From 7c22ba2c1efcbdd56e8db733c07c3ca4751f3138 Mon Sep 17 00:00:00 2001
From: wassname <git@wassname.org>
Date: Tue, 29 Nov 2022 06:07:44 +0800
Subject: [PATCH] misc

---
 notebooks/001_001_run_MS2S.ipynb | 496 ++++++++++++++++++-------------
 1 file changed, 296 insertions(+), 200 deletions(-)

diff --git a/notebooks/001_001_run_MS2S.ipynb b/notebooks/001_001_run_MS2S.ipynb
index 25bd7d9..398df4b 100644
--- a/notebooks/001_001_run_MS2S.ipynb
+++ b/notebooks/001_001_run_MS2S.ipynb
@@ -3,11 +3,11 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "d1559174",
+   "id": "d2d7a060",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:06:55.731972Z",
-     "start_time": "2022-11-28T08:06:55.730182Z"
+     "end_time": "2022-11-28T10:41:41.699622Z",
+     "start_time": "2022-11-28T10:41:41.697583Z"
     }
    },
    "outputs": [],
@@ -19,11 +19,11 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "61b1369e",
+   "id": "493a85a8",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:06:55.760248Z",
-     "start_time": "2022-11-28T08:06:55.733246Z"
+     "end_time": "2022-11-28T10:41:41.730196Z",
+     "start_time": "2022-11-28T10:41:41.700557Z"
     }
    },
    "outputs": [],
@@ -39,11 +39,11 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "94cb38fd",
+   "id": "873c7ab3",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:06:55.780884Z",
-     "start_time": "2022-11-28T08:06:55.762049Z"
+     "end_time": "2022-11-28T10:41:41.748569Z",
+     "start_time": "2022-11-28T10:41:41.731432Z"
     }
    },
    "outputs": [],
@@ -58,11 +58,11 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "a58d9d6f",
+   "id": "6c991fe3",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:06:56.489497Z",
-     "start_time": "2022-11-28T08:06:55.781984Z"
+     "end_time": "2022-11-28T10:41:42.490541Z",
+     "start_time": "2022-11-28T10:41:41.749534Z"
     }
    },
    "outputs": [],
@@ -75,7 +75,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "77f600e7",
+   "id": "92ef6734",
    "metadata": {},
    "source": [
     "# Args"
@@ -84,11 +84,11 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "b46f211d",
+   "id": "8e2098cb",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:06:56.762126Z",
-     "start_time": "2022-11-28T08:06:56.490469Z"
+     "end_time": "2022-11-28T10:41:42.749164Z",
+     "start_time": "2022-11-28T10:41:42.491911Z"
     }
    },
    "outputs": [],
@@ -99,11 +99,11 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "dcc0f57b",
+   "id": "99d7b86d",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:29.460882Z",
-     "start_time": "2022-11-28T08:06:56.763160Z"
+     "end_time": "2022-11-28T11:07:52.167744Z",
+     "start_time": "2022-11-28T10:41:42.750546Z"
     }
    },
    "outputs": [
@@ -112,18 +112,18 @@
      "output_type": "stream",
      "text": [
       "Args in experiment:\n",
-      "Namespace(K=0, activation='sigmoid', batch_size=32, c_out=1, checkpoints='./checkpoints/', d_ff=2048, d_layers=3, d_model=512, damping_learning_rate=0, data='custom', data_path='OXY_2019.csv.gz', dec_in=7, des=\"'Exp'\", devices='0,1,2,3', dropout=0.2, e_layers=3, embed='timeF', enc_in=12, features='M2S', freq='h', gpu=0, itr=1, label_len=0, learning_rate=0.0003, lradj='exponential_with_warmup', min_lr=1e-30, model='ETSformer', model_id='Exchange', n_heads=8, num_workers=0, optim='adam', output_attention=False, patience=5, pred_len=48, root_path='../dataset/stocks/', seq_len=256, smoothing_learning_rate=0, std=0.2, target='RSMKs_18_144_72_2ref_2ref', train_epochs=15, use_gpu=True, use_multi_gpu=False, warmup_epochs=3)\n",
+      "Namespace(K=0, activation='sigmoid', batch_size=32, c_out=1, checkpoints='./checkpoints/', d_ff=2048, d_layers=3, d_model=512, damping_learning_rate=0, data='custom', data_path='OXY_2019.csv.gz', dec_in=7, des=\"'Exp'\", devices='0,1,2,3', dropout=0.2, e_layers=3, embed='timeF', enc_in=12, features='M2S', freq='h', gpu=0, itr=1, label_len=0, learning_rate=0.001, lradj='exponential_with_warmup', min_lr=1e-30, model='ETSformer', model_id='Exchange', n_heads=16, num_workers=0, optim='adam', output_attention=False, patience=5, pred_len=12, root_path='../dataset/stocks/', seq_len=256, smoothing_learning_rate=0, std=0.2, target='RSMKs_18_144_72_2ref_2ref', train_epochs=15, use_gpu=True, use_multi_gpu=False, warmup_epochs=3)\n",
       "Use GPU: cuda:0\n",
-      ">>>>>>>start training : Exchange_ETSformer_custom_ftM2S_sl256_pl48_dm512_nh8_el3_dl3_df2048_K0_lr0.0003_'Exp'_0>>>>>>>>>>>>>>>>>>>>>>>>>>\n",
-      "train 37075\n",
-      "val 5294\n",
-      "test 10632\n"
+      ">>>>>>>start training : Exchange_ETSformer_custom_ftM2S_sl256_pl12_dm512_nh16_el3_dl3_df2048_K0_lr0.001_'Exp'_0>>>>>>>>>>>>>>>>>>>>>>>>>>\n",
+      "train 37111\n",
+      "val 5330\n",
+      "test 10668\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "85f7ec0327cb49e1a18c800612f4382d",
+       "model_id": "88350c6aaffd407c82ced77be879bc81",
        "version_major": 2,
        "version_minor": 0
       },
@@ -142,7 +142,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -152,9 +152,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 1, Steps: 1158 | Train Loss: 0.3039489 Vali Loss: 0.0921374 Test Loss: 0.1340459\n",
-      "Validation loss decreased (inf --> 0.092137).  Saving model ...\n",
-      "Updating learning rate to 7.5e-05\n"
+      "Epoch: 1, Steps: 1159 | Train Loss: 0.1754474 Vali Loss: 0.0231598 Test Loss: 0.0334731\n",
+      "Validation loss decreased (inf --> 0.023160).  Saving model ...\n",
+      "Updating learning rate to 0.00025\n"
      ]
     },
     {
@@ -165,7 +165,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -175,9 +175,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 2, Steps: 1158 | Train Loss: 0.2563745 Vali Loss: 0.0417388 Test Loss: 0.0712016\n",
-      "Validation loss decreased (0.092137 --> 0.041739).  Saving model ...\n",
-      "Updating learning rate to 0.00015\n"
+      "Epoch: 2, Steps: 1159 | Train Loss: 0.1607344 Vali Loss: 0.0065583 Test Loss: 0.0085996\n",
+      "Validation loss decreased (0.023160 --> 0.006558).  Saving model ...\n",
+      "Updating learning rate to 0.0005\n"
      ]
     },
     {
@@ -188,7 +188,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -198,9 +198,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 3, Steps: 1158 | Train Loss: 0.2333940 Vali Loss: 0.0330352 Test Loss: 0.0573823\n",
-      "Validation loss decreased (0.041739 --> 0.033035).  Saving model ...\n",
-      "Updating learning rate to 0.000225\n"
+      "Epoch: 3, Steps: 1159 | Train Loss: 0.1427123 Vali Loss: 0.0055523 Test Loss: 0.0080176\n",
+      "Validation loss decreased (0.006558 --> 0.005552).  Saving model ...\n",
+      "Updating learning rate to 0.00075\n"
      ]
     },
     {
@@ -211,7 +211,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -221,78 +221,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 4, Steps: 1158 | Train Loss: 0.2121243 Vali Loss: 0.0315717 Test Loss: 0.0495963\n",
-      "Validation loss decreased (0.033035 --> 0.031572).  Saving model ...\n",
-      "Updating learning rate to 0.0003\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch: 5, Steps: 1158 | Train Loss: 0.2010674 Vali Loss: 0.0252529 Test Loss: 0.0422979\n",
-      "Validation loss decreased (0.031572 --> 0.025253).  Saving model ...\n",
-      "Updating learning rate to 0.00015\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch: 6, Steps: 1158 | Train Loss: 0.1899752 Vali Loss: 0.0233886 Test Loss: 0.0374318\n",
-      "Validation loss decreased (0.025253 --> 0.023389).  Saving model ...\n",
-      "Updating learning rate to 7.5e-05\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch: 7, Steps: 1158 | Train Loss: 0.1816380 Vali Loss: 0.0244228 Test Loss: 0.0401366\n",
+      "Epoch: 4, Steps: 1159 | Train Loss: 0.1279594 Vali Loss: 0.0096495 Test Loss: 0.0123530\n",
       "EarlyStopping counter: 1 out of 5\n",
-      "Updating learning rate to 3.75e-05\n"
+      "Updating learning rate to 0.001\n"
      ]
     },
     {
@@ -303,7 +234,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -313,9 +244,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 8, Steps: 1158 | Train Loss: 0.1756075 Vali Loss: 0.0271009 Test Loss: 0.0438157\n",
+      "Epoch: 5, Steps: 1159 | Train Loss: 0.1277149 Vali Loss: 0.0093008 Test Loss: 0.0128422\n",
       "EarlyStopping counter: 2 out of 5\n",
-      "Updating learning rate to 1.875e-05\n"
+      "Updating learning rate to 0.0005\n"
      ]
     },
     {
@@ -326,7 +257,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -336,9 +267,193 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 9, Steps: 1158 | Train Loss: 0.1704306 Vali Loss: 0.0237322 Test Loss: 0.0405497\n",
+      "Epoch: 6, Steps: 1159 | Train Loss: 0.1275677 Vali Loss: 0.0053658 Test Loss: 0.0075932\n",
+      "Validation loss decreased (0.005552 --> 0.005366).  Saving model ...\n",
+      "Updating learning rate to 0.00025\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 7, Steps: 1159 | Train Loss: 0.1138183 Vali Loss: 0.0042887 Test Loss: 0.0057305\n",
+      "Validation loss decreased (0.005366 --> 0.004289).  Saving model ...\n",
+      "Updating learning rate to 0.000125\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 8, Steps: 1159 | Train Loss: 0.1130605 Vali Loss: 0.0043534 Test Loss: 0.0060191\n",
+      "EarlyStopping counter: 1 out of 5\n",
+      "Updating learning rate to 6.25e-05\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 9, Steps: 1159 | Train Loss: 0.1090457 Vali Loss: 0.0035517 Test Loss: 0.0049039\n",
+      "Validation loss decreased (0.004289 --> 0.003552).  Saving model ...\n",
+      "Updating learning rate to 3.125e-05\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 10, Steps: 1159 | Train Loss: 0.1034120 Vali Loss: 0.0035072 Test Loss: 0.0049077\n",
+      "Validation loss decreased (0.003552 --> 0.003507).  Saving model ...\n",
+      "Updating learning rate to 1.5625e-05\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 11, Steps: 1159 | Train Loss: 0.1109674 Vali Loss: 0.0033732 Test Loss: 0.0047901\n",
+      "Validation loss decreased (0.003507 --> 0.003373).  Saving model ...\n",
+      "Updating learning rate to 7.8125e-06\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 12, Steps: 1159 | Train Loss: 0.1124570 Vali Loss: 0.0034817 Test Loss: 0.0049386\n",
+      "EarlyStopping counter: 1 out of 5\n",
+      "Updating learning rate to 3.90625e-06\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 13, Steps: 1159 | Train Loss: 0.1052720 Vali Loss: 0.0035949 Test Loss: 0.0051179\n",
+      "EarlyStopping counter: 2 out of 5\n",
+      "Updating learning rate to 1.953125e-06\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 14, Steps: 1159 | Train Loss: 0.1118911 Vali Loss: 0.0035167 Test Loss: 0.0050038\n",
       "EarlyStopping counter: 3 out of 5\n",
-      "Updating learning rate to 9.375e-06\n"
+      "Updating learning rate to 9.765625e-07\n"
      ]
     },
     {
@@ -349,7 +464,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
+       "train:   0%|          | 0/1159 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -359,34 +474,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 10, Steps: 1158 | Train Loss: 0.1624045 Vali Loss: 0.0244505 Test Loss: 0.0417811\n",
+      "Epoch: 15, Steps: 1159 | Train Loss: 0.1101214 Vali Loss: 0.0035256 Test Loss: 0.0050054\n",
       "EarlyStopping counter: 4 out of 5\n",
-      "Updating learning rate to 4.6875e-06\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train:   0%|          | 0/1158 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch: 11, Steps: 1158 | Train Loss: 0.1756617 Vali Loss: 0.0242605 Test Loss: 0.0415354\n",
-      "EarlyStopping counter: 5 out of 5\n",
-      "Early stopping\n",
-      ">>>>>>>testing : Exchange_ETSformer_custom_ftM2S_sl256_pl48_dm512_nh8_el3_dl3_df2048_K0_lr0.0003_'Exp'_0<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n",
-      "val 5294\n",
+      "Updating learning rate to 4.8828125e-07\n",
+      ">>>>>>>testing : Exchange_ETSformer_custom_ftM2S_sl256_pl12_dm512_nh16_el3_dl3_df2048_K0_lr0.001_'Exp'_0<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n",
+      "val 5330\n",
       "loading model\n"
      ]
     },
@@ -398,7 +490,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/165 [00:00<?, ?it/s]"
+       "  0%|          | 0/166 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -408,10 +500,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "test shape: (165, 32, 48, 1) (165, 32, 48, 1)\n",
-      "test shape: (5280, 48, 1) (5280, 48, 1)\n",
-      "mse:0.023374028503894806, mae:0.11202067881822586\n",
-      "test 10632\n",
+      "test shape: (166, 32, 12, 1) (166, 32, 12, 1)\n",
+      "test shape: (5312, 12, 1) (5312, 12, 1)\n",
+      "mse:0.00336787779815495, mae:0.04273906722664833\n",
+      "test 10668\n",
       "loading model\n"
      ]
     },
@@ -423,7 +515,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/332 [00:00<?, ?it/s]"
+       "  0%|          | 0/333 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -433,9 +525,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "test shape: (332, 32, 48, 1) (332, 32, 48, 1)\n",
-      "test shape: (10624, 48, 1) (10624, 48, 1)\n",
-      "mse:0.037431780248880386, mae:0.13626551628112793\n"
+      "test shape: (333, 32, 12, 1) (333, 32, 12, 1)\n",
+      "test shape: (10656, 12, 1) (10656, 12, 1)\n",
+      "mse:0.004790135659277439, mae:0.051230162382125854\n"
      ]
     }
    ],
@@ -450,15 +542,19 @@
     "  --data custom \\\n",
     "  --features M2S \\\n",
     "  --seq_len 256 \\\n",
-    "  --pred_len 48 \\\n",
+    "  --pred_len 12 \\\n",
     "  --e_layers 3 \\\n",
     "  --d_layers 3 \\\n",
     "  --enc_in 12 \\\n",
+    "  --d_model 512 \\\n",
+    "  --d_ff 2048 \\\n",
+    "  --n_heads 16 \\\n",
+    "  --dropout 0.2 \\\n",
     "  --c_out 1 \\\n",
     "  --num_workers 0 \\\n",
     "  --des 'Exp' \\\n",
     "  --K 0 \\\n",
-    "  --learning_rate 3e-4 \\\n",
+    "  --learning_rate 1e-3 \\\n",
     "  --target RSMKs_18_144_72_2ref_2ref \\\n",
     "  --itr 1\n",
     "\"\"\"\n",
@@ -504,7 +600,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f4537246",
+   "id": "e1abba91",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2022-11-28T05:28:20.356399Z",
@@ -518,18 +614,18 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "0b01f395",
+   "id": "0495f56e",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:29.476894Z",
-     "start_time": "2022-11-28T08:48:29.462100Z"
+     "end_time": "2022-11-28T11:07:52.181496Z",
+     "start_time": "2022-11-28T11:07:52.169188Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\"Exchange_ETSformer_custom_ftM2S_sl256_pl48_dm512_nh8_el3_dl3_df2048_K0_lr0.0003_'Exp'_0\""
+       "\"Exchange_ETSformer_custom_ftM2S_sl256_pl12_dm512_nh16_el3_dl3_df2048_K0_lr0.001_'Exp'_0\""
       ]
      },
      "execution_count": 7,
@@ -544,11 +640,11 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "76ee8bff",
+   "id": "3e3feeec",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:29.627830Z",
-     "start_time": "2022-11-28T08:48:29.477662Z"
+     "end_time": "2022-11-28T11:07:52.326810Z",
+     "start_time": "2022-11-28T11:07:52.183063Z"
     }
    },
    "outputs": [
@@ -556,7 +652,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "test 10632\n"
+      "test 10668\n"
      ]
     }
    ],
@@ -567,11 +663,11 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "d2c5d0d4",
+   "id": "4630d105",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.513692Z",
-     "start_time": "2022-11-28T08:48:29.629849Z"
+     "end_time": "2022-11-28T11:08:01.458832Z",
+     "start_time": "2022-11-28T11:07:52.328094Z"
     }
    },
    "outputs": [
@@ -579,7 +675,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "test 10632\n",
+      "test 10668\n",
       "loading model\n"
      ]
     },
@@ -591,7 +687,7 @@
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/332 [00:00<?, ?it/s]"
+       "  0%|          | 0/333 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -601,9 +697,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "test shape: (332, 32, 48, 1) (332, 32, 48, 1)\n",
-      "test shape: (10624, 48, 1) (10624, 48, 1)\n",
-      "mse:0.037431780248880386, mae:0.13626551628112793\n"
+      "test shape: (333, 32, 12, 1) (333, 32, 12, 1)\n",
+      "test shape: (10656, 12, 1) (10656, 12, 1)\n",
+      "mse:0.004790135659277439, mae:0.051230162382125854\n"
      ]
     }
    ],
@@ -614,11 +710,11 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "d2bbb184",
+   "id": "ca0660df",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.526965Z",
-     "start_time": "2022-11-28T08:48:53.514947Z"
+     "end_time": "2022-11-28T11:08:01.475975Z",
+     "start_time": "2022-11-28T11:08:01.460043Z"
     }
    },
    "outputs": [],
@@ -628,28 +724,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "dc7db6a7",
+   "execution_count": 17,
+   "id": "303f36d6",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.647415Z",
-     "start_time": "2022-11-28T08:48:53.528023Z"
+     "end_time": "2022-11-28T11:52:10.925631Z",
+     "start_time": "2022-11-28T11:52:10.840065Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<matplotlib.legend.Legend at 0x7fcbf8343be0>"
+       "<matplotlib.legend.Legend at 0x7f3aa8c88490>"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -659,7 +755,7 @@
     }
    ],
    "source": [
-    "i=990\n",
+    "i=190\n",
     "(batch_x, batch_y, batch_x_mark, batch_y_mark)  = ds[i]\n",
     "l1 = batch_x.shape[0]\n",
     "l2 = batch_y.shape[0]\n",
@@ -672,7 +768,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "fff9cb48",
+   "id": "b86fd6b0",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2022-11-28T07:33:57.703528Z",
@@ -684,7 +780,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a2555d9b",
+   "id": "bb766173",
    "metadata": {},
    "source": [
     "# TODO check index"
@@ -692,7 +788,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "815cdbe5",
+   "id": "49c590e8",
    "metadata": {},
    "source": [
     "- s_end = index + self.seq_len\n",
@@ -703,11 +799,11 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "abc903ba",
+   "id": "12d58ee7",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.789777Z",
-     "start_time": "2022-11-28T08:48:53.648714Z"
+     "end_time": "2022-11-28T11:08:01.743317Z",
+     "start_time": "2022-11-28T11:08:01.597271Z"
     },
     "scrolled": true
    },
@@ -1024,11 +1120,11 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "0dac417e",
+   "id": "1459473b",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.923652Z",
-     "start_time": "2022-11-28T08:48:53.790995Z"
+     "end_time": "2022-11-28T11:08:01.889732Z",
+     "start_time": "2022-11-28T11:08:01.744889Z"
     }
    },
    "outputs": [
@@ -1068,11 +1164,11 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "a6a5dff7",
+   "id": "c443acdd",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.941224Z",
-     "start_time": "2022-11-28T08:48:53.924828Z"
+     "end_time": "2022-11-28T11:08:01.914709Z",
+     "start_time": "2022-11-28T11:08:01.890955Z"
     }
    },
    "outputs": [
@@ -1107,11 +1203,11 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "91a28ab0",
+   "id": "c34d925b",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2022-11-28T08:48:53.977072Z",
-     "start_time": "2022-11-28T08:48:53.942153Z"
+     "end_time": "2022-11-28T11:08:01.938923Z",
+     "start_time": "2022-11-28T11:08:01.915802Z"
     }
    },
    "outputs": [
@@ -1134,7 +1230,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "35053a3c",
+   "id": "a1bbd05b",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -1142,7 +1238,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "87fdb36f",
+   "id": "d99af325",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -1150,7 +1246,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "cf203a63",
+   "id": "234c99f3",
    "metadata": {},
    "outputs": [],
    "source": []