_type": "execute_result" + "name": "stdout", + "output_type": "stream", + "text": [ + "0.005263924598693848\n" + ] }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ - "<Figure size 640x480 with 1 Axes>" + "<Figure size 640x480 with 2 Axes>" ] }, "metadata": {}, @@ -3786,7 +2369,7 @@ } ], "source": [ - "mkhist(mkbatch(BSZ, large=False, target=\"onpath\"))\n", + "mkhist(mkbatch(BSZ, large=False, target=\"onpath\"), \"Fine-tune Output Distribution\")\n", "with open(\"plots/tune-hist.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] @@ -3802,69 +2385,52 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 159, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.09692102670669556\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 2 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "mkhist(mkbatch(BSZ, large=True, target=\"onpath\", largetarget=False))\n", + "mkhist(mkbatch(BSZ, large=True, target=\"onpath\", largetarget=False), \"On-path Small Target In Large Graphs\")\n", "with open(\"plots/test-onpath-smalltarget.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 160, + "execution_state": "idle", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "0.20130713284015656\n" + "0.13019351661205292\n" ] }, { "data": { + "image/png": "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", "text/plain": [ - "(array([[1.7789e+04, 6.5000e+02, 4.8000e+02, ..., 0.0000e+00, 1.0000e+00,\n", - " 1.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " ...,\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00],\n", - " [0.0000e+00, 0.0000e+00, 0.0000e+00, ..., 0.0000e+00, 0.0000e+00,\n", - " 0.0000e+00]]),\n", - " array([ 1. , 1.18 , 1.36 , 1.54 , 1.721, 1.9 , 2.08 , 2.262,\n", - " 2.441, 2.621, 2.8 , 2.98 , 3.16 , 3.34 , 3.521, 3.701,\n", - " 3.88 , 4.062, 4.242, 4.42 , 4.6 , 4.78 , 4.96 , 5.14 ,\n", - " 5.32 , 5.5 , 5.68 , 5.863, 6.043, 6.223, 6.402, 6.582,\n", - " 6.76 , 6.94 , 7.12 , 7.3 , 7.48 , 7.66 , 7.844, 8.02 ,\n", - " 8.2 , 8.38 , 8.56 , 8.74 , 8.92 , 9.1 , 9.28 , 9.46 ,\n", - " 9.64 , 9.82 , 10. ], dtype=float16),\n", - " array([ 0.879, 1.156, 1.434, 1.71 , 1.987, 2.266, 2.541, 2.818,\n", - " 3.096, 3.373, 3.65 , 3.928, 4.203, 4.48 , 4.758, 5.035,\n", - " 5.312, 5.59 , 5.867, 6.145, 6.42 , 6.7 , 6.977, 7.254,\n", - " 7.527, 7.805, 8.08 , 8.36 , 8.64 , 8.92 , 9.19 , 9.47 ,\n", - " 9.75 , 10.016, 10.3 , 10.58 , 10.86 , 11.125, 11.41 , 11.69 ,\n", - " 11.97 , 12.234, 12.516, 12.8 , 13.08 , 13.34 , 13.625, 13.91 ,\n", - " 14.17 , 14.45 , 14.734], dtype=float16),\n", - " <matplotlib.collections.QuadMesh at 0x7f201daaff50>)" - ] - }, - "execution_count": 27, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "<Figure size 640x480 with 1 Axes>" + "<Figure size 640x480 with 2 Axes>" ] }, "metadata": {}, @@ -3872,40 +2438,97 @@ } ], "source": [ - "mkhist(mkbatch(BSZ, large=True, target=\"onpath\", largetarget=True))\n", + "mkhist(mkbatch(BSZ, large=True, target=\"onpath\", largetarget=True), \"On-path Target In Large Graphs\")\n", "with open(\"plots/test-onpath-largetarget.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 89, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "65.92536926269531\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 2 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "mkhist(mkbatch(BSZ, large=False, target=\"any\", largetarget=False))\n", + "mkhist(mkbatch(BSZ, large=False, target=\"any\", largetarget=False), \"Any Target In Small Graphs\")\n", "with open(\"plots/test-small-any.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 90, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "52.1881217956543\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 2 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "mkhist(mkbatch(BSZ, large=True, target=\"any\", largetarget=False))\n", + "mkhist(mkbatch(BSZ, large=True, target=\"any\", largetarget=False), \"Any Small Target In Large Graphs\")\n", "with open(\"plots/test-large-any-smalltarget.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 91, + "execution_state": "idle", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "81.48127746582031\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "<Figure size 640x480 with 2 Axes>" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "mkhist(mkbatch(BSZ, large=True, target=\"any\", largetarget=True))\n", + "mkhist(mkbatch(BSZ, large=True, target=\"any\", largetarget=True), \"Any Target In Large Graphs\")\n", "with open(\"plots/test-large-any-largetarget.html\", \"w\") as f:\n", " mpld3.save_html(plt.gcf(), f)" ] |