From 044a8c90cff2ff7a8eb26d488f20f23a537790c3 Mon Sep 17 00:00:00 2001 From: Eric Kenji Lee Date: Wed, 22 Mar 2023 21:46:06 -0400 Subject: [PATCH] Bug fix in notebook; added full_data.npy to top directory --- STAR_Protocol.ipynb | 1004 ++++++++++++++++++++++--------------------- full_data.npy | Bin 0 -> 240128 bytes pyproject.toml | 2 +- 3 files changed, 515 insertions(+), 491 deletions(-) create mode 100644 full_data.npy diff --git a/STAR_Protocol.ipynb b/STAR_Protocol.ipynb index 52f542f..27ec2a6 100644 --- a/STAR_Protocol.ipynb +++ b/STAR_Protocol.ipynb @@ -13,7 +13,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 3, "id": "11bea910-8418-4248-9a28-2d474c3fe468", "metadata": { "tags": [] @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "id": "4a98efe7-6528-4b31-8226-45d7a50adc51", "metadata": {}, "outputs": [ @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "c01efadf-4699-4f41-86ba-9ad07d935646", "metadata": {}, "outputs": [], @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "id": "63e1754a-bbf3-4382-b033-3ab701c27016", "metadata": {}, "outputs": [ @@ -87,7 +87,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 7, "id": "849d6319-719d-4f35-8c56-d5545ac9af32", "metadata": { "tags": [] @@ -111,17 +111,17 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "id": "1a04d04c-c726-47a3-9d5c-95d6ca58af5a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 9, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, @@ -153,7 +153,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 9, "id": "47ab6453-00f8-4cc1-a2ce-5bfb44b16db3", "metadata": { "tags": [] @@ -178,7 +178,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 10, "id": "40018130-22c1-4e04-bfea-c47e44c1adc4", "metadata": {}, "outputs": [ @@ -200,7 +200,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 11, "id": "9c51539c-1087-4c92-a4b0-955176701a3a", "metadata": {}, "outputs": [ @@ -209,326 +209,56 @@ "output_type": "stream", "text": [ "Fitting 5 folds for each of 135 candidates, totalling 675 fits\n", - "[CV 4/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 4/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.4s\n", - "[CV 1/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 1/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.909 total time= 1.3s\n", - "[CV 4/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 4/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.8s\n", - "[CV 4/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 4/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.885 total time= 0.2s\n", - "[CV 2/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 2/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.6s\n", - "[CV 1/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 1/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.9s\n", - "[CV 3/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 3/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.4s\n", - "[CV 2/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 2/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.898 total time= 0.3s\n", - "[CV 5/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 5/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.931 total time= 0.3s\n", - "[CV 2/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 2/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.7s\n", - "[CV 2/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 2/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.9s\n", - "[CV 4/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 4/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.954 total time= 1.5s\n", - "[CV 2/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 2/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.3s\n", - "[CV 5/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 5/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.885 total time= 0.5s\n", - "[CV 3/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 3/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.931 total time= 0.9s\n", - "[CV 1/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 1/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 2.0s\n", - "[CV 4/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 4/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 2.1s\n", - "[CV 2/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 2/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.909 total time= 1.2s\n", - "[CV 5/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 5/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.8s\n", - "[CV 2/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 2/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.909 total time= 1.0s\n", - "[CV 5/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 5/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.4s\n", - "[CV 3/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 3/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.4s\n", - "[CV 1/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 1/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.3s\n", - "[CV 2/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 2/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", - "[CV 3/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 3/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 1/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 1/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.875 total time= 0.6s\n", - "[CV 4/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 4/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.6s\n", - "[CV 5/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 5/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.9s\n", - "[CV 3/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 3/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 1.7s\n", - "[CV 4/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 4/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 0.7s\n", - "[CV 2/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 2/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.909 total time= 1.6s\n", - "[CV 1/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 1/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.5s\n", - "[CV 3/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 3/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 0.9s\n", - "[CV 1/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 1/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", - "[CV 4/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 4/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s[CV 1/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 1/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.5s\n", - "[CV 4/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 4/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.920 total time= 0.9s\n", - "[CV 5/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 5/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.966 total time= 1.2s\n", - "[CV 3/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 3/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 2.5s\n", - "[CV 4/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 4/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 2/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 2/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 2.3s\n", + "[CV 5/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 5/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", + "[CV 5/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 5/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.4s\n", + "[CV 2/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 2/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.0s\n", + "[CV 5/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 5/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.966 total time= 1.7s\n", + "[CV 5/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 5/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", + "[CV 3/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 3/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 1/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 1/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.4s\n", "[CV 1/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 1/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.9s\n", + "[CV 1/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.6s\n", "[CV 3/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 3/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.931 total time= 1.6s\n", + "[CV 3/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.931 total time= 0.8s\n", "[CV 1/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 1/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.3s\n", + "[CV 1/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", "[CV 4/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 4/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.885 total time= 0.4s\n", + "[CV 4/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.885 total time= 0.3s\n", "[CV 2/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 2/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.932 total time= 1.0s\n", + "[CV 2/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.932 total time= 0.6s\n", "[CV 4/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 4/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.5s\n", + "[CV 4/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 0.9s\n", "[CV 2/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 2/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 2.1s\n", + "[CV 2/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 1.8s\n", "[CV 1/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 1/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.9s\n", + "[CV 1/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.8s\n", "[CV 4/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 4/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", - "[CV 3/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 3/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 1/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 1/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.898 total time= 0.5s\n", - "[CV 1/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 1/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.8s\n", - "[CV 3/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 3/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.920 total time= 1.0s\n", - "[CV 1/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 1/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.886 total time= 0.3s\n", - "[CV 5/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 5/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", - "[CV 2/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 2/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 0.6s\n", - "[CV 4/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 4/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.1s\n", - "[CV 2/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 2/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 2.0s\n", - "[CV 1/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 1/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.886 total time= 0.9s\n", - "[CV 4/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 4/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.931 total time= 1.2s\n", - "[CV 3/5; 41/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 3/5; 41/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 1/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 1/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.4s\n", - "[CV 1/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 1/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.7s\n", - "[CV 4/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 4/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 1/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 1/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", - "[CV 4/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 4/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 2/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 2/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 0.5s\n", - "[CV 2/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 2/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.5s\n", - "[CV 4/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 4/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 0.9s[CV 5/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 5/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.943 total time= 0.5s\n", - "[CV 2/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 2/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 1.3s\n", - "[CV 5/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 5/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.8s\n", - "[CV 5/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 5/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", - "[CV 3/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 3/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.7s\n", - "[CV 2/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 2/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.9s\n", - "[CV 5/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 5/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.4s\n", - "[CV 3/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 3/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.897 total time= 0.3s\n", - "[CV 1/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 1/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.7s\n", - "[CV 4/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 4/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", - "[CV 5/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 5/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.954 total time= 1.2s\n", - "[CV 3/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 3/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.931 total time= 2.2s\n", - "[CV 1/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 1/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.898 total time= 1.5s\n", - "[CV 4/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 4/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.7s\n", - "[CV 4/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 4/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", - "[CV 2/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 2/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.909 total time= 0.5s\n", - "[CV 5/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 5/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.6s\n", - "[CV 1/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 1/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.1s\n", - "[CV 4/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 4/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 2.0s\n", - "[CV 4/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 4/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 2/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 2/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", - "[CV 4/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 4/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", - "[CV 3/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 3/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.6s\n", - "[CV 5/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 5/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.954 total time= 1.1s\n", - "[CV 3/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 3/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 2.1s\n", - "[CV 3/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 3/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.920 total time= 1.0s\n", - "[CV 2/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 2/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 1.6s\n", - "[CV 5/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 5/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.931 total time= 0.4s\n", - "[CV 1/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 1/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.875 total time= 0.9s\n", - "[CV 4/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 4/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 1.6s\n", - "[CV 2/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 2/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 0.8s\n", - "[CV 5/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 5/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 1.3s\n", - "[CV 2/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 2/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.909 total time= 0.7s\n", - "[CV 5/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 5/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.1s\n", - "[CV 5/5; 59/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 5/5; 59/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.931 total time= 0.8s[CV 1/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 1/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 1.0s\n", - "[CV 4/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 4/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.943 total time= 1.2s\n", - "[CV 2/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 2/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.932 total time= 2.4s\n", - "[CV 3/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 3/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.966 total time= 1.0s\n", - "[CV 1/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 1/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.875 total time= 2.2s\n", - "[CV 5/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 5/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.954 total time= 0.5s\n", - "[CV 1/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 1/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.864 total time= 1.5s\n", - "[CV 4/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 4/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 2.2s\n", - "[CV 3/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 3/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.5s\n", - "[CV 1/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 1/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 2.1s\n", - "[CV 2/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 2/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.9s\n", - "[CV 5/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 5/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", - "[CV 4/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 4/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.862 total time= 0.2s\n", - "[CV 2/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 2/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", - "[CV 2/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 2/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.8s\n", - "[CV 5/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 5/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 3/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 3/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.920 total time= 0.2s\n", - "[CV 1/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 1/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 0.6s\n", - "[CV 2/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 2/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 1.0s\n", - "[CV 5/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 5/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.5s\n", - "[CV 5/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 5/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.931 total time= 0.3s\n", - "[CV 3/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 3/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.6s\n", - "[CV 4/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 4/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 1/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 1/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.864 total time= 1.6s\n", - "[CV 4/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 4/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.4s\n", - "[CV 5/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 5/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.6s\n", - "[CV 3/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 3/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.6s\n", - "[CV 3/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 3/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.954 total time= 0.5s\n", - "[CV 5/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 5/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 0.9s\n", - "[CV 3/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 3/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.931 total time= 0.2s\n", - "[CV 1/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 1/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.3s\n", - "[CV 1/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 1/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.4s\n", - "[CV 4/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 4/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 0.7s\n", - "[CV 2/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 2/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", - "[CV 5/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 5/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.943 total time= 0.1s[CV 3/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 3/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.5s\n", - "[CV 3/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 3/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.3s\n", - "[CV 1/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 1/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 2.4s\n", - "[CV 4/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 4/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.908 total time= 0.6s\n", - "[CV 5/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 5/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 3/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 3/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 2.2s\n", - "[CV 4/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 4/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.954 total time= 1.1s\n", - "[CV 2/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 2/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.909 total time= 2.2s\n", - "[CV 5/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 5/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.8s\n", - "[CV 2/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 2/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 2.0s\n", - "[CV 5/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 5/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 2.2s\n", - "[CV 3/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 3/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.954 total time= 1.2s\n", - "[CV 1/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 1/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.875 total time= 0.2s\n", + "[CV 4/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", "[CV 2/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", "[CV 2/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", "[CV 5/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", "[CV 5/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.920 total time= 0.2s\n", "[CV 3/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 3/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 3/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.920 total time= 0.4s\n", "[CV 3/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 3/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.931 total time= 0.8s\n", + "[CV 3/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.931 total time= 0.7s\n", "[CV 1/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 1/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 1.3s\n", + "[CV 1/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 1.2s\n", "[CV 4/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", "[CV 4/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.908 total time= 0.6s\n", "[CV 1/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 1/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.909 total time= 1.5s\n", + "[CV 1/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.909 total time= 1.3s\n", "[CV 4/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 4/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 2.2s\n", + "[CV 4/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 1.8s\n", "[CV 3/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 3/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.2s\n", + "[CV 3/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", "[CV 1/5; 41/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42\n", "[CV 1/5; 41/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.875 total time= 0.2s\n", "[CV 2/5; 41/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42\n", @@ -540,228 +270,498 @@ "[CV 3/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", "[CV 3/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.931 total time= 0.7s\n", "[CV 1/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 1/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 1.5s\n", + "[CV 1/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 1.3s\n", "[CV 4/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 4/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.4s\n", + "[CV 4/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.3s\n", "[CV 5/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", "[CV 5/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.954 total time= 0.5s\n", "[CV 3/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 3/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 1.4s\n", + "[CV 3/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 1.1s\n", "[CV 2/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 2/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.4s\n", - "[CV 5/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 5/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 0.7s\n", - "[CV 3/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 3/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.920 total time= 0.1s\n", - "[CV 1/5; 57/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 1/5; 57/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.3s[CV 3/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 3/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.897 total time= 1.0s\n", - "[CV 1/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 1/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.909 total time= 1.7s\n", - "[CV 5/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 5/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.966 total time= 2.4s\n", + "[CV 2/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.4s[CV 1/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 1/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 4/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 4/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.920 total time= 0.4s\n", + "[CV 3/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 3/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", + "[CV 1/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 1/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 2/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 2/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.864 total time= 0.2s\n", + "[CV 5/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 5/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 3/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 3/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.4s\n", + "[CV 2/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 2/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.7s\n", "[CV 4/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 4/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.4s\n", - "[CV 1/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 1/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.886 total time= 0.3s\n", - "[CV 4/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 4/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.874 total time= 0.3s\n", + "[CV 4/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", + "[CV 2/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 2/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 5/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 5/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.931 total time= 0.2s\n", "[CV 3/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 3/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.897 total time= 0.7s\n", + "[CV 3/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.897 total time= 0.4s\n", "[CV 3/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 3/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 1.0s\n", + "[CV 3/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 0.6s\n", + "[CV 1/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 1/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 1.6s\n", + "[CV 5/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 5/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.5s\n", + "[CV 3/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 3/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.3s\n", + "[CV 1/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 1/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.3s\n", + "[CV 2/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 2/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 4/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 4/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 2/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 2/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.909 total time= 0.5s\n", + "[CV 2/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 2/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.8s\n", + "[CV 5/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 5/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", + "[CV 3/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 3/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 1/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 1/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.898 total time= 0.4s\n", + "[CV 1/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 1/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.6s\n", + "[CV 4/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 4/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.9s\n", + "[CV 2/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 2/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 5/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 5/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 3/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 3/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.943 total time= 0.6s\n", + "[CV 5/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 5/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.954 total time= 0.9s\n", + "[CV 3/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 3/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 1.8s\n", + "[CV 3/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 3/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.920 total time= 0.8s\n", + "[CV 1/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 1/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.864 total time= 1.5s\n", + "[CV 4/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 4/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", + "[CV 4/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 4/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 0.7s[CV 3/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 3/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.897 total time= 0.4s\n", + "[CV 1/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 1/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.909 total time= 1.1s\n", + "[CV 4/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 4/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.931 total time= 1.7s\n", + "[CV 2/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 2/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.898 total time= 1.0s\n", + "[CV 5/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 5/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.5s\n", "[CV 5/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 5/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.5s\n", + "[CV 5/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.8s\n", "[CV 3/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 3/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.3s\n", + "[CV 3/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", "[CV 1/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 1/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 1.0s\n", + "[CV 1/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 0.8s\n", "[CV 2/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 2/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 1.6s\n", + "[CV 2/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.9s\n", "[CV 5/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 5/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.6s\n", + "[CV 5/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.3s\n", "[CV 5/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", "[CV 5/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", "[CV 3/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 3/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.6s\n", - "[CV 4/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 4/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.931 total time= 0.9s\n", - "[CV 2/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 2/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 1.6s\n", + "[CV 3/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 3/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 3/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.931 total time= 0.8s\n", + "[CV 1/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 1/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.875 total time= 1.4s\n", "[CV 5/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 5/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.931 total time= 0.6s\n", + "[CV 5/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.931 total time= 0.4s\n", "[CV 1/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 1/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.875 total time= 1.0s\n", + "[CV 1/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.875 total time= 0.9s\n", "[CV 4/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 4/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 1.4s\n", + "[CV 4/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 1.3s\n", "[CV 3/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 3/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.1s\n", - "[CV 1/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 1/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 2.0s\n", + "[CV 3/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 1.0s\n", + "[CV 2/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 2/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 1.7s\n", "[CV 5/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 5/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.6s\n", - "[CV 1/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 1/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.2s\n", - "[CV 4/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 4/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.7s\n", - "[CV 3/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 3/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", - "[CV 3/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 3/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", - "[CV 1/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 1/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", - "[CV 5/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 5/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.4s\n", - "[CV 1/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 1/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 0.8s\n", - "[CV 4/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 4/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.931 total time= 1.3s\n", - "[CV 3/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 3/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.954 total time= 0.7s\n", - "[CV 1/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 1/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.864 total time= 0.1s\n", - "[CV 4/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", - "[CV 4/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.897 total time= 0.1s\n", - "[CV 2/5; 57/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 2/5; 57/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.898 total time= 0.3s[CV 2/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", - "[CV 2/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.5s\n", - "[CV 5/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 5/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.9s\n", - "[CV 3/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 3/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.8s\n", - "[CV 1/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 1/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.898 total time= 0.3s\n", - "[CV 2/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 2/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.864 total time= 0.3s\n", - "[CV 3/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 3/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 1/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 1/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.6s\n", - "[CV 5/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 5/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.6s\n", - "[CV 1/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 1/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.3s\n", - "[CV 4/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 4/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 2.4s\n", - "[CV 2/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 2/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.909 total time= 1.6s\n", - "[CV 5/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 5/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 2.2s\n", - "[CV 3/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 3/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.9s\n", - "[CV 1/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 1/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.3s\n", - "[CV 2/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 2/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 5/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.5s\n", + "[CV 2/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 2/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.909 total time= 1.1s\n", + "[CV 5/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 5/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.6s\n", + "[CV 4/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 4/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.9s\n", + "[CV 1/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 1/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 4/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 4/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 2/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 2/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 0.3s\n", + "[CV 1/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 1/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 3/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 3/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 0.7s\n", + "[CV 1/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 1/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 4/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 4/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 2/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 2/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.898 total time= 0.3s\n", + "[CV 3/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 3/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.954 total time= 0.4s\n", + "[CV 1/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 1/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.886 total time= 0.9s\n", + "[CV 4/5; 57/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 4/5; 57/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.931 total time= 0.3s\n", + "[CV 5/5; 58/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 5/5; 58/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.4s[CV 1/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 1/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 0.4s\n", + "[CV 4/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 4/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.943 total time= 0.7s\n", + "[CV 3/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 3/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 1.7s\n", + "[CV 4/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 4/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.7s\n", + "[CV 2/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 2/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 1.4s\n", + "[CV 4/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 4/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.4s\n", + "[CV 5/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 5/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.954 total time= 0.6s\n", + "[CV 3/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 3/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.931 total time= 1.5s\n", + "[CV 1/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 1/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.898 total time= 0.9s\n", + "[CV 4/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 4/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.943 total time= 1.3s\n", "[CV 3/5; 21/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 3/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.3s\n", + "[CV 3/5; 21/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", "[CV 1/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", "[CV 1/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.875 total time= 0.5s\n", "[CV 4/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", "[CV 4/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", - "[CV 5/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 5/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.9s\n", - "[CV 3/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 3/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 1.7s\n", - "[CV 4/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 4/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 0.8s\n", - "[CV 2/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 2/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.898 total time= 1.3s\n", - "[CV 5/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 5/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.966 total time= 0.6s\n", - "[CV 2/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 2/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.5s\n", - "[CV 5/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 5/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 2.1s\n", - "[CV 2/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 2/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.909 total time= 1.2s\n", - "[CV 5/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 5/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.6s\n", + "[CV 1/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 1/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.0s\n", + "[CV 4/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 4/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.4s\n", + "[CV 2/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 2/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.909 total time= 0.9s\n", + "[CV 5/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 5/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.4s\n", + "[CV 3/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 3/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.3s\n", + "[CV 1/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 1/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 2/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 2/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 4/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 4/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 2/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 2/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.909 total time= 0.5s\n", + "[CV 2/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 2/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 0.8s\n", + "[CV 5/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 5/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", + "[CV 3/5; 41/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 3/5; 41/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 1/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 1/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.5s\n", + "[CV 1/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 1/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.7s\n", "[CV 2/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", "[CV 2/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.909 total time= 0.9s\n", "[CV 5/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 5/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.6s\n", - "[CV 2/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 2/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 1.3s\n", - "[CV 4/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 4/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.3s\n", - "[CV 1/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 1/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 0.7s\n", - "[CV 4/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 4/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.1s\n", - "[CV 2/5; 59/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 2/5; 59/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.920 total time= 0.7s\n", - "[CV 5/5; 60/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 5/5; 60/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.931 total time= 1.1s[CV 2/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 2/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 1.0s\n", - "[CV 2/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 2/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.7s\n", - "[CV 4/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 4/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.931 total time= 2.4s\n", - "[CV 2/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 2/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.898 total time= 1.4s\n", - "[CV 5/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 5/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 2.4s\n", - "[CV 1/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 1/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.864 total time= 2.2s\n", - "[CV 4/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 4/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.908 total time= 0.9s\n", + "[CV 5/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.2s\n", + "[CV 5/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 5/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 0.7s\n", + "[CV 3/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 3/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.931 total time= 0.2s\n", + "[CV 1/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 1/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.3s\n", + "[CV 1/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 1/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.4s\n", + "[CV 3/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 3/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.954 total time= 0.7s\n", + "[CV 3/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 3/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.920 total time= 0.1s[CV 2/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 2/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 2/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 2/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.7s\n", + "[CV 5/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 5/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.1s\n", + "[CV 4/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 4/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.885 total time= 0.2s\n", + "[CV 2/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 2/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.4s\n", + "[CV 1/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 1/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.875 total time= 0.7s\n", + "[CV 3/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 3/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.1s\n", + "[CV 1/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 1/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 4/5; 11/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 4/5; 11/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.874 total time= 0.2s\n", + "[CV 2/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 2/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.886 total time= 0.4s\n", + "[CV 2/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 2/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.6s\n", + "[CV 4/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 4/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.954 total time= 0.8s\n", + "[CV 2/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 2/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 5/5; 16/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 5/5; 16/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.885 total time= 0.5s\n", + "[CV 3/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 3/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.931 total time= 0.6s\n", "[CV 5/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 5/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.943 total time= 1.5s\n", + "[CV 5/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.943 total time= 0.9s\n", "[CV 3/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 3/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 2.2s\n", - "[CV 3/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 3/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.931 total time= 0.9s\n", - "[CV 1/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 1/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.875 total time= 1.6s\n", + "[CV 3/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 1.8s\n", + "[CV 4/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 4/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.931 total time= 0.8s\n", + "[CV 2/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 2/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 1.4s\n", "[CV 4/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 4/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", + "[CV 4/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.908 total time= 0.4s\n", "[CV 5/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 5/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.8s\n", + "[CV 5/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.7s\n", "[CV 3/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 3/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.931 total time= 1.4s\n", + "[CV 3/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.931 total time= 1.3s\n", "[CV 1/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 1/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.909 total time= 1.0s\n", + "[CV 1/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.909 total time= 0.9s\n", "[CV 4/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", - "[CV 4/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.5s\n", - "[CV 4/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", - "[CV 4/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", - "[CV 2/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 2/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.909 total time= 0.6s\n", - "[CV 2/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 2/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.909 total time= 1.0s\n", - "[CV 5/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", - "[CV 5/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 1.2s\n", + "[CV 4/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.3s\n", + "[CV 3/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 3/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 1/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 1/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.875 total time= 0.5s\n", + "[CV 1/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 1/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.886 total time= 0.7s\n", + "[CV 4/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 4/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.931 total time= 1.1s\n", "[CV 4/5; 41/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42\n", "[CV 4/5; 41/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.862 total time= 0.2s\n", "[CV 2/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", - "[CV 2/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.909 total time= 0.4s\n", + "[CV 2/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.909 total time= 0.5s\n", "[CV 2/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", "[CV 2/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.7s\n", "[CV 5/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", - "[CV 5/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", + "[CV 5/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.9s\n", + "[CV 3/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 3/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", + "[CV 1/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 1/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.920 total time= 0.3s\n", + "[CV 5/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 5/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.3s[CV 4/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 4/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 3/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 3/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 0.7s\n", + "[CV 1/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 1/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 1.6s\n", + "[CV 4/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 4/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", + "[CV 5/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 5/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.7s\n", + "[CV 3/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 3/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 1.5s\n", + "[CV 4/5; 13/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 4/5; 13/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.954 total time= 0.6s\n", + "[CV 2/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 2/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.909 total time= 1.5s\n", + "[CV 4/5; 17/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 4/5; 17/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.908 total time= 0.5s\n", + "[CV 1/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 1/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.2s\n", + "[CV 4/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 4/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.943 total time= 1.9s\n", + "[CV 2/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 2/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.909 total time= 1.0s\n", + "[CV 5/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 5/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.4s\n", + "[CV 3/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 3/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.920 total time= 0.9s\n", + "[CV 1/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 1/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 4/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 4/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 2/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 2/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 0.6s\n", + "[CV 4/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 4/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 0.9s\n", + "[CV 1/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 1/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 1.8s\n", + "[CV 4/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 4/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 5/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 5/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.8s\n", + "[CV 3/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 3/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 1.6s\n", + "[CV 5/5; 43/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 5/5; 43/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.7s\n", + "[CV 3/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 3/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.3s\n", + "[CV 3/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 3/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.954 total time= 0.5s\n", + "[CV 1/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 1/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 1.0s\n", + "[CV 4/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 4/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.3s\n", + "[CV 5/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 5/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.4s\n", + "[CV 3/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 3/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.966 total time= 1.0s\n", + "[CV 2/5; 58/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 2/5; 58/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.3s\n", + "[CV 5/5; 59/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 5/5; 59/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.931 total time= 0.5s\n", + "[CV 3/5; 61/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 3/5; 61/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.931 total time= 0.2s\n", + "[CV 1/5; 62/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 1/5; 62/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 0.4s\n", + "[CV 2/5; 63/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 2/5; 63/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 5/5; 64/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 5/5; 64/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 0.7s[CV 2/5; 2/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 2/5; 2/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.909 total time= 0.4s\n", + "[CV 5/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 5/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.966 total time= 0.7s\n", + "[CV 2/5; 5/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 2/5; 5/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.932 total time= 1.6s\n", + "[CV 3/5; 8/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 3/5; 8/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.966 total time= 0.7s\n", + "[CV 1/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 1/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.875 total time= 1.5s\n", + "[CV 5/5; 12/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 5/5; 12/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.954 total time= 0.4s\n", + "[CV 1/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 1/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.864 total time= 0.8s\n", + "[CV 4/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 4/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 1.5s\n", + "[CV 3/5; 18/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 3/5; 18/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 0.9s\n", + "[CV 1/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 1/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.920 total time= 1.8s\n", + "[CV 5/5; 22/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 5/5; 22/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.5s\n", + "[CV 5/5; 23/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 5/5; 23/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.8s\n", + "[CV 3/5; 25/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 3/5; 25/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.954 total time= 1.4s\n", + "[CV 4/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 4/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.920 total time= 0.7s\n", + "[CV 2/5; 30/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 2/5; 30/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.898 total time= 1.2s\n", + "[CV 5/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 5/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.966 total time= 0.5s\n", + "[CV 2/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 2/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.3s\n", + "[CV 5/5; 35/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 5/5; 35/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 1.7s\n", + "[CV 1/5; 39/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 1/5; 39/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.1s\n", + "[CV 4/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 4/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.6s\n", + "[CV 3/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 3/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 1.0s\n", "[CV 2/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", "[CV 2/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.920 total time= 0.2s\n", "[CV 5/5; 46/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", "[CV 5/5; 46/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", "[CV 3/5; 47/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 3/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.6s\n", - "[CV 4/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", - "[CV 4/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.931 total time= 0.5s\n", - "[CV 1/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", - "[CV 1/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.909 total time= 1.3s\n", - "[CV 5/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", - "[CV 5/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.3s\n", - "[CV 5/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", - "[CV 5/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.5s\n", - "[CV 3/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", - "[CV 3/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.966 total time= 1.1s\n", - "[CV 4/5; 58/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", - "[CV 4/5; 58/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.943 total time= 0.5s\n", - "[CV 2/5; 60/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", - "[CV 2/5; 60/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.920 total time= 1.1s\n", - "[CV 4/5; 62/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42\n", - "[CV 4/5; 62/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.931 total time= 0.5s" + "[CV 3/5; 47/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.954 total time= 0.3s\n", + "[CV 2/5; 48/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 2/5; 48/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 4/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 4/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 0.7s\n", + "[CV 2/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 2/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.898 total time= 0.2s\n", + "[CV 5/5; 51/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 5/5; 51/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.943 total time= 0.2s\n", + "[CV 3/5; 52/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 3/5; 52/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.3s\n", + "[CV 4/5; 53/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 4/5; 53/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.4s\n", + "[CV 2/5; 55/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 2/5; 55/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 0.9s\n", + "[CV 1/5; 58/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 1/5; 58/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.875 total time= 0.4s\n", + "[CV 3/5; 59/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 3/5; 59/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.5s\n", + "[CV 1/5; 61/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 1/5; 61/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.886 total time= 0.2s\n", + "[CV 4/5; 61/135] START learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 4/5; 61/135] END learning_rate=0.3, max_depth=5, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.920 total time= 0.2s[CV 3/5; 1/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 3/5; 1/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 1/5; 3/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 1/5; 3/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.909 total time= 0.7s\n", + "[CV 4/5; 4/135] START learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 4/5; 4/135] END learning_rate=0.1, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.931 total time= 1.1s\n", + "[CV 3/5; 6/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 3/5; 6/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.908 total time= 0.2s\n", + "[CV 1/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 1/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.886 total time= 0.4s\n", + "[CV 5/5; 7/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 5/5; 7/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.943 total time= 0.4s\n", + "[CV 1/5; 9/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 1/5; 9/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.875 total time= 1.0s\n", + "[CV 4/5; 10/135] START learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 4/5; 10/135] END learning_rate=0.1, max_depth=3, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.943 total time= 1.5s\n", + "[CV 2/5; 14/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 2/5; 14/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.909 total time= 0.8s\n", + "[CV 5/5; 15/135] START learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 5/5; 15/135] END learning_rate=0.1, max_depth=3, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.943 total time= 1.5s\n", + "[CV 2/5; 19/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 2/5; 19/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 1.2s\n", + "[CV 5/5; 20/135] START learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 5/5; 20/135] END learning_rate=0.1, max_depth=5, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 2.0s\n", + "[CV 3/5; 24/135] START learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 3/5; 24/135] END learning_rate=0.1, max_depth=5, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.954 total time= 1.1s\n", + "[CV 1/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 1/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.875 total time= 0.2s\n", + "[CV 4/5; 26/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 4/5; 26/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.862 total time= 0.2s\n", + "[CV 2/5; 27/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 2/5; 27/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.920 total time= 0.4s\n", + "[CV 2/5; 28/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42\n", + "[CV 2/5; 28/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=50, seed=42;, score=0.909 total time= 0.6s\n", + "[CV 5/5; 29/135] START learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 5/5; 29/135] END learning_rate=0.1, max_depth=5, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.943 total time= 0.9s\n", + "[CV 3/5; 31/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42\n", + "[CV 3/5; 31/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=10, seed=42;, score=0.920 total time= 0.2s\n", + "[CV 1/5; 32/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42\n", + "[CV 1/5; 32/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=25, seed=42;, score=0.898 total time= 0.6s\n", + "[CV 2/5; 33/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42\n", + "[CV 2/5; 33/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=50, seed=42;, score=0.920 total time= 0.9s\n", + "[CV 5/5; 34/135] START learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 5/5; 34/135] END learning_rate=0.1, max_depth=10, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.954 total time= 1.3s\n", + "[CV 5/5; 36/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42\n", + "[CV 5/5; 36/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=10, seed=42;, score=0.931 total time= 0.2s\n", + "[CV 3/5; 37/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42\n", + "[CV 3/5; 37/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=25, seed=42;, score=0.920 total time= 0.5s\n", + "[CV 4/5; 38/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42\n", + "[CV 4/5; 38/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=50, seed=42;, score=0.943 total time= 0.8s\n", + "[CV 2/5; 40/135] START learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42\n", + "[CV 2/5; 40/135] END learning_rate=0.1, max_depth=10, min_child_weight=2.5, n_estimators=200, seed=42;, score=0.920 total time= 1.5s\n", + "[CV 5/5; 42/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 5/5; 42/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.931 total time= 0.5s\n", + "[CV 1/5; 44/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42\n", + "[CV 1/5; 44/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=100, seed=42;, score=0.875 total time= 0.9s\n", + "[CV 4/5; 45/135] START learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42\n", + "[CV 4/5; 45/135] END learning_rate=0.1, max_depth=10, min_child_weight=5.0, n_estimators=200, seed=42;, score=0.954 total time= 1.3s\n", + "[CV 2/5; 49/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42\n", + "[CV 2/5; 49/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=100, seed=42;, score=0.920 total time= 0.7s\n", + "[CV 5/5; 50/135] START learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42\n", + "[CV 5/5; 50/135] END learning_rate=0.3, max_depth=3, min_child_weight=1.0, n_estimators=200, seed=42;, score=0.954 total time= 1.1s\n", + "[CV 4/5; 54/135] START learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42\n", + "[CV 4/5; 54/135] END learning_rate=0.3, max_depth=3, min_child_weight=2.5, n_estimators=100, seed=42;, score=0.943 total time= 0.6s\n", + "[CV 1/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 1/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.864 total time= 0.1s\n", + "[CV 4/5; 56/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42\n", + "[CV 4/5; 56/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=10, seed=42;, score=0.897 total time= 0.2s\n", + "[CV 2/5; 57/135] START learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42\n", + "[CV 2/5; 57/135] END learning_rate=0.3, max_depth=3, min_child_weight=5.0, n_estimators=25, seed=42;, score=0.898 total time= 0.3s" ] } ], @@ -773,7 +773,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 12, "id": "a19bc578-e924-42a7-8001-fa9beabb02b0", "metadata": {}, "outputs": [ @@ -795,10 +795,18 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 13, "id": "24f47f5d-3065-4b95-b65a-35d5aa4c528d", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Pass `objective` as keyword args.\n" + ] + } + ], "source": [ "import shap\n", "import xgboost as xgb\n", @@ -810,10 +818,17 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 15, "id": "ea03a5fd-7e58-48c0-ad10-0d98327fc29e", "metadata": {}, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ntree_limit is deprecated, use `iteration_range` or model slicing instead.\n" + ] + }, { "data": { "image/png": "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\n", @@ -826,6 +841,7 @@ } ], "source": [ + "import matplotlib as mpl\n", "umap_cmap = mpl.colors.ListedColormap(colors, name='umap_cmap')\n", "shap_values = explainer.shap_values(umap_df['waveform'].tolist())\n", "shap.summary_plot(shap_values, color = umap_cmap)" @@ -833,7 +849,7 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 16, "id": "9165be98-38b6-4aa8-8f79-614158214ed2", "metadata": { "tags": [] @@ -842,6 +858,14 @@ "source": [ "umap_df.to_csv('umap_df.csv')" ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8b9d1291-014a-4567-949c-927760f1543e", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { diff --git a/full_data.npy b/full_data.npy new file mode 100644 index 0000000000000000000000000000000000000000..23eab4b31594e093a64fd15aecddf27cb521b39e GIT binary patch literal 240128 zcmbSS_di$f`$xzsLP`lyb|p!oTq>l6@TP=hMIl*9lC10%8QFX9y)Jw2y;rvE3Jt!m z&%f|Jzub>=&TscQ*L6MD{aNn62MUjgiL8j;aqH@t>zHwiv2$P37v&aU=hlB^W?}Zs zx*3%Oja(vyMvPHI>0 z@JC^bw*ksPmB@49IsA9<| z_d!ODER7t-5PWf#eU;*U6#h3gQBZL+76*QucONm&Y&DX@%9FMw_4N5VbN%-CR zq9QS87M}g>`_qjp8|h=YKi|8RgD$sqCY)Mx@wZ~9w5C=b-t=Ylwx7+#FYoq0Q7L30 zlZ5;bgP#YopGj@Az8Qi~hGzv?M0zpq!>UP>+5+zAm4_;ktzx05(dXU5dDLM46F#0b zfHQnIzt=3rqd`?np15-j#OOT^Hx6zGB00yGkKDU}&O_OZ*{d6b&iB;&o$H2 zJZhw!3jt*^($D5HfTZSJ_|>HZIO2u2PWPffv*@XrLqq`7dds+t);Ypt$AsR$GA*ER zHNEv#z!(*LZD$-a9kJ|e?ip@FZyX->dX!k@k11EVhlln)Bb}{UPpxer4(yjr5se1n zOxL<67hedDlkrd{91TUeXX?HmxkGU-gY1(`SO~5^i4+~U9D-4^AMUab`J=;D!BwG~ z*|?ehEc0GcI{NY?yVTQPiGcIBFu%Lf}#u3?loYlM?mk!8Qi4%=BTF5TyF z#;~2a8!tY%;Xs7l#I?sh7;-bKWQ@TZNqQw5Pgl5N(XA%~e`wt?+uX;kzbg<=N-;2N zQ0L+@TZ*$FS1}e-U7jVSD#O40Tfgr`m!nJnK<6##3UnI(68yNg0$rxmdF3uwpk_;j z{j+1$I5;Li*B8@)%6VGNoYZ4@_0iqzcO|oER&|M?)P51GJ*ThHh%I7s$g@!%p*j3b zoKK-7HjNC=X%=WhN3rHu@!ZaGAKp*UKR(jci8K_aRw<>L@a?nsM73MhNJEqUTl`50 zuAZB;qpQ!xw7nhS+wJja>T7q}_^<~`t}}Aa&$_{aqcOJG$;drhMmVdj_c-MG;z7(RPrFDRo1%!kGeM_B7X-9KTBkFg#;X5OFr zcD)|ND}*0@POSqTemyIe`*q-wOQa(iRST6ZN^0ctHE^e|?Nk0p6=>hm)cf>bCHxdS zkmy}s4*s0mMv@67@a`B@S!F;WaPjK2+)m5`7e`)aBFAhvIW^o9!I%#0x@@_$+bN(k zOHog`m>nnzt$nUqN~9L0!~qZ&*L$saS7m3`GnY!J?1MkjS*{5XBoe zlr%eCctGqSMAIKUFT|Pwo4HZf1hk7F`1S7jvpvb^*(9Pyd-NNcCF!3Ny|RWT@a}H8 zz!bI^s2|f2Z6fsX#gy2_DIkJ>9TdFNFqJM=d@Oz(+Z_~W!CW9ickC0PxE*+~N+c}SN&eYYRX8clU|B6}hF z{e=$+yxpLi$R{mr-2t(Kp>l%1nnBHRpk($)12DcUvtjC}foo@dWkN}+;6IHqZZoEG zkh)Y#VYgTWz2!N&bhq-sOhTlLXDu6e{TM@4Thk#VBK+k$`y`k>OLs%4Hx^!zs9xoK z7YRhqrKQ-#gTZ?J%y@~EKPWq-_sN^MK~|^NUDsmaNLKP!CaW>>$iKYUAYp}*W$dZ4H|_9+?K&$zu>*Gg7W`V6<$$JT-4bcrP8gH@ zoe#(Yaf30EUnu-s;kWrFOKPYWw3hUWs|CR<|cKQqkTkoO|%O zDFlnRl7EO!fSJ;IE2AIT;At^U?sm2S#p)wezefnKu zxE%ccySMlLRt3Cy&vj*yp#mH(#0zj_mqTZZ^(h~ra^Mr)clvR?41PMexgVV?fuh@& z@&z6i!!GgrZ{ik(@Rp1$=i_WXm^!6z1vKSBcLVXAOJTX7;FY{{iaQ5N-{~E@m7fJH zw#UY#^)sN2CJaJ4Qef@RTdxY;M5vZ!%w9=}gP1d7O{oGgz@(wg-FcfZ?+ZhfkRu#! z%M!)N*9F0aas9LEStU51!u5WWycB~*gFVmRE5Z!zlH=-Q`PeJ|nMqnK7q5)bw$7+$ zSsN!-_>7`LVp507h7=jvP;D4WZmT)GM$Y|1M4zJ_v8k z{|;>}1D1QCXUd$aU`|3c^{-$pxU*He)XUU^Xyu!+*oFqUbLFX^%19&l$pzbNd})I5 zd&dg2hnt|hshanFL=&9bWU$rTYlPF5yr*pU8=&FfKq6U7Jp`$8mw&Ra1Nyc+qvrFq zpmow;K(VhHa%QSydkw4L2ER!6el&vOx&wo_Q5l?C;`<)`rWkttZcHfJ769dqz&#z= zT=+quzn+nr3R(fGO;s_;sPa430ps_>{&-LP;` zvU!iA8@Psgg-e|~!TDjWkym*uJZAU!&>GVS$JB4@xE!kk^8DDXPT^{>s=sydS~h|f zb8v15mcoc%h^CTm5$y9(b#7bdL*p9?t>%#&;7R>wBX5`mzf~^&nBYr;S8w0y^~Wbc z(o7=%liYZqS`KM(`LcN4GPB#weWHTOZ{Q z@s5r1arbyFj0w?Frxq+zcqX!`Q z99W|FZC>p;;7hfn<{Nx9m~PD$dM>aKM^*l=lqnRTU4@RrCzS%Mkju`#V^M(By}>de zAqAM>$aQ8t-iQxC-n6=$1=5RMt zy|Udzri1Mrny=Q8h1c?4hU+|5{JcB;`^G5JEr-mnax`P5@Un`}M>lkT7{ORpTmw(U zwN`I2b^|xNfH&u>et5w0@5pG#0JJD4xjS$UfQiGNM?6VCB(ydpITGf?tN*53D%g6! zCzkKJ`AYq?>cW&tt>im{-YR`olwD#e>>G!e*A4@b#D3#YB zr4L!?4reVI-0GzMBwmZbpS7;Uo7LdvkWR>#`6{%QJwBqSSC40HZ(kB;8$#px=4nmy zMXcJUR!#3&!>IzA@7pE|IDRMc(tmV)82m}Gv%%CK6dQKvsy7;dq>$sq*_d`XcZMR| zUZNAklFKTK?{z{;$7UA2X*-CzTI|&uHp7(AW6{%R>*20%YR{N#HJk_!yW|sD4n?cE zKYwKw!r0O9oxz11u;Q8VKBle#jmAGS6{dj684a%rLY+%=I~! z8R{O|E4Ivfg=&ZWZ@N3a!i2m@adLXZY9>`?ORfrR2{0?>PA|u|XEU##cwCO!oYTi% z(v~B+Ro40b&N6)G-MmR#T!ymVSCi5l%kY3ds2nTYr{C_%qJ(v--f|oIbR+(%|@${ zd_RZRIl%YmgjGOaJ%~I$uwOdX1`0QA)f>q>VPIsinVh>5P9D8=(6p=rnByvh7$Vxi zG&guZ@=P1t`cFlk&awsej@|G68`1=-zsd$qhBttRx$?t%Ms;A!9XwxIO89O;+yA}! zg%CO%A^hTdDV*6A*6h?Q2G@(3kH0-A1XuT!#|cdNu-VtJY#y2e8?+DpE8fop$*lv9 zkqaphB*gdZ^yLIlNGoCUNR0+A;oZWMI-y`{lcmUS><{yE??%QheFFDRvg`3R79g3T z@?-bpO^mu8c)c{y6637sEVycPQUBj~yJue}o_9EK-g_bwznz-vrW47+NY>J}L+e?{ zte)5^^D7&9e1BK+Ud+Xfj36re-8?*&eav;!w*)1d7Lz7>8<51`@gI@f0QypP+x>wV zl+xWMRa0ES${!|cuSVA~PBh81=k#}+c{(le zGc1!JvnRovsxBS^mRGpPU&jJH|441NNi=+;u*lQvi-aBRlQG_fVX)TKD|+K;2;6?# zA3fpt1w_u#D%4&23|a|`0cX>E!TS3<#j=~8pd2h&qH@I$$@;|D&IJWzN_=FM{E%k2Qbk+i z3o5$?rEzP9;ioP!2IrM1q&r%)nzj{(msS2QmL5$&DT8_I+;bsl$1#@|lbnkzkpai0 zX$MeSK3UG$XbGEdmK}ZUu#Oz>&N;28&123XmitsSE$GTb6?W)aBglxKb7~G9fTM@k zhko!3f%szqYyP!bn52>kyY*OJc7fnFRkfnzQ&>e?SM&ACv5!edtIWy9pz4GMmwN4We35-%+Tr8`VSlMf&Rwqkg1>e->>1ytV|(g(NB%q6XvU*@?zdSku25tq zDjv*7pHczRHiiNWkDfKUtX_zkhI~a-A;nm^#_4N3h)Cko#^ssOitgD4tkR3axT%8^ z3DYx3cHllm@v{~DaQ+z^_1Zd`aQ^wn-@T0P*S#(kmX2cOa&>sDmo+xWigN$G+y^gQ zhHdk5$DqqMQtK(rDDal+u6m3Nz_RE4>I>ApK$k`HgrcSsnqyagMI^OA^F5|qv+#P* zYKc8C=UxrUHfp<*$rbQ{CQ@GiSTS^MYidgx=L2iX`no`E4oK)s)64K=10U~%z9mN% zR9rqNT-J~d>WaQWBhOO6{ZWtl;Z)i$zw4`bkWovBmUgJ_^W)T*di z8U_6E?7z2Zq9El|)M{0EIB;8t#8C@;g&9`f{5(DVTNt*XZr#GY8hA-((66Or5?I7Hzz;=dHW*hiU_SYsUD zDn?R`PBZCim{^O_VT}v1zv?l1;P9?)YYQ?N>0kQF)q_-Yfk9udjNtyyT_wJ@Y19@@ zG_LVo#BP1%rDWN4)Q_9?7ka*dk4`=FsLohHB6-(gvD_K_{9$-o@%Znvo`S`lyjnI6UBRTNQ_(BGx zUHNyM{ZI-R(avanH3);Kps%gOGJaV3x}8CgTNxDA=z{Oam0`n>>!iG58SdTD4`2MR z4BzLn*IV+I;ehBrFLC)YjEG@KIa^eQtyic;L~fVkeb&dXpFgd@rnSh8p_*Ehd3@$g z4sRc(y=83d6rMrvUmBNY+E+28KKJ%VAHx10=;e4fw1PDKkM5PoeZz5$&f;(8T{yU7 zm~N;TgTf+@sY?!&1I6_Y3m%O&c#(fO_bWm7)RdB)gBycj^>aZ%LU$0f%M`AEtLz8g zmnDdRSQ=O2`cg9lea4YZ{Oe*vnHo}*5b8TZTf_}!Pdd%@s zHS8u$5MNuU0RAz`_2t20sJ}?x%V(YsJgrZ4YxJ@qD=2V_u|E~&WI3+0rN%=^l(p%p z$B|HQ<<_&R^MP>K;%kx`u{$tc$d$~wY7Io>d0(w`$&h_yZFz;_HBPRb>Lxz?0XN6P z^-77Hu>H~lssr~wVX)YMX2wG|>~wRu>l@>NE^b5*42`~^fSZi^D^fpTkJy)Z`Oy$W zO_d*ZJ+#K6ZH2Smem-dPX8Z0%`(TtT?pZvi7LBbp@2yMgB%+8sotvdXHcEvmwz(Kr z*zKLNfhtvWdb4kzM`L6*f$4aN) z5p;e1J^Q^oR%0-%S9-ML{3tjk>Za%q4S<_T@HWL-4+s|4Ov;Y!TylJ@e{o&$arSh;~wP)%%Uki#opzLX3KkdYGPj4 zymsBUaMTBNd45zZHTYs;%RZI)Z+|Qx`2!Y-fq3meW7$WeKrEj>_$lyt06uw_Wo23( zfD86jnSQ)qu=u@m}Pr5xO)MX5#Na5 z3eUz3mNV1dPqXl(%=KMq*Gx?MLf_u#k%mbW{b79}fv9*@*Mo$!2-J@l%4Msy!jfkw zy@y68xL181_PbjHnG7o;{k0vq9GP@ZXM7Po7#0GSr`Iud9_n_azN5Rh6-eYy;pno5 zSx{gn%6@j?Z@^fjKSH{s&R7C(M5T-U`3d;`ip|)SohCxxr1uJ^Zh_BD&o$@Un?dYY zr^$i-CODg!^s4G!Bcy!JjJ#`A53}W)68D^I;lIJrP_L9~sC@L`szg;KI9!yzRytk| zjI+5MLz*REH$nM9kEsx%-nhME$DH= z#Q_idHv>hEDCqH@=jNdc0hSK+eou3Mn0{$edxOAl?Pnxp=5lS}QOcVA2YG$q893Tz z-l&RP6}Lcu*c=VKLnObPw#82tL3~_sAJOXMEq7N6C#1TPlHji6f}Q54nbohP68iTX zsqTezR9~+Vf4rZ8mUA=Ij22l~E&R||?OirXo(*cNx6Hv<7pBlDm0a|U`oK^3D;Klx zm%dwpTHG@|HxWU+?P0v zribc+?$U<9EkV2WfkV9@cItr1%b`&y6}KP1q&W^!lZH-Q^rN7#rMJgcGYG;GI*DcP z`atvJOUDC--LQRtEI;#12lP@(F_IHEgL}hqh9d+#T6N>@Z%4f_ z^Yin8sdFz>_hlB$4CZpEI48oHdBgX#3Xz~pPkC)y&JXA!J~^*)n1f(aGmfGa4*u4y zyV2o=5~pd0a!bCT`xm_~PStRvSdw`&W*&_hPlH-c*2JR6Il9-GzVWDjS%l^!b0WSv z9e;9+J_$QVPPUT!Bw_pT-|UX4B-C_XFV6cf3E5b4$NerRVpYo#%F_^qPgr$SP27v| zoBjEQ$m(MBEg)WXdRc;l(uURwOr^-5ASHG9PbnUb$#|$|SdK63=*{(HE3umVVEvk3 z18V1fx+7B4gR<5aZ>;c);h(fVikiPOXfFFp`u?3&3|8I@jR@F4+1lh=Dv2xj_rSF_ z&FLwOOB$5@wAhGQPn3RBG!=le#GIIqd>8yE>!J=)?1$5WlAYG<15hGz!J~||AGWo} zhn(K_Lb&h>gM4H+d{APlCBaUZxyUBrveX7oPWql|j&6qF^gW6L1bmuVnv*HVR|mpz zDmjA9)v)QU<(wH(2}z3kh1aCZ;b&sx)9Zx(|9n$O;$R&?XK>H^_k1!J%3}43$S-Dt z$#hq1q-i=VR~DW={5lyVPW!*|S&N6KYScU3X)&P8<-5BT6A7~U(Nv9gp3b#lgzqL@cl2-xgb{u&}vLs`S!!EY$Z&&HMaFqOr`@i)nP`p7t`12S%eKjFY}IMA}6G6)_K9Vdo%UzmLS_XO9bGbkK2 z`p=f@EfAf*9e1GQ1xRj4s_MR$hswMf+WJfPap8B8#;-~<6tMDm-_zxT1zjA!29AYe zPkyS?>aAMr;^I%uykCoB#@%>vycYc~-95kJUWdhtG@R5%^_WzsJ3PkPh!d)T2ZJuP zU}4N=z&>R+-fQE_C3hG@x?{)QhYQT3Zo@0K*M$F`@w_tanU!@sBM}_S$GL&u(>QJX zO4sm^ba~@e_u&uI(Uwa4UmnyA?Qi z=XEsHTEKDc>4^Mz6DS{s2Z_3kQ0Q%-Uq4$9$3hd!E1l}#4F$EI-o;v=ak&&oHCGMv zak(NN6RW`a!El(y$4ZcxeO(m4QUMbJXM5_|%3*L#b=Ot56ehnCofRhN%2y6_BuNbw z0=4sWx>A-4&6TeWu3gQ6@!76wWri#uCT;!|VIK#QwWt$y z!VUzBg*Wx0TtPj5h}Kj+9<$Dd?7b3BL?^S8W4s@euuPv%^{hq;T6mxNM_-wa+$Jic zg^k%*xTHx_HIjoj3k=+Qm9x-5>2UY=GbOmLI8ZW2(3cgY9Na&IE#vCxS9L<(tGFTD z!Sh^w8r6T#rINTK{?xFIbsx!x+byL>m+VTQJ&x)f&0sFLQMZX)zmyI3w~NSIiF4qC zQ&XA7ZVp73x{Po=&4v36LN#6lejCto`|Z3yHuw(-CDxc^f_R6^w9-y0=nQQqOVB5R z?%7uvj&U)t{lVR{_4b9AaGyNd`)L59&wm&pB7Iyp?^#`}U>ybkhzMvv>ovoqC6O`7K z2P-xmV3C)5_e6XZUdS4YaZ0Sl-L}Q$0@Yev^>w_}meYWO>nd-9X4+6g`Z!Z)b2r)x z{0i5+)sL!LB+o;+C-5L&!Q7(A0zUC3J7~nVhLvqQjh9(B@Jq#1dPwvpR(}0?`KtC7 za%{R$wZYQjosF(P&2YSP^Fy8+x*K>zWNohwr{^ehK2c-^jqtnuKl^Q&dh=i-$Lf?Dg#AyT@&a{z4b z6yNx)MVR}eXOo?=7f7o;qN30AK!*0!0K1Sb=zmSZ#K+bNzN9v)eTi*Ap*3*knO6&l zymbGH-04?$2AR zLopjDz~pwyf_)90p4z_P)tdUpI`tO3X3W?S?P5Q@*YQ-zD*4 z3zg=lP6EzgBHbuyhnx`p?6QDXkRwz2PF&gy@3h?o#f~+B;e(*aGjAGzPTw=4Hm?r$ z!oPP14%L8A!dZp#g(_%{V#y9ILhv%aUy>PL3elSy!z5jWkWSPj-md zTT~|O@&tO}uwbpP{`qmrjMlM!hD4rpcNxX9HdaYX=CHtLPCcM#3bP$jlWk0g(Unw;!n&{t&vK+|I?QFfyH7(C&x9vqncyHUk=0FJE}zR0-|(M&4`LH^R~iU!>%v4(J}{ z8SS~$4K$T8v7ZUNLT-Pf!TfX|@b8DxRK4$mH<20+mO6b`Fz+?J@8}y4a$X*-V;z5OIzYPnZNy>SHiEw0aN`MQ3#|E$(tl%U zg8gesv{sKApodkip1hFYhn_kUSw`q%Plx$R2ezs~OweF3k&qKQaP8`O&HYLcIg#z9 zYl|?-;p1`dP7t(ro&Kr!vl(TwxCV~uHsg1Vtqh8f%@{M=I-Abff_@?z45XT^=*2^E z!I`H6wR7Be>`J=v-0vz*VYxvpEf|$~O*x5j|88d|{F*_5cFV);*Ozg5m`?d}-a7h4 zy#1}Twt+5>AFSkz5p;<1@ypR9tC*#_aauKE8SQ;V2fd`1P(58BYkOc0KQ%*@Va^0* z)q7v)t!PIDv)@12k7QsJ#kJfziexxm?NfBWmC&|QPLM4H)dOFjrQ(N)W@w#tyFNPK z20LtLqr3^e*|*m5DBq$kAQHOD5+&LLho*NYT zD270{anJw$&JY-HRGU<|4nr~TQD7nTt2c#HBy^vKVQx6u)%C{^%%yK;S8xnLpkv}O zQJO&zQm7GoQ%=Cae@7oOEA~Mi3!7(6Qx90EOP^9a(+zH|f_n$gbwaQ1xkJhKT43@j zZz8pLE&OykCAQ_81s?>ZUl^ULM{?gcl9aQxs7f-n&5=}t+yym?cWbKgJ~^caZ+jJv z|JIeQsVhgb#y~dS3#llZOQe{3!57yxkEQhx@@cOU$VM$<`v|=7l!CCy90rqFaXY{| zGT&_y-zwigtsica$Gi!6v^c_2o{Yf57EEqFFIvDK7WEJ9EN756?|_5xi%HC}O*ypt zX$XI0{wH&hvIl3%A|AeOX~yBs=T4c6l}N#*TS=;#g+#?AvD|vP=sP|UHyDu$0iz-J zW=Tt-y}6g9AiTSHDCXH9M4PR6ybc)zlgz|>&-4aix!~Ej_VfUpep>g5g_(d4u6%8cIo1#L z`%#g}OTEBetI~a{nBY?kh3LHX>xOG9=T#E4xLJe94N;bw3aejxf z92^S0vs=@Xi_c6JVr`Q1(Bz6;MLt~GcM`qm51n=#|~k2PmO zIQl!9-ZWtGV&6a^=kK(}ddtY>|8dDdXcR?B$q!10W+R8SR6?m_Jt!Bil2*_3KwDqf z7xO0rppenUWOaA|_$_z8no#$Fild!zb8I)z1wOkbf4>t*eYx)oTy2HBGKU>*C^mwI zPwoqW$y!*=;S{eYaWfRSx16xTHHFtGtGnHr< zQM-nOwPr=lNa0Q;^67Fb;8G5GMQ4E> ziR&qm*+$?u{CJn?VK;E7B=M1j_W}3bZ~rKVekeZo=)6m3AJA-G&x?`oh0urB)m$CA zfxUi%$s(o`iaBGHEDPH}D7%;|TCW*=-hGWb@U#KuVrz{)B-MiS9&>HRooe8xvhptA zuLNb8KRpc3%7D`IyQ)lL5onowB6`G^55GdzQ~L@0L;EhtDz{+<(6|?PN=PL`=kFsf zo*8k#u_u-${V)nD0zZ0QlL!Ifue^fCtNg(zcu8ET%@tT!byu>}-hp*2xLi@!hEBgu zb*m^1>{YUvNq_tf>Dwf8+B$uaOmi&kiquyW={j-eb8#rjXsuArZ$+RaQ`wPfk7z7D z(rGa67mKBO@9w)iipR)`=33c@38-?FlUT6b5hD)!^qyMJf?h+z=qucjU?Umz$kwn2 z=gr+SziKU^P6t`ZqaW+2TE+Gb3Lfs?VWT9c6Mat~5b&r#?HCbJp!WkUYhUi<~`xI+i%`A`&FxHW;rn_s;b z?$<)$U9p!07zYBXg7NcKMR4|chjNK^4%miH){nHLfPe<$hc7}gVDhB&*U;fFKoJ?R zmvGz(h%`x3-d^D-z~m35Iy^JQ$S=`Thr#zqN^H!Uu#5L2W7^jNTxUq^xp8I=)%ciy zzKdGLe$kWRo?082z~#uy%CL!FyngK)|60eVQ7tFcmX>hINRcX`ViI@Csyh!66a3(V zGNm=#v7lh{jq-^_2f?pBYSSb$4AiHEhPKa4z^|x7l&*&+fIp$GhI?uht}zjlg%jQf zy;&#Cj~)R3bg@D{3PN3Q(tgPZ?gr278UuTRF22*_b+56x6{tYCHd46>%tW7ly+O!1 z{~C+0zQa}n50360eivB@s~3JS%zrO~rtI8`J6y#eaIo-`yI(%UTsy@4?kORUVWU*e zqLT??P3>&gNK-)jQ=4^@T0AhHEmo-Ziw2c*meMs+;oz8%b~x1{7@R`dr$bEwK%A4J z($2vToDQAt&|~$1sGwm53w! zbnf)FDagLQkYWEP4HqKa97szuk>@>EsJlTn_NGlroKVU^@8HmX7YYk8W9wh5SyDS8 z2Vb@}7(RtP9G_^{M+y1c-YCQQBO53-T)x*pz&j;#VTsiT25~|2?^9!iBIu;MClLRL z@PCi&B(DjLg6rd4k0;;80Q?+1e`btAiBL!Tm+M22q5R)$*3mvNplt0E6C>oSXdiC7 zcC>(~`9-+}u6l4ADNu5@sREl>)fZocN`dQBhTTSE9_(#jA0Q&mgy%oCl=O8IAful% zY2|AKBzYG}JJ3+=p1Lhj7}kA?{a{QqdNaBRpJ9!`q{Ows-!suj zf5&!L^G!5INd8-ojKWtuEI}LbB=c5z3IibM->OreqBh7E@c`EDi!Oy*cb6kf_fRz zyA^bqcgRcDUdNTiLi6+^o2Yc+@^x*ZEfifH{}X>@6Gi)S^cqLjQ1h}{67k+5T2e?i z+nt@kOPa5vSRue^gp!?ThAN^UcQ>+(K+Mr zLUCx$f?^yVww747{2YY^ayRepun{1TeCh|M34B@kyGKIsARO$PQpi6v0Gz~6F1>f? zgFvYtYmr<1O3<;F4XK1UMQBj9yJ*=P+iTn%4 zCpa6C%iATxg|87AtjRwc={DjicxQL`dn3+!ovse{YC$Xi&))?Wy76~b0YjtqIL2JQ zXJK@VkSip;9ZCFh6&1T)X)E||;5FvzdaetbNHv$vbC-StMNZx|9&lShvxZkCz0LC| z^z&h+-=`^*j+hb*8tua{DN5T>hZ-d6t;=$2yMqCXR0p#-tH9pus{CoUPH0c+x&G9x z9}*e;7%29JVCY1*gNXD9{30b1>$yAv7i3PI(DEII)#@dQrH~;)y>ol#^AAGg{_$rP z+WpYNk12U6y&x!YA}DaL8?vU@AF~ti;wiR%3?=OZBY~YB+DC1$Nnd$6Q?nV8%sIYU z67pNO`}H1-JRZM$&4&eFqJtQTn)s^2BQXB8yzuHZ7_^NVbBWepz=^i?I#Ag%B1kM@!$Fh!BT!j8S zrdUFcD<-Vx6u;qtE>Cmr!-R8ri5;6QlGPYBrtnRVF9Wo`kdllJw}Qdd+HGmA0cd<6 zApEzjK2lqrJM$K%x!8r4XHC)!O0-3s3RDc z6#-GC2KR{RTtVU4`Hyp%=D4RV9!y4Jf@-J{~5vcvR)U4A&ojx5L* z-}?*;wH|M5NbJF$JMrMY!5z%{DD%X3`877%hUIJTIAVkANVzMIFM7P=GK=1+K_HS? zCYrCoWbW$TjkOvSu;2R5$XJU7@t1d%m20uPFKBTqy%r_NnU8<%AmAUF3oyVC=6O1dvr$-2SfmII~R`A*1`zqI;=u?@&R{EZyC z(+mqPUWzo;4PbKRC|$5e9h~=gkwxcU0|hkI2e#^~VAcO)@)LndIHbG58Kqke8WqKE zw6P`dY(&J-U#tkcxulfXH}ZjoA+5J?As6n>^Aa<&-SF(d7s%ayM=X*7=}x(wk_Jy&B9g zVbT_8BlwF3ZVXffHRyj|>oVE%8jNjqP#t?#gBr(=q(zI@U^&yRpNZg- zxyc1*CSUZRw)w4N#hjsyWsg@is_=`9bopr z-05I+3&e#y6cBjP2+66v<~P0S!0F=qnv9kjs9bnhuf$RfSrJeCq~t4s^TsHj!-;Z8 z`Q}~0q*4qa8$RXv)CJJ{RaQFiC!vok8F@$SWxUxg-VobD*yoa>Bw07K{;g@8 zAdrZY!zT_13ML?D6PvZ$`y_l%lpbH|or1Rp;E-)~8j=-e9r@Xifr28;3;|+USfqBJ z=-E&Tl4dTLk)tEz32DcP6Tbsje#MT)i#>ROxb%-E@e&H;SKU4?yn(@X$7SMzmyuMZ zV$9NK0FQTnDx$M00Bs0J|MjUK;{Pe{I?9hh!%1zM;oWfu&~LVjg|{STefI*kc1>{!w0m>3E~Cu=`EyWk9+9lJayxeRbJ==h++SuZpgl^g81 zAB^W7DGqImMxoE`Pli(tu~?H#%Peyu0gJL3$qVR`P|l<2Z2rS!oD&laRD%@!=4Q1S$%Poc4l(CAxoy+&_YXpDU3~z9qpo+A?B35)S4$ zKV;JfTVcJsYRjNv65OW>SnPwx;gQ@q9{Um;zh>*r1&2lhCjKWFNx`{?|j%K6$!f z=sYUHX8FAjB$m1}T(Y{L@>!JNp}hsa*t$m{9`@7uCP+BHb^Zspxd~?;dbZ7oUQ^CNnk&`JP2yQdoRl$G5s->j zJa>kL((Cc_`O*?aH3bNJYM@4dGWk}vgpet$jJ_3?-6dd7X9`+eT; z*CFy3+UJTP+M@BID zQasPvd>2mXRCeZHZbF%f+`Y?cWyr-{IcIx-$mJCVhDu%h2FgV((MKQ)ly4>;xJSJ2 zH!RL`RWuN~JKudb1-4qC$`!Kcplbx0`$_1e)&eiLO8hjAw!yxnJ6{}q+u{7pOfu@U z4v2cEdY9};C$M#N=QTh(4G=GNq(L8w4r&vJ4ot z!jMRt(B{Jy7{L+w&1X%ZGCd#RL*D?WI5^GK=W1b5B>PeFbT#-MK6!30c@?nveNWoH zQvv_=e>k9(MS=rddEdP$h;x9Uuk9=o9=y*munueb|u*YNQqTV4t{A!z* zc4#vg@5%=2{P`P!B1uo}_kE2)8C|jW{M`v?<$Ue-?s6h0b~yd%Bi{iXj;j!&QBj6|MRNBuo z4y0GgymYZ+V0f>zSx{#f?%l|aHdpKcz1wW|LAToAweuy;=)Hvh`81749-%WkmChPu zUoQg5U(0?4mkHl_-d_eLZ6Ys8mF?-4_8peR8G_Hg{sie-gL&*t7MS}%<8;cl7yA5` zkPY1q!ZQlL{?k1gfwRv2rau#+aLlBP(!MALzfkX6OY@GysdR5i3f=@X2wokvzLki{ zDgK(QS&8UZbScHsGZCY!Xzj=kB;xWSL&2;JaX+Y=)1%Gf3Ex!eR?DY2yurOUHP}2B zH%HES>tBw+?wg7OwS;d=?Oyb~;gAsIR=St!6c>$3;{}1X6fwy3a+vPQ-x#!%^CaDD zk3(T5qob|M2}mBQJ$r365!aG>zLvgB#?*7go|p2|P^-GFbxlnCEY%3Idp zm(E14)ZV4OtzZtn>Rl5W8D7S-;x$Kh0_IR}@Nl=M39&jVZJpGLNhunmgYN%E^aMxg4p5 zz*>>y_VIEssm;m?x?TbTO)YMBqjQOK*M-ZP^Xaexs1JkR_qk%YMn~@StAB3N-mzL+`1YzHk;~PrJfv9-A znqK6wKknLb4LW=%2nWJ$J&!63#J=Dj0s9+7z5;$NOtWSnYx+Ue8!ysO-p5 zX!7p~bEV?4A3di;X)=cEt0evVnuv;}FCT62JEL|NCF}olha)PpjEB-YK}4W^Bb>Y) z$j83ehLqx^H2C0%+(d}bL}-#fF;P|Tx)qYk|RAK@4B2`{hKBjJMYq09w~ zSXl504xPDM2{x~N#)H|KAyBjNmZ?rF@NK&@T-a%WFJ-cob~MdU_+r@eqF+6H;IyUT z;;aEOs@&(X!xexuk#8P#6T1J_Wt%X;60ld?;{PaD0QxUuu3kHk14r$PqOYlBfTf86 zK7Nx7g)BxtcX!7^_`vBl)-#dd-%Q2iR~H21USSt+WO##n&k2*$ADp1@Z6%S$2$e$d!joX#lI`r7X7QTUT_CE;6A^D_IHY$aa(d$*}LBj zWh?jRYUO$09(}z_|FL+Y;qJV(Q_P)enjQB5YAs*U8qQ+TZ>t2M*jMDJE#6t;O04{$la^C_^9xx==icf zhL35Dsz-#wai+;8;e~8SU0vP8#8trl(sLZHBQ=CSLcc)PvH>oBQnOvX z&#Gxg$Hpe8_~^pji*EDiNqPx~}O5XCI^im8odhmoNq!eXl&9<|WN|CH7ukKuFDef8xe0cR&DYDAGlC?7?q1~^DE>np{ zv{7uh@|tS^KgQkJ(b}HEi3hW}Lq24+V<|XI^i{@Y4v)B$dYfsMqKR3MH>3*xjpamX{@=hq)H^RAt2^vEjbznA? zmlOP#;AE&q@z&jorUruL97 zd;}XlO~uo4BADJ%+5Okwg3upn>HDKya4q+3j9Z5f`U~l?tG*A$=v{T0>q#*vDb}W7 zWm$ln`iHOl9Ii+9Gl#UwLi&(R!G3cU~rLP&Ta90?5iqye3 z%Rl*Mgbt>&_2ez()iN-Ar`^TjQ3TnpEOy7;azHMbEir{J9UKbR@;y$(L1EAt-*t*G zC}Echu@&)x^xL$lOrusncFxEk?Dc)*3o)4ygd7*n?fytwp3Q2km*-y!P|Ect11AW$v@BTgG0 zf3y*d``6E$J~0r44{6$G`-TFrK_K@|Yt45oV>=ymQpOLtpYBfjFX%h|M9s!y0|nR- z^2K>6xDc3aV1o1T4A$=RzK;Ck5006Gi}#**17`G1?0V%2!E=>=X!^cD zc(q0D&;4(qROmHREXNf{*46TPdPo=5qPoU1jLeXVj_N^D>n9W*&oRpU=ZIq@+Ku45 zxwy^U%kv>D532{bhsHJYaUX}FLDN_PYW?0=O6V>^eY1`TcDEnIa|98)3dFxMPbzjs z%kh!j4Rbs9794PVu(!Ep2o+PVJBIqq;;P6|ehHRkOc&U#(SB?NDHwK*^Aoz~(sLbZ zpW#WAdUh7~FO zmcF5DTnx@E7GdQo`QVwaODZIMzQW&x8pV?`;8EPQ$sbm!5E)yPeBxWTfG#`UOL`OUVKdt$l;Nc@Y!{bh(w$TTN8z^B%YkZOf8gd%eGMlp6Q4LH zo0Wv!n}5!*pH0TQmxRsU5IKyJngA{h=~RqS#FIQP(=hq4P%y=68Xov~?u&wWIx@+e zu!<-PLq5Z=`x}YAoV)PZi1>gcARW8iTF%gp$0!bJ{$`&?e$q$A%F`<-{FE(^M_~>h zaevu1EA2t5g-dS*1R`-@`sJyP9fD&qu^~t?(gIigbbGhD+rdoyh5wFJ2bkDz6`ovc zgWx({%T?m<4-R;~dQGhBRQa@&l0^U4L8n2$dzR4CEH7LaN+1Cn<(YV*+y>8YIxI{x zg`o7Q>x64VF35*vD6Z0GfyV>ZI9c~J=)0K3wp^0{48KFh+9jib)6=%`&&Lqh9kW8# zyT=#Cn#hXPUb=$R`7f6W;y;17(nf;GEdT-CQbko~W1OJ=(84M61!owQA1F|`V9rm8 z`{Pf(;X#!vIV&H1kmZ24Jcsso+^J8UO(PG$7pmPyxU>V1W=2a*qRk&&L_e&4m;H|2 zw{rbWtn2Z??(6FHLk*b9&N`|++lb<7RO3}WEvWZqu>Ra)Csx~tczoI(LY36K-??f; zeo=wyd1T8p(%EQdO|#5l?s^>MCDuhGSNulj`fV8}%8|^ay9mE1_xqDDC|*ft{9wWGu|bo`w^8P3f7CjKDg`(>VaN zMMPb@H9xQv*bTuaxG2J268_tA$APB7UJ!L*cVQy>_VE`E6*>Ry0bU9_GgrzU*b3*9 zW1Z^)9``gsp_ER@+*kT;huFvM84Rs1mb5|ig-YL2=~l2W&HRAfvHMQHApAQL-0G zfPws~sbzB^-1CI|J@!nPV|#4%=XyGP4cvF(aZfV9e9sB( zfAJvM(70=2HU_d=PAm8H5xLB__!TkT}_tyc&i65?PirupBTi(OyxHEoKa*7-1|XYZ~_&N z`rRSfP9c{D%TnUt4C<-~mNi??BS+IC=uut5#s?8R#V*UZA^yYTsQn7|#691W-m`*H zB%TuuuLwWx{s~R}Ys<(Pk@jqma}hagIx=Zq&Ej_hRTWnEN&K3-727H?g3m(pmBU?I zknK}c&9&ro6mQb;I7J%-E#1~+8T*Q1uHt}a=Y=}R=%avlgf1g-YmEHmY!}>dcvNU; z*azggDO#tP2f=0AVVB4H5SSb}#aPNb0{n;E<6106fNqiLlV!jNyqR~~_2bJ3e9KRi zaTXc@kHVXy)b7K8H|~pmkQsvYf?U&MIRo&@q0MG{y$}9SMzoOj_QI_Oitg*nU0`_o zMxcHM;X_gw$flKS19gLbTJhgaz+7neky@-4YEy%T#M;Y&RAKSm_3#gPAbp}Y!6gI2 z!+D(Ki9B$vb=?DgrfL*&U=2UNScP)@?k!9&s?lucz@Z}BDvS$@`u6i)CEf`ha+4gc zK+etI^`8${qSZcg@QbnGQL%TtM&CiRTMf9L%xK$%1z;;lO~VPjxJ+p6wNVq z=~Wbf?jJ5S%NVTMU2s@p5w8!vdFo<5i_eELj#TnZVcCAaK)1{>eE4Ijz@vBom;3eI zE>5=NwMoax0|#qRBSdd`-^*+qsW@_8Bh3*gJN5{x&*y=3t|--~0~NqF7fipq0(U8~)EJj;SQCDg%KxDk#AlAq(|#O) zM#_gI{+L0yTR5g^c&s0UQqm5GtP$sp&-08&s@fsS%PIThqgI&Y3!IF*-w0-E!~Li3 z*Fu_F1MIL@K&lM2%X3bGyQK8+pUks-D057zlB!LI6AL-J5--KW$IHcg9k!z&wfxNT zqgcYXM_;6AN8!3lf2Q+t#g@mRH-iM)9=Ub^(7NQFW4_5 zo0Zi5ETaFlC$>t1dV%OiGWuy}FfJmkgqcjw)HH^zNPQ;_kKwbs+L@wd1E`TD{L84V z16Rv9R6_RGV{nxA2ln@cNY)bjAV^CB8j{3Isq6}%RO-S*Cc7HYyS60n8s7?U&$pZ2 zVj*&R%pQjh%k@Isv3tSaDf&Tc$YIwloqibNdSPMK&~x_z$o_N;N0U@=;xNoTlm@p4%3TK%x~&I_RCY_Ak!+SQ8{O5luUy2 z)emax3BH*!IZKeXem)qoEXsJ z99L4m_3o_=IBq%f^lN^`f71raMHDr7T`WBA^5-gS;|*on6;_GsHv2C6bXVYaf~k}A zx&pl~1k?Ebs6e`hhBiS>gda=IBv|}XEtb4R&L@)XSoQnK_TO8hSQ#f9)%J4^x6P#I zS1OmWd+@)Z(u@_nzzFrRdCNG%x^HYfV-c%kpRpbbo<;kTVZ+{xN&M(I5X1Is6jxu@ z&@#3RVDO*Nj-4xAn5HzdbK*b?>Q8$oTuQIN@O`7~N3zVDWOg5I2O-sE ALAj}`P$AZ2G zRMvkj&K389ovcmw$nJjVa!~B=Z0HBF%J?<mv9??y~`vzyKVGI1wCuZ~y}2WKA}6 z`r-Qzt8lvW{os>O&75r62Zt&HR(Cn}!iTB-0UMG%uv)mitg_t&=E1hCG6kJ*p20$K zk=Xw$fBi0Mt0Z{8ek>(6H*z59#MR^9hbr;YsZNG_Yn2$%H6?oDPbCiC4=ttnSBbl1 z+8xla3e%F;*o*nA@uuS8e^qQXc*wzq=FIgv6dWO{;^H>k{N5I%{AL7s!!J-!n$Ba4 za!_&dvlTP}v5Gm074)_&WPM)z|NDQlWFT}2S9@5v%xT83ba{wHV^1(9C2n5-M%f9e zogojb%lpAUiY@cx**+M2_;>Th@owmM@a=kD(?R$gZ*&8HtDHml-8>h5 z>)$PbkkXsug{KJLv?AY&MXh}Jy1;F5AtD!81^o~1rp|%wD1E+{*Rz1LV|&|9Faz8v z^)A`erGofgfsL%{Bv3WxSXonv2iEg#cB-i{AUy-w*ZzxwiJv#eK6FPw=*{|T^qOH1 zcS2@(v>_0_U*7iLBKd+;bk*>ODJ?>`b!}9gXu}bfmv2J9bmDlx(D-IhFKYdHoU?jk z2ye3Y*ME~9#lf=&3J()Lk>W4jj`u%JVx+EFU;o}2JjmYt&-2MVDnFBU_+(9Ru6}!t z9GqG~vVn;jUaMa?wG)}jc3=%pc<}{Wz5a#o+Q*B`lUGnPvVHf;izO_H5ZF9O_|UDB zEX5vEjA7ZOGXCt>ZKyV_=6zZ#9y9Mnf~>#L@2*F+u;;!|p%L*Oo2|rLJb%6q z#5AmYT+R*y`6oK=yRSxJ^iR<{+o&x+^j{r@> z7|dwKgdRIK23$`Chgbwgf$?@=IUnl?w7LA73o9Iir>EF4iK-u7l{i?rU+4j^`%H$t z;zVCYsYH)_H&G8499{D`-3kvU>l$XGL#Wa^5LLNp|sWI|dR)WZdg$x>AP?6KjRqri5=l zWZmu^k?%FHNfB}&)D7uV^h=?B1b>_BztoAqpBTGa=HpA+X*_EX`|5Ra4;p`YA~Up* zjT6mnch1R?K-Nj$)bv6-SV^7JEGB%1^j<)@@w6YZ#S-+pIQu~2b?44cm2Th;9_;Sk2;1``p1H9cK0flBGKwz+f1v=T zfc_#F;H@Bg7m^RA7ox~)7;<2D14~!xvkX|MNZQ@nkOYbWKQFVk#KGU|*%W@ndD#7} zCr{6V2=MWkwm1^#4@zCTn~YLUa~#-`g) z5AvxCM?5W^#EKJ?VQuS6n7q)kt-`Q^(beA!U0*L?q+96ao!=u^#q^MjhN!2asV1w0 zW%J=xj9ULUwif8$7rI+LrW5{svL|2V=!WZw|GcoF6ZD;R9k+@1UUND*U}vEfjA8iE z*0pB%rs35|xl{*@*-h)lt<^9}C9Qt_StY#HG;G(3BLRcI%k8T~%rAw&o1NCfzMXj_XYC~VNhSu z#|ZCf3=+BZ`_+`HIRY4@B zNq$FD1qAz(HH7k%gM06ZGWTmFFzH~P`sGjt2YF_E#R^Mdtel%I_&^Eh*l^Wu94&<3 zO(FX)n-JXlgr-pzw>+R`DizS>$bpQPo|YBmu`ojO-|<*xLqb;)c+SmLgXgPdP8M|4 zVrosK;o(p97_ImBe3O3@-nulV&mPc*;)b&gFTA?({5`g>ZNDJ$V}&M~B9)!cG9tzGjBpE&$IMqQco6vnTa!s; z^EOy`5WrK{LGOH9Q(rN9I-p4kv*XgXvV@WPFt5*X9dk>2huU z{{lcbQ;pWz!yojG?&O>v^?;*8Ck-D^_yOgu;(Qi`SU9cq_oTjVCM-)=KCt#KfX?dp z%@OKC_;^Y|D6@s&xXWGZX8K-%lhpfl)W?W(@~(T_ajeUDATa6DN2v+?#9O?thb9+i zNP>Jazv@6;JL#_)Z5wbLOPcj3bcE3{3KBKpE08Ts@_EEa@T=x&4lF4U{Su$FV&BGM zNZnILrlgWZ{SA}g!7EPhM~qRhU9Ift!u}no2QAs_w?2UX>T2%8;+H^1GHz#U z;lt!rZgGB(56G^V=Cm;FfK5U-jMpDKRUfEe~bc_|`v-$S||4z_N@FlhMOQHqOy+L* z<@kr1jXFTR0e__FCQUN*;U@-x%WpnRC{yG3LLv#B(7>MECzTRk95 zPJ0&BvcL0F@J?W~`*IhH+z@t-J&~U8?!emxd;awl)DZV;@3juaETXS^@cv(pa9BFb zZ9D=9p~7@>v1e<+(~#rxt5+?+75scwX`&6P#c!(LuA$yE`F14%S}O66+SD zDOHmwp%47qclR36N7#EMaqc2_8)P5cwR4LBaYKW#AdTl6W*;<8lDh6e>>HodJWCu<`Qzb96?-#`S3jWaBVdZ5cDp55 z*InUYSzGkIl2S-kZsY1IYXkW#!QG^#d| zS$?c21#?QCdx@tCU~b#J`VD^;7(9*$l@Cb)GD*F&v)`hj@A-q4C!PWDu=I$^@f0se z)=#SyBls4tOm0iu9M*;CEe7*cX=24#vv;FaGDiVx;g4%=A2GvnZRualE39#hi+$XB z52tu0(uYGe@X+ay=<@{z=)9%;VS!2srCCVAn!@Hd8X`#h}@IpbLKFrC{TV={;wRfYC>*$U9P};!-un1bt>@w z^Eom!@Sog!N%~-QmF!AN*dm_h{ z@#A`<__E&&>Kn-CZCVc?Gb`mq3#xqFcITJ9_pTQBb!w?tz7zS!y|(Z4O#9&{M?Pf+ zaV0xCVBM0?3nTU-Q#yOPK_u4sh{W>_xD(EaI7aXRMuKSa=bK>h!5Mv-v^t=tIUHmv zSq(g&D`k}#E8%lPtwi!Cf>SRpZ7dO8203B%_S;h>VByoda)aQX*Gu&x_Us!}B+Ryf%ujC_-O03e4`dmET!*y{XHU|?rsY4fD<)B7ock24T zT;ln!zYYj5#KN<`V<%EcI7H`deCt6cYIJ2fTz)czbN7`Dbbl|QSN`X#&L@{~!TX~3 zpvEHB7Ee~Z*PTUyhQY0yCX+a#K7CyE*ce_Wd2mh>>rn4-{>rLj55C;2D&aS6!$KK< znp@E|$oH4RasTl`q%DB;lCPf8}m+v(Z95ZV%g~28qr8cT9PijLw zP3n2mQ~gLrZjnAVF^=+ur;MbH=1^kX?cB5PKXLfQ3Gp?@6`U@tq1x-WiWWtW)E$T% z#_Y2jXU%6<@cRRJ{+DVQ$;`=}x=+tz>Fq*E23q#q zQX&Uqb8k2Qu4k~yB54F`rLbRn$;xxR8J5MW@B7qs0;O}^PR496{8LqCWSkp-^*-}$ z57!}JH}hwTB=UMW=WSXl9EU)sWuK&K^dP8IpQ&B5AAp;t5(Aaj`(b3=I@l?%7xZ?& zGW22Zfq_%WBVL(Zus31aT}`JGPRFn6CDIdImG6}13GqZ9j;{U`2)4rM)_)G-M887& zA>#?Ik3^oJ>~47C=LWd`#fRk};m=FF!&Ev%%%w>^+HEOBQ3)LVLv`Ezh2Wka#WCp{ z1vcEtcg43pgG>F^sxPS$qiq%5*;kN|$}}*i-j#%glA-x`LP=PBusvT_X z%20LZuFC*@Db_s^e6MF#f^$w<C>cf{|Iuv_OP6eAZJ*6za(Ir0hR-sFxyh{P z#}oNqY#fi)Ao^l*J2~mNfTAqdtrQn#@bK&E{-XDjSi>1jt$Jk)|8om(e>XCShi@>% z7#ejWdH&&lJvUmBx#n8|m30+5PBjF3-^@d`x|!DXlWti0`SC^wV;Y3+J>R0xPzut% z1}ZLu|FgZ;b>y%v!3A}vZ#cZr4hjLX=M7@IAfk59KF!BHKp#G#;}zKpzr1KyUa0ng zhsM)~?N9pP*12;sbWXkS-?0*33#A_T72+~PwyPVKebud9)H)$w&!9)KpU4~hcq|jI z*aj9?a=VTboQQLSzf*qqH^J2!N=9=lBG++lk)2ns22#nm^JEFXyU*tb%j5MVSU}!d zmM5jK`RWN1m0;y+m z20=CK%9-UKJ-|I9e_!}xJDdosFgeTF0FJV!*F)$?VD+-Ul0hR2EXJyRO0EZiFykG{ zzS_;E<940!= z1+LP@qo>HKTa#WK@;tvC=CL;pi^GP58odd>x&Bux_t6+UVCKDew;>uY(yi<5p@>GC zv3b7gzmfRT<@H;W{0J=GE)R274ab;UGUU^(p?D*OW8&uiVDzC=ty(k)K&~Krr;kE@ z=$#{VK>UR_eu+^OnRskZa6YBx_q-3qfhYIXGTaEB<#g94-{NpwzR>@HpU4+uL&i#H zLM-kzFdIDB8jou0&$x~@CZMd}Qz=1(6znrbX>5k@k(71oNj;8y1**Gc|S)S)?= z?If{)LHYBk?#9c={m+ZHw_^^6j5mvxr+P6x@`2jyuCG`;(pntKS_S(^mvhd#)WZoI zCdcUW}L4X8h};+=4=glylvM=UhT!4GUY7Kk|$Zrwp_FW&qBJ=%X<_s0q# zsi$7ut2`G{HJ>c}lFf$luS%b*U+2IBXBn|`|K&jO`hcQge+KwxoisWtp9n|x+w|?i zSjbiHa5{J_7UIGevz`pZ!P~V1?fRSvAlGqZx5{!HNNCg5Y)8fc=btZ&Kh0xdEl2r| zv?9UZ`?@Ojp(GqUPt*k(3r-~W6e!3#9xbA$>ARwEWW9fj`;J8b9{kRr(QO%ppVRwM-aZMf zF7#zzU`a*SSl_|z>QrR@%HL67l7ZQ0EUR5#=Afza!^OwXYccHNOp64m7bP*)b~p6| z3LKvsFt1xc$~HROL$!k40S{G(y9kzgXjt!-5k8Z8V@FEQ z0XTUzB#?}(7v3E?G1FYx0g`Wc{zf&m0khSMv(%9-&^ju0?mcBaY>b>)Bdtfkz6?92a?0Ihh1m@$ci>!?rQRfj;m8SqKYwa^xtk?a>5_nxc7SU<-kzb>ijm%48b5+ z&jAKfHf#As(ph{=<0X&1t&ZxMW;PL+|NVG0rF%TnCqB~td*Uzf=XGkQ3 z4ji)lIvEbSqms=ICZRxA(fN{Np9|K9uE%{dOUK1dLFNhn6x2xQe|)k(32WckxMm%S zNB!XXYfT4yv1Uz9aK%Sfb@nS)gXa_XCRG)puQKGB8bRnWhwrYjZyziN z<#f?^+EQg;zPNjuHLnD01|ueBf(k*Qu;BGLZ5|8{9h1o5$%d{U-ho8p2R5??jpmZl zz^Xg@N})I5m!V@B9^Oa*!BBmN35$4;>#xa zAq?&vlb{H$4FoaT6N>5j-{G~c>$~AWA0TarS{}UN4I=x6U)9umf|Oe_+lxV0D8jCn z)i<2s_0PqHax!RuuBsz`;10s+Y|E^e0K@4{3^yun&{oxp?Nso z&+sr)Ar~w2H?-5qa?nxYwN6@H77kReS9X#Ub4P@}H~9Yffm^FZYs#%vIK?~nmr1D` z-(DphT5y}fnDgt4>pz$9bnW>qx7MGi`|?lE9%A?TD*5Md>%M6;K9d-bkUEOa(u^%s z_j<8aN$V9^0-@`z@L!XDLgYRqpOrsP$wn@Y{Ot67L3s4ex%VILe<%9Zom9?~X;8PD zb8&_|A2ig-!fZ!NU`F-4@+(;)m#gwDyt=gnX_daL2YzVPh~n`(HMBO7&YPYsMbyV{a^u^Pz#GaX+Os)B%BXD3+xR)Afu7>AvB zIc)5FjtC?;N|FO}qSnr(z(Mc&`|NWBNgMUrGY5WvX-gTe@L&Plk={Dy_d6F{+~iJu zkjsLPd~a+0y3>LFT-;-g>#1;qar?jI>M=5PY4BJu z*Z4F;GSp5GGXtXI;qR;0doPB@0NKt!+>gj8pgtQ@HFPc+=-!-)kvSnI{N-lSkk2jC44j5EWf= zX9zws*zXKejR3XvvARcmy>Rt%@9?wecJP_ozsWk?3<3&|Qi2}V!uceZR;mqxi}1Zsc34ou^s5!d>uX(}vi3u%55hVRiS^a2 zZ?j`3_}dF_$u zs3;!!MSde4qepsZr>QgW{Mv2%!lrbjGJ0N7eTVq{%H{qKC(>|h#A|oqw-h9IEL)a* zl7ysLbqWsp1Y9}yDF19vEP8)G=3x6@6iz#&R7{IT;ODzc1nwpT15aE1)g%0pl0W!X zOS3AWquugaWkoqeOSWvZ6ZzW-vf`(ES&4dyWXVMS;s>ye(I$L*T?7NY(5!|-j*^@?}rPhhRorSr^~248&doL1hBqf-Y-FNFy1Kd;+()_gb0JCt`Fx;FyC z-=iW}WtSnd##mRIeF?NLH>uM+9S4EiOAV?^9pL@rm(4%tDu`~_Ka(Mx2W&?#SADh) z050nD6_?h7u*sdR>y>ai3P0P_i_ytNpLg|LJLVAxg|qxpI8${ab?9(3QvIQDw)9%a4Qb z!l`u0h)&9*+_;_U>Z#r2yWNIZ)1UwqUGgm*a7?=|L?X$iv(x0bL=F`-V zKP-f==NHTM_9Q#7uy}sV(7g)mc1xZ%kyMA)79Muj4vov>|2ot{Vz!|9m9v)9v{#pxboETF6H5ws4jV2?U-9O#r9wTHZi&=sss>Us5CUqX;S($H^X?3QUXG`h{igwtPNtLiOK{h&I$9qr z;_V^$n{T%ECUnAE78U~?4uUtlr{aS{Obgh2+bzy>z5!$^eCgNZs-d^`_;aT}B!Z(J zGM4D^1MHbLQtvwEg5=cH{LjR62-QBHYh4%%0#s*CCK7YKv^iH6x86AdnK=7YdqGu6 z1%+7`W?JL^U*l;dlWyoFbW7t4uODi@crG;`8iZr1=^tZ)!*JxWpTyD)A~(j^@hv2Q z@cIsOmF+QzLYYHxY16KeXv6>V>&oA7VvcY8l!sL~wrTJEux%KQ{kr8UTee{+qc_qj zsvL~$0?I?PIjOjDr#z{bJq=eI-fuefrr~^?bLKm~bQJK&VCs3Aj(m#O4mv5PqfeQN zcW+w?TAVcJq2{%Q7Czx@G82Sfa&zO`Ma7V*fA;-p@@8zfEObVYdJZusF)x?!pKGMs z$QlvzmrFkID!--gN5ulxp4~T7Fns5xj)GYw$la!oq-1J?&va(ROw66odF`f*m|rKf z>j~{^des5y{(El~$+W@!FYn0@l{EwN{SD{yr|Th>c_UYZqMG2~?!V-%TnzkW?<5xoAwCI7C z;n#dX|Fz*q9}WlLJKqxVlVm{TYem@Tm~=2)F+2AtUkv;eBd6Vo!rnM@;Cvz{6nlmHvC@oox^r z2Ux|_*7{>;Lwe=Y z67R9tpqv=-`>AT(@4PLj>2l`^D|0Uf3(v~>`;VbOQ{$h<33C{Ila^* zn&>Mg#nRo)+3AF;o6X%{6?!4hT64_QtPd{IhU?B8?gQ??D}#57dI-L%A;ZL27fklh zL>F{*z&|Sk??1%3!QFN3dHGrka6DjKJgm_K7whbc%E{{?6vy-KbX3D}PZt-Vt_t9% zj53-dC&BY`qVLxSOQ7!VVV=ED2`;jez2o6axuANmlGBRN_gO{70>!0LfcbAws|
j;MYIKPi@ynq3~ywL<-U-sCe_D4glLDPatym%ciNzzq=J^T1_h z+ZZi=&Q2e^_#FkfIa|JwGSFVD`NNIe41C3K{LF=WME;JQ^R`HLGLGoFACB}+LaqFi z?OL5gJn?Y3_!KcW@V?~P+xLzT^Q$jNJLRo80%L=_M<0>X5qB!-RTpT+(~&2VlD1~i z`BBuNv*(wQ=7MbV@}4>Lr=B|!-#3CnVPTC%-0i5$EmM|0M(9qJyF+aFQ&BDSInSjC zJ6u*Wc%qj34F-P4JdU3ya{C{Hn(I81;Pb&_;ocJ&u=|oJSqf7w3{^+H_GK!B7eiFH z+5L(^&`9`TZe%fZN$gD5=@)^fjO6=g28D1VBP>Vo5W$DhUUsgCDF6+>Qsr#@0@%FX zS$B=50GOz?wdwZ}J^<%`qf?`~@ZPr5&8#N}(t>I8O|}Sqmpe|Sv%ZZ^)3T0 zr@3*yu1Nz;D3aOCP6qj2E6PF_B0pfWdClZ`EU?}!A7c`a0z)2NAwkn{@E;7ytZNQ} z*s*(tqZWR!fA60q?u%aFl}kyUZxJ<6-z%m!C3!@ok83Xj7M2Msv>-22dp1F663E2-OFM3-VmI=hKv;D zZKf%7PvN{_RQZ#bdphxqdwUGGwJzTZyBG_fd7u4e{xJw&TFH-n{y9eQH$4acjuCtq z+p6p;w_cFEMt*1}g5Wq(u)F0FbJ+fT)RN)2Nz4`Jjp4ZBn+`Lk2`8R7hC}J&b?sfY zmY}^6!9FzXgj77OS4k@&_>pO=S)woo#r6+yMb#zZ+#?ysC$g#7A0yS><&lmdp5HW@ zD+#{i(vdP|q?MKwjURD0Ns|2TpI+)uSejsIC%VkmVd~8zroy)lsj)e`JmvsLXpxGIY-Je#5 z(8MXAYyRIN)+n{ImlFQ-!VZT~{f zJPOyIvqaFz4h|HT=#K^1RZ@$;!RcxJ_N%l!>;mA%!a zY}^VrqR3TziS_D*u}iYR!zM^@;mGpKuLld;v;rV zETWg43dMtJCkx*sK;|j6kjHPMp)fAs?@eVw588XO?`?Vz&~wjJpXv97^zIFoVHyv3 zmJ|}865|SMom=T-c}`Fh_k@R9!5&L}s$1`eH=v)0X|Tqp1{^r^4R@C`VnudSEPH4x zX6;W5v18~#YRUn>*4_~u6^ohQUonZ!0+F5OakH5JCfn7lb^)`qt5RvmmvJC(%jAm9CLvVXS*yC(_0f$s&1Ihcq>zKGi9#0=skc1D?Z}-B> z(sy#zgb$bTSagKY?;c`nz0M`N+D&i>niWG_yC7NbY5K#h4kCXq>iy2H9TJ#MouWP1 z25;lF>FG0CAa3gJ;kb$>$k+UmcHvh&Oo;0j$0`t9>FGT;R@SRvNmnn=N23D1^j>*b zRZ|8>+v0py$cXt)cNm7{g0kTKc1?o0tvwu4T6b>HYD9%Rd4w`n#bq8to&3iRk1wI$ z$1isu6LT;0(~g`Mc)W_5)3yhbY*%rdRIKKyzJjwZ%~d|4OXx9aS@_&>275v)`bVFS z;jcNHUr)BX(0}aY5LAZr34V$-E2?ckHGO26hHx3mB}E-4Gn>Id_Vi2Frbdvl`YFw_uL0&;>X%n^>VW;9 z59@*98kqb0I?_;){2x-hF)h+Zzway=JXC z5Cs$Y5qmp)%0Z{-(v1zVDiGAo8}$~=#ES=Hp1waiflkK;8n!%L!tE;??g1>5xGR;r z^!L*yRJmkLzu-{}1$%9Mng&~;UGPQ|lPuv9Zi$36b+iDZ^mYb{f5g}0^r7+7`*PTv zYI58(C<3_&gBSliazXOLOO9vRnS_JA#I-Fs4QMRo+n%3EhVkl6{#2fLX#btt+3OPx zqRkGP+k7KH_j6c`sqRN8IR%v`*7rf#2YwB04E3U+=ec=M@ ziVINkX9@Tx*+3doXx;GHYq0cSpW12Tt4L9D^uyME6@0flUnH5|5R0UajL>Qr;GCRG zaTS?=jxL8kqltfkc?|}aug5<^&O>L6nmzS!eUE?h%ZJwJV;7mieB2Rr7GCa(>T<%} z2PCYMzK5Yv6>X2jc^71f?d5#@_YDq*CFt+6)IcvO@p2QR=fH8%$|LZ+EzoV&Eluz^ z!!I>9`to^qC|9{2YZT`RqxX`nwD%Q4w}a`BZrx|>HrOF~ooNDt=|1nbA{oo=`Au+_Tt8l9H+*ybR67nRC_zW5-z9+(j`qb!&TLkd-Uh3VJULg?@paukS<9t zvY}0eS8dvvbsKSz+^gp6Boqq|HTQaIeUAo1(=vn6XVIXd=Fn3x84ZzJ?7Mk6V!&*S zGScE0`Oad~ZbpBOhVH4NRzX$5ac<<59wq1Xy}YrcnzTr;KBukpTqO$LukA0}@;efA z(#p09#YT`G8fWLk;LlKAYk1uP|%YSw=Y>Yc#$Oen8`svQ&+Kh|>C zWd$R_QtX^%@et5|-hhhiB^!@T3o?|4fzg-WvZ2=l!Dwan!^9g`pm6jvzAY{boK9A{ zQjb0Gcb$^Kv|b1*99Yoa@+TRG6S>rc3##$>S$pc?$v)imeb`26=QJ7zyF8`}TtfF$ zVI!)XNtAfpyWcM+6|H0yTNTN^OEFM-)$8sA{1|hSuGu;clA-6XRO}jtm_4DU$DjAX z?-P*Ca=8<39r^6Gx`*_PseXP}P3D+NBk9jY@<|RNDq+VZ^1Em8dh+VGri1YD^WRcB zqabgh>*=PQJ5Ze3V9?+)M9G`+8@KoPVcu-`QaF7i29JeB>Tioh=9FLYhlS!%_$K#W z)niGR649$gM!)A6PMdJ^UN46NI4T2sSHd@od2OFezlP|yC@ zU;dmlJgJ+dQAbPWb_?HM9X+0m&Kke2YosS&?pSqwElnbNMmfe@l1)P9Uptwp0&D)8?v|>Tm%s8PQ0dceapr zIr*bf^iyQr*`D0Y;fU);qbE)=_#lVLFD9?g0VsI$%xe*rAUtwVEkw2}7`1RJ>|0VO zKH=th`|wm47R2UKuhpah#m3%l#gPO^yBd(@JsJhA8Eu99oy4QK*FYr6kM!Ki$Hd=U zcnuVjEm2~5*67Yo<#VTt{Qmc@>iBTC;!oMMDW2f}bD^~~UNqyleKBaevB3ZZL&^8x-h_Sm18wvWdBv<#iVsqGyssS3$2|oXKx*95b2#K#>4w+XC7S57A z%aaFw( zH}N;$UM^iu34`(*?7Bxz1i{vH%6GBBz96dppVWm7vd=nYEMaQp4oNReuKl;u6}C2a zoX?bV0hQAsF01Cwu(V#Zg|ER8wyr9BcN;rE)}O)zE=nhek>gvcB|h|lmW;8VF>dhk z_uZ#&F4=+ayK;G-UGBK!h_2n&d&Ji>)5VL@)mW9n7c@jcyq^hl{=6qh?rTg+U(0V6Pd;;CxR*Rh{6&lR9yX03{!IR; zL;5sg+UqTTg!JNrlLd_2mTmacuXN>}Ocg#U(s7PGoPwg%TRGp;#)7#I6=mD$axgzq zU3X2h2`s&ib05*^fM=42iyx5uKI8_i|fyKX~J zX4vkM%QgtU&6|`ybNyi4=wj}h*b7bv=syZw?S_JR%}-559U#1(FX8#R4J?y&Cp4X# zft%yNbyKE#xH5P1y4qwFMA81&$izxKimD~b@>`3c#eLv`_U>Fra$^)fNpiyl0!J@Q zt0%%y_2**BhohkT{h`yX8eSw9X(&snRF2!<_E|V{m*W-gm`eh#kd+UZb%{)+Furm|Nd4<)Zuerg@*bKgAN=-ZB+`O^xocYnn|U$2j+)u(aG zjf&olzr?$=KE_-7eHnKbZRxN6xqxbPTn@|+Ca`O+XutE8er%F9djHX&0y*|Nv5iqg zz_Xf%mrSFc9Kxo0QNAcaCq~j1MRIFx%eV7d~C^al%9G2z3|e{Yt3d zVkh&_2EGT&U)#a_=P#rFRlqkOWW1ZL0y^WTx6RX)5l@Qw{THOKQ>>CT{nsSnOnc7#xqLN;^pi!$2!6|e zD@SVg7dodx^6+-_K9>OgV!po1<1HBtiBP8=R_9jMEkuE_s&L>^iz)c z@!9Bq_PfMMn{50n>dLw*k&UO4t&Z#emxaBwo;SXRdJ>;2CyQrR6)?e1hd8}@=ufja zSj*UihTIj>BYiVSl{BaMpVTs{eH+aeXqv;1m+mNUZXYE)T(Ci{Wh?Hy-$tuYqD~_7l=kN0;OkbO4`y$wDT4HQ9zDx0RM-X^$#l9R z)4ib3Unz7irw10c_M9}QBwoVWE1$y|TfnvF$$|LHYFOP9s>7L!(0wiT=+Z^P#g=?3 zb*~^B6wcc3e@QQR)>_lQoB&^NcPOK8zV8I#N-mGikLiO^53`8lu4kw+yeINVhXa~L zQM0nXb4S{rd-oM^dLgI5#GS$_A6)dv>wA7a01Mvitl@hUh&QsY4Gb;^p{#=bCPQ}! za`yerA18hv!GaeXKO;Y)h(1?ddTAJ5zNR;MCM6WNYc1QH-x7**cT|=}{sp4LeMN@H zB>|YeCsKFq5$SpNZ;ZQ;=7YkbA$Pa_`hX3`exF}g^g;^O%fU$}A0UNT?d`BzDi|}T zMxD9a9wS`e)}0c1hvM&eA;Z%LF1cR=u#vMxZ-ylhIrkMkGr8=GOF4&QO&CAJ zd53ckwti}ZwC4}ZvN_6Ox5f1S|NO@BD9^0y^mD>JGxTW53ryi11?N5HKU=ZAc-}|L zmCU=8m{);#-BPFaL~#{2!1}Ob9rf!fF!^H^T1it5>vO?3uO%W>GBw#MtrkMa{p@A0 z@;s1~iP);to(;bT&Wp$-WPsLLgSW=3q;KwDZK+pk8vLG~GQY}`1RE5`|GIvU0kz31 z16C>F@X&Yd-~PN1Q2g=ZR+?uRFl8lpSh)tm$d_XmYUe$HF|d$V`GO0aEL%TIyXp=u zQiNOG>jM1kcXQWc-vEDw_ss0Y>yWiy^%uoEGZaZrkJa$^!k@>KizA}_@s8`*t+ff# zx4iN0g~)C{bZ~7~3uGYt&TI3OGY&rJmLL9}mvH^|+8dHmRxVh2hLfIlMFo9J9Z%3d zv%=PpYP}hIH&lIEh1pkqk-~$=!~0M$%KXWtr55~zTnqAzS-GDv$L_Xw^F$;LKha~z zmwAlu+&+Y#lSl>XbL_vZbSm+1xb_J)=}An`(i)Q+SVG|jnxUc9DZEHg{fX~LJwEB= zdLKdZbINbC*veMFfYz^|b8e}FkXirir{u;Lu;6mJ-*>$aJmw}PZ;<@mLVSL5&T1Pl zd1a5eWi*0tQQ)GMS~cnOb87iXTLu#NPcXzN9}YEV9sa_c0jl=@W&}>gft-7Q(e0a| zpdvW#<-E%oIEF3}rb`n;&0W%I|GHx3>5HLd-~4gFPmel}_anv`Sha@pMxgH9*qWWm zQ5fXq;iyaaKgyw~u=Fi)sFr0uf5SQsZM=f_Ql5y%<~N*{_Z{L<#nz}?^lm&>z1cDO z<4YVeYPB05*oeg*t?{2uw6VzB=f`ioLj00Pxj3JiM4@$Ie9*_+p9%NcX!!lS4^G^R zV{>TrJ>2G)?_4(rixPZaq&MdzLiGRlHL9?go47xru48Kjd zh*q9ysvx@(_>;u=@UCw=oYs7){?WMu_U0u@>{)9goDJoRrp#8-@qIRxo8;<>aBOXF zcq5c)dG;$-)xkA2E+1dM8W_`CJ+B8<;8ioOG)?%{tS1lCl)sdMGAlE6*U4hI*S2qc zhe{rFAHRFwJTwbRUU9cS>P&~1iFBQ24ap!-blp<%cpNahL@zSbM8F09M{eg2g~7Ti z`(|C5FOW8iKcl){V0L>$^~baWD2V-XKRNIUY~8Isd>^=hMj7;~8hjdP`$eGii0?(9 z*t1=NB8v@PR!{I%BtOOB6U;>{Zw!&cBfRn4s0PNJ(m7If$^olap0DkQ@ z=+ZbcGX>~0cTXX+X#1}-`xj7U=J2KBm&>SQcS7fY#dqYozNhtCE$JT_-WJqNasc%g zc{Z3gDvfZD3vt&rq6azb}s zEBpxVp%S>#0ts{uk{XW9aQM%5zppk;U>C3^qjb6v7;TCM2lDDcLwj}b!xHg1`7Mu$ zN7VvVN!Ev>f2!di)7CCLUIka|qUR44R=~Fr=FDf;Dq!hN+(!|ea<~~A3y11R{xQzL z?7@~2@T3J1rTvBQPD5#J{&7AqRR*iY59LBXc3!Sm$Z)mXwA?HktDo_8tx{!SeSYb~$A>d8(}muX!7B|DQa3slbmGwV z=?k&XH1bFhAm-yEk_8Lt6bhD4<3aQFte)G`4t%kHS7IL4RlwIt+FjwL9L_vY4BO8Ll+w(3}rorw< zmt?8wNRNVbMZCnl7p{YSvT7pP6e(Md6VjIgsSF^aZGV?5~UiU8; zKbnQVCo>B}PG(}cY;=gmd%_oOvM2WNml97ICFj+8si`*cB3G< zKZ^AEEWHfv3Wtm5#kwrB0%5<$xz)7}FL3-sA2aXt7DOf1W1ddx!IY#)Li4IJ?)Bh| z)_(H_m7MQdhLU~btvRMXs-$A%GrGD(wImnS-o2MSO!k`!eO&x(lVskhIlQ+9U6`C-uEub#318|*i6*`; zL4{AT9p|Y1aO$79;HGyHI2~j)5UMByHY#hsXwh;=@?^1DYpQ|>h01}a#CI*aEc*Th z$zSZHePOfqwGKAS>_p=j>!H5VJWXV*7JO8ylY3TcVCjZ;#30#63I>!N7TH?`0=Bwx zHWZcMI=}ltKFJernfdS1S#{Ebnl4Sp&rA5foB4v_7mI;9O1Ritq5!HCSf@{K<^VfK znoRjn7SNm>WB9d^0eOtd#;2;%VR^phjN-N=pqQ^_x^w+A+|c%9{i_%Rv(3l%-;WK1 zc(L%*%3?ooy|vRSGNBmHerGeIUMfbGwzj!W=@J~cl}mS6w*)hvvrY@kmSF$$?KV3| z-lggAlZ$*hB^dQG)Q{;z0Sf9L)wdWf!eYNSPc1ICqG%&c`i99Ue!TH4C-LS2(n{V4 zdR?}RG@O14@1}@vqo>1dasN1K?fbFbUPk~6;=sVOvdKf>u_Om?f2AYol#9nB1f%jG1MzD!spaqm{yi+)RtoRCKlPS16hPdV2w$34 z4y-iIdmOCE0I9Q)>i%gdkaA(0Tv0$AT>BTSX;~BjD*QFJM?dalqcQqr-gjFOZUYi;>=ox9H{mdPn1FH?(hFb2it1j|xdI zfBlj2!mO>;orB7OcvmIWX!&|2rhGJ)chavw+4D0OZ1z>)os|>2D#R)7NZ6j`(({PEV?ZO1%b(ihaW2is(^=PT` z0_v>wNh#nG{z|PYrYl*%gT`|lqdCM6bVP1sXwM`Ddkr(@d5_^bH4k^@-eJ7H-+^Js zrVpRfs7|M+v|}&l!+qY})!3+dlwH0*6De49+VZBaz_5iAr7uSstg|=BnNb&mrbSyT zk9Z~V0mwevNqEJ$2~n}l&Eq*K>%-rU;>UjLE_Al?Cu%Y|62F)&^_( z!u4bEq~C3;dGkHuhxN+qtbH%k3}(|>2~xI=@TY+KjCD#qSUH(S7}M9m8L<}&d!=h& zvh%#3$%QI#;!#+Br=I}S6a0@l8Y}Udr6a{X|1#Y7Uf$p)>GK_G?TSA6wv_B2G`E~k zDaG>3(IMMHNgi93X63hVInE?oS(Xe|qP}~h*@|Hu3W|#+9{AFM6V75v*fEA>;a6B( z%@{;*#_5~4)I>3YKNRtEmI~=?LZR8Goyr~ z*fZx?nncwBKkkX~%e4}3Ku18Ql_=?R-fJuS(6|j+e;J(}C;ozWOxf2yk=`Dk&)d#s zs*?X-JF;IhGuMNZrrx>Bw`(Cwv?%qJb~S9KMV;Z_UJ2V|2ad)VmcymT_uuQvmV)YW zNB=^#0w~Zt-CYxtO@0S6pA5<vvJ zp7plbae)%#_;%VX=6NuR&dutk=ETA8z#jogl=;wclXLK^K`ETm*Eq|ztpXG&?-f21 zu7cc|8=OMz@?dHBlBT(5Hng6r z-1eY96P8Y#S{CF;2aQ|Lh8})R050`{?U7Z{@XoG~i-U0el@ZIlOUc2IaOG3ul6?Ri zdKvI1fGG$rZ+o$$(B2QcR;bc-+dW`Ox_rT!+-D9t8Tj5a&O)Q6r5vppk~`v;HRmXg zMI9~r#`>2L*#0;ovt=a+c_g`3eoq8r+>kb1k&r)9gvJ#cUA~5aoGIM{k=Ynzwh@#V zGk^)p`+5%+&f%7CwY?c)i@2f2mAj}+d`&J!ea%iISkl+NW_zfg@GfrA<*2ZA^0w&>=&hRI7FnsKgG+P3%b6_ z!F9JvNk8&BM;MfmesErE1*1%e9J-a&$YjEf6E{_e;d_4w=yW- ztaeqEEQ6Pk^4?t}*E-%qvr})X1ZYy2i!<_y;k3o>cB2PHB$x5~!{4ENNGd+t`jz;C zI$mi99($Vuc8ja0ef_fF`}Z{dfcNQ8v0xkfx*!P}>db$Yr;>ZoVfkgvoiQ+7_lZu5 zHySMFvS;F{qG9iSgOuUv2-xoE-t{p*8060Qw(qG+!h3fXg;?ZrQA}8z`rBp}YP4_M z_@Pu`$w{HqI#(GeP<@}=nqg(vSp&g$rls)-;!XmypeTb)|)C8qXQr|9P*wA4TshT>Rx(ilPd_+YY=+ z1^HP^p&a%~=qfD?U=OT=)8|g}uD)-8O7%XYPMQWdxwgyxNOm2(c9xr2-&0HWk+ePs z?^Q$ZYo1%e>XoolI(aUKtsGjnN4vKxAT%{cD`wT?!A>#S-9Ba+5FuI0R7l=ErRA2+ z52h1fcU8yFw>Al2rbq2k)fowoO1XaAoc4$H8$x@H)82y4#`nU*myN(n^49Sz*SqlK z$y&vU5P6Izj|47DscB2^U~O$mF5( zxp`Q2a^k&KdjalN$cfG^DMH6hdjaJ)q~~3(RMnZQn%s}F^)#UaL#jSs+!r&9T$RaY z2F8<^Uu2&}^JWfpmZ&fqhmdo6>u zkS!sUVhCs627S^?Dg=dHf>L8ax!~$~arZiVHXI83u?gboke770!j&fhw0JK6bK{GG z8OnjtpNGR?>WgJiS$`NjnTV>r`YafXJB`i7DZHUU_aSGsfg5+bnzqi zjf*w>raSr|f_R14l!;%*`-k^9Z6_$bRCL z-Rp2%QK0Rta3J&M`O%>Gx8c~kJotTcBmxoYO~;v*cu7_g3L;8t&y^C~y+_K4NnZb5ULs92%<#$|=6io9EE zWnQ87h-%M6|5xZ&t#Mb<*a%bnrlJzlp5yZb<4c8R`uO(hRjR#)&rtfT_}uff&-kQ- zG48s;JFHA@mv2;Z$KMxz|rPZ}GWCo^R$2+RjJiZCm03!NQTVoju{u zk}S%j>QM+Dx^%(R3l+e){e({q=?6C8uGy|YJ%Izw4bc8%iEu$DGtYNS6aP}@t-r#3 zXmpcLFsCjC-R{h>tr5@HB^ecqDAEIBe=SyB< z>=pL6tz?Iho@DdEjz(9DTzGk1TKcweCgDSc7lg^&KP+`~+4WNrj5^y>nBR+o7}-iy zj_;AA=biu3Dn|s=)0{lieC9JmDn(EQrjWkw`|Dw5HGy!B+c~_+H8n*!oiC~56PEmVEKtV4 zv_{=*Cw+8HNV>;=zzk&y+#h?=+hcKQ@9SG-cBrMxc;I)01@1EayzF}Z6$a-G>`Y4t z#ouMG`yJ%rFi|{R_?JHWJXmSn==U zmSkMj+?L00o{eFRFP4}>YmmkM*0^-=0QS2IC9X=$60S4wnQQhEzAE*;ca&y^?9&?( z(uI1k^Wh`P1vA2tLzLfB;_+%YJ(%>Rkq>;R+7F-49Z&A@Xc zEKod*ia6U#$$)TL!d&VdkdB)+i z=TodrGCp=S=@Hu3`CXdnvBEFh@BVOj+o7F7zv09K@*SU`b#9?>#s@VADoT<3{e7M> zuiX}o@kxCi`ueH?tzHd3s7iRu$73iD9*i^e0T(l=fSqbxkj6`9-OT#8~b z;Y?pj>d-_$!QA9o2cCYT_U)kr@$kvfs{J;b#BdS0%i>*&_$8R)QP%hpDhN?5x75#| z>21^rC;6||ITNL|lY!VRU)2yc)&Sps)?VW@?10Z*9FN)xI-qomPX1NZcKFErI-QpA zKZ1qF&r(r0g5+0k>(ilxH%LfUq8>v~YPEPm(~%2-NueflWf^dWOWRCNHx2q6t!4HJ zq{7`F<<}`0Qs6Ap;DfI%iBRTtyzp^dJUn-n^ze6x1);)Sw~lH>L(@(@X4X%Uuv^L_ zgsSi}2vu#^yxJE+^25fX^b+3C9mOs&vQD^>w~f@3(S#>@)J40?>Ixh$h>v$TW`X>t zi<-UtJ#c&RYDw`ff25-gNC}P(Lb{z7{60VSK|8MQ+RAumw9ep=pWrq@j=Z#VrCqmB zw!_ExdsjI|y|!^?peV;<(+T0%NFPt_g^rAi5r{vIhP?3A%g5mdR?jYy|2OrX+!xbz z%b-gw*t7wfTl+sPL=$BjeCl3^#18yRJP?Jlfi09-o#mg3T<) z#eNa9c%&8MqNb3IJ8IToaTEi*&Yciv9Ypt+VmnI>yYR>(Wvh|GM)Z2sQ=xd18r5^u}}b-ufSt>8>U$xuVMM)z~(@5Ymx zLC@p9%!RLwutik;CGXFA2pZ9d{YgAB#bHLw5&>k-O(h+aMO_VAyGOTwv?lju^NFPY z^AiQ)T_I^-%HX3^T-~jdQV_|w-pz0cq5a6}z23lLC}S?WJanxHMqQ_8wLJ?!n1Z!X ztil`k%IV+zC37D={g0dCYZYi-UUn+5xDw4o=&l}gtil(nA~8?Bs?lf1b@6yD(uZ9i z5>{T;g!eKZ-YFpeUMt1f_kAUXF>SUeIrPXRCd$>RnxxL-Or_p$SMuF2cRN{r*s+Y| zk;iQN+!k=tWA^Y%DdL?mUYgJ49mbP^!%EDuO<4Mr#zNNK9<8^?+VfD8dyc`E|7tFRq*O}0(!S!shP7D2jrrZ!OK3>6;d zXoZ6+>f6Q75`T8!<8P6IjUcafS$G2K$vxwJ^SD7Rgw*d<`f3m5^S;1#VfMz#E3 z@J(aLgl;NJb8eFFGwPRC&0?OU|@0t?Dtx5l< z5wFUHSY?PeYzFN(G*hsXd7} zz;QuGktPi#isuhH)n?Y-oi8k&T0$+_}d$;NlP^6|y7ho6$y6e>R zTJ8NH?smxZ=F@IiFq*j0RNoHlqUYn;$-dsJr>#a>l;n=PS`#YIRzgkFj!}yVguOOT zJK6m6!1Shhh^k5kjLRQQkt9je%mZs{nmnI@rI$*mjmP&G`B?+@cN}#LB%XmCmG(ByaMS%c1BcEYI`b za<_CD*;7o#`d^U#O~)lSca|wUcO!95{BSou6BMF4QIZC)U-eXIY+TU`C&ND zeoxl-)iBsO-^tXc8G`vSkPqp1)=jUJ80wE;o^tC!a4%2 zaB}F@6S4D+@K<2s%P8r`6AxSPaQ3JKyNo^Gm58^dgX*>t-M>PJsJk~R*pUNwLiKvf zSTaFJ-J(%zM+$sYJjary6$6c`*G&4S1Hf=6nG_XWqaKX#$0J1`W|;d zw#l*5t!o|dX!pb4pw>?KX#Oafp;ibuwfc*BOA8#7J-}PIvk?rMYg4QfYC-46P=*C1 znR9-;w(k#1C6qc%E_7{_!P=jF9aB1`z}L!<>ifJHoDXf4k$#mA-N&9BpAF6dUggFj zPR(rCYx@2ZMQIjzRc{rO1HxT>ADg<`K)BD8k}px=i&!X6UFS40fiF5J+(l~B9W#Gx zcfi87HK(0sZ7_Q0>r}T?3pvO9b|n330F#NkzB?G|pn}_bcZG5_NQ`hl^l7XB3OAQ; zdfH{cFlV>eXj%encRY>=Sr!26$$jkyB645~r>BnJ$OL%*^|trbG$^_2<#=Q>0i4bp z*OL>Efs7Pw)3v3~FemOwaW^6q#2fbA4dwTT&KoVnMa~IcCN=WSEm%P* z{TY?a5Cf1Ld=|GDVuFX1!d#iy{jf)I?%=uIW%!DT|6NcLqJ@~0#j6{|$msAUN9!K27fix8((?Bl6u~ z=xDH2^jH_DGzOY9_jbVe6FZZXv~j2D%16+S7Q8uSorY>DIi5RI(veBYM8ZfZ18dns z%xv{Dk?Fg`qqlZh*cW-iZ6qNZKPfl9aiPyeS9)U~{!97T`q^FX&ZSa3=yuIR?oBgp zY`yBCpfZe2!ana$R?lJMi2KcHm1SJCJR}hLdlqwDXQKFgzhLQbsr7A#P!!ca>1n<~ z{MgP9^hf5qVHaz&euhU z`erzp>Lqotl=Lm1SH7X8RRv*A3uRYx$$a^sw;-!%G33s9Yw!A&3-U+ZXVuj+q4-dB zU%4CsyVX+zjuTJEZI$2oZwPlOZ0Xq4T5kv8+&$AJY?_d! zb9zHE^f|Ja$R2j+v_r}d+y#r*Ha`25Go7ljU5Z_VHI$Lk-Y*^d1R z#74d!6@zzzQTp9@YmrF^hDZ*rn!gIg!8@H3vNa*tHej^da0g;kzSzxTjRL%>qZfSa zY#v&hCiCxP%0rK%5qAV^^3eFHkTZX59;U7RmsT5}haK{_KfX=MMh@8eXwoYk*=f}u zOjcE433V7}m-;YP;NBXEeDZeaaw}4Iiz{Zc#M))j#p-FOUJy6VQv6>s!Kr2(`ea1ai z@Lnc9DYjnb7;?FJcIzxTUP3<`{m~OpFHT4#ke15I(lqOv6@`Amvb}3pnFb|4Jmg4i3 zDAP3cQfy7lrm_zz#mc#XAL=Wmc)W~G6HWN4;;d_e4bP0nVB@7gjz6o@_Q3pI7xUakm`V&%*iuysd3oY_|87^o9i4@> zCo1I-$yu+;e;ncA^V$@}=LNv|*zz*#0=Wm(-|G?bC%N2!|D-GQ(!fmjn_k&End9A( z%<*B2g~n9*&$$(mz^f?x{Fz!PWX^uyeT=-Ho=~=j3br~!=<^?XnR{)3Uq-?yq`(3i z7e8hyl$t@_tGq=;D-$pZ8XQ-TdQ9?|jomBTEU{qAEedgOU!?0vUOG(fosBY1($Q6A zD1Agy%T%=tk4#L*-2PLF=lfGoaz-n~+J0NW1WR|Peb$pmzw~?} z;^7D$WHVZris?gzU93B4y4&#glCJQUzAEgL+5=~vWFbW`trNA$d3@4w{@XsIENBn? z@Lc_56>#)6H#ki;!<|=uuh{6cL(D(#JM<4aK;!3u5MJR9@Z+2v@Cj*$Q7WO0YmMYy zly$G*bXhB0R~&BLE!zS+mhxOW4-jrBI)5mss~#AbIzAM7*22XbZ>DT*iGM6Nq%0}C z5^fg#P0X4gy}pC|a9*(tB9A@lRwO;cil+xywjC*khlvp1f4=}GPaFPqugnE&=6hLV z=GoBI%zM{9H52A7CW{NNWDxFMj$(XUItW}SJ|;?;2I1$z%-x4xL1d?#(aN(tyyO;; zyu6x$T3nAfq`1=1P*PG?{%jh_@k&)iairn>f$-libW>5oU|>4(kyHOzJES?Wz78S$ z!YudB*iYNr;QH1#*-oT~-1U6Gxu}06Z|ASGxmTbLrs6w-nF-gEffQb|giDf{H0cZd zR|ZF8eS0%}5sIHiJvQ4@2t6}N3x;HWDSv6)Yc?knY6n?*t%=_`e=y;fmunJeZC|Wz zpo@i!ZQoDVMn!;thkvSTSSb8F{G!BUzb~{zkH}x;d=E6=f}Y;}_Xg4ebbAg~D8ZAn zpTfZV5gxyK`s|#&0m|jS4ZeQG3|$83Y4cKMg|RSn|1 z-D|CBE?ABnD%s(TOy!vBWo6yALHtT#iFB{2%kc~AN16rEa_o7ip&Axfjtf6FR{kUR z9@COg+Zo3?e75esPp73D)wa-js@r|TToYA;j?l&^0~ z&ID5XTU2n%^yAgd>AoJqOSdMoid$cegpKkR3c2!HD0=-fTA$7byS^fb-DQ-f+f@Xy zSwUqc@AIHp@8n-`n{24wm%Pn)IRkiZ&@Yyir9u17uC@cD=WFj3v6ejP1o$bS9APj( zyot8gwDe`7Kx^fi-6&%O@Nfz2)pz{_@_(|1LwG{qp0 z1Me@oTI9VL6rg^;9V>6`?3JY&!Asdj6e8-gXl+M-FgbM@>m}pDqx-)j?uQ3n z4nQrXnMNA%#??5E_H=9x!)Qn%K6k)(wRK9>gKZ!)fA!FMSrg=U8s~3#)B!*4xc>7)6*Q#$Yd5=79II|@Ka(cbDh22j8-z;?*w%rkslx@i_bj=UKGhhB#5w-)4 z!@Ay*%34U{pM6s_*bz7Q3a;KfP4;dgOT7AfgOEYwZ)nHJM~oS^z2eyU8J}IE{@wf| z3U{vX927N)#GX~X-M%eRcz-=WwA_R6CC9hrWtPU`qm9d&Pn_fNUA=^V*I*1jJ1|kP zN5}__7$kP>5q*eT+0=}*U*@5uo_6>lmoC(Cxw-4##cw#SaN04<4+iydJlhZlBB6~Ku93;FV1;5=a2h{^PiA~{UB&WNj#M`74 zq8zqTvmGsgijWkQb&*0yG3XyRTgwHPJ7)xTD`Z1q=3vP;zYJh#S@t`@lm@qWrk|_H zkX%oh!xGn@I52oON9VK<1&8zv(ser`!1bVliRhznfPSu!T=q~fk5Ji^TnvQjz$WpE zEMLgFny{nnjyHV$_ieWs$$bkP`EdL1gLg379zwaD*A4hYckHW$h97*Ei)UVxq4wMTcQ2kT!(eNJpR8hK7^|7SZmCv=lMgZ|BR-a) zAe-7)|ABIx?Ti1*IXe&Q&zg&qO9m@A~+FOXn@7CNaH3-~{Z&N~q3uZ`lgNM=bWqm)!qRET)AP$VQID@sx!qEa$4`%!lG$X?ld zJoesu@131gQoZ;6vp>W4-se8&oX=6Ey*2SHbrLVV!3FBEK^*tKQm)Y4BHL0&F!(Ro`77@Qq_cUQ3$TYBb}jIZ%5^l#vl-6lSX@jQZiL;7lIa7fgpVvB zxWe|a7VM%~o#v{mA^4h%3iD{nvDbBV{=4)7DiwQjTYZl_&l8SK&)(dHT zb(8zp^zwM4(Ay>$ej^fY!B7v4Gd1UdvIa(_U7jY3les^;=|*O48GIdrbTeOAy$o#%5EZgsBHLjeTIPj^s3f*7FE4|)L ze3u_H_Dfh);$NCaMgnmasBC&QuQaF>H$}e)Pfj4dIc%=)e4!S=NJ4$-`7*wpiwsgTSj7hkkAg~x55*zpS?vd-d5rNJr;a)|jpOg?SbZYKu&z3{ z<>dK6^#6V0Ud^*E+&j5?b|SC^Tc-U4bW5r*^`%O;lukajwA0Kgw?<%#BM+O!?@zGC z{`KHsWd`UOxGg$5mq5OQ^cl~-Do8!Ke&}m_1H7pl{VU7T3JRLv&kFdrL(eVRE|uC& zNZ^{Uo+E92lXVRF;SNkDQb2VhPr5_{``=XB3DE_L|pX58-e zL=4Q@P>^9oZT3+Y+FYkLey87$X_DufE=7-E0Do5u#mNbL&qFi0Og)1F%$LOX5nt!& zHx2vhIu_9-1|Bzl>7cX4~5$7O{2@WxbgEJod%tc&@#k#k~Xf=ab)0 zprcCzjYd4Za-T^Q6#h$GsdFg=n53KY$K*&JQ+Q_Q|5SHmIC;`wSN9I#?3qdZ;#OVm!6sUMd?A47MOoHyA^ zof`Wavt9uAt`y)wiflMi5OzpKD4FCmozCvA4~4hE#X+xhKC*Op;S*FIi9@85-%ybZ?xU2VcR^Hr~Mvr^2hyz=szay;6)m%1ix21CP^ z#rLX@b73NB{+OCZIS4)TIHtO*4!%~6ipUZjz^_FcJdd{%@=l?o^(Y8!jC8!5# z!YLdrU-m)l;@kX7y9Yo@?IMSi_#h1Fk2_M<3_`1If4hj_AUs*}8H*a}hfT|c#JHxXX1s^5#+eF^Qbcj%bTb5ZQP8#|VG1|C?c9eiaPpiLd{li~={WYu8R}ufp8olz?i_N(@>! zrWbpp5-XaU=`GtU@VlN`=c5l5IMrF2k@vU)OLE(q;>`$`;O4~!&N1RgpWCW6{-qLa zDX*ztkZH!<{%?^St~f>+ik zI_e&exM1CZhMzHRy|ow%jV+J#7v_RX?jh-(Qyp;QwUzk-@kK;r@47eerVoBN=*ntz zb;GV-X&J2lbpo>qt@+omc5u?ZRczAK3ft5kv$7CQL_y(4eNN#Bu$AkBU1 zO?Ya+IgM&evZUt#D#J^fyW|jukS<(Cgb&23nr1tbhry25}Z1~%hUyXUTc~;HT z)yTm9o8@(C6`nAet(hnHtBIiGPt(tpI6AiGeN(j(Q~2IsRaXP?G!o*zdrlxQcxj0uB5rSMaKesNu6M^LRSB zL$T+{B&Mxg<-u*k$ZA?V_m6x>M(6IuBo@@*fdXP|l*>Y06V@F&+nu3Cg{wu-Iu|&L z_H(ilt~vWs&aKQWvVSld;W{hW4$9PC`=qXQfmqv3S~Kk)IQp03yM<6MtkHiapAZgK`fK%VS7N@R z^oN1|`^!^UT*#4`vS$p{kCuvj-|WL6rgx$@pS7dYjAX_8leI)o{>rskosATXZ+SSo zxPg^QvsorG4YCv2nNA!beL}IBy~aLO(6as4nBjHOfAin%?szW3DKHZ~Y*yL|t2BnM zy$MhHZqn;;Ew>JU{txkngfEn_y;WbiyAuS~1g03-y5LSx;ovnO`an#{>tC0;2>0ip zojPYH43RYH|9e+xf1fh!?`i=WT{B8SGS|}O1e{cntA&>mS@)VWD&c04OL^p*QfL&U z{c)MG2tG;V_9yz}0>d7ND7%~iB?`ZPy-iJmeD@~rq2?$U8kF}PWA+0l+wr0CL#Ytv z&GvE|;VS-B8|bijnGBn36I)&!PXuAMox{#uaiA;xc`LUa$&p{N{>XJT8sg3||GJzR z2mk&i9xLn32VvpvQ5w27C>Ww}`c_Zo4W9bLGfji&qN-;$_iYKIROzzT$H(yR2j%E@ zCt{&0%*!MBNIxhIe%Rx~GzzP0Iop-S2ccpkYwUM@JGca$aW0&xgpw@gJnQ?p5Vstn zVaxvo28N`!+IxS7lGmrSjZD2j(Wcvq)6f*8M)IQVM(psdU_n8PmpAVA9;1@A3c?2i zFASevC%Sh>EANv9(%bTrKHRb^2Hj0t1Ah3#p<4Ikv5=ebI6HrV{_E~|EZrM+_7PhMR- zqcN!Y!1?JadB?J(mC^Lien!>6=jR^&B7RZz#LHnHLy=?`Wp@?^qP%cN{Tnx5bXjFl zX8KC>ujn6Cl+&e{Af3AuMdr(J_H9QV*p;HRdF8He2Z$f&6U`~Dd!=Xc4_~b^yKa>5Bv6GlZ$F3!$ zi2nXk(tHZ(s~&7f&kf>CojY42eLIfHf6QxEs=~|*rjxQ}MDJDNIBuF?h!kGaOmsnU z@HSZdH?LPF*|+POoI6VBru_qYZ+Uwx3a%&r4^=OV7B z&W*tQ@hfY&Knu*Yhs&GMkRI~r5^GAaR#1L!T(M5}MUuk*p4R+p0fF5Tua9`QfW~q8 z6Dc8t>!Gi4;%0jTB%YD9Rr^o}Inv!!(^l0`S)Zs-NAlhmr|cdjR+YmN7qyaMT`AlP z3thiDSpt3kPPgvVEP=*P!5{kxr~T2oXQIf#V%VzpYFN3PaCw(qA}FczK-Vw@Zv%zb8Z z_TN{0*f)&Z`zDZiI{)pL4`UwI!iDXe z5)>x&An@kRak1EXfYA9}s+#rC{3AEGNre0)?ik10(A7Y&gF;5~y(%yd9OpK=Tmf4Z zhHuP}y{Fv8is9yqB_LkCmUULI7_Qj2nl!v9fJ6#gir6mV=gB{F7%UL}&Ra9mvy&`1Z<2sN`?*S`SO!t0jZ2NU4UZR0wgBe8Jlu>(ig zrAYYqBjbaqSvWlUy#X^SfpC4tI}c?(56B-_GCSJ-0q&+;s9LxB2wJY+GMNXRfyU;` zcO4xE&^-5_Z0El!l-srTWNR?V5A8TvFL0s)RnPy~W3Z(hJr(EQ8r&-(`N*>2oiFon z@!Hsx45B;EbuFB`c8d5TMrHffh1*cmb@Fgj1kvAhTKAvLm_y%7k!j(R%ec2+Ci+6! z3Q|P5@E`YCMg>QaSqHBL+&p(ig*$5&EgzIp?`fDsRv|^MS4YN>LZI@5LGmCvTo#Dk zN7IcL=Ju$3Gj73w+DGL9`zz5@es6bfY8H<8=y#t|e2#_S*9oz|uqDe89kGi3G zW`2jNQZF2Rcp-i;un*?)kHm)&p6J;40p7^-1MvI6OM5!q0ocNAd6kcH07}#wObV>~ zVKTMHTDm>Z)X$w20o`#V3di9guwSrDKzJ7q~abG)p-8HdhMfT^MOxOPT zlis#fL(gD}PLhj1M9IT)I38E8@BBC&9EEjai$iQdKKP@H^-{uOI0OYUOy0C3c?EV; z3Bkl_c+HZ3sE)S`D5gAL({BT;H2P6Fxup^_b>3gH+TMXw+q303Imb}5!AxVCaRKuu zK6E(dEu)T4$#f*ifAz1_H)p&U#2uGzTsVCu4>Q>&-Ol6{L*&csk84;59p(_b~h zKbnn-(v1c%$`IVU<2vC0rE!T@x73iipP|WJf^ba@4*g>ZEQid=zObD?N$C&29EjK*uv_Bro?Zi7qDvD zfKCu2*{aOJ6kW_JmO zxPKb++)|3lOLIp9kCA&o^vc6msl~|3GklWiM>c+QS(bejS4lX3@5JmYMlfFH*8Jo2 zMT|N*D0ysX1xueLeSMR;gt5Qft?uG9vP)dO+Wu+?6;f5pS8AFtm9&VwSd2ry^j_C^ za-Z-1zMHK}s1brouP0Ei65Y4t7LD%HE(j3+Tf{Qf1uG3K9x-ZNkT}{xKMb9)9CRaV zrnVh|@{}I;5WU8-Qkp*fWefOpY2R0BBzskvBOPr0bue6UE&@p&{zCXw^K1MhmnWL4 zWoB9iPbuARONSxI=$!oTdP+VBs2ceTiDr}X`C|rGkEFw!$DFqzbqtss zUV7J%8xAxKGj%(IeIeVrX{LPD5g48BJ9D|*2hq3>vwruV;~~@PqJW=HsA@9Eb=ScI z6}9d`BKY8QpL1{~)enu-cThC+F7J5a%OJhjs{MqAVr1q*p*WT+Ns)`$&AUcP)W$ zjp*u+f3e9;Q?`M+b=seGG;R^~ItF0x#qd0GVc54yokv}ij6+n7U4_?$bCXov~UCFxfX<2Z| zW{J`Ea0aL-@{Z`zr$N8CpbNjz7g%~ydFt%RM0np4OGrI&Q2%!D)a>~fNV=&Vbo*=+ zWN{=_2VaYTo0VZ});B|;Dd*3wfxAJ_m=}0}z1$R(#b7U4tS|@{9pE4qTkL5Wj0~>i^8df6g>pv>Xeus+eEN8>`X$8O2&1>DOs-ORy+3nZoy` z=h)77EuzKD^?5D{;{Vsl5{)JLJF9*oTB^i z6WqEy27g8%So;j+XbDun7UpB?Q)ShVo%O2bmvueN?`K$)zuN>23eLQ`XNbS;?@wbN zG7rh7pE__fsulRJXk{hSw2}P$dGYL1ZE$5Md7PX4dpW6{T`Rs7-mlv7y`Uuiu5EGo zI}a27w))H7TC*nTP&xjbp`ZcOdV4=nW!AyTlWbJXUrIq7rKvG^YH-Q?di)HMS)>ROh6zYs>WV@J4H zb08*M)%)j6GVsvsJ5$e<2CCh(CSx6W;L`anl9s*%Bv6Zv!wC6dK`-3pJaG$;BT1+5p+9Cr1VZ-{>vdvq2JYb>DGGANG17>pTNBk|_ zKv<4O>v+E-gzx*leO%TUW<1Y{c8}QL#=XaPzE4HN1;2&EzpQ;>Wa-W)_ai_fJn@P|sB+a?Ph>d`Qfx0guv_%k%UF94j63~z`#~i)l;nw7 zUaEJ+6p;>xM|a#&{B5+{n{6Ml0kl($9=W6Tufh2x9cO%KyY|X;zb&fB2WX%EYln*B zhcLVE9bQ(FUlZ?qi}FX!bn33WK`vM0nAFJU7``T-x!tl7zq7rUWiF~jvtp*#JQI~T zo@ywVz*&W&R@e0fo>e2a+=A_%nmQaA(D*KF-iB(H-M7TcNATp9{SpU1&S8uGB0t}u zW&HKLb@~nQ`|q(z3F&JhzAM^i=F0)ASe7ND>vwnsW9XkG*S?v-Wq$UNz}Y_Rkm)Ep zyHtx&xuZoz>$w=tMzbrZF%TK!OwyXF~onmgL1E)MmLCFY*Xb-?t=7Eb(3@KUC`mIB@*1<0o#9db6$Dd z22y2#DI%i9FtWh%b_b0Glstd&C*9)%xHwJ9oKg&jp&|$Co#|ERyWIa))VUJ9N8LLv z(^jF_{EKeU_k@dex5e{0Wfk(C`1zaSn@w!~y zU%znDKV^H9Z}t8Rp6tIvY5SS;i`vkAc$irpah?Gg6V*QFr{X1{UNsS?2 ztlFC(ss_y6GjQl!A(@9i$;nG4wL?I1uQmmJKkOS?5tdOIgavLkE*ZxG5aWLqDpt`4 ztd*uySEqYO-->4RkK~fbTbM) zD%hU{Mi($Yo+Scgb|2gm#^M1M5BvT-T(bx2Ck%Iv@vA}yz3f=(4Sgu_`o1g0^fJcZ zHdnjXZinhJyR*Ie-V;Bk5T(n28)hBXC{}sxi5-W1|9Tnw;Fo-jyv7}w$RsTNs?9eO ztvhD*^;WVl?~gv4a&9&bn!Y{D{xchQRX5AuUCl=Sw4(pM8|0v$TJg-GOF0a=>`f!A+a7>NtImam34wbvEU{=em1X;&<{2ad9e$Tl!|FB`}Ceeh7<>Q=)#KWr$VjNDrpijQQ5xWqT2P)tEXN9ThSi)^1Gk;1fedd|2CuNTIb(H(vMs|5U5-%3h&;3M@5PDzS@GsJjMpnvYnE$k$=}kCDuywGF74>O+&Us}sx4 zQ0epdPT*L<`Iq)wOX$ektlV*r^v&vhOwn#x!2`D#wN)}#(R}#g>-bkInAy0=8K66h zhi-fIES>7b5vF$!>%O^Qx{x*|M7G0?(ATSJ;v>+I?s$Xq!5H|b1h(H|8iUg9@AYG* zMj-ORaQw~hLxht)KP#5k4?n;&>*~WEV9}$tdtufIf6j^W>h%yFP-Whoq31-$s#+HF zt!RM#-)xGjNk2tja-#O6bQN&s7qnYBlK#|JEH3qg8&Pa*$zdr{O!nN>dsl@>p7L{f z-f(?3NX#FK-p@sRck)J(%&Z7#X^AXw+PGMA0%Y2I?;l2qkp73v2MVTM5dx~}~F~xkt&X7Uh8P9)+`JKZsw@MSLGW z9oYxZoDjUv5eJhSI=48Z;AXPh_4Mvpu8x|2~Apl-40#ST@*y(|hL|CMKl&YgTM~^z z?etXN^@{Lt-V7^kGa^k^Q3P#G2|iHUk#%ac6o-6F6-8f{W0l$Ci5u#bcekCpJNG62MtWz)+YYX2)muF z#DDT&ASB_o!#IXl)|gU0sYlJ-oQ;Lk#OKs9{~ zW&NH^9n8y}+IGjc3XYGQ;4!>k4yK1nc^$Qg@A+1$b(vBDgziti?UI=d3`@cJLR#tI z#Vg`9?Md|6z1IJwFvNnsyJPN+G17ZsOSL^-^%L>4WnDZ?=1D#$TiP(X=g{K5STS$% z2sQMXcWrh$;L!YcmNhC5TuuK}UpnlK=5C_Q(ouf6(RSBF=}VS8 zbI&;ecU~-JmzyNKd*zSe>*JpI{DCjigRme7WclToQC^SwLY2SNl4ekU>4WwFGvSYM zW${%P&EkE5$rt(wEht9eUwGqc4J7|8QJDJN2iY1tH}dm`U`EkzNaVl}?CJbxY^~D| zyW>PYf3+p^M#0)14-LZQc(Akg*MVl>Q2F%cMsW?qHZ5Inu`Y+dRta8eJBvYGByvi~ zIvXl~2Pi^o*c(nodNE8{EDoSFC_eKE-u}`NZ7=Fd z1ULAgAzP&GWN$E9&N1D%XBmN)Gdqr+@rp#D@wYbPBGLH%eYy7Dj2Jvv8g<=pM;yAP zmmjPqI>3Wz>hd$^)jVq8SMu1mM>Uo3z9O0RHWlg7DT?urNGJ!f)8980HA+EvA@s$a zjw0yzJ;V4zqX_6NtVQo?*T8O5{ZU_U;t#js9_Mc#1Ae;;hK9DpFW7cbL`pCl9i4>b zK12*5bso#r@y#@BU8TAIN_GnPO5AKK)0bf}vxfWH#5{ywE8NeI{JKzqXVmNe0mY*z(m*^b+Sf7+IEgL^3`+gs(e__Y9U%H@AD;VZ*v zo~^+>(Uo}gcfBPq(ND#$^9YP{SD_l;2fj+BYW!XtpinVaL-I~*`C`$v*mwL=(4#Xo zm_E8xRZ4Wg1e+Vj{D~ghv-e0HeNHt#SC>7MB3XrI^Y1e%0*U|T&xPAeCgnKuno8~F zN*SI%=NWputPF#n*6yw(I?3q+JHM7~7UKp}gTGRJA#z(;%JZ(|p-sF!^*4qre6yfB z;+jeNgDnpwQEkSfr_NwyoN){QEen|c>eYNkqdbqXik=v=x#EF<%r z!5-%SR?*%;t>Fj-**{;ZI&$Op1PTjxUGt%8$CCZ(sLJ7psf>pf<*wBL#kQHN|B*ag z(?yNMSG-;Dw1QdHHLe{_QZ)}XU2h?M3;MyCI!z$_MC5$@Es_h0@S4Ax*#Hg>cxdmF zdPrDITeTo2j{X~Aj^S_WfUTJOHJfKGoad?E7I~=w3Mlml*KXFq7KH->R*FP7yrZAx z5LXIs{Qn#h`B(}oI%hu2jF*9Y$dic^^`+3{uC?{oyArrp zDg4>3>hv1jOwEKFl-=<3sNQhjIl>kG@zmp!b|KR1*hOD@oPs_wQ4X2ljA!@g)^3~d zhj}U+YBj=or4SH{5V#lz63M$nk6q3reZ9BBrG(3&W!!%Gu+e|OGG~@-5;%xIygk+) zr!F8TcW&^>VWPh%$2{Beb`k&1Kd@=Gn#Btp&x4t`CXhe)bMaG^A>=sVOWk1BiM~O* z+uIfE(4*C0quePMr8dKo$`)P|?kS@}_MI$<43?$yJx%s(w|Ch5WUYm8!MwxHjSZlJ z=RGGoTfjk2I^`?jJ$pzq9M0|M@=$JstdH|LNBbIp zTXVn&>OLorV^@`T< z0(fdzq)$_w4ayfU8Mb6(!U2n(klW`nLFJVg-L8=|*jbggbdl~0I2t5&t2o9$+jz(G zCte=lv8Ttu*zh6Yu1)>gQDy-eaSM`{+DdVBtLjl|wNm8m$bGg^i^!$DOTOV*3BF`~ zTRBU7iGPo#vD*Po^9CKDGu7I>Ot_OCuP;Ug*>%Eq374yq@}lfn=A7GNriPvGTh0L4AC%2g$GaF4dtBi^D8Bqg5S{Zd;4Nwa2s zT*QY`msT^W=UEP%r{BwZ2$Tc8S7w!>bqUZn|NEm#oeK;1#qgvZb>c@Hn)!XFj_6eR_XXLD z$FbjiRP)jEMPwa6UbvA>@)r_=9%}OoD7p4(O8V0b_ANi|d>lHCQ&blouWuW`=&$y@ zn;C5=d@;v`-Lndrbv-_mkp3Cg??TH;&cQGeadW1~CIdp>Qrky&7s9UkiO6?^>ozFi zu&r9Y65h3*X@1yAdg4Fq_V}1y2XyY~CzvJ9o zHMCXkebUHK4TjlkE5rO%uxZ92wz^Udhi+;|6O4vz?K<(%|Kx%qYAaBK)OLsR@B& z>I>853H0Zz5T&tOMpeT>LlfOqe0Wyw;_l>Sl+Zfc8znoBwqO6=y_`FZhZtX|x-XAo zALXCvf&LLJ2$)EDZqSE+?mT=Huh@p#vHVReN2>6`w;c&=)){D87ykUIkS~xe*gwlB zq+Z*1xq05X5}IF6YCah(_wuzn%sv1Su0p<*Eq$QX%zw|SzXu)}uSvXF?t-P2l|!169dJM2ZfCf1D~NqC zD7+WY2slcJ@}ebRMD0kUv4-a_)yQg-7*lzq|U{~Tf~xF69@gL z!WQ7F6Y$iLuYu6|=jBR7hkUhst%Ql(mV9W8Ey`?%= zfFfnvz$EKiu3Rfi?NYjWqb(EYWP7m;m#m0|U=>Lcu~{K-lt}BRF*omcaUDXVk$k;CZ zjH2-imi+b)b5n~Ty=(jKtg;87CJ+79g!VA9r;9kiMCMlYyW0-@jP32TqaU<+B4rO~)RRvZh$Bd}S`ziS4#&Wq! z8Elv^s#SI)jIPR#Uj9ycz}9{J0`8H#g+H?&t5X4NOZcs{cQ6wu^giyk`;ZC21IBgR z&JY%OiSf`I?i|uHe{gP1nw)3av5VHTNzinQWzI1$3Uu{4N0?ZAp(Na?*X)!gW?$I$ zC(X(O2V{4sZ;bti#x32BX>;D_hCGU<7t} zcdvgP2|=ePrzHQG{D-NZvNNL9eDSVfr1C&T7!GWdC2b)&$Q`v}B4r|^w>MB%PLt%m zo^uH1Vni*5C2Z^4WN*cH?7s%}Z*^jot9RsjQ4da8sQAxQ4Pg7aTKKV+VU$n3T9sox zhB~c#r_(qI&p$(z(US@aUWv9@F2-f7O`>_CuxB2R+b+z#Fd_SgJ74dK zdbeQ@z4QKCChuGq10NZ+pCe zQkAnF4wS4kNVzt^(RY*6rBsa&{z`MjZmI#Q7tgocl4}6@h|V07)jIeuyv}J)ZY{|8 z?`86|sev6KyoFt)FaGT4O5q*1N=S{fS1Gb0dYSI87UPrUkUXqjaleA_Z|ptar#O_r zFEMo$A2Ro_TMU@b?j}0sVbwn!+655kdd@RhFb{T)Pg(z8-*?D8sg+mg09Q0(_J#QS z;fIp(yj?nec=}8qB?F%)rZHyj{KEbo-(Jf*+)-tRQZ^xfxI7L+$*$*h;YYJ^$l&Ga zh6mZmnt!r9{9+EajA~v_J)eua_i-_{_2wcAor^*uF>(TG)dI#hUYh9_*aQf zaQgP|FG5Tmu$&r57arLPv;&!(w@B|Ghp37uADM3$pN9KSMOMMxYnC6T$@~byC4!w6 zC1B@mZxn7=K=cDp?bIZFQaL-aKNOL3;cWc=9l;53HGL#)H_1(0_|)OYDHZ??+n%$< z*u4kayXk(Xb(LWEq!g!RjV(%QY4%pdxnZoLC*^i?Ppmvq9v1h-m-JXrs6JZ_z%5&R zgL`5_Fk{bunew;8v7t_2_7nkGygU$>>#^kl#Ao%7HI-!I6dZ)A3^HVsdBH@&mJl7+@S+;YRW zb4VXay_8UR21+g7X*Ro1hAxB7MJK(7Fu^W>F5vY7UKT#IU?jMLJqu}-@o96|VAaK@ zm)DE@Pj6nlcrO~A1kYOSrz5=~e~;=5>Nmo@Kvq2tqPu6zeLdk$`W<8Df)lQpw83$U zCIQ=%tsropfnH3j84T{U=Q6F6xkl?ml&NMdh;Axgoaw3pXDRp01NIfL|5meLEa9=T z4>{D$jUdd2xGt!DB>SEK>C~Xo97x+jw{%@G6Q%~GpG@pZgHbk@kb933;O~Q@KD7yv zkS=nSCBlNxiSHC@88>=?a06AxsjDAAHnKmeSkVq_CoNaR_ua(-Zy)23TQ=AtlNcn< zPx9@p0SZ2q2I!(*G1;>A0!>TbZfdsMqF8EQ%u9JU{2j4-^F29-LXCuj6}ATAc1gZt z54p;4T(qAhXsQ&`t6y1Np)A8Y#`ZqSJIm0vWNxGSP#HeCQP!v>TZYHEM3+-?%kZbr z1-)mL<+#(o;-A1&B`Pl)vwXB~!M*Z-1!cNMQQJ%0I`Q5juB{elP9(0NT)~T*A)brq zV>$ih!uctjsi=<-{46Zwx0|7^pgG#-zd*a~Eoe+%cy?_Kwb&yLSq6G44;&!bV| z8|VJvPkop4QOo+JJgR)w3;Um)T=L=Tg-DKl>RJ1VAHU-b>acf$3&rE&48?Yksp)N+nde;rpNV-gjaw=@Q?N9iMYClf;d?eq?*M>7^c%$KE_?SSxO$6k| zJ6yY;7YrLyFFu`!^MftPrK`;2UhsU8JpTWL=_R(&RMqv6(=g_I&1|D~u?zXfNUYq^rvn(qOaPZH< zFM8fuz>;9baN}ywc$~5*mQ)S5F0kzNp{)f+5ngNi2%ec>zTf)b&|fQ3W`Kh^Upjadi*T`yL};Kzo5*eX2VhnFIO3P_e3JeQ%D@t|5gZi zZ*BJB#R4$3`)l&wv3$^E9b}9t&jmK)zMYqeABg?NuY}9w-Jc}laWP>e9g>_VPp9gp zfsOF52QPC|;M}}0^DoV0c*;C_!yWh}lqFE59zzRnF}PMXW4NZSd-UrbbbVbA z>lZ$bcMjU{g|g3Kl#LauXXOIU(#3dR_(Ax3*>5OSXjV`u%V<7Cg82S}XU{thuHpv6 z2WbVL6%;sm!RXCCau0Nz$WzpqLKCInNH8D4k^T4X{dVs{z190+&%NrfQRZ%JSNEluBSe=vd0KH|ewR%TiKvYlWAR|6QqI>jX(hF0RZ2JwV^86)W?u z4}u@3C{>eui_O$wJNNVfxKZDu>g6^7FP#Q)Gk9--mw>=7$h0` zxq6^vDg5cNtS<2Soo1=_s1vSiW1Qc`)d39U{!GGO37@_spgXU#6{>E!ramD1j$hmr zPQI1Rur{ds?3+#_90|W9E#OcNBVl@p;anj|!Ex=(rP)Nx=g5e8=^BZ)YOPlaj*?z4 zx@k!Hb^&VaPKFjKR^$5>M)tACRVbS(_JY5*5_L{$F;M-i!1Z@8jLHQnFvEo1`2M{L z91|>Ia$6)^s#NZ0KmV)8;=QiBtU`LwpuX-GE{tPgS(IjU*Bo+8TN!GoliuZW?y2uz zR&aOq);NZz%ScZ(R9oZx6=$^D{OqSEu@pYNv#=dO&)B@KPo(ARDsd-#s)W+$q-QH_p>`*MM6NZOEG=&A=ey z`FwF#8%!8&4o;JImwxYP@_B(y(6T?;);Qk@dPuY_p%cv2k<-ip1#R9y@Cavm{?$7{i9K3~A^Z6)~7NL74Y z41(bEUWeT#0wM16=BJd5L|mw~_8wwL!>>ofuP^eYq1IYWo5z_9!abJetZm4~CLLbQ zTcnr7k9w6Z@MsklMX8(+^=QHJWihLVhk9^Gty#5jJINDW_SEvHx3bsZ<*n z@2~M`uOZy&{dv~Ugxi2tI$mbW8sVF4ts6D1ZUWKKNrp!0dYI@HV7$1y27Vv1esunR zB?O=T`#f}aIeexzmnrWm0oB5pQ&%1l4$$;G6ur!Yr{ez#cPM3pE|pgGg^&y=>zbHg z9!!JGLZ$k>+$k^}l{r}YCm!C@1}K!zM}gUz?_Xula5&)VlJ0mb1p2hIcL;F@L)t)Y zTclYqESH(;UHKdYZ%&4Z$Swo`G4V?~-}MC_$_3}i1vgN?%o;X1<^arG2kg%klAMCT z72C6p7N`))-JkL6JqD?5GT-&BL0y+FX+y(WjGmM%wQ{M$U@f)lmp(LLpZq>K)?F>w zWWSKSe7_y7GTA!KhI`QHo70(K!x8+}anB?0!6XXkdY*4Dn!}BdeiMxcODKB$!}L4a z73ADcQGT8DAMt(P%6pmYpLxe^JXlrdF*|gPg1&JYce=imSRNV0+0`rTUM1}~&rm#< zRhNS!2C=>g!+zj!%~t;Q)m#`5*1U81Vg=l1`!RNJJL&(uI#o+Sa@8G7(>{@{t&q*X z&?ryx!|PK<;qqfkn&H1T>6Aq!vgf|L??LD3MtC5e&7Vv7uaf~x$_(Xo zu+Mq_hLvG0m_Pc>&rM$gW#N?dUz)4n$@-luFV9zk!>G9GjU(moTvPwHeO3u1l&t^f z^f(_j#U3B@3?@Ecub@r4sbKIPjunRVEc7T zB04e$lTzNvIbF&{SqQRsKStgG);}wZTXRrYB<4vtPZs7<#)|5tRia~V?OSb=VQi#r zf9!6vfJbLTrQW)&p!ddYp*^MK=YI0@WW<#bbo=k305g=MREtG|!9q3!KDI9SWzYz_ z8p77<4BLU(PIPPBF~Zp>6^x_F>3~$%uL^=Br!}unVF9_Hugfajyy9E|4L&A{wB&qZem!C%nnF099{p0g1`5c3^-t5UN4c=dV_SLW zKG_rSj_}W9r^CW0#T{XasqkHz-ADUo5=8VLUVnK$4k}bew+}f-0exDv#WVE?=*p%! z*whycmS_JSQ8@hxw*BbIp!w(p(lujkjPvfWj#?k5E1e-uqvRx;n;poq&}F!ay#i{B z?8-k8CJ-Kd_yD)E7SLNSIVx~^;XPiX>GOgW7^;!={Sw(P?-1rLr`=hKCnU~#2oN6A zimcn)ci)Tgg!@rvm82p(SF`iLP1i!)DDs=-w=2fc_dY#eM}!k)9fel$zV_&az_Fn4wll`-8&@x&Yklw1t46Q9I>Iw8l2S0ngP$oxYBl#y|hC?cz1>y+Ym*($RUx-nYWy znBu%(N((H+Y>oZo+6)(N#*5tdYy{(>!IZ0&vQLWweSGywD#Ss21};Fi&4tN z=Nrg+zlQMM#Jr_ghfPXBQvKT21IY+?1tOcmo)*GOtNiF?;(uRpwLh$KAsgOj$TtLk z&VV1P0X>i3ySN5e*GPFLBw0d{N6D%HIHPkk*MiU={@_UrkczrP;lh?ZnO*fVQ zaNe#$t)RyJLVKz)HlHq?OQRkc1O5q}9BoArKYghiAG%O;Lu$Nhp$`QtG{mUQM(|Yf z4deGj{|XE~QT(2D87&7T;~K?QQQ)-D`E0LctWh>M>-#f@dQzrrTuzhtmiJ0E_mNQ) zi5IVNPUyo5T7e9~=ypua7cP6CUWd6SAaCv`(eYLXCiiRvq0|tM>t%-o7&t99p-uea zLR*g>l;2weO@IHs?>BCSEAK+=-_@{0h90o7{n2Rk zxCh2w@Dy}I53s*xI=45!8)*2lZ%9#h!{9{5-96%6@G47BWmCHoHbn|qACTNO%aqK* z-FJk0b{P+B1hxU+LG8lK%2xO-kil@8x)s9t*^HVWwm_gPwQbR-W|-o4`s>u&2z)(? zr&_3LL2O8aHt<{#Oayq#m!(C(Pp+jBx}ZSFd`|t;5&Xf*>``dtF2d8Qt9qk%#sfB8 z#@(soK7uXp>Z;Zs7x0hYrl_>j0nQrk3;R#P88Ux(L?oOFfX1Yv*mB_%*xjboxa3<7 zjQWTF_#ZGM_x6clR-H*4z9C>iMYD{?G5Pe8|D))<@4Z(x*{LMyz23i`KYc!)`?>GyKF{NOd^^TblZC>O zgRulRqPqRLV(Lim5aZ);E0R~&$bV_%%63_W^YP^L+2~;KX zZ|x;shNx%<4_2uZ5ZdkUvDY=4%;(z_H047;;>xXso*&*|Nn(JJfv(`Vc*9ZPl@*NG z+)Fk1t_!wwXUz(wk0Ql>{?ij48aS6Sxx@LOA$mIcb}NpV;eoOTmq*WA;HlgsL4k|r zsNK0+>*k0Bwo#tSEvbHmTcyPwy=t~XN#7KeJ5hGX)J$>ekET7&9$r7`O=pAQZ+1~U z?6t-G_s0)~QaPZ|B6G==vvyd}8K^GcVU3f%^_j*sFHw88n=wWD1=e|=s(F<23RzW1QWvpQ<>w2Jd~QvB zU49L8qlQc0_)CyV3}cR7E@kj25w@SvM#+z~$N1u2Y z;{9;#(!XL5(9PlRJX`^<>vJorY^&kvr_`IHLAAhaZV{0Eu?{90Fl>Q5hgnU%T=c)y zf+JL^HPhCDpS~ne{Z|7wdFU?xxm*QS9Rk-!Ybr>-U0S$NiSTdl*=KG<>8#C$yDSA`CS$~h6~$uv zOClYlT=OktAO*sN?Da1wCP2+&-;@6`Vj%9yKRu@TNYD;G_$x;_9FA3=9eVO60F3s$ zb*4G+8cOrDUV7vgqLt!?4SiH04i!4Q6f7%3*@~V&W@I1#F5F8#i8KYg{mOdbkZ2v6 zP0DOx6==uWnjm`4Bi+cYpu5O^qz_xRQ_Y_LIgD9}R8{-5rwCs$9?I@a^46vUT~ewm zxc!j(IK%S=^tn8EK#_M8UA2dgIfzx`I9;~pGnYKreOSx*BzYc+g}`x}rY>;(HPf5I@_-no_5l_d}Ln@+xwn>n-r}CnrluwJ<0#QoQ8eIkVxB%Ll5JsC4*``UuDF-eiclE?Jn;6bBMid`i_R5pYoB>qZ&L zhsmBXVbFNs3#vK(=E9zyz!QCr_R>K|SbEGlTlHNZY|Rv6W8pHEX;F6W<$a12C#CGG zN$+MuA>Tob`=L0@v**bT^I{MS*um1dRsgnksZoi0^FiWe^xM|UIVA5hC1aqH1pbstiRDX!QKnjrr!`LcSLeXd2$hqWV_(rP zKgY9CX%Qc*WbVtpJ&fM&>cZ?lTOjH;ovj1=1Y9&VwyEDb2@geA*G#>>LRXJ{G^aoh z7=2u)SS7hF^;kvq65cWhlsm5TG%Shm3N?J$3oqbFzYe9|%TQFem{qctPsEzLlT9{O zpHOXVVBfh9=_voLpkTXdCTa$@DNBlGlm3EJ7p_Z_Ufnx6_X>aHVCUn%6evh|;-U6C z|DNVzN}e`j&`C0Xmn*MuTFk|IVJAnuJ$bmo$00*Wcw`Ui*JtM&vax02>N;C<7A7%l zWy+7qBG5}v>?Niww0CoUaf>elyH3Y3M?C+8WyYa7clM@Y?#jcAcST9)G2@~%c$9Ej zHyc%@QetrYEoaP|;&9|ie7KK+D-GQu%mxCa6R@P?+^5Frc)a^eUxQsZ4uxgpmg${h zuu1KfYeiHf@=$1Bay#gXw2GahP683Y6fYTh|LrF*NRj0oibw$4lBR8p{#CfFZ({qo zY6=B3XvAdQmQeM_TF@afmvE)JB}sL27<&)Ioy`=j!6z)yX*ZsDLNUkUy1?#I=soxH zDaB|xFsO8tE{K1DzhOp{LT%;nSn;up?Cx^tE`B33eT?*`>E%#)a3d6sDops46vE|4 zU$>5nkUqB3-<(tTbAW$t@O@=S7RZR)@cwv&^z#_}zC{yB{DzAYOY?uz;HNz^y{JJd zJZk8F=Qo-RhkZD<@=OzcVY+JTRf9NaG2HX!&DB^a-u(FE?B!^OCaogWk>|DMXN@dC|1E?aHmeV|UP&Sgiw56~qF z?rl2Z0W0sMYuAz;U^d(B7VEkR>ErnP!a?&ho@(1?%zx%HvM2~JVRIR_iSsV)c~XX7 zz1euzPZADAoJwkreEw%vZhhfkHSxFYX>cqfo|rv?N*i;dm_d zfxhuV%Jf0mX#3d3Ws%w!#f|?4gwyy#kB4vKJ>i>mKs`o zhS^BJi7&-*4rbyzxGW)k726@X_vUWzns(ST5*waqK)mP?6ja;(wtGhGJyo)ysiM|2)HrN(Gv7u3$A?6=5_IFMxWR2JOzr)*duh<|B*y9 zUULsDAg2m+u+;uSx6z8Tg)DE28awf32bbhgfgzMAH}Wm)pFj)T{_+9o`#pdBRyGwZ z{|5o6Q-qlz!Pyy#oc&rsJWWho8O2$>}WdzhuptG>ExkL3Jww;zQ zvFL5V5yi85%IRgeHk>z*4GEaOMLo;WArMRoY|frNkO%n{H)8*DC!CbZy>?ofdRV<~ zaP8!sR#0$K*;+Z#0d;2UG`^|baIm0OO+Ty`?EYROU1xnQNcb<9J z3@QJyOI{jjfKTihJX)%RFIt$FV>PS+S4RQqMv{Nq>N6r9QBL^Tze`;l)1;r^Xc>Cv zl@UJs`rIyy99UwGJY@4Mgm|f0RLqWEL+RQ@zu~XdxZTPm^d;d`{mRW8M>i`8M?J5k zPVz@Pt9G4erKv=9RmqhVxk_xwywIgFSc$h%L~fpBtU=n@?vhVqEx7&J@gZ-U0pg43 zRr?@6je&v}`|r#x;fGlIz`ExvxEcDoriO6PWkLpDm#yc~!kvlIyl5J)JZY=k7V&1?H;>S%G8M#xiy%IM@whU*oW#aj^i@J(Cy! z>2u8rD57~@4N3tv&*)rQ;L3lAZ!=nvbbT9Y9xxQj=~Z$30)tA70l284a59 z2X&gD*JV@i%YNc(zp;MIi1cVv?od{)I$R0%<2$uZll^QOfayeew=$h4YWJ&|CA3m2XT$xJ>Ju0IPWdCXEeGDHSXx#-$gvn z=eAKx^_{4 z3;uknx3e$!>N$c+d+eQ5!!of@hgyeE(~cuu;dwjZaS{rkJA z(2QC^zxeH`3h}&ZvO&;E8)O;`=-wNa4Ab4$PMps!1dmel;5*kUU|XDWUkT}>FgNwcg63XJYDVp%18NU+e11)yZWBW=&N?njq82p(cKEM4hgbJf11JQ z-!6d!!r?9j=<@DLuYnV}#!)M0E8*G!y26_H^{&}M+UFZp`JKl&W(%F$YfN6A- zAjyNF(-}{L+o+*0p7y@=1u~7y`DU+L;Vns~#lK&D(Tj%qzJGElx@@~Ha6z^db;5t^ z=iM(w?c$S%j71OyZRs>QAC;lLhE_5=@y=|WJ6lal_Adu?QYQ13n{aE7#?3Fgd$6#4 z%2`DCEBZs6VOjDt9%#RB(MRSzdAai2MVMERcFFxXv(p0Rg@)2pg^ZE+g^_|azGl?^ z_lSr`lVIIyY;Q#*xxS7tnpwnkf;iXLC+=h)C6{Y&RKeW?_bP?e`pJAo;#JIh8n;ex z^8I^!W2POVYJ&1S$vpXTT;j3Ug)MMZ@2;toSQGGGmQ$A?@5#mMQ#-UeYoLw3|5o++ zDlmQF&Quru1+I*-d-S_~hUf8TX{C1~XiSEmzcpG21xy`($EfpQiD|a<&4(-yx250V z^f4Vi95r{pYLg5XZ$75^k`)UamVz|Qr4jJJey7v#s35Q~zMDYz%nNKatk?eBaRko? z;U#U~UxMwZy{;MD0iM@cO4Ce6SaWBCFGBV$YAC&SntvRE`>VxSvTh+h`%f}&_rnr| zZUg3Hmc6v(?wFvX4kM0OED8_Ul$+Iy=h_{~AG-Lc{ycu%l{>zK?c%>mrV&C0< zeCJZ@n&7Ka0XE1e;SR@DPuJCrsJ@V%MZ1mant{ZM$LMsWayi4$h5k} zRK5u-tefxtm1#l>vn=6*ElsHAH>o?6(}H`m5BEMCX-A*ha7x$tUW_Q5{kzUFiXK#v znX8@C7|!zaUu4Y!&V%r++XBn@U4H$;tF~nve>~WoO8he#tRo^Gl*_nnKXseC59wo8 z@GN9o{f1pkEHX>CrjRWlC+$-62=1ooKkh8kg43QVqx(K*pzV||f2HP2lDFs$H`#IzH%wH?u+S`osNiv6KQZNaV&1i&`?}|P-fi1xOc|^8}y$!l9yJ(I2 zw8I~2Kbzf@ov_1_BbQ&Z3uM&CeCg7mWo*DRsn#4Zy1vVHD`Ll;YIO1*>%k-($%w{XM%9ZFULXdNbI7 z-{j8L^groDx$ZJk9+eR+wZ1wfM>CCdS~I5cWbVnA_92*_@aJj2g!T<@EZ`SQLp4dt zaa2%Qun}fY?HEu3QMK)+_p5J-F{G!sQ`OYt4BEp&)Y$DkWF+(*(Ay}JpQ_@4ly zbQfgQpT9np+yR#_NSG<_AbXkvd3L=ztuS7Gbo3JO1()}2U+mFrAU%=qi+e8-4mWC{ zc&|Yf%&9o5G|YX0jlp|Q5}ZH7Hg3gp7NMo^?W(}gx4lKc+b6mp)J=T!Q^U+CkptZ{ zaBlzEOjyoKkY+DTg=USqT~)^Muv*#t_eXgoXfl|0JiHqWA_KitzbZUoX-HipcF+k% zCT>vL{jr9QpC)5cb`~H@dpiGNjS2B?_(#v?>%h+_+4qH}F6a?n`ldYBA6GjcmvT9m z7}f2PmhrE<(HH?17XH?C{OjhwV#Q2R_-6;-CfoKD0@bf zllW<$PG;^bxJvv()?GhLNx#ekwja|ptyQq&@#4Y@!kdTs&JCqqC;dqezE?&$l)#+% zHFIO90?78IeCgzsYG8Yt#*3BJUmi3=X`B<3ulFdpZ4=<(t+6x2)y&=ZnevqRGt!}K87B`om;K+%(ZylvL zXORE2Mfn}+inzlvDCjt&h>M9aj^O6BJSE^lv&rXj4|)+7Y;Zq zU|gFWidKI`$Bp@mmLH07B>sAf)|ome{4LBVpx6f&D?QGYy!;BUyXf)Tvr$lF-uYF8 z`1zzG{lp4C48qRu=d#k|$$9bV3Fp<+4st)W4yw-FXI?yt$X>bHLP7j-H&{&p#w4g7@6BDVV)($X+gQngO*Vlp1S)_%`2 zfb`}i494w!lL*4}x(+cSr0*d$*l}xo3W)R{b)PFrhu6H!Tg=AEJn%5+yxYu#OxFD( z|Gkfar4E~ILW*y|=DNf5H#3q;($>q8CjM~>nXU^d0j5w;OjWe5Hi2swBsFAO7qL;F zKXR;g4C$5IbWF{N5c(Wj{mYOyx{y*Ox`TedoL={IP1y`tb%(+-hd9*w9 zK?3n4-oK($!4!epU%P+e_V>pMVPX4y%wedRcY55>APQrS1gOc+N1 zK#{K7jEvcZcnhqKS$l`@Y4X0eGt4@2ixH<1Vo-#^Ji#Y%YF3ok-%#|UaL+qpl?3OCk7}0xi3ew?#O4&USfJROFcmNz1;^>i6=SzVz%|iy ze*2hUVCnjXYrp*=zmoF(lTgCBF6r2Y`_F!bxnE@;^(=bf z*Pg_nb6Z+qa!N?Pk?f-c$60^O|0#sla21p$yiQlo(sgcwD2Ncp;yme>pw6Q+5s~DL zd)4YbiyR{Tp@*379Niy>anY_Fic1L?Mb+EPU6X{Z)x7&1!5_0d}qum>xhrW&P^Bsu8%A1Wq%NK*&tuJ?+`xl9_WjE()LaEq(eL&sCHav< z>1Sz5{IJR7?k=f!-uU9cxBbI~jks{AUUJ)DBl39e>EIyqI0%~R-QUuN=il=B=l$wN zYE9+|rbEMMxbtBN-Mul4^Rm@DPWJ4o2i8s`#?NBiktRip{foG;rWq75x{NOG@3&qy z{*DIO6z`6!e#exkNEU_v&)?*lR>K(BHCT^#*L zJO@G~H04Y7J`ADEuIHP@hk2?z5{)A)ZYCj|u_BHnlKsWLWX6sS+|CXX_20 zDFdP3Ip>D!(xF9L`DB!W9XyKpbxU2a6xF#o+1RFYQ0@$S-ItJTEPE{DG;%2$y&gjW z&(Tag6vntv_cs}BZ*SXn&D0NE?p2SUY_Ejk34QG)qb8uZb3o%>ZYpRgF^he*?8Rga zpJX*l!u#kmj0T7;H@G|uB9xNtA=oP=|c>68er>*x7%Q~5zc(1+$r4F2s_W|DHky}!s+bWN-D-= zUteKQ#Z6fc5iCC%t1s3-%yy%Te*3E6-gN$jed-mU2;+sSTICRNrre>ztqh*Y2XkGn zDFH9XE6OfOMPL}CTD+uN0A_MRCuvB2J~*5G{c-+mU{e%+ek3RZ+8g~1^5;?@y?fWW zj)8cPZ+pa9^)40|n@^zM_h``nNY^R55DAX932JUz!eCos&BeI|KhRGQ6xo~kp5$o~ zWR@}Go%uEkv4dF*5@K5^>Zl9yJ4)Z3O4Zc-91 zu33pe#G@KHKU_L#l3tC%lUqiLFV^5EbKTu5TWfK{)o1ARMgzLue32Wk-H&%YQ!~#B z%%YUyuhZ+^%XpiZM`|Cf;KqrwUn)K4 z?ZRU?V)(?WrKT$u$gO%Ymgd*#0HtQdCdV3 zkU!m#aI_zS)*rq6-P;SbS?}Zx<$56P@!Km*!dMaQe4s~ui+DwiZCv;zIiw(a82 zn&IZ*KBg2m@2 zUoU$(0mbQ%GptvP&^6ar`GKDY&eOlv^3fybm&dE!m4b1Yci`JUwxoCzYZ#U^Z;wM` zR_-_2V)2+e!#a2MTq2HA1-siW2pVb86QfFYsn1LC3y$ZhfaYg%R^{+JI)-9DO# zIwYa%VUdKr4X4Y;bW$+wU61Us{1o)42K~XB6im&koefG(!0w3SvF)0%*m6@nLMA!} zTUq97c9=xtse+*MmDCZqHQvxst|1sT?^qXqe(R4?!avnYwLC!F@KeZ7c^6c zp_6JThCJjPr?b8{ zPzv134b(+#o?puU%palcXm#6WrZSfGh1SI#w1Ln$Q9QC13XDe z%Y&5KF=@LV0ajatRZ4>@!BSo2${Tj#@1%)N`a^mT0_NWL_7`SD;hm6^ zdZigqBypjYsXh&!SV<}{{!4<4 zaQoCt;y*cS`MSzG2w3+7L3t7J4Vu&Y*UEUqi&urRskb~pm*J}46IWMwvedF*b<6=S zMJx?AL;5!yT{<%a^%b#sq1KB@FjV)Q~>*#cp;JEiB$D)5f3l z7_G4(%YT$2?k;gEqxmK1ld2BdXd;6Pu;H@(&l=P#HjiT!cL2s^D^FD_1^0Q;j8UTceZ{-wp$#FB9=qdDX#{MHA~ zw}=>OUKobA>MLhlibf#3U;4pOk{|l9IdyP6iTKFuJwN>PEQX)56BY4Bq?houKn#sT zJiLg#=e|oV1kR6of4|k}397CP+a+!|faf62Ki#GePsXHq3ZkrVyG?R(Vb(hoyE>@R zC{A*|tJ{=iZG6!B+~INcQR1Do4~z(L4a3(>J>9jY5qOU8!%wP_AT@*Z0iWd z;dpljPX1u@Z%P2}9l_|}FY@qdav&;%Q+y9U=#SYaP~TnD7u%*zzAfJEg$638GsBxx zNk6URugkJYcz`nW$Ii(Z#K4)^RmZr=a`^Gum1Evg~k ztp!9$9*-9-BhykpK>eGnkN!695Gqu@ zYgO|-+%5=%w-wH?bN6>A?)MJRa`A{EU%4HK$^Fg}dG!XKF#mbo!)XcOOApHpGhcwX zc$CSmvx)FPM`BdEFBVud&r7_183ipSG*s(^ySQf7sH|_E3@b}=W=$WmiTAWj;`~wt zICuJGOh0M^U6Iv{_}}dy6w@8(bfX4F#C7UxN6XPImyPws+9ZZ=E%WaAxro$ZlRRuV zj-I{?TmuJ^k%h@WMP;M|hMZZ7PBZnv0sFYbFr7|Vwc>slK47z%TzSbXep8Q_&g#dhhdQflBBLJ;j*`|z1j(Sr?GAUteD2AW% zpUp@J$1ug>crN~MBp2J_^d{-s=Fyb9xIF|PsCPb2nhC)uZ)HXH^I=%l$lH72ODI0l z>AGZE9Eej*r@EJ>{PFdTNPSWA_YQyil&Ngzi&R@ZchlN<;9s>A?zR9oG&r=gA{g~eG@3QDWQQlGYDI&9J!tS3e0+(N+mi% zAv{&_uB37ruv)A8&e@hi<$_bi*84Tk<1q5;#_>2jBFvVmP&I)R*}bxC3QKsUfQ#FU zX&N*BYf;lJZAONuR^JHfGQcxhPHH6YzMp>ZJ*7w!DBKsV^-Ze+ZIRAY&ndDeiLn@} zI9CWAdj?df%dxMMM5im#1!8+`m}fVo1)T4L&+qLXMPFYSdFXf-3zZ*FFeBWXwW_3t-F8QH5{ zX0Oaif6;~21;;ex$q7se98W~HC}hCD(KujufHgTJ28ApGsndC)@R}I2tIiHrG_j)X zU%MO%8e1;7{&ICZ%v%GR#YKM4D9X{dEmh-O-xOv_Rb6Z+98knL z);;&bW-)Cw#yzom7&{IYrr*x1L8Ax$3-OKtaI!{6D4lTi*Pkj6h3FDq$5q;xE219s z=Z+ffAimYO4(@rof1hFDWnW1fLkS#_XS3TV&IbW^Yq46!T+(Bt@*sUV3;g^aHED5X z0?)ISkK9)2&~rh6<9JRpp6%tdzyE)`=g*CPK<%@*W+dw->pa~RKa8K}+M&LI83NapSFB^1g|_WVrx zcUH18qk!}e4lR7;=GUD>heUG$y4rTMozn|{p!5(# zUk7~Jcy#XeU^is?1UjTO_P{Oo_h&R7^uXn$cY^Box?!i(+)Qg#Cx~*XvGTgN1N*V0 z+x$mcp^IsCKsTxp{s_}t8n-9j$%z)eW~M684>;cyvq8M8jC6;tt{^Ni-1oIiEd;*T zEOW-q#J_6sjYp$49o7SNYf2Up;8gQI{T}fs7>F|aUQp@}Wn-Q!l*+C!GMF}G-}w~M zFYD^49(jpo3TA63i(FCe67OFYeJ|{?*4DS-^T!@6F1x)g9NCJEmT$5~;gg2zv2JwH zcq=2=>##;Rim~z^a)MZLPCNH_%Vq@J5z6j*u|EQCtBNKEi+zNcyp81nyI8ofvE$yQ zrF0OY;puO`OZK%d9qJWa8-Y#hMav@bhm-z_!XnXnc)eTq_0-i0)Ob<9uEIHujqrD7 zdW!tt3wHe-dO40-&dsjfp_zEC`gjS~W-G95HSsw4p$qtsRCgeVJGycLC|!&EFlaXcY@f>(myUk0U^|Wg*cc&j*Gs#j@|Vb^*?W zMsDLRreOQwh-=OJqY&Zo!XQ;aAJ2~%W1QS;wD?LZST*H@2|h`AHBqiuJfnZYi}3^g zDc#5)*YZV4%E~2o1wVZHC8TbZ%*m{+n?h8d`Qgd5WI*s*@c57?3UzSSgw6Qj$lbkndAR~{hWcg5j4t^;)Q9=o z8ND!6H?UY|)DfeO<^-4S4uT$*E1Ek~{2?v1StIs_H#u*1hSa}z0~YIuyrI?VJP2JgUj}c71{dYq8!3_hX@^**$DV zEEJr=vI^ZB+Eb5`%b6tFQn(%V0QgH8%*|d6$}37lX)NPsh~FG7w+Qn%&cQ7=$~| zm+qVS6pZ0RC2@a*gE1h*qSKKr5D#%|-A#KX0DtY0F4y|(hwo{#;^Pv1a6;LUX;-Hg z3Ts9G5UcXU3de;j@u%Hzh5E+2*<)Jr%v!ScSr{41`d(~EEsFNuD2faX81QOM@M1}=Q#kfvL7;KTYTaNAxS zi+%PL#Dsr4aj6YKFAH6sSb8tCXe^1Z({%zR-II~gJIx@yB9<0TQwc3;rzu3t3t+<} zw$!FA9n!VAkF{h3!i|(S54bqrW5@nwm)ixQ`13T^a$sB>URh$h)_R<9%T&MOGrV(< zn^DYU_(wJ#dpkxsYnhL7fzq5t&82wo-k$EYxH1$fh|0`QD?&;Wb`rJ8!;FI(%GKgU zn7(ypb1rmnA(4(SRoMNl6AfmJ6^au zE~}KHCdI&ssi%lq-`Jl`-!jvlIm4Mw>Go#oY}ch`74F{~1V!aC0u z9ws@utUrt#Gi6YbTlr+Ce+krb-QZUbD}bVrPp!TM*^rt~BboR-9dZM2r|sxZhRpn< z-4CP^U`75jdueJ6oKq{+7FUgc(_vQIj|};dz0iZuh>Q*)?SI_ZJ% z;_l-ACT?OwJk3>adpjIAAFCum`&2@NY9{Zd@p4{Ileb`-`gEkhQW89KG1uM zSR&Zxc1*q$?Rx*6$(k#{>xS4H_p}txD{OB5t^16#3|#*5uSI^2Xo3>FY zdH?-NFktV1b!NpamARxxxKS{H!-w=`ro3tIHEIF-F8A>GxF)cU$c$laZ2-C-g8l=E zbr8tDOD=8Nc>OvdEJqpg~R>lJol%oh=~T z0fK>)-_8_~{XJ94z8Hf}sCJy!;3nTsUb*+Q%U{wz$j9w6=+O=7&x0G%h*u(eR`>Ap zL~`!B)4rV1)&uK_|H0MV9^zdZkK>Z=frJEuuQS=*!1d-pTg(1#=w}zPw0P15hx{DQ zsU~y+S8eLd-otGmyZe2A{wr$4BAPrPke4<0N@ABlx0w>YkqWJSTL@guy4?vkG7 zAE)-FS%rezS(}~G+~j`x;NN3WL0>2qFXgN2^a47UH#4P8;jp8XDI}EelFjxKx_q}< zp{CrFrs{Yu@IF$!!E$&U#Z0fX791oTqS7MO68!|Od_1uA+m8&4KE&{F(76qEtGBwm z+USG}Rt!}<$&=okurExP2){I$1 z&a%Wp<%Pcz7p=qKl&{*J8695`UlP4qTm24hQ~z!im$w1!&noWI@3kPIbZ&8xPX`mY zDH>n=wm>#oivjvgJLFuO(!X@f89CJ#6Ipk?!%@j64L|JM(c_rAW=q%ytiP&5ajM=E zn-t!7H2G|!9LY~}oZ8j3|ByGbR<9<=yz#;c%M)%&o1Vn$vg_ep zJx?^WH8$aC^1w<;-hatsZupDs{h`FW?=a}0_YT^ZE_nBh@b=2@k&xoWBYJdeBn-%u z{nl`c0;3CS{?9iPfqg(sK=oe^#B9ANp~O-Sfp%HGix+C4hNatP@kAX|>0|_$HkO0y zl|ISGm%TtQ>4fpZwszcOcz>Pt-!!V(nQgh8yNJ_fxp~y$+M z1Y`GSA2Aa@YKl+2PdxD%lZe4x{}*NOq>IlFxEL_3FPU*Sj)Y%~QuW_%hl5U~hyH9_5ah{FciuVV2P?ztT(R*VAV)Sq zH_P7{u2R#;JJ#BQq-W%-UyrQ7(zW`~BZcP>cv$WGRVyu^$lUwy?@Jm`Jt*gtma2&Z z^}D(JnV+N3!Lbi-UYg-Dh1Z^r@K-1j^B_=dyCs(UhGz0yv_LPu!uXwbukfvN+}V3- zHYfvcyQsV0AS2)2vHD3H6f9ck7nwMU`O1OtQmwg7Ih*5VvB)<_KhZrk+ zMD?=@lt}hX^bzR9g4@Be9=FF)*0|tC*Ubgwb36BR`z_-AUsFtaxIBk7TI^G42IM_$ zN9h6SoOImWq?TP&sfR9i?t8o;ok0ERxvqpvFYq}Gus1XI!D_`5{+6OHkPBh=Ycgnq z@6w}cUrAr1)b0M);a5qH%q-*JKG6n93wcO&zoZ(j3^VNIZutWAXCwvLJrLIVGB~*x zNzYD=GNc-2z?#9Pi??nx=svuE#)>WlI{kcDd%IJiVcK*0=6>SmF_jvCb_bwvyS?<^ z;q!35LhfML1z!~PSUq$2L_9KWGMa{RBx9+*BS(cqCI+w9KI7X@_O&-0zdE}lVDmIh zWrAP~Dr>l9m#`!eU)kBWbNdsKkCN+MgKQM4GrEt_aL41qj{Ns0bR$qh)NH-B7W}YTo#w8lktk8Qpk)&D)QwGiQVkaK{gk!v}d3&g93+bQ!A#@{pa01JcE3`JBuu3m+^^A;2pQ{8NAGET)X5& z_A{}p%7H>;{@)z^AkD80Xx%iE{#x{a-M(JzAwG1WoZ;Qvd-~v|L)CzQNDpjSEAZXo z>I8-SlOJyli+ot{q% zUq8qOS_7NGA^K0SYQc1(MLHHLG`?S#a14WIVdsr*G5SK_K(CaRs16ibr$Zc(m_2h`VenQo`U-_yZk~?9 zf68`6!=&O($IoZqQdSh|$-WX=;*P{XIt9sTx+t`|)vowZKL%M6Ra}15N8v9M4UOuf zjktb~Q^S0*0S#V`1Q>j&!SUWB;V&1<(AJ#6@p(lda_XMbbh0kP3$b}0JBO=K>5$8d zRIXNh{cdP3EOZF}ENt%(7b0_qLS?q6Zn=!c({3dj*-F&8+uL5f5?M zlFf0pB~+JvHgsI;8}8h%KU6n6f#+Z6J-pj7g3F~QM)JprXK_+ra%D>st}Sxi;rLdJ zWm_oUuO&L+xgDxjMah{kt<_!e=0q8sUAyJ1kWKh~is$nCe%FEbjiky^;sfA*Z(zai z+YWxL!D<<2J0afU)Xp77T_Apxq1tD>8%$lMzL|{mfR&RoeNI*%6KfvSKtF#?`aMCHs*rBNp#%ccM9VI!1iZ6F`g^e-P$FMP0Ex>;D~v=I(}s zE3Ba0n`+*zc7y|cnByZ+KZBWG8Fq_T$FV=`ijI!iAReJzxx&%eiVa@iK}A!7OW(&T z%1lGy!HKil?`^+8{Q6kqr#CIo#NAmW)J>k-O9$==toFj9mw!|-;~=Ou_0aG=8iu@# za1V3S5xAlf!MLw$1UOgR+^6eC;H6?gSlpcvNZ8F4?jkS@X}nJ@<3t95?&8tQv%mUa zk=8@8Bb@Yb=sZ2eb)^de*XAU)ZtsAt&Z@!--&=tz=oEJlYYXTO-`{B5(g^l$$_Mxk z)a(Ph{!~Bv`XzMChut#>~TMJvvB)ct26Sh+4%V2D+j61IT-Rh zDPtx-2X9R>_FW!NM+Oep-8CwSXeGQ>nZsF${w|-EPt=Xzfy!dd^~QPJyInnuk7^ko zUHi+rYx5fpmF+myqCJAzS{3OFC%)j?gvfN|KrV!B^v5#E*TQ#psdv`2jW8T{>-N{Q z1}Hxgq0Tu_4=sVavTdj9p;S2LKdl$_Af+dgi{O>-r!6(*`9N{}QQH6angmn&*n+ox33tlnmrH=)PA?1WFS>g{UyL)ZYBnn2$kB;o!8U;h< zEZv?K5pa31<$F(9DA>{NauZPr1ZRe9?H>pIA>`TD&BXKMToy$CoHf@I#FRDmSY5P& zoyU*L9hPyxg|uf)^`f~bAt+MS*OG_Ss@Ki_F%;mwbK3u-=se@Ge%mlEA*579MWU(5 zDn|nn;rU!pDqlT2wwPt;$9A?`|dU(clhcSs?>KN zGvzuru}%SL`dO7M(%*M+Ztb4>;RZPVI%aJ|tPxs_?v^tm;qhg8edaH01Q|MwTXuxw zFe7B==#oqL13W6xmzQec0FB|0?QAtvT)Q>Ymq9oVrhZ=AiSI{}w)nr}R1|10@s?w5 zErMF-bH2Jy@*ywyQ1+kI90=B#TzD&%4P{l#xrakC!6vH7IdDe?!0-6YL#AmU>!dF$ zZ<-9!_xY|Hl_$X8)1lexzha@9y*ETJA{uDIW>lzS$-d$6pPrtBK~OQiGIPQ=fSlLw zT?vl~fRO#aO_@jiVN|TgK$+1IB!crl$@&>#1JePy+sA9LhT-P$?DHDjvhplE&xZV- zbK;0XR1FGtUDMvstR?Bv9?uQdIuvyHZQ)#9hsJGmdA&CX@8M&wbJ+6^)HSIT;`{Uk zU-3V6dRsG#X9^D#{>)pzW3o0a+`kvGGcW9B+4MYS_Iro%%TJ@Yv-{ftx>2NE3O9Js zHh@$EiMMs+yU;m(Y%*?3Gd9*fOUm~kc>`MRT_>orF#XgYuJK!**!z>Oo9cBW1poZ% zn&y)O%4XLb={YH+OVo3Y;$8_lp8V{+;o@qxGE(J&+jt-KEZJPhHqZB>TbK9fD<6Ct0eVc3^6;~Z-_3|;<@KPAx) zgAsMtPez>~xDjX-#2-%he`n*A?!E2=4~L>__n&0JkA0&{)8~ueSZUaTc1I4dhTRIb z$|HW0^`N^wcatFT+S2}Al}QjF)b%!=kPLLzMY5QP4oFMYl@zws`J_$Yyy+j&9eoR!El^fDWHyQi6xAK_*xO(>V|g|6%{2HM z_42V=&%j1@Xyk&%ICMwq>T^E*4Cx93vlS2eA;9jyCBgY_P`U9d&{vY=iuTj7w7si< zqx~zgQjvu)5*Zts{Vy37#;RwZ_Sk{pe_C6gxRAZ0*2Rykdwj5%ZFKW~i$o0Qi@R#C zn~bAV%GDJfx!Aws_I$ul5r(E2In1wT;~48O9S6D2j}7ufG~Q++GmTowKjOzf*YqI4 zO`Q0I@3g4j`$)lA4fnZu0SYe5PAl146r77 zK+%UH)c&1im!DpQc=5}@XAXrZll@5ZSyv8n{TdeK`Iv{qwj%%J)e*NxdzlAIS%bMNdzi{~O1ngpjrjF3FWc-iHc+!=h%`ntnX zXAFOqJv%VRKY+VpF2jM)R+L}bl3D$Og1kyv@Aiqr;Etp2-s%a#knT#=qOX?&k?v{o zFAFJfulMAClMK}`a`{Oyg_HRHZ>q-7>}rLol@CgKp6%e@T=z22&7fTLG_)tBua0QFWE<`>WVAv`|I>G=6R$Q6+JmmJgs z(wkrM>iKoSKAW0gwksVF{`9Ft5P6Phsv6UsOdH^czauS2Q59&p^Su9Th9E1Xp^{B} z*1F%)lyhvu!NbscbMC>Hc#BF}f_(L2?5o!jb;mq0UybwY^I|J37%h}QYZPM?D7p<3e%PdfcXUtHdRt9$zZ>IrIy*;IEn% z6PmnkobPPeBpLDrKRnu_)JZ*yx0jbor`Z-!(Ny%FZtM@F)N4pyre4I9in5{W`@UgY z_zkOkk4fa}{-;4(N&M&)daL`eAN_*`f7w>FW1%45t3{m}tTg=c-d{EssdoG_?lCsT zTVoFbaQkxTyvpfnYC00 zRH}+e2sCv<@TsLojU>mEy;|qqm)HYIhOAl*Tl-+&*(d(x9{o_bPpRwc%m6S|9{M!L zFa*~(X5N1KJw$wFC@1bR3~aIs#(-GcVjX@&h%Q!oO{seUZYqd8+0- z$#JPkMgHw=Kv|}|yNlE09M+MV_GNb~rfZn}P9VBur{D19^3$D|`F_(msfZrb_~){R zj(!k#j4RvDvwgwvvMRodwIt8=DD|uF&#yT7k~*+aWD)(2o*F3~`hhM|lLUH9{J3A8 zzsiwQp;JQ%5n~rX@wIg3)7_wEtYSR7qX$eTLzjP9^uWq*Rmv@&9?+UUGq!w(Tvruct5aQl zFvL^!lG$4%&B#Bn+MMlU$|32V;0A-cD)-0Q;o9bh7zpnfud)EPe%TtMczdEnW>s6rQsglvnzX>O@{@&aEHNr{kJQ}mKs~Q_u zhyQ-MQH5M{*Xq;jt1y}JgokNU2j)lB(;ZM7$F;nHfIA|DJ2SugpxDeJ`mPmr9ezBI zM+LssdFf80^>uSNYxxBqDV~|XC*O@+LFu_a0;qR``{xUaczM35$O^Bws0agWT27V<6ZAdxdrv74VWi*!}05b$z;FFWFVr z_;$hi@7+PML~k}YF~n!B+YW!IUk4vkY6V}(RO*O*O~51aR{ZqmTKKVddO7`96+D(= z=35A=0D1XsS0kk<(7!>Kaf7=6M)saR$P$wUDjd2YkImCy=q)u%kBesm z-%eQLD$9cTYZUu&KayK3ILC8kG#xm@_-2)eU-!^WyR=_QDPXt5BWIc|8OpZi`;o?D zn3qYb%io>=Cl4KxlXQy*MhDaFVbyW4qvyR>=VCNGw&zT6G>!yz#jC)xKLW(pLyN`Y z!r|_Z(A459;b3VnF*$xW1Pp`s(i~X(1Y;8R_6l=^H>Ms!75vT@cr?vr_ULp(l`^GaV87(Ny_ixMaL<{;nWDjQ-X~l0B3?*dRTXEM}jF`6Vz}?gA zcE^JHak*e`c$~r*^7?!huyaU3umf_kIcG ze#ULmmi&PMag|>-_0Hop69TdRFpERE=S!EVCa_rSa$~aV0M5z(7k^c|2E(iQ^<5l; zFuCjLm94E=&>i-xpZaqRtlB5UFJ`vGf5LzLe_rZ^kc0CwC$tAaNmxnbAIoPraq0pK z3*QK^NKfk&TpWQRnC5I*Bz&3rEYtUu!?3_XE&4%b2*d*eRF_=_Ago)JFDj{z@N5^E zSekmkW)~e(@ zu@BA-^)N;uHBJ}nK<~!&s|7VRz^m{lx2LBH{wyl>J9Ab*vd>x1YKsD>J=>bM_A&&* zx0hN!uy~KI<}d4ve^M|&HRY1RD+*Ft4ml;C)mVw$9ODgJjeVsB+lDPI1j(IR9=Xk+bz=om!G$V-G0^zCpBsD#zY$wJG|XvYSa$d24dD}#D9@` zUdrvEc^mvFc>YcINh_SewKIwQ%`nHk;Vk0T0A2k_$tE1+b5brA-Jw+t)P{#0FV%e4wEvFK9wjiAYTgHFIB$!Y!rZNx?H}YQ!bn?&kdMiBKLvCe|tFBQek+Y*Pi!9 zJgmNpoLyXxga>BALQ`Ww@X&RUPOHot7JOr01!dZUkY{v0qt;{aq2<_C#H5YwuDj+m zxXf_X<6~UxkUisbb zUSGIcgk^&xZ!VLb+S=xppsZyI>S^=4Z_^;$)^h&uS7>@LdHLD(e})sdFPm<2*RgqI ztZCanVN0He(-{d=qz}W2cf_uTa0b+klbRtt1QtAPJ3vx2flNLfbWuq92Hhzt(_#g!}17Hbs2P9hQGn| zkLRYteQfdAmUDW`p&ocjv*`V=PoHqs>aq{(^)Q_0qcOjGJ`|aQ=GVQB1*1XblS?vo z0mwUd;b@)uCp7mu@I$321m`X$Qnxc!;gZBWzf^x2DxW=8s5nSLCC2miLtiP_$P`|( zr;dUhqU!r9St)ocskJ#gsR(WM+g`cvQ;6m~nZ;{Fk6wG6-rV2OhippYJ^r;*=(g%{ zES%^*$NN*rt921Qc%y^zA{LP5XTm`4S<(xmEaI3rH;J(wr#L(^M$z*;{qkbVFea?& z+>hAZheFZ=LTY`4_bp}mhGnV=X*f^rULboOSGtk*#hhGR*wk6ew&9QI-e1=zpGCrQ z(c<3ui`|D&Q7~W1}+iO@y`a=!dRUE5x{cl#gxa%>v1I-^QB59bzW?G$9ovGbK! z%zcG&Tr&44d=X!cx%-u!V&W>0z9(Kv=0X*wpQcw36KF(n#Yw(bPX}~ojo-;eJ0NbV+kV8z*g!`;?X7&mIo^z?o&-ZFS^l3kUGY(JfLUva7e zhkjq5M+{_MWKXL(mfsKiyN$m3*$hAlyx*HdcvePlxJI2%^+4*~?ZVZqoe+4#rY$0> z9auwE99JV+;i+}T;Cf&a+}>qWVz#9oroE>|*E6c2^T>_V=B^4z{WVxe>r@6~)A{qH zYmDg83?H5a5*9&FY#cs%qe3wl=tndKj*!(ah-s)$H3d=j%?<%uP}lL{8G z>GLtL?Dyg)?Ttv-X{dHQ>uwknYyK+>m=6S}{=+^ur2OIK14fhj2ycklDEwf&=n0YE zkHs2X}7^p{i+f0g+)=I4$x zxWmA4-u&GHa&J1~O~Q<*I{rg%Yup@;I=#Q2(lLRr4l(O=9q7VVD@S{&T_hL5Z*my! zRl}Bc&8joxzB+uw%m#?BfM={g^S{+Tpe;7N=AzjL8E2Q2MeBQDb2!&D&u|y8*_uR9 zb#=fFg|R%*(l&59mUYHLlk~kT+#BGrZh*%PyLc}y6aMGbBByJ)#9!J~=$O(}1}l`u zZM`0)5Xj7Iw2$g;}j5jqT_X%Z8X;^%THX&pad2EMtPa4k=9Ph!y<{J}#bthvM-SnMJS*|~)d}AR zS{h@>UU=p1N7XJm!ZSb1moVN)a;Ss7EH)c8purTL((6_UK4A`JPc6&fr1^_Y4+&3t ze;c3jyG!|S@QGQvPA9qFXL02-bvnQfi(5Zp;=zACHs)Ui`MjA_QY2mx9a;XQqUTZ4 zfAsT_*{P0qAo)J`*nwnu$hUI7wd2D}^rJnVwk7{iPpRLojpDWQbTDp6kF`wfA^r?eYk7uiN5g@&l|sGkXDYC^v>p+78;XK7 zD=95gooG23=BM{+77I19Zv<5?px@MA?@POez5&@1(&Cl zAw!wN$;BvlpJ%if{UNN!+?%Hn-H-ha#vV@F)X`O9-d8Zao^+!@4Q`I8- zd)YOAIx(=`%X@J!^f=*7BseN2Fu)$@R7{sl!rFy z$m$jL05a3Dfom{yt6Bz@|7=+^49>!8RjT=#XGEuU_&g$}pN5uCsyodT(g?Tv%kke& zE70{GkHZHglRCO)kq4>ct>+8%^WauOL*BpNIqCl<(Z~e$T7Jez-H+^s| z0`xsYELfJp0k$$(yt*F>Vyv!oPC~x0{l3@Sqhc@EaU=QfGF?9WUCiXaVNd!o=<3vZ zy2`-zHk*uja5KDrRaCjb-w*40b7N;$N5J0OnD*k~VGv3yabWDw4O`-f zuepfABWnvgjCM|JYIDV_p-RQC`9p9utHtOy(XIEaa`n1hP9oQFlH)>Z8jjV6Iv%UZ zK+f;9$9IKg;awS5;|2O0yw!1{w2C1YD>>TUTKDE)<-LZ8iRNsyKcpk;Jd=$_->z5L z@MYue>jTZJ{aKjovS~PrGYfCrTG{f)H3Lsvx)PUCnvN>VdKYVy)6vn2?eE$9DL9!r z5+y7hkKBJ{>v~_uqNWml9~X(n-|g3XxyHj$>Ft)o>4l+KxRd{n+5H@(5y}Y`w#mU7 z`TZiAG`Yxnje4t>ZZ1Z0H_uaV%EQcOhY#{p<{@m1|F~0|kF#uHX77XYF(lq^{CZIa zZu}ScrLTqfMa8If-u^d)_DuBg`wo3azM$k?)!vKP>bIlZqTm}wG7s#Tj{A(h+HzalV*;s5W;Knn;z3urNT-v#G`27>RE_Q3CV1($9?5BQx=xw-FV7g)8$ z?(EuVhhu7v?^jY<;o@Or=p*M)x^$_a(J!PQvd4Bf=XMpLqh{y05FYM?P@=WQesXMl znNoB+o%DGLC2T>VO(9h#FyLEdg zxP{%><9LSjajvU+jC#62z%$R8Ws+mDF0G=S8@Y<%;%YmLTg=ddfot1&sL2R zbHZ@ExclZs7qlBSv|m$n!NNeni!Y0uk)dOeW3!hx#)jyn?Y8@bmqq+PotZ30g`e0W zvAY7p=M*+K{3^#!^=H+m#4GT{AmfLn{v;y^LE{wl(uSAYxtcGk2wOD=T z#RJiGqT|F0e*I5)lJ)4Kpq~qy9V53B1Q*WHJ=mVIRBi=eopJXb9%5^*u{`K}_nU``!}{db3aC z)m?QE6&Y~nLv1z4S3mvg^QjVmx2ho`uN2BH^0z0}&&CYf@;6J4>k3$T# z*sbtRz2HR+)(JWUTMbuZ#XQj!fdUw==rT(xivs=cPFR=cNDTOTLDSPz%`uAO9B1PC=pWd0q|oPbg$C zyC+mF4fG3^<#?FOVfrmZjm0;Rd5}fDkggp{S}X_buXTYBFZFhpCIX*&K+=Ou9gn(U zY}*NDhZfL&I`goqljK2m?AuanUk_Twvd=aV?!%oG6Y3k}d*nqTb-~J8;#V!3&eZ5E z2S>-)1*11*FoKy&c_I|(+3B}#x3d)5H9qVwx?Bve`(u+FgbSfp^Y)*Nmo~tyR^_mV zvlVl{PEZmjoALJK*;6+UH=~`=gQVqvCUnu`W<^tB-#M z&B^^KF;_+)OUkMIXvb$L8+a(Cdv+Kc?D}=?tPg;>=)_|c&px%Vl3H^WBLc)YQUIaLo*h z*PF_Hu9abb%c|?HEaEGflj(4FLL5IH|NV|&33_kVEdkeJd_&9ej+?cFu-mptY!)s+ zO`0=nwBnIym~ybjb;bj>ta~>|yeh#9qtd9vJc7cUthCAt-!Wp7x;FitMZB@hDtC$S zZ|8POd=xx6jeL$?x``cQC?GXJb;@o8hii+C`P%#OuD{5k`?tHWOPwou&)ZgX8hp>W zLiUhCobG>_50zqg!1UUcfpnBqFp0Aq@IgtoGi~D)p)l9PetNHK7H~xhKF-TQFsaL; z8uKG_&-%lTvCev^{hD#vhMddte>F>`o3_CTk6|y}vmJ0yLg`|=MJGgA+BItuA3Ez} z&Va+hT`+SALc=^eiT~Gte%Z8x`0P40`$>NibrlG1-a>T0=XV6{bef6Jd{|yBs~%*} z_?L5Esf9>vd6E9H3N){OiM7fq2bb&Dc6v>h!t_w57<)|~*xWixy(2OMB00141xZgy z!Afeck!u7lyqXBl-jBrSD3pu{>k&Qa2H|gG+?q)5fOnuKm0WcX7KJ|B=3qOE=4mJ5cTpCw^WDsP zBI7LP2G;ZN8h4{Lv{@bONr&??{R8}kZBQyGS|Lw-@?xO=?eb~Dn=BNnp}9x;f7dSC zf0*flXrXTpO^=aYJgUU&YoAD;OM?ichc*GL^>OKjizLsqU9S7T&??xY^x=h?b~yy9 z-*XXqPz*|TJ6$rG(qUqA`5kAED98`Gr+VXTC|K`&{=xH|GSFu@FW6qR#kZEJiav~% z7%;!|Su@cGv#J9v;`#{BZOi(fBY82n_aTpy?9Uj~HyjQeejkfAV)R$@`r`1yYNks1 zcobqT#~nvX5FY*@Y|_2g9hX+!g3pC`VS5sVaZat<8_in#@K&mZD9>Ovr<*97(E=Le zHz_+%X3$-?LR4L`AGu2d|7APoqJe9Gmvd7taHew?D>2jnTUTcPcti_?X6?GT?ArmF z5^)DZAND{%l&@OCGr}tqHR!#0m~hH}HHp*iXav9edn#s1C?G5<>l|I5091FK6I@?v z1B3T|ff;o#ydik9R*=;K>Dw$%B;C|OBg^9@yO%y-{1e@ICJPrFq<_9rWod=SnA_hT z^zy`mVxDdP@`G{tn(An_rR7wQC>X4A3CGLF&DN?17&!=I-QnS~DA5ud@$ylz5MGe(n{fBEG20 z8`QL+Ylk1&7>D-8lp{nH8I=~3zF&^Z-;dLGY6Z`>TqT*MNIIkheM&c2evlkwcg?k~-L}ZYlcIy;`2M+w?ay} zn2zSpHsWtSaXFmmNTQdP-q7#v1RZ6`y_;=2fzRPFE5B(c;Vj&e?_cTw`=U$T=^P!P zl%8^%o8(g{1+r>N8?CT^_M^a{YYRMT*NO|-)dVMp7`8Z9!kL2u`*luNK)Y44P*Xq|P`_jqOn!kNM%6!5`lJwqmQU2nSi}Rxl5%co z%?c%j)(rx*^|3jK&muuD3dNp04BxRM9;+1C3vy`VQQT5;{pRC%oLFg^*j$o`Z&fwQ zsd-cIUubu|_V#q7my`1hcF4dZ^q+Q`oh`)j=U+5=svGg|aO;gSsS(_C{NL$aL1fMe z{_s7ZdjS{RN=}_KnZb7V{=+hoT}bKbxUQZP4%Nx$`^QxpK}p}J-%O6lPhgtvD_**T;B|7Hx{2-R@4K-9?uq8!kzDZ%(R7Fq7nj3$T9v= z83fS;hwf%A0aizAqhW>uxcMwk@e<~M;j564OItEwP~geO*xSj(A4>N^csUw6a@DK; z{0@U*v);X{Tmf+USP)MXyC<-HyD)HE)B!ZP3*R7}5w!Lg95-#(L`Bd2Uz7*UP@=ij zQaRlb^RK+r8>Mr_eHS9m`$l|36}`B*#BO&yTRO)ZcgPD1tM*hgiIM#2N4o2;j(cNZ z2ipk|Z!hek7_`gPdn095Hdya{0&=>Vn(!r&eZb8pR$8?-n6EGC;4fzn0$T<%?ze=4 z;pc+4lf4P>vTi*;;5p$BR+zQZ8WSD2hl`_Nu^rZLTF5?W=z!H5vNZ>O7vpSdXVr%f zQ#f^>_u}103wWM7r{%KAEV8~{XRFW|z|8Mb{2K~+cy7?>Y%HXq!S^#va*mOZ|DxSjCj&V+vDaKOzcoT;V_ z+u++xme2H@gHU;gZwlnjg3 zWxpKAR#>txAOacoq>MJ=Hmf>J2>$!s+dmB z8VZJ%IvI6MKyk!jtLiQ_khJ7mJ2rM224{GfEA--^Qe^w9dZTc7*tMX$6d4Ilf{U$z z$6^UzpQWMcVLUkL&g)DW#{u2^CJXt|DEOz|eLr%LJkQj!YnfA|M|~+r(C;7Vi95b{ zE{D1i<9L;`LQ`jODlA}#Mt>e3XsB`vT={}KWbyW6u@G>gZr&5G-v+kfSCX^jTcNs9 z<$ej_^9xJvFMaZ-1iS>QwKt9DK%7TQD1&VVv`F8yti6y5&WGq{xYm-u<6~H@$-x9D z|NF4oej^GrbJiY*(gZ<}Yu(hf2saQA)}Sa>yn?qyYybYq-p0xI+KF^L7D%zaJ>~wx z9*-Yi_Hxv8zzyR^)wXs{m=irT4tHFzyP-I0HueL0 zMkmQ>q}m%_@ihx@WcmZ^S+3)0@;NYG(dW)_s041Ey*iS_lMO<9uLO@aKEk6H#jlKg zDnQFbCH2pOGUj{E}qPKhZO%6}dtZqe|f> za?m$zF9wNq>7-Yr-(5@8^Cm-79$c#b!D^+L0~2y$?ztRUkaD(oLOd)3mi1gS9$BTs zjKb!V4iD16pa1W^`=ZIf&fM0hFc}XwqFyBxZHLG#pG`Hi@M9 z21ClfORY+8{UJ=we4^jX8=@->_`69Cz_@+WLBUE#xRd2-y~J38+j8H<+9wfcM?wm^hMB;Jv#Zmfi6~6e_sVr`CXAH_# zEN`bXt;fW7qoKBEM)7dz=HJfx-%$-te&-}UTp1p!$*V^Re>jfUqr-awOJ~oday=fv z83A33%j%8j%3u~CrJ0U0zv4SwmJ;Cr&ohsMx@GWgK79U)KrIY=zFzKo*Z{Y$v}9Z> zZ-7I~aI-0`9z467r!DB~plilad;Me$L`N6)7JFC0ultkk${dxz`0LN~T0WVZxMLh> z4ay)MziTbrqQC;x&FpHWQrIZ@=`6xt4CTf_?ks|Z@bZ0oVp3E-TzMkDUc!+_cnW-W z)xJ6Kd?Hp8e`SH$Y90Gg#Z1^Gqg7jOpAM;N=DJCjQy|7$ttoOT0Zcq{-05dx!H}}x zZhRsd?(ejOhrc3Vm^Y%N)gq>40Cim@1@N1-)*(&J+xI(>ugG#OjJERLM{<3!9 z*H@Mwzl1l6LCxd(KwM5+0R z`e1HqiqemkApGw*vvQe51WGo01{D2@#;{o<{rdv(_?LCOH|R_fn$Ps)Y2?OYc%$*p zmQXjCeDAW}y*(aiOb;=Pv(#a~d)i3Nrzw2C)x42GYXQqC%s~TEQ>dhU*p$Vi65Cny z<%UXHKyvVjtanQ<{Q9;1co7@vdvP@Np@ek8g=3*E-xgcJMS^4Nx){k(Yz~wPAm`hu zEbDEu9Ayyt%+@TEx(G}*Vl7T?&jHTg!OW+}(tsjI+4^a79NbP0@;~?@3?9Aqm7203 zygzh-kIo8RzcgB!TOPktB?~D6m>g$Vw^}zP4 z`)g=>4aC^Etk8Q@LDu#)ZPzyyP_*rl^K;U_L;u>Ma_lbY-`N)J7@u4Ojva#of~NT( zv^A$uKPU(G`W?~!rk(|B;vQ7)t?3|NVQkXdnhf8H*#zHFC4g!N_SOBQSDEv%`5aU@k#)2oF&BFzwzGx3$wTZp5cd06KH&zG>G!nc<1wXb zt2Y}tD6njsynHhm&$j8zluzYh3d{ay*Ij#1Er0&Nb>3MN;hy2BQ(V9s+EG(HPSdCn z7BeeytsSS&bM}3*E&ww*OPjETHW&yrtzW6=1m%;~=DH&tFjuddmDNf5r6U)K(ANU= zUb41)Cd5x7GGgL(ycz;5&j_p^COS`(qsjlzTbk>x5^@u{uY9FC)5p> zzvVllMyq)5Q?h?)osM;|s&&BIGg?Uquar%Q=QeqjNC}OUUE+|Kpt64fZjurSH zh#j#sEyL#h36_WB3b0h*w|#YPIsQm%ADUDfz?Viy1sbBR`m!6XS zJ2l6V18QAJ_45wRBN;m|c%VNKKU59;)WI1kBv1YNTF|hbW-A=g<>R4AY=JC;7xX`} z8{zcB%hjxR)?yb@WlNFM31Qw?!iJIrTtwgh*I{f*NYTD!s8mV8INpu&gy<4 zdNLip+&?ez|9M4pA)>VVTr8+H*92K$AM z#4tEGf_lr{;>9(4Xobf$tJV&n!DCf>A%Oh9fqR1^6K%nWx!!(n2;uaxcwD4WFoL2C z?^`=BXv4gb!?wgtPhdol`P>b2Jyi> zzgY2rU#EwxgB*q)rgeM zd5S4Zd1$R9?NE5b74kD(%w|&yfhl1ZaC6jvqVwM!9~DUN`=;34Q~Nu>$36St5JNX4 z7mn%=I`o20_SJCJ=zicbxh$lhI|#0f>USM`hv1$SX6XDHhD)a5wk##2$FbLVd&Ra9 zu=+ZifA;TZxc+&E(?ylf5NUJgjr@^eaMFu)s(UmDGkvWetoM-~Lp!d`;krHW(9U;- z=5;499zRp{_dy$|x81$-z^M^<&mGpi=1>j41$(z{TBX2HjIXN@Q$9$zR|mZMmI~va zOH2R7hl90uI#X0eI2OkHMJUc?BkkuW;ycdg;SrtS8R3~ce43Tn)Tx<|S(J8mUhV>% z%z1D6VJ;uLv42}!eF26%yj`?OryK?LY))6=X~Wm|0;vx?{(_fto{zI@eZw;&{|>Hi zCLEyq1#NZrrg7s*NL=-kZtSh8V(+!~#@}X9hH^p`VCCokYyUt4d^)z=wXlzHC})GS zf(X}VF!RfKx0HJ5HfNAIu~Y-v3Ar4vm8ziIsPd%$_i{MoT`%}Kk^||1z0S_KM+gbZ71^$`(W!yTN2-a@V+sg}Mfx~2v%k|kv z&@;4e)Y~2gBy~8q!!Hn4J?AoBi;|x2%S$Wj{$B9&sfBjf2{%ZUd#9hs`vHbNC!OC$ zaRA4`qrxqOpqFa&z4N7kEmSE`Lkp2tv~j7tPKdY2H^Sq?uS-#0&z4tV)QuifzxIF zwr%1JLMjWDxU+h$NT=5J?!wO$C^&iZQR9|cIH-0$Q@Es!_>z+AG7}t7cI%Bqy~;^6 zP(3b330%NtS*>m+pJ`lJbX9Dg>qN?B{%7e&tUzXad-FQgV*Uv89vu&W8)y@2U=x zIq3G{lh=yugg?1ujh$^*8c0Mc@$ZjMgtuE=xy@5a|4^a)-D|>xE1P#dfs;2J-d4^Y zEB+e@J_BzaN2U3}>Ks4qxi&8tife4^nEnWp3`PxGv>ixJwArvT$OqM#?j*eQnX>{PLgNu@a;<+;JgjYXyGPxwAp^gRj|JB0xI$;PA8OMeswWWLDu~1sodHQS#HRhFu5eyW~jj{WkX@j_UMU z7!dIOwGvwk^#vu;oZD*Qlj6e=8m=06@?&2~7fm%p@OTGG6;uMpNsAq8;)HYj^T)I@ z@!8PP4QPB!rod+g*Jddrgt&$J&j}|=Af<@UOo!xKCzRFd6<+7VGyMy9nMgjY0i(SeWK} zX8uAx8diipG_kZr0Nv!ZLcReXh<$%RKb*e=pQ=o>CpHx0Qc)7q)QMtL-M#oC$ft<# zWln7iBD}fUhkFK*xd`(*g06S16e43to%EVS5sqwY+*uP_h;xp5C%hgvAoV^KAA#Fn za7e1Wj!pSHimKeoNOdPU$T^nc0$I|(T&excv3s2O>an^fjk8y$Gzbf#(8 z>qeB1Rg6w0-{T(1Qgq`Vi7%%_)j5`M_45ljFQ}jJ!Eh_ftO&Z7kpFy;*<2wQ@~7UI zXSO8)qyP0@u}{RGU=gG7wVndKD^_f4WS{d~=hEn=xkfn9pDAIKM7Uyfr{&g$+kl-S zV_C@C4oXW0*WHM3l+KGKaCE$toHN3`+*u@gP_YPF z%viVXr4&F^UCc3Yi+q^QwZAm|%N@q~TsCbQLX;U%#@#KzJtw z1ydG(%Se{tXpzdHu(2}C9A>#-Szm!0w@)gT54E7l$Auz0n;{fuOVAf+@f ztG*R_6Z20;bvMC=t4)`R#M6F-mYol1l1heZ!Nzb3(f z^EJ^mTnP|pcyGHvcP!9~s=e7Y7!7*sGBb^OQSjR&JX;|=5)yu$=;2e2gkrkL7I)c5 z(l0D=hSxQMaNlWdMmn9qX@~PnrH4Cy-*-Ra0BtR*_3-N?h}2-G>76|T534c0=7Dm& zR24p+aGietvjSPW3oo|Wk^R_O(7*7gGMv1T(^gJjjYT!Tde59|$J)Hm(^iCQUdkbG zL}O(di{JeYtS7pUYT{7D7n&cq@57O_Cz}^hY|*FShRt_OJbHWSmC7{s?z&c9tT~1! z1WdQ~mJDINkww~UR~K$K%F8v~(~PqpCY%^m%2ASH*qL0LhMIG+l+z=&P$^nt70;Cg z-#%2=fnXW1_TO5eBm3{*>v#Hh*EEAc|Eny6OYM+>wXHsxoly2by35AA4&JZr#2&Tm4+U0>CWntqw4|FyX$9uaCHOSH}j5tC%b@A@a}-t zp-#elYoXDg?*OLB?^*gJe`9i_SKqRu6-2eRaYWX&z`papy@bj9@c6H?+lpr+C>xYt zsFQ0TpF4fF+(W{t*mKu6)4G=En7f3Oenvr+p*7Xx?G>mgni^sJKZ?#fEa$h4!)X~! zt3s$$c8ZjeE+vH0Fe*w@Y0#9>RA~wArL_0nyQ{tTUbHo|`4JlL{r=U_!Qr6Cb3ga@ zx;~%t464MrbT;*iT$R|ay}F)QQGx$_qWi<5Dv+0**{H>@0wqdmQ%_WuBfW@nd~|vl zndgS=&myk_m+VfSDc)XWtbXir>G?M_9jw#J&|bvbs;W=lG%lfTj+3bOo<+1B-}Cp} z{_ogWpEUWJVG7qmj3lTojH8|?8^=wGVLZljs-Ba(57%_cg4fAe3C;c#PH@8)9%`*74=c4ac`5LJBlTQ1pj@+mE z&OJTJ-v;{hmsGw8b%01EoxW9OCoCQisQu^H1#?M^ih|Q!Fk;H({x0!W_@+Igq zCfm{HKS`r!3GKM^(~{(>Svy{ipNTvm){d>I(+*76+i@3L-9g{S9XR;!XZ^WdJvi!B z(ZrPS1qBSR3q*QO;Mc2)@wUp}(V_pww-DM#&m?4IclA%GUBh&9pyJ z<=_$3OXDlJE!6CMWA_q1DtY^mm17Q{iKj<=Zk>#UE4LF><-KQxo0(7Qvb z*~)VqwB}qH{QW0DD^g`(VR-@y_uPADk}v@e^>)T;*N#JUayxH=_88Dc@4P(zc?33p zpW~!I_XTFPh2zqG6274$B@fxW+Ji~41$^2iSdwt?CH>_RT)pHPQ^sF{^v5^S<9Nwj=qJq%*0o}k=aKsF zQgJalTW_c8l_EHbb zzs&42kM2w%3ClF&NTCsZ^U6jCdVh1hBjcWp`3%fFSG3aM$v5SF%}Z6Vp;kRjKhy%j zm%jJbX?H^N%UG&i#ods+^{0y(Q#(tN>p4OWFk8k} z*x->$YP;14Mt?o_M_1IsYf)w4D%&a;(u-+qGAV~!(avpIk|ktrm;EK}Tt0k_oQ*w^ zn+2kGO>(XfP8kdCU!InagGyWd7kvuhgg^PMTw&4&#Nx+yY-N4};k!$(&&eyH7Ug05 zuIhw~GtL~BZ+W4csl)5FpZ=(E+GIuC_!D+0Ulg4E_8ITjycPdrACAr}Cl06#lXU30 z>=Q5RLh;=`t||f7IBW=@qIy1?fWEAEYzKEI<0(BknSEzd@z18qD(C)mw9#~u8rq(L zIlc4|W`{FT`BnCFCany-9;iLdp%{yw7&)t}xH7Qc*hi@Obr+79#*YbZpT&ev(G|2J z%Xsv2?Y88uS>pNd3-DL$#p(XsWr~~OQ2tQUKa#E;_IdsH=WJvzXfU}X?kMepiK-(N znZJ7AtlLLs^8;N__uuYP6ZUpk-2YoSl<E)3~?cY_Jd>bGt`t-zDJLvo~%cvtV4>N3U}A#;l4c{5F`)EI+zkMO6#7%E>r#RQ!GU1D%R6TF<3jOh)X}dY&e*q|yxWniU z;c=gM5r21^N)X;JI&5+92V#rakc|4SGW4+I86Dv+!&4PbXQBkkkbbt9PeHc~LrlG@ zg~tj1O>!(%o%Hm2o;rWwYW3-f@hzn;6JF&q3P>+dXcWWuLDm&n%OG)Rs2qP4e9f{c)3 z)N?s;5KEQCHk=#{FW0OMl!PKdCcJi`i$4s^DVml}S_Z@A%tn!eqyE4ot)nQA>;+=J zCzJltIDpZj{o200AMo|JxPm6tI^28AsE6}QEjkZ)#JwVUzo9o;FD8d;5G^zF1|HO4 zz|?Zp1;!e5IrX61zO5Q_9-jWMs=698j(^-5wxt;rkAK*t**=7FYgSWhQ`1;8y?QLO zV+k$3?A-bO_zF(&_4Bb#kv)t|=i8GCb9mowv^lzH5*>apbX-XOij>Yr#8yl?QEF3R zA}6&HJrCrJ?>_2_-222+j>s0mlTgX8sgdOQcuSi>gj)wtj5;W@ke>8ThNqNPHNB8E zty-H+IEhW?eRdev^@34K!;ouF53qX*o4fmV!=JhIp=BQOdHXOgl`66W+_OZ|Pji#= z>aO8QHR4q}u*AbWS>6PD4h8##sy0A*@7M6~!*yUS;P&t7wi+;V>=|Jv`!vpxtq(`_ zD&Xbrh4&x2%izAOa<0*Tr7-L6cx^tp7#_CB%4ZSoqEU{_(eLsFut`T#;d>_^I`{5PW1BUFDhYsj!|OBQYA85?2M)AD94-IDegLNlp#c$h?aDe;j1X8 zl4~!^@a>|}=B?AD2WEHRaEePYy8U5IJ(xiHVmo(6Lq-kKGM(BIm)=ddhPF3d`X-Pn z$Z<&T(IT4tq<#HfcNs@Ke~UDbT-H+L;8S^$)5_h*aC!8Zc!Hg?>nUy!eh2m7j>qfNx{04|zY`UuoudE!vYngYc?&prFGS`N-lR}zJV z8=-tfTr%Z$JA_*I(^u^1BAgB9{LF@Ku$8{no3Z18QXO1Ay07~WdH<-g zWTomvmqWKEps&9+B`NnA zXt&LWEth*kNVp+;>YxkMsSCI;GgyM|6PIOYiEQ-dcrMx?7l%V{cik#wBOW-b6w}O$ z33x%+Y%oIN&(G1n!(_$}9K59;@UcU} z7vWh?e0{d}9*3I`9t&1`qT}I<-OtOfn&tT*+kMr+&C5CH%DYGB;BYqnyqe#}?UaM( zgS}Ma&*UN-n@tDTbS_Rw-!FORn1{ztr#|g0%tD5T?;mfhhT(x@4{an(;*tO5zTocj zO;~6YEk`>wie9;AIk}H4;3>bv{G|uW_)f1~>looK-4~BHqc}5+-U9kR*fPtpN-$DI z%RLucH1&G+7n?||YJMK{TgHjqEq z&BnX61z5)En~gIXK%zHjba<#1EOtsAKdV~}+586AI4CMXpLV?96PZVt{dgr5*;)dY z`|fAi-zo&P40@MmW4YkJTC6+kmjyK!eVjhFko{I6(~6@@3j7HcqIjT}0Cu88%g#jl zzE@c|6a|SV`(2Y*u=^+2-<7+|;f^0{%+-av_<4e7&E;L!Z@U3?(}Mw%%eIi;q9K3h z=3^*pvI-V)Q$*&7F*A;R#;D;T^1~7 zW|$BSwey;djv_AVMA{b3{v{R_fg)P*G=y*bl; zF4rnNL($HVGBQl=`K;k$SLSg@eyF$e@iOlJ(oSJ@e*q;mV&%1)iHGfX_R=H&9yGc0 z=(vO?VqhD)c0B{(7cq<5v-(wmQ-|##wzd`s6_)j80$*Jz|5OxpC}%OL+{aR8ULLRg!H{)0;Zomi5H!6@4G9GAhWP#}}ZQ9{@$Q_G0ERQ_ee2;unqi4qk(vVLf{*=}G9P~|L zy8d1+4-ZhSZGpvnOdH7h$Cq4)(dkdRi@b`lG?lBx<_e;=JCnV-e+A}U-S*=xcN+?p zX^q@CKa4^Yx$72>rjXB@v3+QC9&ZdAUo6U9!c?ZI&&FToa6EWD=w8MMx*nS|STW8a ze$H3__4YOcSHi1*EoD8B@-lBpj=2|H)pD=%#&rYb{2Fy-Z71}22Oobk(gvMox8Ep> zHbP$%U!Cgq8n`Z%t^DU{1;kq1TIr8P*tPw^JsFcCsK0B>YrZ!hvO)8Mm_iP09DbA) zu|&L|zq$7?eou!E8O~joq*6(aC(?=ieiED*w!N*n77w4lJ8BvIh=q+K(nJ3iqQTl? z!9;u|5-4ZRAD6fg0YPWm#$}18?IXwW2d#t;Uq>_Y)1*8Iq(s%*vU~kOF;(sBReN9H zz9KI9C)*o5v{Uao27AKa&jW>OHXhJ1A?7wO;{;DIp?*ce9EG~nyf3F!W3OfN{=I^g zSd^ssR4ud|qjMSE4$YLI_=ivi!yTjtU+(O1LLi^yOBcdyUdJLOpFwrNf9W_kf7Cj$ zp&mE3(0;E-8pLeT!rl7BtDtqG?B4GEWd7!RT4uM&GP1lBc#zDtgxeghf7(s>SJ%Eu zUXgbr{5PJdB8qpT$dU9p>uq5lIy^lIzjn9awl(h$TS@N4zU9wZ0|8A8uVfdp`JDsB zmT!!0FI7RNn92Nwq(&IH^HQ@VtqqL6`Krm6b`XE^;7<#dE{GN5@3*TWod4f<81Geg zf$ZRiO@8q%Fiiiav7p!q4?MM9zw!}YimLLfH{aTTKbK#6%X|yOb>~p}&o+YkwK%bq z%{rKDswsOVNc>t;PT`V{mGD6D_x>y7JdIr@5Fq9h0oql!I;$(^LEMvhk?C_lpkNG-TU8U&{I;2-1>-n(sxG z!>_2?n<=)H5S}u!;@=HK_DhE-_GA(QW@dr(>ZSU&MF{B5<$*f)>4(zL_Z z=qAvT{ItDHm}E&8V|dXB?=J|2ZD(x&kINf<4fjbdeC?8$oDtz&@aX-%EUTK$2$=3uX5u>5jX9>T@Dg#ttFA+43N&Mj6`Oy4Th zsPBUqJ1JsZ{=OLdL{C{yM&zS^TUd8VWG+5Fn3JltkdEQGj9qV=wDFXC)CU*xJgLcW z@rF4K=}kPYyMKV>TeyRJG!n=;B$kjiHCsH67YaP9KJhQ$pU>6e+e!Z9Zt3so@1^tj z(zvNH^}{zjArY&|r}Pysiv+kPadjZAL}1~fVmXF;w;0;D_+ZToTC1858Q^+eU@-Z8 z8H|<4g-4lILvU5fGTn_jFo~Mw`9{+K4;s9c)o4i$+KTu5*O!fO#Zx2cpU(f!r=!~5 zp$)L}?Jqt@wR-SWEwlFOtcCVVzt+xh*ML}`-|HK?RnRS*7JVnT0@(YPKfOOv4q=xc zl%C^3@Z+OuXYMV6KNmK&7!vbAIp01|C@%+I9{MrqUYrRjd$RUwwxz*y9gb7~JxYZA zlJENZp2om+@zL}9$zC^jdgHccUJ%4ywHjqU=>r#Xb_?sMyn{;XIH%(W9blrs|Ia3~ z3Dhz?pY@#~xn|zs31_EFq|D~jHrkPe2LB1&RPo9}-E#43kN(TTr3yW-&RDGn)$c)wqc#6ToXt02!=@A`OmFs4oAd7gma9RG5ot= za9a$?|14y>J|b`N;1-Ng?YZu(NgoF3vn~EZo#IQ^|rXyGqN*%`_;sQlI&6S0ac9O|q*; zMniYQhj+fm!-$6~G;sQcKh!Z@wuBB3aEju0yjx-e8asK|Pv8~s-1p(Y_BR$d@n}5k zON#>z>D&^Q|K)~%n&^dl4twH1ie)~&MsJ*oRF$UR?u%ZhMC`H-`r^cvaM|&AUwo2f zEGU{DgszFsN3uc+vEUi?J!8Eh%ojcQvt&9S#U2Pm-Q&qeJ{!i$1BdcZvghV{>Si{+ zi;p}zb|wXP-Pf8;-Qx#ZNABu9Aw5}UUx$9D>etZ9Xny@nUOy69Sy8Ie9O~q?j(e;w zA@|l!;Rht|@YHr;;V+Eiq1Qv>#uZ&?ufBIy;4b1wtU;Zfx(B?DRK56MxCm4_*Ua-dKlJ(m{nod4Ei>`!_~CW7wt$_?O8s}p3+ zR0ljcxw7&j)v!A^jOki^B^0LrEi@}Chn|_;OGPpWr}b>jdzFho=X7^BEob3W$s`cZJv^y(A{L63?x#0;M!?_V%@<~q!O)bt zAy>QU1D^W328RvZ;nbE7i-k_FVWeSj^ls-}(0Dyw@O@1O6UFnH`&eFL2TUF+A#)>- zD`#T=PB|d!p0h1E&8_&~u`*fakA(Y{!}xIIMJqDi+p;&*q75S^6BHh$^ur!Sf*ZMv8AIAttkdi%rxht1xwqmxV;td?C(`U zPCLS#Rn4HKp7{!IGXEHTJ39t3KmA^pa*o6CE0?ls=f~jId_eLv&lr^6(Oh$88U=}b zfjf~2!@zd>^-+d{U%=qXmjjET1F$~#R{6PbAJm4l1RnZDyxMR5vJJ*N;r74G{EMWo zWKU~ZGJd)ZwC}iZaj`aoj{+snQMLwHnCuCy(XEB}*z=XA*Q>yAvc1Ksw*oAj18XhT z%OG>?MNd~%DSTgIeqv@=1lhZllvG-;mbtjkf z!OBFeQ;dcY)(Fg0;-$B-$wl7x6T$9vxfuUW;*9N!e3WOs*`#fekENDlhAqbV=pJT2 za*dsEIS*<_KW50om3FS@rAA5E>9IAIRyPv*B62;ieEAHim#K21uXo^{OHzNGo_)s# zb7$u3qf0pIA9=dGW){onlt68H1fN(9q{w%YzV8{9yLOL?kYoM4uBEmKQ2Nia2tf`| z-Lp@Pep~@3Y&`EXeyIifyOEE4f*K%sMEG;NQX^DPss+dYYk<_6TeI@t>LJP1oYhXg z4xaWkEPqO=0jH}6=HA-&)LX9i0pT%a43JTXVkqt(F(`z@ugM^ovlwn!oTJ(_j~ zTylZy>P8p!uS}5Ga$ae@EDavQwwa}8iJRMyRbKJG1 z{o}NOEk-*?$^T$>z@7BW!ncm(pi^mn+nw4R+@H{uEvAu+zS_)EX}!6aoP9UlO)L*B zvMP?h(#S*GxUlTd$SmX*?7LR7FNg3_jd|%Ss`0Rs_i?d|F1%vf-ji-KhMh*tb``<% z_-t9eSkZAAX?hGpHpb`BE_hd@U)nJGy4PY7;S8N>%iY4OPR<4MLo>1=9blK3V=CN1 z`i^yhl_gaDU^Q;cTN}{}Q@z9LpTxSMTc<{`Fr@=rw(i)!C_(%$zrUz)9ccoKrFy-x zYjqG~PTwXuQw7%R2X+_zEQcQqDi2e;N`VP}xBWIK1j^b+m-Ma4bML(!fjt|U@J&O# z?#1^s$lalTi}8ITeD4yu)fEu~Ww%>>-Gm~5EnrDVmnRq=NzHt#%kl>MghL0Tx46Mw znv%s|S=Mkld1#YakmPwcD+14_+{f^aZ=yXqrpSEp;sK?Y*Ep@duTNjo9$l48eVv0H zFpk42EaN}o!T!Nnc*raO-B~uWT@uJX@pN@`f&%&a`w;AvIej+BSP+e0f}lOnwulA0>ydIq0EMsO2;!MnZ#* z2FX2}b35c&{GY#P7tmI;fIHRdZlB?v!m?!6?}{EnByXLzbXB1NT}7`9Sl5OkwYuW- zE|P1OY{s{muN%NZLxgGNYCCLldEVtB^B{*cu8pr=go7==oI`i66I46+Z?Wifz**Mz zAX}w&U`}@#q~K`-w|v^#H#yC~uuuLb8&4xSk8bYB4XA^P>b(wE$o(hSD(oEJbS11j zn3iR)F9(*(g@!IkNcjJh)JngL!1socn9`ekxUXC`=q#N>^1gk+ZO1d=*&UvTMnS2N zzDGnhW`6=ayFGTXhurUro4J12nUlQr(U6i=|3LWkUGC|6xHpJ@xFex-&K=q|uH8AW zY6lnO0yCK@wZQd|W_ksi12(X93GA(ofkSeX_sdp@x01=9%dF4|%Fbp=m}RSi@*%a7 zEy6F6Vqt$R!*N$^>R8u*An1*rE;LCK%4YcR{gYAF48l?Bjw@?cuK?dl&f-j(7^E3$ zH}p~>=8!U(_g_h{4qokpQ_Tg8J4XlMfz;ZfQqC9f;tx%lIarO1149^GmCS&Ve&)RHPuPtQ_ve-dO`Md?~WLYr#|Tf3XVBSr>+jj6kw9> zc-R3qwc@>|_{+dVFx~FGh$~nRSnDzTKY#c2^~n#mxsV@47j%j6L}gxAtgZycLAVT~ zqUCBF2=2_g&XYv=n6A_+J@wHrSC>0B+8zam&K@z;+@21Hb~X&V7BmnaMJNMpcQ3Tf z4?T-)eh>WztGO2ZCXoAt$@UXTa~LixTD+@&sq%T)*T+x3`yI!)o9iQ@=8NF>+%p%Ag!`e6Q>s zjVJRJ%6|`5TFY^;acBOIm2!Og=4$3tBRO~TT+>dbX10RM7dpG*@yqd2ozc8vJY`7HVIf*GzRt5mly)1)0K@1Oba znPD$ddf_ks@NwKpW%BNn=mOe2KNQA%o#d}>Dwg$Mo5v5nmjw;}j$&t|tX12#dR(QK zIwf>A1GKvJj!EP+LZ^4ipU1Hs@M&fE_0nP&$c!FMnU5g6f%D%-3+cMyz|YvLtAuOr zdo@tbI;S13E1xuS^lpXj*!Z;I!%dJ%n*5(i%yGEXP{iUR*CF2NgP;ZXnXP(hMxC_H^MVBaJd3=wC3*;#l8f(q}v z;og0LuwFV;V6Y_+M73sSJUl-Vzn;jb%Gn3FQ0me_wZ{uJIfHU%%qsEk^10|Mz7?pU zM3Y{_Q;uhbPR&zqAwF_9>#;3|Ef7}#)|%A`vW3p}F5aF-8o(>-E##ztD-c)HVXcm1h`dx4Zo*FW% zU|}KrlRlcuyuH?-%y|F#&?3oS{>nS|tEU7g%e1>gjL4o!UUtPzu^u$I+T(8xHA7mS z_)Ni%HhBDbc|ND41FlYYQ@jxCf)jdaGjLQ8Ep9w|0S` zYQy9dMHiUy%vHuM5Wn=BGXetn?V#bzp7 zAe_5?a7dsAGP`!D)0S02)$`k@C<))#pXv^Uwq6Oi7oFF*?wbzI@uL+V1ycx@@XieD ztt>oorXekCDGR4|Rc><^%*Joh-wfXC6aQe7aMx6KCVu>KIcB3L3gw3-LYFiwVdG#$ z%(lTOl+ibf{k*3IcRo4tvdNn8&E;feyVU3LXUrvs-K2+PMm?3EO#0Xb`H%_!hEUy} zH?@zt96f(GdR>@KgZTda7F;CfOf?|K1cciurFVy~b(Z8DMzT{M>~4guLYBdmS4jSn zW*hwh(gQ1WowPlxPzfX8?eR#s95^((?@J7q!i-DNQ}6a7;4{r{VBjc#fkRte`V(`Z zt>}E#Grer!`Z1Jp_E9F-S)B9uLjL{j4ze_bY^ksmy+<)SIFZcFYIW}w#lg*@Q3nlg za__gwDP#W-1&m+M6xoyesDhqBSaU=uOsjc}38V!BZG_d>yX-(17+KpH!R`+dd#$Qh zyS(AFt)~V@)<>9CyH|e6^c`@&7B@=0@D?mxjb-khw<0~Yt2PAZPV&g@&EE;X&CuY_ zlu1t>CVt<`qAQz^Hu_dVfeFM1z4lgnXioudciuPTlt$(f=2~~hDl;)CWoPJb-bg&Z z&{u!|R|dj^H?ogZ+c0L2f07^-;ri(O+|83dkDTsA0jj)&YPFvkT3*fKerYG+9K&I3 zFML1699Dz;YR|NmZ%4qQNX*!(UKNC8m)kc#Xa*h352iWX2KLOVy%ggu5X)Z?YU^ipW}?vOO(Nah#dkRbB6DB*OHd4Czi+Yju_muWiNDjBYXsb4(D;;fI1DU>w8s_ieFA~&Lz$Ki0pxRc zA2;tkU&!nT=#x_N2KoM(<^QBSfq9EXWWj(7RBhQUkrQtX6lomTu~!=H=FW=$@yJ58 zsf7{R!-aTnpw^PlsR%2#+q`wOEJps&D_lONCD?oF_{w4g=|_)QY_;?&!Tb-A91-zF z*d47m9+z8%dt7MNK)DAeBzOH5o#s!qz4E62SQQwmo`5v7qR>+b(V~8aNN!8xuMf4OA2fwJmLt z5SJwR!0})NWJqrxsW1zJDwe!sIG zN=(KGXBGc7(NuJhW|wC$OvBH=AJSI8Ovf!FyVV+~GVnjD$uZl!4CI7N>~e@9<3p;8IbtGMZC;RFn?f6M!85UHDc;9e|9F zKkaCKnvX60pPd~(7vL{_p2TB%g?Mb-_`@^yB3!m{(!0J|gg0tEIA-^k;8mTP#ZtCX zq%X)3SS~KYIdj*Iv-Sn}`L6oKqx&0?d%|Zu*KibVBq#@)7U!{zCrn63Wf?2#j~&%r zoWmdmD(ZjtMsX86q zY1A#Zn#{*CDW8x&t1LxJS=uWE=~Uj9U4ILpH9ApBnmY%&L=3tn$v*OR4C9@o@dVhy zCR4T^5eX898TcQ21w!Ak@Pljb+`%{e#@*GerqE{J**~srgk$ehwwMGs;@@`>ENe3F zaBEc1uec#kG}{-`c|G47)0krUJrDU}(8`Fd;}c&Ty6_^5g~=D+j67hqHSj|d!TRC^ z|4;ZJt~Z{+tPv$S)%u;e8u9Z#G2tWY4Y>Nm&%Vlt^eIfs;tS+kQJUYj(2jU_vU+wi zcK45?MguG11=set2kEz`{H`1ivEqE1&-P0$UYsMHr`k0Sd;Q#l49` z;FWD0`S0o=_~y7#Wc>g4+a#y?ZS8}9;rHt=Yxe+;gTO`C_AcmAo0K_qm+-zhI(G6e zw1d;kHZ_%alCPK)3qAj@1$0#c)3bY;;80M~A-Z1;z}s+T>gAn!a6HcAYVfrd64mq1Ae4qr8VT@R_^dRq?cIuoZ7{w0I-uV0ie)PwLQYuCJUNfbJKo4*EDK}esV zSzsLf2Jb%bC{r*GfcQ--&aWjO;qnOc?X=nFU_WKlWwd059BmR=&tH8&rzY-`d#VD_ zWUA?QXKX0>|9gJPG2=5Xv7e5mDGI?ofsrdp+?goXJ+_~jaM2Cu?p_MloyP9RpD!LQ zSwfMxicAsTDU7A-E6%%s__OlC7}d8fa4-0oZWZ_yR34RG;tU-ECF*-_rn-c;DlBo1 zGmh{Gj@_}jR@)5MeBHzz=F~!4_K|y^s!8wk(Vaz^$P!R}YO7BpkOvH&H=`#=@7MI$ z#l_!ii4drJO~!*W8qz60sz@+|g7ctJ;ujH;pDlT2+$ih>{Ls7N`$Qj1VEOOTb}d{T z3%Gm9&Kkp+Zl3uMUC>@rXRAQQdvw>~r(ojoM31~15{AdTajfRjjbvUw+*V`osg)^! zEGL@yR!FY1|At|N+WtTcsAO%BoeMzu>35G$mjz(w&kzTj_W>AZxjU(zHvo?~YJ6(l z7l1F7b&l?f4908Q-PbOSXQ2=8`Lb;_xwwn<#m--k^02ffrTxgId>rt*@@;Uo043SV zN>WZ1qg-WFhmAuC4qnnZ+e7vyLiUH{@2po746 zqZ~gNX_v7hLbZ3&Y7R@dt8P!zj$pZ++Qob66lL zM0hhdID1GQ%!d0XZ*Pxq98nEpUj!DUihY-ab)2HepK{~I(RVaQA z9m-uk>w}NK%(-;j^u<^C%k3K1D=}^U!u@00NPpVT+{sO|9AB7sUvXz3T*`IZpVSRy z$QC)~cgL#?O-w9B7`4dvw@>XU^(jTmm_A#>TLq*)aMHjvrxL~FD#zYbe!&!tAQ_)$ z^C&!)J(o!QQGtHpR+FauQyc1ZmT{}(g^*~3{Iwy~OFNC&aeZ2jH_{odC z=wh*(cqON=+3f8CuLdrcUE&>(d`JEzw-)i0?`0}o=4pnrlYB8;S@q!kAN}4|vaifG zf1+IDPzlUh_NL=SWw4$9?A9!mVpz>y>A3Yd4~&P8oKq9e0-dyjeKR(xutFJf`ISf< zFzvl_Vm%=oT2%Q5`rXLh-A`Hm0;MxtUe-5$Ij%~2lAOXfLSCTReah@AJ6AmRaBXYx zNiS^gYnP^e<%@#{w^nIg_eaY@al^;di0t3K@@^--5!XkD|1sv2A?I0z-!lGXIIzof zsQXzNQvN<-{A6Dl{<*?MZzYZBp`eyBLsg8v>l;polq%Z;eYtzuMlU=#-o zeICnO&f~S`BGmFrq<{KUohhbb9-TYVSF-57p{l8d_RYK@;tz4HJIvLF6J69I6Hf|p zsZ+v)ChQG_d}vp7BE7=`|A=O<#45-UY;v~Q(g5eOI86+1G{NhNTPaW8G=Y=v?9_kr zjqtC^ltxsb5$?Ag|IJDEkQ7Un!aDcsf$~~XuQ^X0M5p<_R%oe#&;iS(|Lze!XZX>+ zI?Lis@u<7k`0W? zd!8KnnE{-8C_8MOQX&6zYq;*y1h}?kdVIP#nyhkcI;?HO;bhJ2rb?Y47-Cg$FCug3 zg-hE-Y@WCQ|A8P;A9GtcrmDSp<3Am+8-B%~X_}6^_p%JU(@4h*-nDuWvKNmuH&`zn z&%mo2|0TX3&&0btopfsbSvVxXAY^HujkIMiITtVkzuIVj{q3EC=_T4s?&T zhjj+f>zgY@m%w-8jn~V&K=S_~OlosFN9T}3zE9LMn|Sk%H?hx1q+%h{pt+1j9e6h{ zPSuWg0aqZUr`rwUpC0@u{g$o|=!dx&_WbDv0WX(h)H0o*91u~o63_-C0b@}NqD`Qu zTo51ENBR|xX9r-j5;8d^DTpx}v<&3A9O#Q-OySyYEqRjry!!3+?Xy{6`nm#N9wT#W zgK<8al6X)RrMerkJqjd8@?@wDL!ekzeEz{LU$W0m(kQfYgQcb;V%6=IKr#I#RP^L> zsZp7>&a1s<=$X0eA_b#89;06=Hato=4q-YJscY{r-73cBfi>Zr&?el{wem)70|trH z?mj5=pWu^6Z9XXdaVxWuwl5ypUOb%Go@yXr-wVV^{pXTk+H(z1T3%#WU?l zcVKy!eDMfIw)P!J*_gxB*lm?1yPKGvO*Bo;DG#ouLIfxpjerbz&QMl`|Mev2F z2H2-%&+53d2flN#Nj7dBfQvR1F?PoXh`(rmP1~V9IBZtQ@siAGoOhiGR5;lIy3;of z-gR$*;@Mi`nYZ<@G!wM^N3t5KB`J4*O(}ibg)09Z(U%T2s+VY!MHUBPEibB5#b95!{hSpN6Z4i*GS5t)%qjcclVW_DRcmS z3GW7%&Sy~ev-NiWPE}-c8=k7#`5Jd5R34k^aYWzwuMP)H-H~IJB5}p`Bg(L=KgS?1 z29O%iM>iP$8mYIq&2k4w;td z9h|7f%ibTlg(t0Xo5F;l=G9{8(+zTbzO@PBZ%RB^HR%EnyVR6f-SryN<%yX|ZTvMS8&mTCd({hLcg#SPG( z`>FHx`&tMQ%(SwOs)DQoESIhRmV;HS6x+?62u-RYCNfV8;SFc;TUqg3c;Zg(5pReO zCfCMmRx}m1CU2)@wTlNHUnV-K>?p`tjHMFj`V0bv<+ZGw0T8kwBvw!9NpkI;H_|Je zAYI|d%#&@efS*-QJxs{}(p^qjKbU@iI%PE9O{u*w^4P2GkG~b*?!!lJxh)sql^Ui0 zrsfNf-7fgjmc9a#ec#ct_sQv`?8l|3>Xo`AxZi=U=>0uNxl2uj#p#g3s&l z>>K9gs!vrgD%SU&<69qa*&5eAVjhO%`iE(GG$Ua2V#efB>{mD`a(mwQ*bqnuy&bJ# z?T6NnCfAi)yCJ{f?{e|S4k-9K|HgyxfBa7?(%(|52QicDeFY*_#B2B4ZcGkgM|qw4 zU&%bM-yS+JFP;v(6f)70n$fT)+j+{IikvrBg%i&n*9LZm%X4kru9%$L@ryA!5XA$x zyI;Ib{LcyTTQak!6CNS@hgx=?~3n+c;+R35jWpwDaYx}yFcrcPUYUQTJQStiP z_2~1&lR>rcywU3;R!~#Cd$O$>y!5_zzk1mTa&1@ld|~MasUT)8%fSKY4`ER-9q)(y zufIEea(m&Fkmaa~bT%rITe!o=u~H0Qx341R_Ww+Wsv>OzXK&qDe&RrNe}wL zSV*R0wO-dFeSit>*9E1R(;b0rTkOKz ziB}-c|LMzdsV6}3h&tZK{Uk2&YRX+bYmRMft1p?PoKZRUzT%n9K)fz@;?5dxKCWiy zHpM^8!!p0m6{@WHIQ6CD6b;Ga(6lgn%h?s6C(WprkZB>-@m=XU|Dyn#9tYgrs+y0o ziW)bRhlm%crNpNFSv$rQE~pf7jN!)mhwWSb%%ea^N8kIZ#!M9> zs6VLn^wy;+v{-(4)kh~E3TK>*uDG;8c?!?zGTR=g*6sc`VAls~Eu8Z4q!&HC{I~7Z zmu`}4y1^$K+zFC{kz9wKwF6(z;gXAUEnwE1|El(JBN%3y&gdSf1Gzt;8m7CdA%(vr zP4Qs`oZH;1PvSG+7bErbxoQ!-`dp+EMedhPpREO7Y{`ZRfx8BnOY&Aj_-HyW33&HE za@4;b3m1fySQqw?e%||Mt@kbmfs-+}FFmI>ob~2J9F32*<+k3+(f z$?N<#1WM0e!iUjxR*g!OC`Y>{xY@65)-_xEqvW=DE52Xp>vo2H=al{xmS z%L!m@oljPJmBo#$I=0n>kZ?63c;hUJLU*mcC9R*e7IqQX&G2_1%-Tye|QHuY$ z`oHvn4i&3{D+MrQh1c+vIv2V`@-!p^1_ReKNyt%}iCjNAAvQ{%(Z%u%=F$q;a z32%Jl-SHi^9-;8pE?O~*(-(5D7&7iSae( zYC+MiD4U<89CXqX-}5j;9J=F!1)q;Dy*T2Bcg(KLvCR14io;g!ed(^?Ic9uaCk%eTQO?Q4+dm@PSPwo6V7Lb?GGC*s4EF}8c2JN zs$;$1*1cS?e5F_`_n#*oZ@t;cpzMdzab7;By#uk%`kZ0x&0rLLH}=|(>JxtB@>xg1 z_o?)KKX8XHABW?l$ItJ}LurfD=ZhqNE}EoSV6L5ur#7E179P*VhxvRz_#$&q8kv)} z%VguJl!)T3EaA9zkTX|@a4gi8#>DT=mcg3hMihHq8!iZ>(|6C2dB1=j+ZpX;e7TA_ zE`&$(pylhUo3^8vq(7%E?E)&% zb2rxZ_khG;r|?=B>04{N(hqO#0w)H`=aO{9yA~=EB0Aa%Ny82jN7@@fDO#oK{J&bb z_kp8T=S~$g-KhUcy-^0O`!Blh=PU-jWr>ZqzjMJdnos|VXeQ)8WINjXHwjMN-tRZ{ zHySSU%8qOpg@Vol4>pMQ0(+Vn#z*wlFhbAuMe%?(&Rw1wBSa^+5zGjW6xfT?xlSy6;|Ipa{nc z_7Y7|H$u^GFO9?U!F=q}tQ8OlCC^pjR=g!-?|5!#ztB{37H*;4A2YL=iK7G53vc(P zVj08m?VxZC-1I*$GWok4PRX3!GC+9QL1nkDDe&b%*>UbFgHPSKEk*p))*Ih($n8VU zu*5Qs-dFHA^K>37(+|@7k@KgV=^ayR7RkLlF!i~0*A&j`ioEAlCp^!oi@5!33%pG^ zquvqG0oCr3w>ksJoH@vb?b^2vF#RZ?e?g@k*fnlQ$ev&;V0 z%WnwMWwm?-k($W77WHfJtQEdIJT1M2aEsX-otw7Pd*IanC_3+Otlu__OXF9vqBN+q zl#x|grAtUuMn)vrBvEEc8KG&0BxJAby}9hY_uho;)lhox_pknPbR5s~e82a7o!5DO zPIikwhxxovgBosa5B-2w{kS^^61~wh=-VEPOFsDPo3lXZzFLgD9QXMiALY zUW=kqb}#Pv))6lD^Jra-M%3_hykZyHiuOM;U3Y|aqY0&UsnVWdj8N2%P81l&X1UiK z4$9M*e(@xozAfe-btM`Ri;D;+#BA9rh0TPk#_?m@h}qiQB77(S(2H z_vs7W3&MLbQa$}lqXf6`-lJ1HQiLbXmd=x`KW05$xkulY4y-g>k(94$p^J6lZoY3b zgk~jbcCPq?nH}p_=FMT`bndm3t60Ec+6SK=K3c-Ee_DT8x)<=y>w3=JduP$*){Zz; z#VLH1@$QJF#5hV`3Z03e8^(M2X^Xv7qzCDPr|OBv%^1KDaHPW zJJx(+NZ(eOa(m+^ zC>1hQ+TciN;IH$fKkRz@*)Z*Ut#DXxPPN&NaMQkQoiV-N3|lX(UCXdsz3W7eTC@$4RuL?P1b#lAQp#c|<9Bm^hxw$BjLk{5 zDH~Y$Q*{r~WPoq!c(JW#3gONPOJ>%_!-2zzr3pdNkQ&{QK(FNo&6<%iUX9uKGOJ$u z!rL5l$mPC&>Ou}aOXip5mCVKcn|v8*n2Q*^Z)nFU!o6C_)=CJ=##cf5Uh881NabXa zu1g47GA|c| zSy`MZu0f%ynRoKC5x|g<8Cpwx`}e{h-Z~xM0;W_ejwynq|E8Z>_MLG%B-P1wC7fyl zp`omd`tvQI!fmyU`g$Ww{ag8RJcQ(2r1*#YDy!hA;>Y5uU->l3WaxipSBlTKdIT)ZdhLFT*PDEnesg;u-+IvFcy3=j^(%s8 z9*m*yq`~Fu4;s;5{+gUtfIn0YEEyEaRYIMnhFiN_Ge~~D?Xdcm{62X&J!hs`!NtB$ zIS{ti`8)UM8#!|gO#u@%tz^%S_Vcx zsdN@%N`O{~r@-76;qUrLitSuJTn+Jlwreg2jDMV@Jbo<;j%00qH_ImclWR;;oYzx< z;WbO2GhGq{eiW-1d;b;KelxbYvPFSVBa4fuLm2e^xgYY*>26ho*M z{h)QV&fnO|7rgB<(`dOrz^b!`m1Nm_h^wYrcGYzO$xE%W*I!$MB%OEe`Gx1`SlTvF z6;O$~Rdv5sTq^Npv2K5{dnIPlFPT5_t3-2?b5^~Xm00e~`0s)$>1U%9$d2}_!4g0F zlV)M9sMYuEzkI!6>}@{F!R$4KPx&TvwVdX0QU5`d!lfl#>72T_&Om&hN%nhW14$3+ z&Xlha`)9CBe$HUVaRkNf!ZgHxwqmSyNy_DoOr&@tB$(Wi1=o)sq6!>ofZhSQxD|Ke z)17W@EBMw8NqTfbzdrWBxtZsp(9#Vpwz4Nr*>u5$@^+_~(GGC-G!tvM&bt4oSQ`NqwDK5yz~i7s2}{B)pbK&b&d`rEql}$ zR(0m{YsEw_AtRd1cEpHG-xA9%Ts-bOYUkXGy$_PF@aGQTm6FXz2Lgt%$~m0oblfNc zWe0_l{sa!ubFbdsK8;CMu!2QvaAKMO2j4#VxFs8@?PU*`AeK;b<8{3W9K`s{c7a;9X{$7d34FK*hz zYL4J$i}Ak`M&IDyj@t8zmQ#@0xLA|LI1QYh z=UGQ@O~cX?;RAPsr(rx%%9*lr3M6QC0_rbJ0oSSaPRj4^3z*HZzZx{<4`(7)RaNEVU^nNGHdA&Qtk~{*zLrP0%3pQH z_HmJX!n#||_mleIpAx0mH5`p{w>&?+CHh2b033`z~UVVG7%Kc~DdCUBvI4 z1A0d!Coo=3UW$FO7}?9hB$P`^fbsZL%i=;c@fpvWv5-Cc0?)ZM_VOw?_`Bf2moMeO z(0fyz=~@ZAy_-M$-HUAO!6STE{B2EDtGe!Mc&>+hgBBzGI9{^@$f_20+Pr;PEf#kwd& zZ(bOmZGg9zlb#%TVS*|&kG~lxS>W-nx=MXr*65m~x78=e63+!iKZ?^b!{%FtU0$~> za9fDxfrH}aSoH5j%&q8Byekp?_TN*|J2k(bc9!JY?+nM6*tV5otIw7I$Ae`kX+e8O z`(qhaHL8h5Tb1MXOUv)Cwv(R7{t(gak6TcIuI=OY%fpzl#((>i=QLi~c&UBCViBKo zW(a>-Uc!8LmJdPviKHiwe@`#BR6gUwfbv zc3t>e&3wKO(jwh$PG$7LywCQNtDLNY7*; z=Q15nXML+*BRpJHGUq;C2k&ej9de)~y>y*vv(L^~fZ3d^i%(K1{9FiWYcwTuS@8Xn zgYgA0aEfI|;f`F=A2?bv)SC%$_3voe$+`S4&U|i_B?Z>ZyJ?dq;~;NOu<4i{;WiyV z&f4}V9K6a-jFfK#L+RFwEkbWULu;O<{=FT(;3d#xzPREEQZpJKYKcBKt~X3=B=#B{ zjqTDxj@bgW>T>IILm#BRBD3}Uv?W^6u8X&(KS7aU%STs=pQ59d^t4QAl61 zM3YCCR*$B7f=H#ij|^)8T$p9)DnHN&8b7yo@_%lHh;RNMs$3dj^wMe7W1|)LTxWlO zRN@r&P7LVB882e5_JMUL`WcKrxhB`#(1wc-KU1lGD}!s@l`L%3J@CtqL-lEHAK)RQ zyq~GWw?AWYSJJ*6E(Lsue)F;!7S+VNT;4*yUsImCDsRGje;hh z^QF&tY0Ib1Ts?nW9#peRm-0meo6)A+%pAVFC(tqLJ zY#~p4hEI!LJ(QO$MD1%FTKqM|=rnHU=2cGSSNYvdzA?Rch3g{6=AKdX`feRE5Ps;Jt}oet3I5Xi^ZsE6gx}bbT+&GNX2q5B5<1P0F6_ac z`Gnll86(G%L#u)2K{I`TTm=aHym!&ZrxfnkWdzflDJFf=id*R}5uN1A0^|624jkTd z^kolc7U>^%;!>_khrEPS_6!B7;O{Y^(h`{rcN9)fZr4cw$F{@m5&f}{(&=89Iv53; z8LYYmMG>$mM>}wjF&t=@;?*8`hk}*FqaZ(*U~pl`)O(s81TvgP%_%*BaLJ9yW3Vj% z9K$rLe=&1_he_st*Nyx!Zs<_8qSpsx{?D3Mz`O<-WIR;s9jh@gOE1XyXccCMU#ay- zsl-axqpq&LmDtSfXm-uC5*Zo4zBsa-^v}{sU9>)3iS>Uy5A2q&LYJ#mcO9Y|aQ9s; zC!304Y);Z+YtEU+PBq7<^;Y8l*W&jKCi9nA#4W!9hwu14{D=By`zcIo&=z-}9mCbt z18!EFJ$T0J=g+JgL9C*Hmn8j}i`15dy;bBJ-+?!tE2U8ldj$fjew2 zwa^Nw*n!bRAAjR&GWc{_!;RxMqGUG6$B}#QmCsU;pk-Z=sD#OcPBwRPh zoz$T&CjHzc&-57!@QcOfJV~lxTXK=^lhz`Xd(a?Z&zO&DHgpj-<%Jl#lH{%?ML42P zzZ;A9cVJ3Rl-1h&6w*@rrtBpCL**}Vf)u9~(Baziq0%l_TKf8vj z5!S6w*XHFk!yQS_9+uK(!qcVn7x5ltjnlXubk` z|Jb%YSf&uEs06&dSBmiUlP&k8FBc)B`_1zB{a}(hqM%dd9rH`yigX^5Uj^4^++DJ{|QWexDxh zEB9C1$iFXdb{Mq4V@`!yEt0d?HnhHKNc8J=Q`6O0o=P}*jv|_wp4{hSSX#FdUoI_W zb9{|XK5TatUs{yO2JaZHfA{**;U{hH{gc;Hh%Y3IAxr8j{8Tq?yIB$eNslf>w3E+q z=lr|#Hq(TIW%zxEKosE+Nb=_0j8lf;wS?gZ@}{W2h~}H}&UpO_z4YHD545Kok1*%< z!$OB`Y#h=7=<~EYfyz7p6_lR#)K~>z>ej2(vU*?8V0-+*?HS$d zfwD8hXp3_jJegnhq9pS$U8G3C2hRqe7yA3MkRXXI!g@X)e_RQ(QNqvGpON>9a(q6kgt^aRTor?wyAtS)BzQL zUhl|vYK6AH!hD~Xn&9XS1L`|sb?{!|WXM*ADu}VYkP>4|^u}EW{dGi(A;T&1o6nwn z*sC#~^42j6MzvZhqd%oV-MyJvUE-e#%ZzGaYm5am_E^5ijtEFNEs*4MH3YIaHN*v0 zK7q^)Y7U9#q&G((F*Wkf8weuU*p;7l@aHT$E6;!lP{fKvI2Ru$dE_wJ15t+LUfrZL z(QSohf85!9XP#sK9m|x=n5<@uIU$3+wp1b48_c7xWBq`&D5hui zFP5hUxjF`6|bP8SGFTyK>Ea5e06|XMO1-e&^Au5i_x66#Gyh$dSE-{yO^W(#IB& zj;>o*DeOBowtLkWnNOmcmR{hh+z4j)Z#ExW@5X2`y}WZQ&3HV?Qix8j7`3A^@7}Tb zfT3T`oV7R2fXcYl!kZT=!1s%iNxM)J9Pw2Db%5v&p3T#j-yb8o#I{qMJ0^SKr3T~A z68V1EMcb2Z;?@r(jawcI&G*6Hq6D791-+oo_zDyFdO)pMMTOd~3+xt)X64CT5i$NI zf|}&Mc)9mgI4ZWnmi@t={<(znq(~Eb!@Lpp6tMbGCf9+s*i%Cme!{omWc>1eu@d@k zZC&~@Q4TTN-G*NsAY3HxxWGyG63{u~s}_B$801~{B@Z+ffc}YDIq7sC2+WYTT&t@` z6y*iq%6iP!Jz5Ek^(fT4t8Hks9*Y?4F34_cz!jZ-(OditcyDuFEXt$-+crc`ET=VK z@}4r<`n)D&NIH}uPCJ9%B}w1aih63agc38CYe{VT%HxEeKNcH{+Bou^C*-* zSr7|Zacc6)WS=#8TIlyS##%V6F68Xk-3-Tuy0&cF(GI51^g2ePJK>d}V7PK?HyqQL z%`Eiog;M8Q<-@Ce@YOlV{mFbkoF=u+gAN05f2+IR#jpYJ-+y|~iyH&LZb_Z~z@{Hw zHkvS|Om>Rp+bTBTjA%+*c&(C61Q7iRE)nOQHl{1Vz%JN3UxC;g{; zV|r8Ad(lzgXwmy&ZS?!Fz2Hqq6HJXs3?H}cf~rcXBUjUUV5`CN?uyWE2ntxC;s4PA zv9~Fx$9hQq0Ni&Z@l7=i?4wy(qhYqAkdXJ0r>G5YFN@&!SVO7HqJ z!qo_MShEnLeof{9|DP#WjKOhu`n6DtDOSrUIJsw#-VimT*tp9cc)8-fi(;@3`tIfn zePr_qou_@XmQn-ITPa-aH}e-fcG;(r^Hwn0H~TuARS!lZ>(|+7_FphxZ#ML8OCTP< z5=xi0m*n6w409taD=^@v%Hp=S6*x?{XXxNuIp%GQ>Rdfvj>;1CiMO>%QN7^D)QhAX zqz;;i5?qhN4*x$9rer=_r(HkNV%LENsSa#BNt5U{L9-m^NP1^OB~>UzmND_J8E;I< zB8qIM-5HxQgIXIWjxI5c;!hX$vo!u~xO(eGIiGztdQncCV%wSyX4by+3tlxas%>_V z?PMDq2;D7s$fFDHidOwSQQ8B(W7N;rX?kI&?2D~Gg?b>6`efQ4zb@c>!C)}`mFT5! zsahf%+Mrrht2>g+0rei|&hoo7fko@UxnsSxaQ{cLlQC5lSQr^Sat|c=;Hruu$%10C z7bt5KE6RuP86npbotZ$(Yb_vjCKWTEW==53z|uIr_?0iuJ@p-%eRutAFkeKMFt$hKT}wEyIli(@c?r+p zdV{vm99D08J7j-z0wa=w!8ocHM;lhhB+6@X(e@ZK1zQ6Cq3-|8MiCDWg?hSXwiJV- zp>oimP9?N1yzXquu7ev+^~tZv{%@K~?$VuOgp0nb(&~s`2boLxICqlw11lR<#En7X zM+|J%^F2uVGCX`3oJ2YxWv8g74B>|!VN>sO{m=x5SzD$9Cu$(ve={`jLph}6@&Bsv zL&&@MYEzIQ8`75!{%$;;0*n-07dVJdZg;&t2dl_Os29!pyVb}B#A3yHM00JCbH$K* zpwSC2D%cg!-}OhajOeWJ%^-9U&1C8avVYfk9D$pmILt0^;)Po%9^1S;V(Ar(_hS!h zu*n9ZcP6c4MM*36>ZVPk8ML9FZ7jpzm=3(veaHESRxdKq9=_NcH;i_}4|DG(kE697 z_j1ygDSV+YJQmJ0i`oAKX9V{W#9dy4Tg&Pq`dqEc>M&o%%ZCJS{i#|(ll426UTUkz zVa^&HlD2{>P5I9j7ng90 z`-fm`>Tvj(f5RaDV&(5V!zdis%QQ07J_>Y}TJdib#y~Nxb)DB^3{D5MxGDRM!BT6F zgSqJ#T;Y{FdwlO0c-uz!7`u;>zPzhbL;WK#9OuTIx@!bR1nO%y4-JD*s_$-^bA#Zy z@0DNm-hMFj)uYO)?*V>)8qJE8HpnUa(l-=PNcc6{Vim+E;&r>_Z-PQ3dTD)^>pJ-! zi~U+R_EeMph^^85mmP93LVrXnUNIMAUI$%nznY89otrU{+POHReRD^{t6Ze63sL(^ zbfEwPn>PoEKlJ2sqQ4+p9(H#ef4Hn%hLL{L0x}y!S6gW|_uv~t^M$Z&K0D@7PEb=Y zRbmO{f};#}k^R^5#HY63_9UNedhycI_9oQcVL2S@<_K*1_V--gR>7<9Sxy8#2KIj& z#FJY(f$@Gjtu@(gL`R%8{cn2*XbAtKifd^F%0YwR+@NOQO8+DJZ%+fTy%}aNRH%Wg z)VA)*+bh8;geJi4Oc@BwPgW|&5dT%BtGUHo0gNPcoIP_O7kZ2gmA1xa!Xi&?n=Z+n zdUdrrzHUl}NaN6?7?NM==pWx>;1CVHdAUYmcf;Y1!=eBF@_&J_A00>b3i?6mn{vy4 z37%xmjkP(-=K|H|(}i?vEg`hsq(Rb53g{`u{q|89U^%alB`cRT9!hA5q5firj_OkP zMBJV5eB!c8%#0h_8YX6OHJ76PJ;(3z3ne%rbU$Gxpcpm(NYcZpVtgN_FX~-{_|1iY zpf4i6J)J(jN_<(-C%1~xkX-P48zHG3y_M)a=AN7ila7M$$=yN6)Wx{B`^kO3YujvRE8J$-R3k$Z8j9*+*#d`l`|7u!rEzny
  • O`OQ26(zFaX-In3kdDi&2sf^1s&IT!QbAkFw<20YVSr1 zEc0(l$&!6nqDAD*Lz_*|_4xb!=MZGB z^c`ns@0y2;k@vr0{q{e1XHip<&2#2NKZee`DR&gT!+VCuZJXJf;a0__3d=?pJS`;M z121|Z@<_{a{%{YlhWlQhB=c9`Z>61g9NIxlFk7k5yagyt%NkOZ8wht#^i82gHT1qa zpuJ8}4inT{hf<`9!RDfE)Pz^@5!4;2#PaFNyCeI?ld92a1181k zN_W)c-rD7f#W8eY6@>jp9ynq3zr?)LME}?W@lE2r%dHnrP?c5T}2+6myKkguW-Swxpz2d{mAu88vSw*cI z90U0LdFqE?&S05)!*mFqmHaoz^rR2u&wRY{p4?BF&V2b&bEzHP{#3ZXH<{-C zCgpY>@ULzyDNoJ@`p#nyKg$!&)mqAv-{;ez%4tqYkfRC zei`)ND&JSa(VbD8*bzf?2sXE_b5WrB=a`~rBgq3OjWRoSg+tQM2pLMAa4?to^iEtm z4D18$D{d0MwD*rGo2W-0P;BMWi^JzWV*av(^x%hd{BEWraE&Vm1*sI5ID2yN!-cu@ zPf590eE9ZKKt~>mCtkJe4a>#X@7^&eh{ThgD%iXb?TEHZ!RMddO2J^QZw2b3jmW#? z6e=}5f*+YL-kuPfLz`k18TkgnTat<_VyOF$GwX#eGv32^ZdX5({l{uF`|s+;i_#F7 zd?3nv&9MRuBqS$7&No5+C2(0Gy!oH!Dc5w!{-wx4;!gH#18hX<#CpD{g`Y#qyY*!V zub$P;N#Q{`$o*4n-&oPHP!l4Gjd{&t*CGzMo)qtrJ7A6d)sWk+g+AQyM4T-d@3btZS_`FMV#mSMxCruj z>QCrdMx>&U^F)RwQ!d4$7bGwB~UmBhXvN< zV{gEA-?N>)SX!BT>*LyYeAM}(^U1{}Z}{o0wl>m5*5RvYp_licGk1Z7m)lk-?z!{x$iGrUi;nd(}ohZiDM z8zUaoV4PqUa;Kpjeh;7QHUC@!ng1CMX?7Jte!P@Tb#N~D-%}oXrIZCG`Aep9&gr0A z%Vr|QmI{$MJELNMCIZjhBl~Ih$AL%moQsB2G#uY^NWN|`9K3fI9oWwr4D{P>-bjo6 z1Pr5F&8as(5RNVnm2K@icz@XR;#Yr1sDC$X^K+XSP^6TAtJlDKW{(=jpQ8`)u7=DLp5q@860z9zB*(HRQ&l}Gu$i$8wipF0v)Je5F8av1K34F~2QvofTOU4P{ zmQtp?(p2sOXbF+?i`Q1VgF8phvE7pX8}i;qzMOC=0Um9>^cqggb;myQGb);kKKP&V8vh7~Kh6npo(7dbR2aVhJ?h67 zeC+!^p5splT3Nr_8*d+qRvPl&m0_Xy`~n^8UiDDi7$O;wvmtop(bP^Gi7dPk6S+Gu zBpVyAiF7=-%|Q>twiua5xv1zDy%GK*50$y6HM33@AoJUrnT_>Qq-^BkRXX2<3*v8j z^sPEkFOQZj`_KTge`z~aZ8nZ{{wm4-^>av}Zr!FHMEq}!3%6Z=&SB)NogfA2hwM%L zqjIIM6vxk3-DyZD0gFVoU$o_I@Lwq-=3VM0`tUVQY4Ux%{B6T{sF2)059PbvcWnon z88z=Y=~kF+I>%*vv>6tvRbKMR68^2{7NPE%YUs$Nuic9krCBTqG}=d?b}wsL7s~PeMg*&1hSwsHd#rM=&vE1Cx5UUO#$iM7O%Z0;^3KI?e>m& zlFQ2v&nhmd_iH z7#PfODsn~kR-7XmZCu>9VfF??yZQF1bGlZE9sw+EGe_1^=P-Q3l?L&!_md*Ub zc);L7P37SPJa533XJu6nxAX5#U61I32YP~~nKA<)*6}jOhRivYb{-xUyu&1SXFW`L zcMvuV63b?J`@nf{#7TkVkf=Z1l%^IToU+-}>>H!a;2c}EewOfATR$|2TzgRgx0hxA zn3|AW?~~VpRll>~=9~Xc+^tD~$gA8b4BEkvGsgR-vECYX9{M}B)5;U2{F6GK)P$jN ziRO=UMX@;L&@)QAn20RzIwbE$rs6tR_V9FkI(AIpjsyQPP)SbyaBX!ax)DJ;;B*!) zuZ$1NEtC7=>koIFZf9byu&Mizvzh2sU`TDJlYz;y!YkZfX=tpt_pPs4EXrlQuD85W zNOE1KpVH42;a8E2wyxeHj6GPi@OwYWSzmv6G(r!N!^b1dvTk5P3W8h;eVPOwypJ9B(~ABu5v9)cq8O#px@FwZma$D z%;*B~AC|3uX`-vZ9n}(4`q#=~Tj*ZSrkqX?&*A@z#e?un`TVh8A4gz*&-0cnu2FK| zT;WO&9)Yrrp3BCT!(d#vIKr4V035Ww+-svfz@#7h{0Z@`tn~Sh{4#8X`o8|V+Y1{& z=*3Uf;x|>`&G7SsQX|>x)`gt>yp{w0y3Gs8#Yu2d?(Qp^XMx}-t}0WibqQ12U-Djm z@EIR*?>VR08iVme@k*W#Qn0MB#^i`W1};wCD_s9h_`h?iCV>OFsP@;x!P6`slTu#4 zN_tm-Ni_8xlsW~dy|D6EbvPdnoRG#?@qF~8E;HpMe7#+wfp2_5voY^fi-zpEWZblL zt=5SfKFtvh2&RSllkX^X5td7VtWXM88Nw{**o2y#)!E zAip?}m!S~@Qyx$4Zf!?>`N^?;F1>i4r$sBSU=-CUB!-5s%;y4ElZFMXgqIM55rQJm>t?smYk`JNDa@n)dfEMTt{sRAap zYdq%`$o%hj>Yr0x5=i%#b1ine0Bv+Tf8fh7l(aQoJ)V|^!=ITxQxe{k+n}z6FyYX) z*=F=^kl)3@Ggoa#|5o8R>*7n@H?{a9L(|jdp&R|8|heo zB$?eV#^%fCm&{%2P+@m_Z`(vWPHJ!Qd0Re+d`g}TA!ejklOj#XV$UKD-4$taH(x@F zr=ONOWoAj9?_G>ac|TG_h`De)dJIJqhj)KYYlSmhRYhS$pa0HO^|K{NTR2aoMTaK{R5+E#Mk@F<@=EdL`Jw+B{Vzb%@MA@{jU&V9~Ap>s4G|M_HN zOZW1r377=@^di$c?EH9))He))@FHyA1@E5Fz}1k82& zE0oWVz@?{hvVm_#U?+F|sULI0keBgm-*oN}a9+zwQ~ygiKcSXlEcCq)bVT;+g9UJkCw0ST$f(EA^f z;F7q23pdF(iY@p2ixIWJ;_9cVH%&uOy5!M(*{cMkkx@I3-_w!w|7b4;<=`mC9y5wV z1=vsBc>nDQ#0QTVimE4zks?>Pbs@6^#km^_+5RiV(Za`PFFY^7R|4!R3loT&g5F1F zhjQ_JtjB@iL#ddXs1|s&B@MR^USN?W-|z0%(_A*u>3G(`=KkPXI#SIs^FJj$M>~o~ z;;wh3p-;hJ;=ikbnDK)-aeYfFP|I8BGqR+@%Or}=k0lF`Ww9~%X7>Q@8Ksg`)StyR zy+T)W=_Tw{KC@fia~5OG-h94tWDrwIj!GQgl8BCF=cTE3lip-2mWzs)dcdQ>PqLn4 z2yFA&CpDsnA^pnHd}Hom5L5drbvI}LY;BYIB&mBrI6YzCx_BqB?f!4>{kv8eV$vvk z%i9P7{<4l-TdQGa<4M1lUMUFmZ}aOW91RLuvx*L-RM2Qr$!*pRhyG!w)Nk{S&}iqZ z>g?%-S(ypS&-o%Shpyyo)L;TypFQk!J0=Z@>YOaWl7&5vL8}ujIry~I(xHDQ57+7W zPL&4`fBqxB*xdt#xK&Dn-<|jrIIen3ilh|bgYD*ja&3!n^1W$weOw{#8CJ+emAAtl?vSY&zbY}=?~ayh@OBFed_^3K9HhK`r5GIwMRv706l0g@U?f7I|jP$}btCdW}_`PIH@((dYrv#w{y7qV3EQ;Ow)sK@gZ|*h(Yt4Sb-Wd%Y%UKo77d+fiq$l(BvD4gTaOyF$m3U_nXnwoaV>6cxZs&eocUK`f_o>|+ z9-m`ib~4G=XfOyuAO9H&4I{a_OJx!V@Fl9B4ZahU=#OqCH(K^xjX-T1;bmgFLGDPs z+tM~k*y6!rn=6ru9~<5FCbp$v#-v*8fdQX2P1`T&sKPxaK`^P`U#BE!S5VK(>OnTm@q-(OQe-z_? zbCIh;ghwwFJRTjUS%T8<6JK7xRElYVqD*r4D)89&yW%RD26R>T%WQerjlYkDoGE=j ziQOtWrOw2ZB+{L2Ihnjf{GcqposSl<`&92^1KDW|cqu#Ut4r>oR}+h71^e+r_DeSb zlJ7I|rPbgqDI+|Nw-1ERhv5s>&D$!JX;5BBF;z-<4xn-G*K-D+TNS?;;1AA?|hyfnPBhDMrt5n_tI7+;tzKJ9PJ@ zj0cjQ)3}uPWd7aDrf`QjAq?l!uRpOB3B~WRau&y@tB_B%G10rG89B8%p4OjjME0un zPrd==I3-rNt~H;H`UllRrl~@(J@HlY){KbM^YvVp4oDOJE`GHBa}pIYMz2P5w7 zqw(*YV6P-+dh0WHy!pKSLZ4(99_P55#GCdNt2E22)KyZ@c^j2yqe40!bG#urP?AYF zKUczlE*ry3Yy8xuvoT6Iq*_Ka3j+>IFPsia#=Ft*QFBKLzPMxfe)VDr>d?rZetNqE zW9duv@9UQ!m8w%~>75dcAOGIzCtQM?H_xieI2I$F%&bBk(MKf|;%JULChh zvhFd^cdoso?|L&l(vnhR-Ryx#5wVZrCc}`?azZ1TZ4~qc(!~ye5#WnU zpO;q~f_~iurh{F5z`hx@dYGjfSZ{2=x@J45KRjx8vbh{k>2r~`^*^hU(kyIyBeA}ypF-x{o1WHkHOM{pX=2AO!OkzE zsGMAOX7}|@Y~G`?PGeDm3P%@T+|`MO+ARYf2By_e|KUUF9N|Cw=H345RaGzK^(P;; z^Bw~6T#=OTE5opEL>oy<=7RYc?qyTmVbTjjYk4qb5KM&!?v#@A)>D{Xk&~mWOK5WpSkA zg~fxKFTRpK)5{lEsB=iKV?{F8NfXk;Q*J74awHvtWDiH(H%`I$>t#M4#}WzWnK_s4 zTQWLszjS2IDFr>R=C4Swq@t^v=40B1RI*n*P_k&1hR#bOW`YUnSP|Rop_Y|R-qRiI z!5n3{IQn{g{BkQ+i262cwH(3rW9DZcd(WcVQ^s#M6qaz$?i(C#`{yudQ$@{5cmTbA z$uXPFegv-*=B)WV-C%Z$S?J-ZF$mnG8cNcc1Q}^vt^MAU@Zu&j-N5WPJP4&X>9!b! z`|FNwI<`Z=wjd#Qg|Qc+n~oy&N;}xds%=n6HG>?#@xNa*gg>6}_ek~IVh~O~$$2S= zbd_-fs>J)Zv8-E`Lnd>QV0Hc4xoF27H~> ze8uzFFkPg1lAy{}MBtNkK=jDb$v7XKt=7tuf+7OTn*3x>FwPhK?S)n_ zs#)K^*OTuBO#cP{e$JbOY4E@}N2v=L1#^D0CeI*)p26vQ_9dKOntJ&`gmCHa3+w#X z--XTY-FXd!vwZS_k=#y+P8gkB-g#(Xh~&SRVmc^BAve+6rg!HkNKs`!y_YZyhZ2Pi z)kOzDNXYO|26h7n`xKcZ?vO($uR*dSWizl&Zgq) zpXzbvS2FP1CH3EwI@xILEmGG+n~TwOrlOQ5^KhKT=D2T99)9{_JaV4+$JL6(4X+gD zVf(3r`^-=0;bwpKHeTXq*!nZQcYra6aCgM+{%4hi`HLr|m{~G#ION>+sU301^g64L zf+GV(12)b+(9T4b)X3)aEmY!=?~ZjBpl%EG#EzP^yRd9Zl9TW@R=*xoaa=-i4)bd~!E;#G zkaw&%bqI^EN}{TM5E@&4j8`=1ApZD9TG7j+pk_?fA;dZfbmm>AQ-3C5I^23MMbQKV z%(ArWn2$kyi`S78MZ+M)|3F|@M<3Wvn%)rb?*#uriVq26Ef5h(C&aLwaJtPs90ZP* z!RD!O!S&-gpgqEJm#a1gnioexDW2GXmuhg?#}+&yC7yTft6N#9!VHgPT91HgEK4|C zZnaX4AEGHAc3i8$fb`vA49{xN{Q_%c$@3aKB$$$tLHZ^PICE_dJg7pN2Bq-z!BnK> zFOmF1{@=qtE}X6eQUgPZ}c=;Z>gK7C;m4d(o9uydkLRwH;2|5 z&7pIJ4!2Ut2>xIbI1r*rc%dehobm?>K_U6J*a@QNXQuh?npW%}DD^JUm$wN2aQioZ zg}ps6q$6@f$gCUg_^Vyrd9MpR@7F5b!49Cvf1tZm(FQx}GQ5QoTHs{A@=aytCg@d< zewtoX3$ZPH-J3p@!1M7ueMWUD6l?Bn_-J1Q(jHe%C2b?~08?=#b3rm#))_YP@RH|4 zCQ0MC%zNMsx?n2$&m7HqF7l{P_~BOylmAh4p5a`+Z5*dk3MEmAWR;N_f1~1(tRyQH zl4M8O5=pW`WhL2r@4Y$gz4zXGj}WPz>v`4DanuXH-|f23>->(-SnWnEyjlFa5iFAe zUH(1cd#ahBIRE6f2Fii6zmL#8Z_R~g>DBTjr|~}iEwPaACeAaDVpoM9-uDbRsNIau zggFU$JL$H~N%JChig1bC$>X_!nQEoTGWx4d?c_mGl0a0qu0* znSWJlknbthICTNf{~4d2_o*+#07XDj6YdAfyvTgTXgUhoZr%H5Dc6F`PpYs7eCS6O z!?0~8HG)pm++y6C7(s#?XT08O4WVoQR$m4Q^dZhb`0Y8?iEM-^_1Lpp(cb*20d?$q zeHL2kizw?6U87*tw@%E7RqE{(v#mgy4ZID{(~Ggc$EYr0r6evR=h)bQsvN;ldRW3gH+ZzpH!%r8e(qh5wTUVq5Q37z=N(hJ9#Y3NI z?w)%d<}AgzuO`_zAUcs{=E0t0W!m+F(F@K^bY{d(RU zp7-B{=3w4e0omWP1+XhB-ApvLzZU{is*lAeDHYagvi6^?vBd8f~`AYze9WdFt^Y1L}O?qn7HvXPJD@j zq0o^g@|;9aKjcavGD?9=_JFe0a~THXn`?nJ?W}$OKOE4YLPBDUhuBptsbt4o(|{ zAN4sm0WvcSo9@Rk|BiBt+XC*XjI7LL~4B254*Vj+HCgI09$ zLRv#^(f}$`nSAO^H-?tpx`t{{P9Sq9U3r!V<7leTS3N6o1QA#nF8#+ch#U%x)B5du zk^F>iS1CF6VGWDbW)rp{J<|f)ew7AfsVl~9htGfY%V8#QBBkhd&-i6JtTRev|9iHk zg?-ODN`F2&1RzIip*!Z*LMYWPb()&=8;Hm=-c-Z)D$oC}_T?WWfJV0`iRzbhcqk!r znIbd`n4c=^RldjpzBX>{E$oltcI+kE^Ui}j#^^5Xq&(QT-$lNBB@d$Ye^}e99L;Y;>at=1k-lufH#bJ1?%Cu;MR< zpSLC&Mkq0tIgm^sldc%&c+ELZU|-_&J<%8Cv$=TRUCw3qA`?ROO^hi#O5jwCwsD$5 zC)gK}-D{1Vf@iLMM}F9?!A#laeWq@lf4OPuGg-9?Q~s`zBDlxEacY_56V~yPPYS$T zChkDlR!t5~b0dg^@3S%!=M>7;*J3#1H;tT%9#mWZoM}gU@k@ob)7_&e1O@Qk^9D6sHI5&i|OrBaDLh=mN2k*d!=nO1s?L zmI-kri`-Wza)IkMw@!&iKHj(YM>1V2gsmqZj;`a+B`W8qf-6rk$kBgT7k-I*OlLaykAcC6iRqVnF;0R=pX53#>1=L-qHtK`1|1e zR^#592rlz^*6z|t&{n79s)YX@n?=RAlpGD(5@iL~4MUI%J21)L3r9M^uQ!#8AgQ}>%OdRK(rD0a1+TA{G-@Zpa0N@^TqF5+>R$B zfhR|88L)0bGuPqkr!J|Z9)vL!RnoqwTSo;ebKLdK>MZSay!5C(SbRE%DcbmDEi{o zxb#94>UeI`FPP$q$m7%`oh{#C{ZLZO@pBMN&K@UM(u@U9qaBIuKS|(kcco>OBm+{% zzOvlu&4LR370X0BtoxE#YSLHa!n>6t)z60WAg<_Ck}bZ^UJWyEiKHojk)!b{wSV#< zg7#tcynjA;s|D^zoXQ6=4cYzc6nUU6uN<+=h`GvTl}H}sY(L3)Ms z9U>Tx&3<=A1BuDJ+avNfflF0eyazmvpz$MOg`C_C9AlOX>E#|EPf2cJCZAk1CRAoS zgYzh)MWW|aG1uI-Ou~nhyBk^-KT&K@ErMCn9nts?8=%c#)E9I(4{KUb(KK5JKh?+7 z)N;DeM|-wuCwzZ>DSyL()@B-A(A@G0yEu)~HPx18DJD_=38C4bun~0U9!Z4tZXbG1 z45{ziJCWS^7fE)QZ*8IfC^r6Q6>7Z@e2H_Y5FIv}hGu%FAVY0JYesfIWOgs<7%`Uz z)Hyr-B5{lXf$62X_b<{Rvb?leJ1z$-!s5eg)eC^Gj{LytaWNd@?fv{aq7(vJdDES7 zFRHfWzc-Fw0d|7rUv|h=fQy!Xm;vr3f1#A5=UP+&U7PX&)GZYt`>&frETsY-UU=y9 z`9TF-DY&+q7yyu=ZMPWgTn;~)X>m?3CiRXV| z|C+BjFLoxfgy|)Iu1~CO^^VU?!Q%diZ#~^A^l$wsnHAZDb5;?jdrmBahJX3$=939@ieSZYfj%|GnDVPOX*TxO@ETUS}2bAAcbsLRAe%r`mH*a8^Ui55_YICe?6l z#F>F#ts2-ZG;JR+RKwcoD_ouU-xD(G?eSi#0=BEHbvsx`U@a53@Ab|EmwMfxoa$|egG{$J+g5pyTd)6M+ zL6_-A8x8grAQmqYh!W|6o$+wX@x}>QCJX#v|J}Vvfaf0@QR1=OyNke_C4V7O zrwg)g)Uv3?SE4w{rZp9zesneA-jgTV!zg0n=(%KzK|~=^dWtC=_e`>}ymoqn`#(h# zD3q-5IdyS)m&vCCjdEmo&*S`c;wu`yK$>P`H)AF71pAp^J&`Wr!nwC6Zs8IO|5c#C zv%9YgZHiGt<8c+DxLhQfSoVD6Xa;&mqZGHT7l))yTKq2X4?%^pGc0fDanH6u-LxX9 z2~5zlIxo{XgVwJ1gAAhYa70myX|Oc{;x8TF|KSt^Tlb##eUwRp>8BK=*{x~N`5<>) zoFD7NA~aT00~uf@LMCoKlmRLv*MCO6&H%w9;`!He(;(k)A^(10GBmMweb(!Xfm~|i zJ+b{X_{Kb#z+jdM9Y6Jj=G?Qus5s^-!7}zkw??;Wj^u*ob8Dq}rUE$rIiS?*b}7!c zPmikdLi2ZEc>J<1>;`~ds^ z7wkP#Qb!=O=|#lecmb04C1f^NoIn>~a(l680Tl;%m}DuhAhyQ5K=+hoL?>u=J+5p4 zC8yX$NpsGkCiXWnAN(fKkEItbNjN8Wz9#!Oxo#iw(O<3fAnrsmgmW>MY8udgw>_i( zey>2qDXr<}3$u}`j=tuLOFxjIu;iI%76Gt8Z|0ajln(KFRcC1~6#}zb6)hQ#Ar3W8 zhI~`5hWX_5)5F$vPe^U+92q zZeNGK=5)Z2>Xm;}!kr*^N%ShSNhh2YxJ@#K=aSLuR-Kaz&CtpIIZ}VG1QwR%63xeQ zaqh9D;g4Y>d~d3c${%Y4@dK6#zh8~;S~@|6gQf{Y$sZma3vPnK_4--@;uf$-`Hu0M z9Ux_z9?bZoA0$JI1V%b0!O!ap^U-OXV|h~kJb!WnCWN!o@1ER-9v35vrI{`8KmAh4 zp>+cs)1K%PaxcNFQNfJk4&x9g+bb1ATmgQmX0;BqRmeVrpF|kC{YM@^$k%;Q4SKPS=U zvYK#@#c?!XetJjLW*Au?p;Z4=+=m3^x+R-VVEZ|>!3 z(Foq=mECZ%1+4F`Cy&jw!ZmC8&W*J;I9+fwuV$eQ{;28_Tzc6Gy+X4^R%#7c7qOsC z=qiTmP(HQCj=8cK&xDgq8-e%Koo)&IeaIJ9cauG7ga$F5!RR}UpjPhc^QN}}E)_Z4 zd=y;=g6;(xs)F@!Gx0A0J@&l~X`ExuJ3R*6^Q@(Vkqc19pm0O!-X@$PAaTCHy$zi@ zQm4;IZNeo6k&8#JE&~%~Vuz&rG^Fuzmz4?)LUhpl3mxW0&=T)<{qOG=xE-}55=mK& zDt;L7jaql1S6Ba}QpXOW=(;@X>nCwP`n8opF2hMw8?{tG<}rn+lgZu>?@plwGUf@U zk}33^SIM@ibrR8TCeUgqPasmQf40&GBgn6G>^()#0BTKmeVf;`2ia9;D8*drK$OCP z3~W2~2p+d+bK*Y3yREI&Gaa~(fMWH0K-?!J`ap7bktrH9ly2DaV_uzA)wTqadnvq- z>m(Q2u7uL*hHt@3HL$mQ=5K^tJ?2{T4%rPhz~<`2FYEY5aBu!>du6&2Ha^mG{!?v) zLJXR0$gLA$L#$=!0=(mdB03g@LyN<9%oELW+Ls^Zhwu0k9PI)RA;B!a#*Bk#!QP5E#R=Cd9gYv7mX!rvs(K>Vg*2(2r zq!KZs<6Jj~e3&=FjMQckjhTX-;iYL*VfOeXL&*dx%q*hMipBgdRqM6#^SCE{)X+Vaj?p*t>T!qf1usN+z6rm<=!L@?3ndmKH6G>KcC?as| zKCj=Apm211TAU5WJnKD=46{MH&){|aR1Qco#EbIcy~6;FSq!UnJ}_2R`1e_2 zpBLR(@oJw!ptlWV6s9Wy+Fud<3Rfy2y4q1-G0q20Sx`DzIBroZWU=N+3tJ?G@z zRk!DmucP=S(UbG&t${q_gxoALW?yh2Xq`e!!*s#>)Dy__-uU*7ts&IU7jd}{>+e&# zb&7|Mo#>c*x#}@a+&?2z%XefCbEkG*wrb84qjJH?XX-aI5Ko#R_1Z=ta?H-kc*^1k zE(>>=Q@G67$;RsvgX0)L5i`&EzI2tW$H8hQwo=pr?d}Pac|ukkA$6D zB^b1>()p-kUhmjH&y4gcaAkYf&Kr#RQF1NDSMOATRn6K7?yXAb(~tO?c)1ef(zn~O zJOkex!yMJNaGsN!;7GMcHn*3?fhMTN^Nyv}ng55)QD+|+HcoAyTaQZ4%Ix?)q zL~L^*RKljbBN%gbZjsHvnh6@wIF`2g;S)0cwE8yuR3Vtvh)718;`hDbcQ&J(NqDAu z@zisHRnYJq5t%gE1kwxF?(Mx;flqWbaTkg3{!{T+$M}gv6i*-%t^Kke_iQs#>EY*J z`1|*WHk%prlaEY7BWecSUdz7Z-!g?*cibtY@I9g8*Rg<5E&P2M$D|mH_aV8+!`X_` zF0{6AgpC64e*#-bjk_)Dk!hfw%GdTvBm-x6nmLM4u;8UVJJC$kWSSxqkD`#6rHq1^N5H!1;x50uZ&?36&}zxKaY8`x)i{mlCLkz)A1N;q2VTLcg8om&0*qY(C5 zC^Y^!;paKJ%>4DkT#$L|!|Qt~0~p)ljmHb~L6+F+Q!~C#1Rm+bvovB7Gz3a}k z?6`NkVt!skxC?i2tS0 zxh|VN#PDIWqwQA@T4@e?%OTp0OzwRT!v&#;b8nIG^d|0a+8q$8lEON#@e5}`=NjAx z*&fY9REhSqJ3kS%mm;qn)7RT``G`P{HF<6|6K%=PC;ZJ!LJ?J=pLu5^QNS@AAPknH`R4ktq(99&`AZ?cPlz^?u-7}`crNgWHC^y! z&x32N#hwj#kH1Dz%v@ER0cotd1YRc5V6Q&LZAnxB$g!SZ>O=lDAfW^}+Ra_~ z=*!^-kKwXrTP^M}KVd^{+6`&DzIspo41uAc%Ax(o5JB~1e+-HwyQOr#tf{upN*0Bk6 z%*2Spfn^l^Jvb`&{nh|7nm)Vfozaa>2X)RxCblCEnY9VIj0O~UKS*fOxC--3TEhC7 z3X#ucDyzIJi73(c!S#w8E@%N962ol*L12qUYm__{zIUtOPT#gbvsY#F+EJy_Ioaf65*2SwC|9>hb|6CjDc^7w~;g zl$<)>IS4+kh7v^xg~8{SDI^|zk)VHAVNv%e9PD#V9t6?*Aj!|V0ty51NQL)ld!Yr^ zZH@&mR;Bd8PMh6T2dsnrX>Mexs>l2_E{Q%u;w5-XIjCh8*$K?Qm;PKcZblS8-5$IW zoDY2I&{b$&@xu9Q-*;ouOHtL(LD6dA zI)HsY&i%0-g1FRI|>qjf@Y4t(#pXd~OPTLz->(+}1y)8OqbecAHXD9Bte zk2%s&3893WM!z>kVPxQ~AMN2P>^{;ob+F!qVAXgx~^K zIb-A5rK)bU$?~81zaV^0jput+-S0y}Ji({l5%!^8soIe>a@tT9IXK!fNq!&bb zeeAqN^aEB0`R~!(2>~9FO%t`oP&i~5KKF?v6gq0X5A2JBVC(suO6sj#a43y6`S&po zdJ7v12&?nqz?#K8lA#dJJ((u{jpu-mN%SjDGWdLoI=k{|u>_{~pRYfDkH4Skv|Qu4 z4v0D_O|5uu6q0AIEH8-8fu&La`vvxO(Dz=RJ=|1vT_3-H*9m{T z6iq^@CRXyNKH^^IsjU8UxS!#|+*ip*?X!q9REsyMXclS4KKMF$dX{0Z z@Xd?<_>BV8v2?m-+8p=5H+`w4ulGle$NkjiR-8cG)H2PVG8&p5@I{9Br@{H{*T+BO zyr#lDHMn|&- zk-+iip0_GS@x(gL{+xdT$>%$h-|w41Rbvf51L`M`jBBF97yllaL<)4hvB>OX9$nfz$4;E_t``nz-5cc=>AwU{5aSpYM8+M z;*IGg=fn>9d;QwOs;Ew=5Fv?Ce%b|Y4D9AN8@eEM@Wjd36CLoV`orNgZ$6kQ?LHNK z*96n2&#|d_mE<8Q8r9%Th13V}v1H z;o z3I`YbAGd+PX4N8{b{{B}8uD9)PQm<0SY6JyWjLAl_$QyzCgk@;29>LCf%=t&ldgZ) zA&l)~t?$KI&<~fUvfOI|RiA(FPrPYDth8LCwx=hM>WzNQ+SFMj`qZqYn0*0-C>jfe zDled&EW77&XXlX@gKn1z4L+Bm7_W)p^D6yKr=*Jc1mZrT(_L_F1ReT*{I4slAEkHF zx_M$=aN>@vxbgEgr1)W+k14hek*c2Wbl5CM&mJhU3-o58OvdPmlBgdjQ~aKoFo{3> z?Qvtj<%9Rci`C^1cnjd#J6Vru+j0ovOwg3+v1kPOdQ&ck4)9ki$dvM-esNpK`5|fDI+Gs>JOTdFBmG6tRjne}f2R|Cy5?+a3NhDLoc2GdYl|?*{r2n+i#1^G z@+*2OHV4hrg#>St3xR@ic%-~*3?X+B?>)CAbTLexD_n04J#C+x-M_Sor0v`IPH`qiw;3C(2;Ir(!n@K_{iAw9GnK91D+ zxePZ#eV|O%m6T?g)y)YdaW+Uv%c|X@{DNKE|=k9T0o1 zlk@O?2k`sG@?nn?=E_|qE;8tVxu(9mCXYKH@$S))aUsludg=0t_Gky(u2$xgJlYJJ z$~S&0{>p;ndw1$?vTnrarRfCh^xfjvBs zC4PM;`GzbCCZcTK4jD&+@Yw`8a-0(w$Q$@AE7A=t#|$6Hm`uT8udzpt>Kg37G60=} zP4K+hFB=`O1{Q6IIrRPvY%tuPXGrb=^5d5yE==O*O}C6CT><;R{{$DYpX)`*->p9X zksU>w%4Ab+-zL#E!5L%DC)3DHmsulYd>ToJh(|pUp2nPzUx9p~lj!)#uQZeI!9V?z9BnO`9AJ3ysoWjE7$_ZsCCo@s+uAAQ4lxH z)h3wC^m;L$gLAw_9-e$e4bYzyc&n1G0dxjMBfhxRfy_nA`FlU=V83nq>_B!c2*xBP zv4>W`%?AW(-{o+wgX*1wHs-?&nQQ);!u>yTx)xsWE^kKQy*MB(T zb)xO3_c(G*Tai7<#rx8U4JiKW%O|HV)u00aIbjLeegzW;jm4ooB#htAChKLisYC3Q6axWg} z=xu49(j>rCR{V$d@9{u0K_H!^UJY9lr{A1ss|Loqlz#=WzWD5@@jZp+DsT(BdCl+} z_IHNbe5^rLu&}N^)Bmpm9K4oq64Yg4eu?E@e(!joP1cui76#cPIvGMOL-HmJMa5&7U zRheFhV*h-QFSKkyai`^ey$Hj5dh_cc1vp=EYs<&ahk6vfm!gVggVqcOo(^-ki=ni$?tz%$o?wZt`1cj`nCF7z{aEw zoz;1yb>FERsfz80^oeAlFTW?vAA9&CvGEh_*24i1*!pvlzC9goGL`bWZx?`Pjx+HC z34q}jU+z#PSHT$y0@WhgTDaj}b6xdVJ+MFdH97RE0W9Wra!+FYM6#ceqOuw5S}Fr) z+gcle+4>npq#Ax-&;rlYNDdhCf2@4!lnru>P4C8Oa$$x4;pvyFc_5wYs`=Ea0KN{p zjvTlbLE^#AhouXpuyR!Wx+fdJOun^jQA#y@*nMNbO5Xwd@()kcnT|kZ&T+$M3iB|$ zE_!42?gqqeOujG;-GmeAMR~O=+s{6I_upPDBZ?0&HX+#40R^(F;YtU!`?R#h|M=n>tFiNE4p<}Fz z=5Ga)kr4R>Z??YgsN&tTFYT|ap<`F?!%yLGn2AsBH?dE~K6(!hpGTNS{qG>)YjZy6 zo|HLYSH$-qdBwEo#!|5C-*O$s{e%?7J>qqzD`5}Of?2xraa7q+Z2K=shL^m(W~f$l+XA)BujZx)tQ2{JS7FK zZzbYhyWXS1d$DLhNa{bD{V2pC2_J&mqR}gbMd^q9xoAV<_ubwLg;;k{P&V&!!MW2z z&rR)4xMrJ?_S1D9rsMgviqC9-ZaQAO<;_B*hTQxqKQFkbKyscA=OylD<+ab&&7&dD zQ17!(7tpSa%x(6NSwvmGqrF`|iS%PR{`-?KjE+-e-;DIby-PFyqO^(eIn->~F1%BP z#MWN(pM0E$0$2C`>as^5vy4lRPCoMl&(pro?=>bu;ec}~-*^tNfB%pC%ZXy3$Zj`^ zJr9uoL$Z(%zlZ6Z9k$*)u7)-ugCt*P`)`QnM_(;?hApVZ$R>f@wXE6dm$+9#`c;99L@qFQC`Qf!}!PcksaNOu~>{?ehjC#4cOe_z>@J8J=mp_xh zDRq(O{lPrEQ8+Smv}7H=@>KTcWBo;fT4Jboas_13nv5hFe*TXQELbsDA!B_t_p{oQ zNcMAEpxQj<+6ehLy)<7$fwN2`vY2<%b7wY=v~w11rBeDz;e3YG%tU+0vk7G4N0jti zei-fhtxhou_n|Le2)T&jI#D1WTb2@SGYX{glKZ?-jS}>Gn=5Tfkov@RPJi4#mMJhV z_vl$Dnt0M|_+Z5nc;XfQ%RUDcQO9pW6&YA}@0l`8;~a5~XnnZ>ZW z*!GP}x(r4Xgj{dbmBS?sYf6J~0K3@kgI{XcPon*r`&1jwi54H;QlhDZ$XUIr`?Qtt zwDxQH?_8|Q=)Ppvp~L(xE2av@rc!9TOx)FGnhlp#n+&f@)k5WjEpNzSEu1%cBi)3* z@5lPrDKB6hp47uTXEL%C`dO$m4pArgyD)RcobLthU6wO(MkDYoZ0`6%%QRTEU9h-m zvjpEn+;-|c@V(dX9lb%XWzD*cw5Kv9FWZUk{=_s^-UMtuZe( zUL>=XsS}Zhv{^P6;oj!sH{P(CR-y*1s`;DZoQ$#7KklnPkiAdIqi1QsASdGS6mejk zB#YSE9`|5!-#zK|IkyUobbDtceCr@Yr|`$Cyhez=fqv*ow*c!WcGY@`Hdqo7Om29K zdzr_)=cX##@$Y*DQPGv%j*jh z=rVhvN~zZnYQNlT@>;(aQ6^~>CpLAUFAK>IcBYM};PSX?m24IIlHAbU!d-}V6TD3| zSW}Rh^qt$4G=9j3P1)A=izjHtH?bzZh=qnO89ef91YEborI==`065aYGgSEd2MwD6kq5;#tKMSZd%~&oz>vw>2QK z|5NLqdkvhcjM!5otbq>O^N%t=R)K7UXBLqg&UHK1J^rMf4GjioIsdzo4OQR4LufJ! z`ioD;ED+(|fvpq^YRp6ZCL&!njrI7O!?TZxd5S>xX376H~w|}5o^zt@6xNHKJF|$aU2kz|aR}S;Cfrk@~TVr>oRpKeh&c z2Tgk|pb--;Cz>QKRvrYSf=ea^Xur0g`e5&8bx$ zi?pcsXb=4@;o>IMmHVUdKxzKD_5V6+%@VX-*D3{zcSe`=vMRx?d-KL-O%23U+!Y@+ zuZN1IWu=x%%==3i>dh@}1_I5wkA*s|z{LBWix1kM$iYG;58sDWIBBA*+r_+H#3b-f?Y*@sU!f^|1b;H+2OeYb6#YosvS4vxqKheqpr zWn@_}PneWgpPB{NUQ_BNV=mXsmxiMAPx9bV@$0FLipVBzlXbG&mEYxM}xh^9xjyzhZv>F?xVzI^li~3c<0o~Ux zz4sJ)CwlMF|LmBq{?7v*QW2A~=V~R`K^7)~5{f!>S`s(YS&e-39*gZe;vo%mmeQiR2{F6p!Y*LHPHkkC@ucQxZ)t@ zkmyEJ2Y2_O722;Ed*8Z|Q)o=prI#J3?aS}8&lj7}lXtf{r+?HUCsU@r%bl3VD?yU_ z_#WnCeygl?v*VG5%(7S#O#q@tEu8l|Un0Y{=abw~?!f=@cIM}sLGV8B z0S#AF6ns@#zoK{}9$NZ}tJma`AvcqN(ZV+kuvh9a-`5PBZ_D#r6U@ZEl`moH0yuZQ z9ybM8S8rfQJ|P#A4sPx27S}pb;V)^G&cDrMVD+M^6(>uAMNQ=j?`q639(Dfs;cqxR zr4Tc|ThR>0(>>&(cweL}dRxMJy9IO}JdA3pY=!eWiwOZi?VwI}<+DXe7nDC*VX)gC zgq}mMIs&>W?89D__}hy6HYz$9%gL8P-eb#s{Kf|S*H>BSy0!&dhTLB3GuxoIr|;h~ zya`^drF`Wwc%{pP(2J~e#s%rPVQJupg#f|NHG&U1P(to1|wedyn z|Lz|`R&}cq7MtTp_5Js`lFms~Jg+^o&oPbIce3o2C}uE+k9zQbRYMoi2%?{D_e&(EhhWq%=yr*#fSO`UQ84qj2D`D61J$DFo z9rhvD9cSuj1k1t=zrU$1z&V~RE??CK9)!783V8mk@Hh-JFK7eqeYs#(f+o19+jXn^!S8D5UEKjoc}awbio zlj460SE6mP+fr=m$F~=*G^fLaSkw=y#7nFz!e=@aKoxt462D6KFw1LRwy6UZQ9uE}R$0zv8{2@B@ zE{oN-!Q2xCG?1kJ9R^}G)6$fp;H_K<{iW-Lc-|8GD{`e9LIc+XeZNnEdvrz5xrk-> zJa|{5&QkdI#`s(V(Ig@rU6s7{Y8j;$b+-GtEu(|cO;)9~ zIV9M1^e}gE5=G{OO$y_FlhdA}d&@(;=x<5}K6j(LOIbX0bPdS$GMVV@5BW&w4Mm2_aX<8>u=e{M@c>XAnEDo@69?rQF-(Mx zDPTmFAEr~74!7^R44YYH;CurctD++A6*ztNx&Gx$Aj%ehmijjny6%2u&Zf))O1|$K zJtkS08xb}v96$GW{{dX=W14rg5 zE&Vfzuo$lC+EbVSC#T&kIqxUHtEZ}0U;D%X!AQ{4tZ1B5TqkpBzZwauEbngK2@e5V zI{O35fBrzx6C!g)zzfv#+h2F(IYS8#K|FKXHwY;3tob(>0J5DD9IV8_urO1{w!;<% zInnpsA76-o2`P`KPQ;OLyC*rulGG2lPL(`eI?O@tEhI%&|5YKaHyMirWFOFreZqR) zwH`R-dgVPBE<&FnNg7r021GsY%TdL>Ge<@L5=1U^ffH{}XJ2F;s_El5rN=#ni8ll1 zJ#D5?7EAaHgVQuR2v|zh)1E^08mxLm1QV!j?9RS0_M0e<{H9mr??tV951-e*>p*q= zBY&0R8_-ko(`-6!m8krl@Zy`!e6*Hc`^UB+5jnNtlgmC5dcOT)|}dN z6(GlXw?am@0+Ql9+p2I6kHm*5mXenh@Gi)ZET0R6838jfIJY`OEm#!`Iqwgz zomq+lw)P4>|I>+JMCeZ}FPIFp7e`J_C8t12QrdBf?HH(dX0+oor41{hj47lA*ypJK zS7rxub&l1QwF>Ag!)ujqYM-m{`NQ?BU~zU4JXh{{bB}aGBERLIyEc`ms>O?#z7}() z?4p(|OUBX0->CY=y$PhBOQ#})eQzJ~b_ga&$57@}nC%rbgxs9hP5YlL!_v{VPOe5^GQ8Fh_@ge}q5hN+i ztvO=OY~Qm|6y%2mHn)wmGSGe%1f#|uG1@Niipwh*Qbr|cJ)3xT)TbL|3m0feU9I6RAch>Oyf zW4$zUp^GW_hV$2K*jf26`Z~%4sbk%#zZ?=l)@=N9oI(vWjkKTS#eYhbj<=prtO19p zX7RjxHQ0wscTY#Q2CS$l{2q(fU>-n-yUv|z=x;o*)x-BMN)s)@BFiRtNcrA`UVIS# z8)UVf9-V`;1MitkgEzor+`%u)a0_VveHL=uUWavl0{`Dca}e{Vn$VlB7aUh!2whEZ zhVTx3mo>aU$bGicSJ~+*{{W;(OCbHG%Tae@!!pqmxGFeA*0}IEWIx zj(ItCkB|QMEf~+EXMzqiXvfhTYIEL+Agmo3=tDf6FV6{SQYlxBQQy^A5-QZR4;cA!UT9NP~=weif43Rz)d9lE@4Rl}#lH8Chj# zuWXOUp4Vf~?7eq(C?)f~-@hC>j`~BM@Atm1>+?C!D!B1$hK8l20_^n$wq;^4Z~J`k zx0?q`;7})BAk}0M>{KuvnrOs%$S3Y)+qyZ>?s(Oo%{?2|t6K*O%n4BTOzZb?yBuJ< zGTHd4D-U|um4#&+b0O9I-&B?n=JZ_&5#}SuIjqz4qRwKAz;y4G(8$0~2)tD$ne%NP zj!E@D^o^Oq&Cic73}nVY%r`^(FWCUB2xN0lY2)V-=jx*0d?iRd*+<^r911SM2J8O{ z2xz3s^ud@Fpl9Z-%8zubk!Y@Wqm6DIS{}Ql##vvFJX$@QY}4uyN7%Qb^NV%pNUpF> zK}9XP({=gpwU;&M&*N|MK7Cb4N$tiE9eE`RIdYd}0sHBcYBYmW+se?g8q250lqHDX zQzn4Cya4TAtxS1Um5X|M%U|v1B_en84Q4Bph5x-8kC60K6r|@FM`HhmGDMmxQYsyhaIQ7Tfz{}&;R)RUIe4fiNM*A z0o+dpBc_OTKSVn9qk)pa6={$;p0|^egD3xU>lNT( zOX`wy_yOAG*cFgi0cM^&XK8(r1j(FG}**B%GFgNYrZs&F6ife(!Df_ z=J{fbKbsFAKCa#`#M9mA`OcgE0Mv%wKA)Virl?0#6t5R7M@dNP4gGLkMILfepRO;_ z!JMD_RL^Guy^+22`Z42DPmsA{rGjK)VdPh|vw}=2WHO2p=@tlZ+D?Az<#G<}6MJz- z^j1EU*RhZXQ56C+-aF+xr}^Ry!6TVDt#W%OCK&QSR+EuMZ;g^xIgW|g=n87rh`=Y zBL&+G%%9;|`XXeT0fAx10<5?)fm_y*fyOZt?mF7rO?l$4`-^ufS~FnTdtdo#O(LxC z$ajW3PeNqx)FxfjYEV(~Guv;ybtopF{=cyNw`kukiKI(42zE8RUEs9`8m6Q{1?-e)S{sdL1Fg z{z2rC<9y=uJ8|Y>hN634W!S^ApOP2r7b@om^?=e^g=Jv-w zSE5%zqgE@<>F5%)v5yL9Dvm>GS6dTBR3)S@8@6-(s6(u;ccA<9Bc_(fM~V3#I%J+G*(5&SUFCW>J5+*$#D~ zLBDCC9l17?ba}CAFQ@@IoK{tMe;DVQb3(tIQ!Yj=YAo#+J+lzi&p*~n3}J{QInf`@ z{2opo+D`b;8VBmxK}8R!vtY#a!rKR!Oa6@`K%*eO5C$moM(yzPf9BGi2MNCA5K7O* zLM}~$Ir8z8%xV&tM@+Ha;HvNRVJVUVQs`ISg#4 z?W*XM0JRu5L(X#oXe!MdJUpBN#vL+=1!JjjqJTP8_j5X!HFkYC%#jK4pPx#+bj<>f zVRy0>P6FKP+bw;Ok_pLIsZwdWvVcv(GVnhr`LD^ z8hL3&P0p-BDJ*pgch19YLeF1a+FlrQjn7H*%tt3fHw$ig_M+3qGRb?Cm@9vnQKTnj z9I3VGe>l7`jz(A%7gf)Xqf?e2Imw4dkkpT(kA>U@Fz0yIYw%DHx=;0+#h@F{of)vs z;CM4yNTIu-{;&pJ^?s6Bp;3;?E)p(D3*;cO#B~4b4ROf1bhkaX;}zl&72WHy4S{m& z&ouST-#~25TlQ2j0Zt@9wXAh6c!y}5XVAdB@~tZ?Sqa!X=eD2EMjLyf{@9KFd{hdZ z+hxxx%1c4@2~X*nvQp?Zx=)=-RSNcF(j5|m#b8ajvh?6q5rhmM3mKL!fFf%8oa5!W z&{8bb zDu$lnn4L$MXBnfkdy5!S44*Tl91ROfao>gio@j18G#*{^i(c)8^ka1dU8-qd_B=s~ zE?WkJCpwmSn7?Oq=liell?50qjrWKX8G*K_H%I)5nQ+gpY%Vpr88x1oc`9VG`0VH(?;Dm;wTEe{BC+2=~u>`X~lgP(tE)kefJS0Yk_{XVjd;&K(Bk>NDm60 zDO70Z>_nep)djy@ZAE=AZ)I<#*P|cQ)bz%wmB`5a@XI3s#VFZ)@e<820mb~3ao4Gf zMkF)CN1}-;h-0#TSJp2K)HdE;Q#q3iU1C=qOoA~VMtA9msXXq%Sr{)$QWSvf{F~g> z`9iR(;)%>DEe5U+h9P!pr667*I+sldJ^lt^=9h{=SE`72 zb-MtJ$YPY2F6ZIBNu;~L4E7lDu%xahl*3=%-LzBoBxo7umDk37%3_xz#g_aPpkZor z`d19*PShNnEH|ixw1#swp%m3%Xi+#7TTllf%QsF&47P$xs_ESFuRdsBWA53!J`F!? zTb0GW|Adz7$__NA)q;cDHO5q)sNnu33O}sIr+2S zqo`Vs{UX730CDm@`_k^$jRH=V+^b~7^P`o6Pszs`kdv&~b8r1h^y?=Xm5e3!eeqE; zmlb?NF;{3?ZCf4Cr`kK6mF|(?%wEjOp`Hm()L*M|5b{97mEZ3VT?vG*eULT4xPY!M z(-+OP74RdVSW_{`70yg7AvTR@m>9d*uHA8OlNv*5L^vn>0$@>Z&krT z8*8$av`nRoGDv`6U4WCcN~GYIBw%}}zOUm|Eo6)@=~M*t!vyn9rpU}6 z(DN>Qx$MviBwA&sv{kIasQ;bNl)|4-sMWJ^(VdN@H{HM!LHS0K95E-ja~O|{Xn-L+`ISEbqeuU#|X0@8b=TJ z^ZvJp`NK3Sj0{&oyHWVxOApw^+fbP2ZGN+Tb!d+#C04-4_LWaN{O^VV{eg*hEp5d)|E@Y z72O7l2DBa%pW47Qe>mw{MGYJ*y|}-tl?Z2BBj#%+;-JOaK~(X3BJAFZx|(5<48_UP zgVLA_YT(AFirBKC=Rc7=#pl`J8k9Xk?8oP#VTMcFm%@SMPScT5{Ry&^c-GRUNU+Vh zH&eJc1dBrN4FqKu!OwyhQA^ZcDU{yz&zJ7N1bP|BRU;oUf>M!n-y-fo=CZs_eSEJA z<%*K~3-q)iafY^c7W|m|Pfqw!nqPsoE2JxO^$OADFXBm$vNO=^m!r0#!Qn_MLhbzh zAziq9B_L;OJ`6$$cQX>cB>|zty70Mv7PPXpvDU5Tz%BOzho9O7!16(G+_tm`*t5^j zLRAU$iZ&_wi{So?{LM0)T!z4I_f!6l%E2~E=Ja!+a)=7=V?7^{)3KWnS*nr7py;HgzXgOD zv44ch0nATxVl02P2=yIbPy9fuaA-f{zmc&85WM`g5SdUNlpKx5?_Dxm?>hmV zI3KsYy%>P`^RkN3ys7FvPHrW^5C7RfCCyqmU2=`ciaGS}xqD~#1=hle zMy|^2pS2+F=Bf3sw+`H|>$&z6V@`CJ$#I^a%`kbaZhQjg{r$dtyY%HwABYVN7rv&M zf{ldUg2bCkz;oL|xZMnM2M$HwHlwGDX1pi9c!1q7a@e_z!sn=YzHOo4r;VyqEO(b3e`60g<)P7N$qCf|M(r znH!q}jEJT!=N|9`y^@WoLDFZSxK$-J_97I|E6A_^vy6uSdM}$x@yCMy_b_v_AzLsr zi(3827zYpErxqog?u7aeeO8XNbCA#cGp~w>c{JCBE>p430!38zUoPDmFp0fwd6~8g z2{Oi|T5RI{zU+TQ2%JK$ObW&Zyi=%kx-RWD_9lNS?2Zt1!MT2Y#^WYMedyVsmC&MP zCyHPm^q@}rjuKLW;$jIkXtQ?Ia%`>)z4u-ZJQzhpF7oOGErvKG{HD9nk?tkpWM(PQ>Av8(03Ue})!1xEfCQi9Bn5jZt z`s?LTJSU>wb{^+zw>A2;{7EpARIbQCB*Bn&`pkhW5~R{PB~CezpxlU?C-^W4a-BoM zC$YcF$KP|NW2p?vx!pd{JS>Gci!Y3p)kUzJCt5shp9=K*rI-y3Yv4&@Z;qXCHQ45* z2KjYVfX>(d+=HDffb!i<>gsD1pyKiR`J+h^s0c<;OgZEGScpt6c{TyKgAK&p@Lat$ zc&Flqi1%;b+gpgS;&@A1KggT-TD z`0`T9nN8p?1^GRc3}hq~!R^DblqEQJhOZ zzUi&|CL%7+SQ<4PI>{SCKCD`8Y=cDrw|pM znyorDn1vp`ah~k8jX`f@I}MKxzD0z8MYlEzeBe~^uYa4yF<>cu*@p|~6vT?=L?)Qh zp~{X!P}=0A1UWiB18?pUAGAtuAnZI{F#Ja0(Xj&Jto zB|zSH*D9G=0_eBC^ceb>4So#0q0Op9u;x{#%=#|}js#U7y~djZ+rDAS`5O6<`;yj7 z;$96<_gL+SywNU%yf`3WdW9hrF)0&@+hzS>H&5YA!Aa7Jy{VXi~?zLPt`_#7e9qOuWG z3B$*9B+g~wp3=3gtVQcu@K5RQ=N_qp4b?^EfI|&%#?NzFn6eSnKT~j-W;X)47Nz*; zS0YU8s5IEtl5V-=s#ML zC_WJ3E$@usY5czUK~-GFE}DZmfOX>b>^b1bII~~3oCx~o?~GQKB;X*VzB{ z?%A#1KCjU2?4#bt&v&6u!X)x(u~9^sPcCowY62bdtT6uTJBi3?vlits4>7^oJgL-b z91Y3v)}Qvo=b$=Hr=ug-(^-7U)DZ9Ea%@I=1Gd}H{AZosPBzSa&h}r6nW{vG4)O|& z)E1&(zVR_G*Hjd<|KSVM0Z*j7F2!}JAqdZ1Em!I3QsG__+1Eup*9}kDi1oqGZ}&$B z8#8-LVbkEnUIqUD@MbpF5DBP&*TQ8RAMo7y;9@}dG5RX-)pS0^C0_;X`@Sh$xm^W1 z4(3Zc)K&1N*0AQ2LnR!&%v{8ijQd@`iSFy6BoMLJ`g=SSdj{*~ekuzSATVm;i0T&h z#>$MukRK|8dZ%-`5fbI#`%ZOq6!!=Ga-?V2_$z^<$NF~?sRTB)t$)6ijRDS}Ji#YN ztN@9@z$WmYKQ|X*nTHqH9`CP0 z66p%vOn?wv*vJ;;1TiEbPJKlWu)g=bQXWkCj*-6Oh)C#YtN;Vwm598^u?uDFB4J+>N=74hcNl9Dg3IqiB5T8iT z!+2(lD1Ci9Tqu9JG?DQg)hsuMhT-0HY>eV3catfUc9N*0x;%xB$P_w~eVjyFGW`?} zN5_!$eC?URkU_+(^xMU_tQ(C~el^?hYD2C!9-Nz|sYh{J_fd-s3H>^jvYGaOZ^a`r zZWn1hk3W)>S;=h;6Q%DTomGm1!pY{iN8hrr&{A^YgIgZV_V;bZs1}3s<&=tDwQ@Mb z$KharbNurTlWTuDDuG|YpSAfy6+98__whJT4blYVTJh9sC^8VbUBpoXzu4XwiyPFy z7sr`lcc&WQ$Os`j=~x34tE!QFcn_n+tuiAzTMhcF)gAmc)nMM2m42kU3e?W%sm3s+ z!ppr8p+ETfGr{*HYU?BsUj4~l*R-Dy+3M?O84)nC!*Iea7=6L&pcg zsd)aDINYp(&pY{wt5<(L!u_O*50_m8I-$>&wVAqj67GnJ~X zn>e`uenm!)bh-wB5Idh@-0>OZ-=3a-w%mb4zWpu#f^*JHy@y=}s&KDe9-S%B7{|TD zHPPqxV`y87BKc|VF!ov${Gr^B^H@qnA4Bf;AQlC>f`Fn9G@)j_q_fe2&M%CyBf18} zdYeb6y%g_ToX(%EWiLlOMfKEP&3ULiDDd`ZQaUoB=$ntCh(`YB?e0t+b3#-OT;$^> zo?!Nm&S%Ui5_J0r$8TIr0>;1c2kZaf{d=kxL(7e9$jMjr8h(=l{ciheUnu3lD^(G^ zB8wObU@Hdg0uiQ%+W36Cyp=!^jORqZos&4iI-sP^aJXM}0t}X>5*=)oploY4t>1PP z1f6TOjTx7K{&k<_J<1Vq-cNN;z0V!m@(1r+cJD%GM#X%C*2j=r%fv^%peYo5?$%93 z^=X`Y>FWsDn?$^+uU<1)xLGK3W(RwLJqJJ-{Ze85NIn=fCG|DIjB#t~1bYN$hIt#xSYz|NpNR_~zb7#*x66bi0HC?H1Rl>hE(lmUC8P3ipi~>dR`SVA~yWqBn{fhT1ynh@O zu2-UTKz%L!Jv##x$U@xt;-pm@GCViecBZZeU5E?yxv+l-Y1up%dCP)*wA$~L4|QJQRnT%>Pn{NT;<%p$CG=vL{fPZ>U+tRH? z_5i-5eb;Z}6QiEE z-%_mjB!KTO?mw#1D4l#hf?j`j(xW>wh%$#9AF}xNBDuTgtwn!!qF)cv59oPg@9g*Y z%GW9I&#jyEm@T6QrFx4Be3&4iBK?;Uda6aJ?0}{sdY6s#9fX(KV-gTOfil)c%pch^ zZWEAX;Q&HBNVu;V$l9g?TYiFwi8am-6+WaA#^=MP%!m>G-W(`b z^w~N}mIqh=h-aj;K0|OCe zCvFyV;=PNP8r9PyEh+Fw=-j{mHgn)j2a^vk&UId~cPek6#b5OrrwMpY{r&ItAE}r> z`DRPESP}baTOX9)(5}NdP_}ETcf50eN-vmAKr<06@2^cIuoQw4w{+DA`2cj+PlS1I zFW`Ad*Bw{ARgf5Kvu&eY#9Y8}i~Hikpkc@UfwejXjP@UtTM}+Tru^AVimsUN*>mAe z2*oH;t2muyadI4;71fIOY8*!(|E^{O_q*O)e38w$H-flxO5R_K#y+Y7+asS(^`Jeb zmHVw!z^B&BJRcnJebu2?B@Fx1C<8oqUajLfe!=I+ZDs5cykUQp zdaN8IH#I_MB5{v5I&IlmBok=8T~5f2d_Yw0kvzg zz8mEqz|4QrilW~WD6Y{ZIX?7-(ElErrpSaN%3{NG)yPs*O>#OU?VN+chZb48(wjgs z;(pra7@U7AUb`sZxdJ99-mSQ5&Vr!l-n+sVwLsiB-6pxziEMly*j=k0N0a<#C{_A# z?uzBNlG^b}%;~?cq(VK81a~X6rqhQIQE{0fkER#V+kL8O{Eqis+KbmuIW!{qk>wm? zVkP?HMT`lS#Pd#uc=PzIR1`==-rJS|XhYsmXrHhr{CA7FX<{`FpZk0lR#h_~fXbGK zyP61Z>bZD)S@Yp4Kg%LneIfAO=coA8R19|($hmDqOJQU;#qAtl8SGt^6_U#-1DUlY zw&aE~=;+hQ)qYh5jE5@RR`C8yWS!#NrIr$SEHV3x_fs+0j4BhG`U}B$Pw4!Ip?q*$ zO+Lb!i0^qvnK>x06Cts}Tasxz32N>MdTp-b{t#z(HV-ZKiF9PjJ@Ksrs>oHvjfOh# z{$L*8-c$!=wcnUMpVq;%b-N2stmAo81*9(KS%dWc%W6=*%7o@1~&bYwul~Z<{ zBA8?TZp5UWID~lR>CRMTkE31+I&N3SNu+kwCWMk4dr{X8>bo*epfA)x7$G@^KI$CR zMl3j=wS8e=>&pO&d3x7+ma`Xq{(kFeWNs&l)D_}5`>+l9QjA7?_HRVTA1YLn1Zoh0 z`IpW=T@qS(_~O%KRROv@Gac7dpMgBm|HK4djzCho#ij2B@1smNudbcrm=|rp<=TBY z5p!(UzsWt#1ZRJLIEXzs9^XG+QW(txKCL%<{cf0>ZuarJE%r~*QE<|Wu$O?5x#Jhs zf5l){f^fRE7$SdmO9`kI!YoSY?VQho{z#gGl(x9<`s1@LS$ZCXy%aF@@Xv>VGEp04 z`$8yiJQ=X=R}6-%8mjKs@!Z?lRptrK+pW5Opm?iZ3Ds>6B^f@|gFJHyyS+#^a5D)h z9A=&bckSaco1RM$>%x*(a%&aD&MNdAOI(Dyb7D6KPbf6Y4 zb-UXd!^o_5M`LJc3~_iWjR-J~qxyOm!$iCf6T0%c{u;|LTF^=|eU;XalzN*fE%flO49Qj$s6%o$ac)4l$q;5GSB>I!M;LBf1L~OfB=tKKAhyKy4}5|I zq%P3&FwHw2(GT4mc>diV2{#zsbk#M5dBf|=YwJNkok2bNKmc>jU1b{VmQ$d-B&_XB zeHKXk*LClo3=t%XnsW1x8Y}`kW%W9_yhV({oGbGA}Up{JcRj0 zHNhIp6WuUesB`}2b=?1&^0a28T!oIC4YbOz2tU%AVtn3CfMVca*_X2&@Wxc~gBwIR*%s{Pel-w`FvnR%(vMkGAP?NmmnL%Hws>4Y?^(Ib;W<%|0&(7B+W zr`6AtVqa?T^-afo)OYIaZL4_#I{D18=d*h<>b@-XCL%i;^(-~nDaiYwP&f8WkyvBA zcP`5xyWs?e%Of{F76ia?oBT;8rf_iGeyZU=84b3day2h^#KNXsf#``#@epiKt?pwK z51M85|2 zZkOo*{Bb=Y=X_%VVs|I)GN=}z%kSH;n(!)^>WdcbJz4pZFU#!wWal~0-V57auY#*_4Q4p|rMTDY6eqI6#;OOpFEI@jZ9;BsLCiGuQY0Z^F~*4{=C&qtD%@ z;4RqmkX>D){|3j8v}@b!%n}1qg-RnD~(cIT}j&6aok+03QO|XCTDrchf?^YNN zWp6ltq796XD1Y)#XvW^70J`V=#c<^4b)RX;95^Z#^T6gb5uS8~blIe3!PSRPqux~z zK-xTbnh~EncY-ff9aJDfq>OuaUKbIXm6~=2J#xT`^WxoP>;aPdICDmTFAKB@v(_@R z0Ic3tWrkld2mO!gh?e>|oStKhCQvUy@h$saFQZj>m;b1#PcQsn}DT$rAP>Kk` zA$OEGvQXddF^gZj{;2Jat=_wD!C;X_3^Tfv0hE*+j+)={LDwy)Aho>=;Lq_gN?M%n zlzqtis;3%EmahtTUao_q*Hy2t-e>@B<7eUSxKBrCW)ae=(+qYy6(Vz*-(lI=uiy(+ z3$VY7a?O0#0@vyVB64u=NL=+!WqD=`P^1uY|Fkzl8My_Mcoh+hnBU8m&9ne_rTG(~ z#WpxC&A!?!*#X?^0g<-Q3AgtZ=AFfSNMBNw3uD*-ocsIQq{(Lt#yu5;vQ4Hi@Bg#T zD>AG=P@^kOvmV4m+c$GNTE)7GqVBBPgS*Ndv&ASimzKHcrH=GVdd0UIff1t zD3SP;CJ?i4znr?nBnk+dB1TzEqJF!!nhIu)a;p92Vwrev8&`ya-GqJu^#aqa}4}=SYF5ILjb9NpG(iR6o4)N!AVN|`)@04 zR2ODm0XsYKp$i#Rz|p%%@;0i0qq1N1E~eIEU&6nk6CQO?cStjL@Mt~!xbNgnhPfy2 z3_FeQ*4IIt^o6U}aeq6tkY!1+6Z5QsllOMbYM_Tao%I4+6)4T#qLaOez1Gz~0?tk4 z!u^VKHTU`QLBq$cvEgkwWN^G8!ODN&Gu-Qr4OJ^fdv?dei(u zRx@nh`A_u7LOV!`av0cg^@Gr{Z2o5KUw*ytGkodDA~-GIah9}O0b7B`(4Lpx<=1(Zx|T7->c=`|t;fqYmA^Dz}^F|DEnG}{U%u}dd*+l^r5l_ zIhqYTp*e#+JeJp0{Pa=~nM9?_HjNsxWC|AKlt_TVH(w`38t{H;jPh{_J@(x2coi0&E~3=>9+>xzO$?+j(rlQbZ#dFFsG*Ur_J9n+d8;fby>)As~QCFZC8Gn&4)u4 z&YU*qDuLxo^Tj)Am2hE|vFW&*z45ef!i4Z;O8BG%vj z1f|7E0{MYypr*R9dUv=T2u_E7CkCXUdtP^3lS4a@I@?p>{K8>0l0PLTd0-MndQ&v} zCSo3|^AoMS_8C-nbvo$n#0;t?KYMeH1#_XNN^?eDPN8|Wi~S6X7 z%iPWTK8{7uMLp6sgy(BDEhQ^Gn8QX0EZ6ZNG=hzSpeDXENc77AG&TIF!p%O?G)0Yw6E(5W7=hs#Qyhixg z@Q7edg5-V16cu$Okhl@@{K5j}U%8*<(dj3_8T0VQ&S(;Nh$)8k+{3=GllIo9mM{l5 z=qU@6ZYt<=ojc?2h&_Tgx4kaPX2Y@}_hDxBZ1{S9lY22M3%n=d0-Y`JMNg!B1Bv&4g14({(I(%sa%ZJZWK6;BwN=-Pmc0m< z59IZuz8C6fYOf#d=#Nh5xc4KjgVGm*U2tDXQ}LD3W)G57?AWiuiup5GzvfHRiR7a% z3VlszLv7AfeL3%&Q2zxFC8MAkbUWFOT~LXHawo!i+1v8bL7lZ9KR%@)i;>}7s@z}{ zh}A*B%R90~`m#Dl#EUS?bbrpIl&}n&sq6f+M5~e0Hq+4~kSnOn57b=EnOMu3%enjw;YbKi)51 z$Nsh)*YGyh3?MV~bhFfRL1c2y`)*Z``*VF-^&tDMKiqJ%LEiIESL#i@kcNmXJ&Ioide>MRY*O zK0&u&4w=clI@h)~jeLcSFGgV>_VUhK1>IEqIrwEbz{T8yW^Fu~EO8I-Vm3K@TnNsw z@9ZNJA1p@~PEOM{^bt_#f(o&o<_qF1h#>2r42F8b?eMRdyJ0BkGZ)mA2Xc3x_7?b* zf(~n}9TVnn&ZIdXTXbuQnokDebcJmKZv>0)?7H005@N1eT-qrg-CT<^2g^Yz$A#x=-Z9&(Eec}JApI|R%}0RE7&do z|B;I&#-=N<>9sQ^rZWTLmK*ywKVlD@%L&1Q&oGBd=_6I6(jXfCb^OoIY&^g5JTn|K z)`RH7=Bih?I+0w}Z6mi6ZRnY+aIMq5CS)?}N^@SR4&{vBE{^W4LJnEIp8_2*pHjSw z-^{-l9g>+i7}J-FCUPCChFP=Fym@@bSZpHVDG2hkuMI;Rik-~?i>}D|YILf`O>@X) zD#_B)^@jw7m_J1uVPHog_P2*T77~=S!mIQX;MmHY!-ZU1)|m?MHE(;`Ck2itLRdU)GF<5(-!EH}1j34fJwTNR z5%0|W${6B+tn_9`d+k@SunT*jfVpHXpZ}PYoFu`CkJ;N6(S^XpamkJ{Bo9b5N*{Li zoVm0!dj+BTAz+%)8b#{}%_8UnK=lV$U>?O^g$bA$0zDUfL= zP}3I%peTy9n9Ik?5a(bg$E!behouDqHuhk6OEHE^%@t-ZWwyPh^8vl{6c^+U2Y{wqpM9Z30KD6Z z60BMe#QDzBf?r0T;f+T4R{e+%%n!(F(PQ4#!vapiHKSa}!&3EMNqN9}>4~9VXg<90 z2|qCQxBzOHHPr8liM;1NYH$1Cezmo#!L2{|2U?g zQcjNeE_)es%AV4kj9rD4CpS4i@+`u{Y=nf7$^djVQ12fMAt2wA;g*%M18C{GLA*`M zBvR+O5|XAqgGR-k5xaS3(9P@AlI=!QXi?|6lI-3%&TUE#E6tA}Wp5{6+PQw@WuttU z4ChZM)U0SOFtj7yue(J(9*yX-eK;>W?%UaDej2ZHDnWw>CdMpq?qAoZu*}yb8uzEf zKV9vV1b?53f105YAW~zeC`6eGOXc$C<1iQaVp4}hk8C~+_psGm$NAf@_a+!mx?$dA ztV%as8}>g%jhEfNKmv-}dYoPFN#Hu4JKgpK^Ccf!F(6(NI5tP0_?-yQL}(?3-YJKO zgr?$a_ev5X{)OqErO~S&CKZ9bG`R6WR14 zY6foiwo6*Fu0kVi#|g87H7LG(WdFVct2hUovn_RE5k$`OI&`*A!-SJ$zC_w6oc-%0 z_+LD}2mk&#ZjEYy^OMiLdwV!9SY^kv%wLK^|4oaT`g}*){-+*g;CnH>(G8}1*9VdH zvjyT6oc{+xv>A8wIMU+1NbE-wsPUpql2-jVN_Ra?-xoWEzP2CT>cV?8l|%zZbN)fp z8u0x7h0?jL{>lZpCfC76A)II6dwo?%G8wp9^;~M*e(b{>MW54hx)S7Wr?cVLt}}E zFZOsOo&9&9&-*yB`Sl0pJJ#Q%zq$g^F%y|3XJ_Ev8c2tE#DQduw!q=zqexGUi~T_3 z3^F^*Lcj1HbL9osSl>!bqiBYE?-e@6QFCYP@NbDB+{dgkN>S@Z1MG=s9MW2lkgNDp z+;2b|sbL3ez3_fry<0SRH4%~NN}rK?_qW{L^1x4? z?Z%DvB3S%q&_m7cT?EKu8sn8D3s(rHdA++i z-V8sRLlvg%CqasEv*ozp3h=p7TeaD(!I6K$3KRHy#Tjc;oyWeR3m#X=w@{rMAbLPTVzvtJ9CHzSV)+G#a*>`mZybf(=JL~|bxn9A=PL*>sZ zIrR|sJhFQjZ{z*s^7$0@l?1%6IoK@LSw4n#S$fiPc}7t2+(Vrcv^cNw;pc&UjonB? zTC4kKRy&$%zmTU8+Jt6@&1@Sjs}UL*x4J@KijLe2US)etK$;P6crRWHMJv~&lzy*! zz?pca@ylnE;7@LGoxM{w1X=}N@<_}F+9zK7^q?5nElaF3{*=L!!&O&Bb^vDYWx0~$ z=kqhw$+6fYBnT}RvWjfN`$r}+J>m;|er@x#O?J$MMwYYdV+my_RG%h#;b;k}{Q7iK z<4Pg=QrJf0{_)cXJkn6qKC1xNFG+~jmPdr_S1RI6 ztqu^D_=py5qF$&NH$zMQ-ifL0X{c0!{FvOI;F7)V#r$^?V&|haCW~qjUdRy(D`(No zbhj+c&?WSPiZ`&FbspK5^#u+*m_p5Emj$X%4x=-*!@KJzI#E-{;jI4(YY}5|#725U zJ_=>q`-dKfBWJcu*U?8oP@fV{kjY4co$&iN?22=s!*XitT6Y2Dnp8!7{ZZBK6aMLZ?D10kx%uvEE(9-i z-RO8rgt)Vdhg)O`z^NM@#QP{6W}d_-yd>{1NR--YcJQiX%Jzw z;Czs3e;ydJ45noS6@ux|>TAi1rNH)G-lGf8^*r|8hB~g*z?s$)=e#8Ge3jv%UVmf{ zWUP3Lx}F~ghPV*50qoxt2oubCsQMGKjyx0on~M9_9fr?dk}beV!F!YQ#6ehL67TpO z8wmsLqz)^!TGV`XKKu|{I||`dpnHbjr?E3N*SBx>qP`~_=Q2ln&~me&_dnE)KIsI# zkd^I3W4D(2Qf{>)V-Cj6k?j`TyJM)6b812-AJJ3>57Z%BXUg=T>(z)mWB&U15(#x} zDBP!vD?uX4FT(~wkY1*JXN{tv`P%JLYR!abrQ`y!K0oGgq}AVH9C;-X42<|y8tte{GQpQ=W0Wribxb8AtKudfW)KNWv) z7R!fJrpdJ!oaam#xX;CFM+Cw3&)_6Zgm>1i*+GoiAm!Dh7UUWR4~!n1V{yqv|NYha zP|;M0Sku}qzGcRsqURrF$pm}BG0upIY<&Tu2b<}PpRa<$;`0Dz$t5_=-s7+2JOS%} z?YRkCZQ$>)JZ|6`0bVyP|7&8XL?b#Y*oE$1BHbVP+kxI1GI{CmZ$}<`M_WZNh&|F+9nKpZE}0#ug1f~JNpGu&t$M^px`ymO^2=8X|cE0vS2Ny zHUEGZ0ZbTT*!x}*;GFa%;}XtwWwVk;1zb z{?VIMaiU%|q9kWLtUj2H27T5ql^nqS;VW$Ap;U9AC(r6Yjq{(hCx=V2wC5mnbA_)l zw;g_4XtHF*R-hLi3#KCj5$>JP?qQ8yh*TiW0OM7BUl ztCG}>oU+Tr7f-aKT^grGzPpVmGMiu3*SiWGSUshrR9%9GD$1gfCK1)vihYctOhlZL znzP?VebE@J^*!$wZ$X&*phfGwa0nvbca*m@0mMZ%EoRT9Vef>XhM5!rG7o?My(C+^M)>*1(eV5JW`!r)@Yon z0H{m$T|aN04<(Glj~$}&u$NZVKRP@Y!t^?V;x%%Bg6{pYKRtpuV%HSZjd zWA1cxOrz#PE<^>aKY9CKBn+MVbR_0k7=$sTluu?>!%kmaO*~-?JSA5-6vmf9os<02 zGmUlN&eHq+UnSnpjK*vb=S_j$`za4wiayZ!vPL_ySP3*sCoZs1_#$(*{8Yi73bg;F zN@35s1wDNj{-M4F`+rZ!eH;$$LXzxP_G<2SqpQ*Zx8pB%qql@Vp2w`a5LfE&H%`ww zk@T0?RnFaZ^jYcA#HLmovPW%gi;~S~>q+hJug&$S&RR9uSGxvfbA8bZSgSzfVi~5T zyntqZ%&XIulHLHy?%gsuxSc^-tqlA;oQyHg}k(6=0fXh#E&zk6JURt)(1`ECe0$AAE> z$L^Ln-tT&KjaBwWz)+GOqs-<{u&1_Qj=mHHfsE4hHn(DdHqqIY3x^1HrGkifvDa`+ z`QM+T_cI`B)~^4qbq>T8X1j68SAc`Pfw*!_D?H42dXBuM57J1xiF8CJf$6;P2nWY9 zghYM(FHLYAc1%pn_!$;qN8+kD>7i~ID=+(1yI+fh%7-;K<;GE5{`bvh-&y2d{E9X` zdLE6ldz#z~oI};Dt-Mper%@=o7Ha99KrZC=p9Ar^b-}htEjzgnJu*E_EHj6>{|Pca zq1BB@0~@b6459l@uef2{s=Z>zIs1aF<0^hp_*}r0A)|p z&Ai_f0XTK56q1y~UW=7f@Kh!IB4*rYeOv>?zLpi_#&vMmLi!vz=6e#&a0!T)H$u_h zd2;vT&7gGdgu6R+3p~6k8?Ii~0_z1~f|e&+!D5ATzwt&ZY+B08zM5`wL%l{Pzvch-~RJ&IW_qZNevKsW1@1aj_)bNcczpBu@BS zGb+`+u)TWZs>Tp#=#J^3 zXN&M*zW$ouFYF;<-0Pajn1_7HHvxk_?cj1Ef!s{I9tHC)9JUUGc3Hdv1=)9Tga< zEr-Xw-eftp*b8{+UU1Xj3g~l6-SfCu35pD?Qhui^!Pk1Zr)wMURl+=PZg^r(?d8(` zp~7+~`HywT!K@6v+o}qk@Jxo7rmUKxM(i_0TwaS9twTJ?y_u7p!M#gb~7CGlm+7cuSKy2GP=J>iQb?kes31Qug5NK*9s! zQ8Ki6p69v56HHTqvQDcxeBmdcx%kk}QQ2N7_@3T;rgjXholzfbug`^aO^SKCjWXCg zOrVj8t%lCB{lbpqdMF@r>N-M&_wHU#k6*}Z1vhKYS39k3!2KopKE>;HV83X|Bs?BHE&%_{G!k+f#7jrMyV!%92frGqC0r5{dh%3FR&Hb78IWLul0dYD4EHbm2r?!{ZBSb zat`EVPca0Ru7YbIld#M9I&3HmxlBH0>iy2oqhHr2GzTLw9TczKaF=YcCCNJV?bpEWyuFztodeXZ@&yQ2Es$<-AV^T=^q>@$}39R4hoicWsVC&yt*D(c2ji z`!;4lLAwNfv|lt_$MD`)hM$kTe;qbUijGGYtU!gG>P~JR_GAD0WMkb~1qM%_$1z-L zM|VsfO1-^4f%sPI-vvd?qD%W1f$<{mTnQ+=xFd{#DW zZ_8zHKQDqV&BNT?(PdzAVlnLh-jdm!PA|j8YA7ha7+jc81M&Bt_#W1*1p%684tjrU zVO_fPGv~EBsPU67zdTn9l)ZO_b{T8nr`Am#=uWSJnF7>q)L%TRhH{6n1BIux2m+d7)yKET5I(&uYKz`9gc5-t&j za(&qwF3k2KhMcpx_N5c(-LyR8J%t(UKYf(Tdtw&lMTGnv&Bp#0{r2Z-f|KarpCv7i z0_M=f-A$t$8bI`MR&Qs`yODSb4||Ji8%k_u_{?;v4$J#s1^F1}4aCfNlb8Z%+7t62%W$9)@m-{3hf zX*!iKbv+zg3Ejw)ZG;GoGxPm7o56D;|Mu_J7Ermetp0_j4Gg~-haQBqK}Oxg7nA)q zp#KxlDSfLQ7%40?pR2Y*_9ePRex7zP9`Ln0f_tl?tp~j!n7`3sa02M3@?eOA=j+vi zd?1iW?PTT@K$gSdFPO&)ZKGPA|7BrsU*>?_ge2~RuM#55@jPkm{mm_-YgKTCeLDC0 zTr2z$e{E45FaX)R*UL4Wr{U_070VIURXEV#?=vo2hZ3W-9J}^qm?2)(OV%2L(}&$P z+Uye{VfM;?^5>woG@ATO7?;*jaN|^j{ zJGGsm3YtHjIO0rS1veE}a;5Vy2UpD4>eWBoN0qKQ=ocu5>qq9UENf+b52U52K~+kHacmljz2s;DI&yX=D{7R6hS|3Vm<*Qo}?ufoO?! z)*ZD+5XTRfX}!okWNWz7VTHZQ=Pc+_=KgC&rv((3+!(6SxUyh@>v|Dl9Wr-*c`qGx zB`$P2oNj*HT5k8;S zR}YUYnqH$cj34c6a^c>jAlL1|CC0UG(0;0!)L#z`>~zrIofqF#RGtJpKlM6<1_ z7o7}Z(Hv)Xw6WhLvv$Z=H65mSDrjPaGGI?XJjJCT1DKaYwD12-gIR~5BPn5_aQc2o zcesKNtQNbPsGiINw{Y@X{nuJSK0BCm#CHtte*RFEV7vsZdM__;v#*09xn63N%OdDp zx1^=e=m$Gfb_u1!DTw@2{6SK14{B|t*6qbT#~22=tFMD5kZ{friJtBRn&~(?eynf| z(W6i0)U?Bh=vAfJDL?GrtTfTh6YE0rUVs17)xmj(Jle>D-g+cH>?{#nT8ZkuF$QcO zDM4>v@M!7<5>ShtOr!bdIAnLiJ6|%(3(?R8*s#Sp!O36GozG5&gPViMzo3}}h?aVI z&FNtV=G~#tXGGaBynMovgE9{qKU6b4kSc&MYi9|m%SE90;a9%u7UG}(m=vD0h5)_-7 z7ns2w#)zlyF_&14=ZyCj=ALMZ_h0579Yp^g_J80i$9#t&qsaWj9q5?+pW0pPM#P(X z0yCy7(Z~O2r^4SCpwNhs*zeLwsP0QM>G`wvC|`w{qJk$J+9G;t3i6!gXET8EijC-=yOQbgVddYV>zu2;4!`4bCkLX zq6Su$msXm9xz8+q(y&JDcHA3s+4}YBPQ>yge#!+XS-C5*<$dwP2Ng-`=SZ z`vwao=&l7}{x_@X`^2I`+%K{&`u?H>j#@2_J6o1PMfYJxO6-A*5-rHIuc!fAIq{eW zRn0IxceYaMpc69Q{oPx}9xqYLRm=FJlkl?Vyv%hxXH%B4S~|79CZHm!kr^$pQ5%Qiz*+i5tqvs2@2kEV+KiXQcU$?$Gmh*lJkgfSz6yY3r+Ty9ZJS3O{w;Dg0ZCVH)tw{V{ z5tTq76Zc0X1i((BtJkJf2AwsD6Jz-Kc_>T!tllbv?XIY1g}bHTRIw??xs?y&rE_gUM_QaTD|@qm76ItRSV0GcZQ(5V%-*ae$~0s(I5G z#qi#_@yHcQleTJLY}yE#r|kgaT$W}^w-KNnkRH!;#W~xd(11R(RS3@QWuzophiT#p zn`5O5AmSkzT_oKPWmInAClwA%q#oCfhQ6KtK zks921qZftMin(1C=tk6vc?Qb#ov4n24{Yt)(XeE_>7(ve^s4`M?AV89bSXAHUvatt zu_?8W6u-k9j+IOD2{Gl!-5|T?re87I?e_5hY@dtBUI<^W*h)hyjnyswxQ8iX#Y|Ls zIRK5_iqmlz(MD7xq7-$!zM#qVb(D5106rnx0&Ldua}ZZhlyn6!NPZ~q(i^PFqGVT$)j8H#<^F5`X9 zo5#LKd0vOXslC02Ln7(OBRWdpn>PVbaI5agxfejOLF(Ot%cJll+pO6|c^QhUF28a< zwGRI3`P4rn7NCYx+e{(1AD^pIYkp#m7XQ)nU4Izr(b1YXoNwwvr}pC^jUXIlIy!Kx_DMHT82}NS+1f;<36|}sSfH>zmV*UPnM-kykd)wx( z&`VwZ%^q?ecvHZn@@w=55V-8AE9GM_zkV;pYA*?{{gbUxexCu1zh30m6=i|mqTg|r zM+7L3ke#DQA%JZa)8Os9*|6v!W0<@`08!eox{9eRXr``g`ijv;Px8Js2E}7v?3;na z2*FfPjmf`h_9O=O1AORq4gFxQO|W7Hdl@ELScSt`L*dT#!d>-anAdwkTkQ^86ii?H zxok`t4NlI5!Sz={!BLqY?Aw@t-k#h~UmPw$)Mp)k-qeXg$$WzM;&?m2x>!c}!)45$ zXYN~xDqDkB6?vosrt`31`7cdKpdG};$!~63)}UOW@ZWySgJ{IGvd3Y64EHTg(ELro zdw2isSMOireDkp(vSi^Q)Yso(5qG{9ab$}`#((HQb1MA1+2u_rg2Ko+-v;-6i(VQQ zWR{`}U4_?oJhRc##PslQ?3J)8{1NN@E&#Q?G|eKcnZjv)(Pl^8AMjH2&h&3@yw5ec zC6()*iu1wxhugI) z6Q&)v@?k0W{ygbM9vrccP&=-h2ZO_xPD^a%!sXPMLh6+qxUGIj@80cfX#E~};=j=> zs6Oy`aiEt8PY&0|&i@w!5iTn)Z=l%G4H}1m-TGlx!ZevaXxqVC-?&}3oMZA*2 zy;tJwRr86yGWc8gX@-+f4u+nq#(hPVujIx~%wOeI*Le2w07>EI~VWteWx*v(dqk2N~zb zlacTtE%!gK@Z8}E1gwC3Q^9Dw1|+6qn~7Vs75vik!kK# zCpX0&WN9X-Cx5RUC9H*0@T)3H=!!rEC?@m-6Bks1 zta2|B#OI+;oAjTym1;nT)PH1O0sCd2efXt@djWM)LOkm3wQ!~8s^Mpx`&5X1G5VaZ z7S`_4GH%9Ig8~_wRX5H@KVrI-aEgoo!D-}eL@TvGRq|cT{$?%iQ6y|PvsHs=d@4th zST)p4N9iKh8raEeKeMEZd8;u;2FbXqVdLB|>ugOa2+ugVCY`~#>T4yx?gqBwo`-W~ z!{j7b?)o^-9$JHXKla`IiyP2hpH>y3f;|{3HNS~n0%@m)`6yQv(2(D6%3Jylmw7w9E}hFo@-ieOA=hhBRPw*AsD?H~xG7=3kN3k{ zQ%|n9Huj>!0t$*JYx_}5i}Lr7u>q7yTXglmg8@|WY$HyHe*g{TNj&_Gdos8DCME;8 zdXbLks)-;)H!9So)wqlKDU^C2n2&3;p&Noxl!;M|$lsTxR6eo>T}stvy>Y4nnHpTH z36?5Co+7OU;vQM3*JYi{lR6FwJxR36bNGhrdZ~Ke%Shl{*qFZGZ!fU=HSadi5DMi9 zSJq4;qTsmVs2y=9<^&LpD^q*LLz2OhwQG-KU_W4R%Cl}23#(+Li)7!#j z9%}CCDpt^7&)4U}X(L3xK)BZK@fXChom0f zU3}Lzi!#?qtU8BhP^RgYk95p5Vmfd9A792K+HP*9Rbs*Xnv17n)_)D5=Z+^WoAdin z&y3HGT|yT+BIoUSq^AvKd>Y*p= z>)*6f2({=fVByGi)~RPxrJSxp3`o z(y#Ho*S6tvGDR<1v#Gg~5YmTq$@at&9d;((XN}pzPi9}UG3ti8cz9BbHF1CyM z)=26D^}hQX6R_D}R$BY+3asvD^jz}2Kz1lc&Qrt}{wx%oD#3F=g%_tjXzt`d(nsDa zWz{%;mgePi?|cc2U2@1VO)Q7*nrkDLPcbhybe~B$6?3-z{;dqYZiK}3pVC30?eJ7B z{Q@`70BE1RVm-S#0eyOJtlT%|p_ZIUy^#fbzmA_9v&7#A*1sBDfn>{YopfK%^71%b zjx$uX{F@J zp_Deti~k%3(c>d8(l6}e=k7LZbDy&t-7qIlF!yf9JQii42Y8;n?RB_1$h8_(JQ9;4 zb1gw-H8wvi#j?;3As1DI_=vGX3q3f?E`OD8;SNqeorKiU(g{{l(^VO&z|^ef&b>R2l~ak56mPWj@e+^I-hN zvt)P^dGpnml@yo~pzAReO9LWir+J3o>2QOmpQCsUb7@qSA70MG_k(W53XzC(pd$B7 z?)D?Vn$-RagS8qsaoWDW&Z7tCfpv{u3QfZCfxAAE_m<(_><9`M#r$)H1Iq7_OK?H- zN0m6$5ZJLi$ars?iX56Q`&}IzKwiWz{g>FLkZ8hA$2-+oWa8I;IjM6NEl}l3o6F81 zsw>T(k0wo`(ErMqW8=n(?8RkJ9STR<$aWT+uPbMp}X>b1psOzL|ykc8yAw+@sK#NoA$9v=xde{!{hmZ2-je zEb<-<#sUR{C&{668PIuh+%nWG8|Ueb%D^BG-k2Th6V)k%$nEcweqP1keSgPZ3Ue_U zI;-s-OO$}uu#Dc*>=L-;$vuyav2av8GU zQ=$8sUW5*PcwZH5nTJl^w+dR)B%t0`clmBV$UtYt;~AR8lF$c(%det`qmbc*O8pjT zDC%%dKV!1=4Mh_Of8Ci~k*KBi?VCY{NL>HHXW{rap!3x8@2eCGp!0|b`0>>Wv{^oO zhrMzHaU$B>fhZSnRM#gyKkWb&KST{4wA#b2+1j&-1}Essk+k0aV+Zu{f_&^PpTKQ{ zLZY$20`7FPE1ueo1$R=UcGfuoWIvAco@h*j>EHb>h5sePT$r9FcTp4yNWfUIi-lMQgT!h4*!O|0q zc>e6i{PJV^BF>W@+-BbEg}Q`I%EvE?(bSm3z0R0Hq{8%I{<`cWx?m*vZ&H041v*T7 zQ}<7yLrUAz=P-Ab>d}cHHp~yB&v>$O;`0EySeM67e7_r6$H_i$c4|ZAV{DGD*>&hm zn~AS`NIBv=2u{d+lZ%R#iYZf>;*d!ROZfA-59nl@)AY&8U}&Je7i{`G5dyo#yLwJ! z!3hqk&APl?Ag&S4*2R8_nqN=seIrYt@3m57=#4VC*%$O{_kB4WxvX~F)fHsRVjslInN2D4NgpiJd9X^zqzf|G*{)WV^_G`DGJmKK_$D9gO#D3xVup`EBs6=t?}#&2H!% zF?YE7Y#8*vDv}jTPQfvn@xtq0=Aikr+%KfC0MCBQRKI^|n(-Hyf-Th>Fu zM$uU^<{Q`PrV(kOTK@OCIdq^Q&#t7rfFjz>LpS6WkQYsG#oWRix=ga(Vv;d~G|t}W z4#fGB=aL?EFIC6U`$icJqnbHU`ExMj3&4%i6R{;oP+44&rK8PBOT!g^93n^jdG*fZ%_P^r_74C@JSdzm~q-CG4ZR_1&iF#$+Byc=m9N z^1E|0&9Z9x>AIJtSSo@QU~E_goXm zIxk-P8+tY|<(Qn;@(6+O`nJl z<)z0Uexj54GRNEyzxMg*s$ECO|LyXaw>tu6oJO3#|4D+-qC{`I^$hH5`J<(um<{3P zHsUuG^WmBHRL6bHr82+UnIZDL7?=j>xLa|~$LJV~505|ze7qy%``En%?ws-~WLzwU zgO7A|AMA?&_1g8e$YXDzw^Girl?=$zzpy`?nGI)Wj6T#Q7P^M;KhANzC!;@^MSyJx@YE&=iHGZz^BhMiyL8^D-%bWPh(P=gHLx0Tjku)EXQ~7i{ z@(M`yCpN}DNL`QQ^mQYY62HSGJL?Z|EfXf$d~v|}HL`cOJ`K*7$jMgE;r9bc@2bj~ zTu9~^9``t!4~xdz)`k)Vz;^2H`k#>k_^-e?X60NVOi9}ga9l2gx-O4v_V_vJTz9D$ z!#xmIr&o)_O*z2-`NgiaC*CXOJ%4Dho`yfqhSATqsvzM()6x8}3ex6; zh0Bxid!q`Z=@*g3E|wc(9T0&Z=WC}t1{CNWR!t6OcOaY?9*Vtbbp*{v)MS+&>Eb`&CkC1EOeihkK8$fw;8X@AJO15PQc!o9OQ#VDFb}5;g86 z`_m^;B;+F(x%fsmj}DY^SDH$cYzQ5xTd=eFFpkoh&X#cFex$M4bb7w!6msVgEUw&{ zL}ym_^lBU@koaN!rtf%9#+i1KVpn7ciKOhdhkxkB|5u_2=8Xtw zLXSQ1w(%)XY6?;IyLGjPhZ2#UN`Cr-c`d+|L*m@Xcv#`-IPyz32P6+)5dRrb0;ucB z%)|dGpm2n{`wO1G9lFhbGWcyRxI5^^zdV9@8&`gi{$pqWjWe_=D)|l28_!>Ltfm1- z*#eWTA2z^kp(`68*%C7GGtx#R?ojTf`5NR-OjFkM}ZS> zB%5)5>V5E0>S~v1^w61}@!Xwx6vD3g(gx?>TGmSkm0!*x*Jqi*+xAmv#z&Ln0{;Cm zu#-RWz<&q@D{Tj))$|}I`QHoY9otcyC#gzecs;sr8dCY+jdE0#BQ73gOF*Akmj=U& zgAr+y$jvNn%v~D%=JO~d9U><4E$(jSL%e#3ZL@0`2pniH)zegg*QpP|!|b)Nofmub zYiB*&@-1Y3!`TEs&K6F^3ADgW*0IOpTdhFa|5`OAyA2M;`l_FawL_CiQ?N`5=88xs zWgG6a!ym=C@)MLD5OVWv&s(n+xHrJJMyyr{G`3;2%Yy_cAt}mMk}Co6^7#|-2Dm>q zm>_#6qXeiPMt|Zp!F}j;x|S)-1086rh*WszfjL)P>u-8u(VDKR2LrnyR2VR2`BP&~ z;>8`K#;9Sq&)e`>?7=*Ae82KkC~OVl$P!K(+v4AU(bs225|?4*=>Zaxodln2j|&eo zVSbIX#P4Ne>}^!yKZ7TG=ttYJ?j-s?45@F9)?yh#E|04cGuUuGF8Uy zDGZF}!Z*VPqVl>JWT=-U9O=uG!!J8mEPt zqPLvWOTEF=u%mb1CmbrCRLEXsh=+;ac#{1w6)N*5+*xm6U+p3H>rHe77%E)rAGwkZ zE|JfR=<)nMS%G2Pza|H^Wt>`^pJPs+D&^ZfJp!2gk#|)PN&w}0oe_dv40<%yvzJL5 ziW(8(!YDs=qGgUdKIa z8{>#d?2~QkVv$+dz?`M?efoc|)}rFjZ_JIQW#~oc5^<$q4$5Y$SLjHv&D~<#}9@hL?|39Z}n!CSuEP?_${(tOTrI;sN`fno@ zz+_RWgjgJNpTojiS53-5Gt71O8e19IeY?`bb`OB@Y}unD<0bHgkAmaut74#eN2eO# zUWj`Y&|1Qn50#&fALv=-z=AuEjX8c!*9SHV-dxB2$4RJj@7|`ulpO7&V%;%F2w?uW`2} zb-_^$wKXJpB81y3dKD=#o5k-n5C8iv{5aRjT%+%%)m{#i3v7{XLYQC6XW_o- zPzJ51Rq5m004gI1)@pSn5YJNN}dUlqbdik|7x`P zhu^Q49dD_}-pvGe5t;fGhBQe2kHqXcSrV)e^UWM%j)OGEn-k}%BH?<1rlNXzDu}<- z|Kih}0WvPU56GJ{fz^Wc=^6p@o6@!+3|G_lHr`XBF*)Qhxrf_Rc^u&QUt`q z9!eHvWgs6}<#`P6X-*#ZT)n&A15A(gY3}1W=-ZOeteR`TyTWT8b4TvIlg;UZ zw#TlVJd&7~>*3k`4)vqQ^r^2o3Hbh`dc#TN=PVKu{rkK%1?PcymlwzIxiob~PWS4$ z5oGbM_DXC&=Fg})@%=m9g*4vgvWQ^Di!|F?>Z8PUh}&P~(rcY^lwe@6dmxpER#qyM z6-APel(sOZQv?1!A4+NaF#H8H6??_KJ)^+f$WD@z7~k*v%r$vZvcR|^@ZOc>9C$}? zQ+eT@4?&6X%kQ2RLbiGNfk#9Uv`Ly-lHnd|pf}$WE1_a=&Ep6Unwv!$KHr=5UcM$_Mr?zQd!xbFt?{a3iiD8zx47J*XYW{6fLdvnu6DAYO4%Z+D;q z+{uDF7V^tLgr-#rv4 zzkaGNg-<-?@RskcQ{(L#_(c6Ri7aLi#2?d0+*x0Ome{XaapW5y+%sYLPI?7S)4emW zm6`%&{d-oPY`xIPrdc{pT>*A!IY-Z`MWd$O@t56G)wuj<=%g~)hA737!tnS*W8mgKGPkY&6VBbP4p;C*Mw9( zwYpSL4=o=*O--0JgJ1uI(}GwRgvsCSQB;})gEN`dfoIlWDF4t)QJ)PMdx9bj@2$c2 z0-moA%IC2Eoh9Yq(KxstsInO;bVCzeZb<%P%v)>pTemR|L{4;zc?492u6sW_T~5)C zn0RWr-pdy3pEkmLOwJJ91qW%w0XwjQU;oq)O6j(5tZw z*^G!XWM@j_BV?0{P6@0u=!_-eIUbXw#DOpRRN7l(?BEQdDfwdzJ&{2Ap8krKP73b1 zRB5F!V!u1NhVi0uHq`wE=C<%0Xk_JXFS(El;h{RDwEj6@w{!BO?j`|>sE294VUFjK z>RMVx5|C2TGOakIL6WAJUjFw?pz#*Ct%-d> z3tyI0)Dm-HYC<*2*RvFgYo7nRLEi>@+X37?@5UioLtr9pXbE^oQEpx-z6Yo+ai_M< zgGc^@BEGL(uowA=KUKB>`2}^iuW@zayjxptWM&@<>|xCA+8aRJfp5i{{u@BktE>Ab zDtocFagCUIstYNuoVL-S=|CK8$G?fhwxCU==h>8N^{9UE$z)!9HOhSd+(*~79Q}6t z(2|p1gm^z0zgFbSL0#{dyZ>RH%s0zx0^VPv5O*qr&}BYfM09HMu(_Ee+N2H~ZM^6X z<`&i+J_8{TQpyk8J`33rO%xw&MNET-pal z(?~dH_BBEm{Q#GVsbtlJI0zsYmzm^Cf=$zB#HvwA;1Hh^xO*)XM8YWsZ~VnQ0H={g zSL$pCj-&c}YaQQD6tCU>A(aOQtcC-tvUMPH=Pylb;VAgVFiWuEeM@{`iHvpv&i}Mh z@kIn-{&~sV{7i5=bnzJnlRqj$k!0m8Yw7s8D*av?kL^d1%+$dT`LG8diK1MGeE@|~ zJTKvJ?L}1+#o_iipW<>jD!m%_?%s*59Q(7?gjnt0Hm4AFpSJY~;efdMzGGexA)>p-Y5LlO`vr zf64G|@Gv{CLNdVABX{kVL>O(nBkqmoI}&?#4b}&7I4`=W*oph6;uq+k(b}&e@bJ}?D6&ik?{&pw)v}SYHdLL z-`F!3h}WRd)nasQVFuU|C!~j6hG1#Q;t028Bk-U7)VfOQ1ODepeG2R=kxotIlWfda z5;>!4slwEc+Gh2umW4);Ku(EJ$kZ769+<&GOEQ6+0@>dOXkj0rRd8);FXo7{cajTy z7(>cuI=?iZ8AhDyCJSjZeMopobc3$33*EGL)o@R0LvDO`dDms?5w+>l)NB_#uWmE) z6?e@+Z$wtk{5cnk#>!j|mU{FMB}0nVulEsfpGY#O7xy)i9i~4SRb+!tfV~~XvjTXd z&!RWYQv&}T-LrX+22eG$F7N!Y40bJUj9wHg15W9$q#3jT!+gpe#8f4adqVBzeSAKp z__FmbJSGPs?=Q+Fk^%(vwf1v4mSP_I^UAIdrLbVNX3Y^>3T3WCD(728%w~XmY$=#sYJoFn7$V@2M1NLAaWif5=1o&30U z&1vbO6vS<2GKz3L$y=5OFZTv65GOQ2nB<`Nm_}Pbk zKJxt+)zyoxz835$nZMR{yb<=!cB@CruV zLUy(r1qkKexcI3HiL)pCnVarFDq5a?t9bWYw`V7b2HIKO#EJd(nI&dFMuc0%FPam+EwlKsi}*G9^`hh{nl@#GLvK zx_n4i6r6stR4_Svbx0aQ07%~COklkI3~ViK$#$&$4VNC0UbUH3fb+|jWh0sM*yG2h zwFj#Z*e`b;-B^c_!*}`;pDjbzj?C%DG-IGsT(6+h=mPSIFE(_Rx=?wi8{Nj?F?6jl z|0~PQ33S$P)5tt`9O;~N-~5|3iVn95mKsb zC!>)X_eRQG|8rw8z7TFF!Mgn_x*v74p?xMyy>#4fm<0nJr5U)GNjfTs8R zkdSf)TzXlT-uGVyRCn2o(eh*g18K?Imm zchBd(OaP+>HTShEnecV#<#X#BvGBDqc;ly(KbomO8S}a>3MGY$v?x*iK<9`}Td%VF zpzO+zLF-Om5ZRsEY{d6`(A=LnPhu2|{DsB~jM=b9#pB{a+lU89U7*%o+^z(bOD}uB z?&E%4=X_qH`yx1fYcRhivIeeg z`FnNkNXF2SgV&`Q&8nHTmwu>4EuQD<6hWXPk?b;?7O zK9#u@Bm~5+Ty*6bcLws9SCR9pPelUOmE{cS@yP4PqV1|kDAJm|X143=f)q(PNZVqb zVxB>T_xWIZRIGZbM%U8^adK#=m}>YU`(ncDdv`pL37t?hk(Vh)B?9W#G;O5ANlan%vjZp&Mfe#-}YA*x5*%6Ja)kKuJPQyRP{ z+%6@F{Rw&lHM+zU&Pc6${mMr|GLjtFXI!z)L4o)3+&^0q5Dk%yZ}(ONqWtnO`w%Js z=W`uXEbc>KO)~$1H*E$jVAagj6V7N<(HLdxh-1_gzn;8h%KkD~GbnSNA6Pb6^QAnX-q6!&rt;mo=jo z8l$rp5;aUk6xr_-hFl5|Q{&ZXK8G@tBJJ-bU{rx>=8yd1K30uL4x?j^9IZt&_ILce zFV&%2J^Q%>)pbbr*yZ^D_Ue!($Gvn8_d0YNr2QoAYtioe`ZkBeYW&;QS-)McLipnD zI;~fMY)Tqr9O=tYLcL^M*sCIBAHUr}csn0ukK29idy<137%~zbE@mLf%ioS%`J9Se z94JpWk0l}_$;REs-O;GGyTiqjJp!$Y-xnPX2}Vm#7e1KdUK*qGaTI@oZP0XPfw#*! z%nyB_Mjj{92(J%2Z>aM%0?ExoXcA}y4Naw~e7{EAYdFb3XNmJQzn*_?S7-rAN^YY3 zcU|C2G+B~aJ^_T&GUog<_)2&5{Iz$?m^UA)5!Jo70mV*gOLsCiVS6ucdl35&1NPLo zH{@1fB!T29OVt$6iVX4ZQ*{H6!{=+pYiS@f25nlJX?b~bBkFboC_A# zwIadi8o7rvKkU9wAifPVNx7{_)cfdAE{qK8#LpJ3x|=YkL*qvM*+0{WXe;zo+1?a- z;xhAWV0r@Sa|L=WvW+2M>vW1rr2!PU&vERSVi&UK95_F>-GuBE8{#wT%2C_hzXPMn zDM-tcuU0hI3p!@5d2O%a9;mULxW17Jd=6D;@2RKqa9rw=n6?E#0JSYS!86xji%>VTIaV1U;>y;wc=*~qX=i%N2;do8@5-?Km z;r|kcd5aIv-C}5{g!8}lA5crSfv(ZekCV0I;3_oZtvj&-X`+VphM9Q%?;kU;#Cq8D zjlK?N^=Xj%8F)T1&ZcZe z<5hCxs=RHepg-=Yp&aJ7?TPIk`_YbGp3Y;XYi&nbBR~1m{X1}vya*))o_GAL4X>W#{5vbTX%rvky-J(8T6f}~v+!k&Kvk+4G0c7NWsa>!iInyhAtcpk{^`h) zgGm{xm~@bI;>bhA=5qO=78$5cH@R2YJ02-f+HW4W2t)+!W2Uq+v?!qS>phinHyE4z zp}a!k4=1NYD_8DEz|Y73T_Vegf@L@2t|!Zwk45lA^Ic**2=J8g_NT@`*)e&kAj>FV zihpswxz``@+pwV>Q2ielNe zYGWKjQ-2LKpWPlnvdJUy91C5DWF?uglBo^dQh8wi=}#@{l(DF1&nrV5g1*Aj7jsZU z-KW)HpJ*gvqGIqi{WVhID4Psi3k8+<__WT$WH`v*GZ~`JhBn7%EDwA0ftJbdra%6B zM0vBXT_FQFH9AB*$t4~h89k5piO>f^JP^W`Ae@ZndxPdS`yJuUSb z`y!t5&a;MOVcy|ERWt)J<~@IIAs0qV!`+xe6|>s45K%NAP_1j{vCym1QrSdcSwWHfs*DTW)AA-d}^H zEfSM-fmw)+v^kYAmj&lJHvJ5}MvxS`U9gOO%oiF)-IuWLHD`F}_jY3j88NUo+VV}J z>z`AlM%_kG+wjaA*O$F$rn_A?nXerMNBT)c?$silAB?U;0j0=k~N)7Bj6##b^Lqdzvli`kG_#uf)4v=pto|YIYg6X%5(e9pQ;Q!d1GQJS^j0Aq~ zT6C)do=(zou`@Lg#Js+I#;6uV8t5*SJ79i)F=_bCSM{J+E9U7#-2jZv_DI#O0r+ii zh7B$^V81Xwmn?rHTO+aC(#H#r62wlA2h%@gJMNH)haw! zuI>;sQT2bVS6E21@XCYb8#8q9vYxp~=m z9ftb_NYe5bpj>ozbXB$&Y(iNG_l9y%?i2Q#Gs?ZFou-AugMJL@7zcAX)sCYb?_y$+ z@NuN967xpM7xU*ITNU(N8bQ96SG$Yy2M`PA4<|$3UUdE!b3m0tCvy9{{60*e4TZ&#CiLaVI05&jma zr!R&z%Kd^VPN_vjyLf0hVZal?lMV=FR41Xkdh4|pT&RmMb`a@ zLhIW%BEw!3UvmGCtWOt8=gkP<-*3k{8KJ_jtF7pb^rKD_S4I~KflE%| z?d}%l!_^Dg{ToY#HZ7(H-9y@ldYEtDVq6!>bn4>$Tdg2h!q=zC#1SO2Pxqd0_yLwh zQz5T=ySGZLvD)hlJ61B9HIqA7$AIB%{w4&Br=p`-Gx&Eye`{|Si@@wZI zE$Y(@21eMKxP^ z8r5+7GZJh~pjCe=<;xwTC_pru{(W>ms(6=SYIULuRa^bi_x;g=glu*bQ|{FuUwgwn zKgCki=aDQvYLkg9TH1KH;`85a_6GTwVddY0}~=BW18e?R@Yw8}q9w*Cu7uDnK@0 ztu*;_1>CUW8osSk0n0x7m#8mQz?37!`G+gGr~K&N?kC@J(0%an@)yQ(VDq7jx`6ex zlL8K#RFVMxN7uva3h`XDlg+B+LpluhRgPKnWWm9)=d+Zbv!T4!PTuzf*1PIsF8oW+ zg9bOcm=(;;og-EkuRLA~rhCum-xuOM)TxQ$H#cw(2lQVDH@h$3`-H3UF zvP2x~z1ra;DIcZ>5ZP}Ei_IGYXp{B_yZntl^!J)hQJ`Np?oobK_PeA5U6N$Yo7-qb z%Ko$QJ=P8Av$bJSyI&2eQJmQg>BT)@qs8PG&tl$;+w?uMX1pTM`>CIB!My^KB9rv8I9RLTX$zLgtq->?r)#?K%916^{WdJU~AEK>WpwKwAp>$ zSkg~~`C!$N@{tsfc93C>v`+(h&vk(6I#7sGaYt`viT&;i? z_In4iSQpt3yZL+S3)a2v%=x*$uYgdJ)foD|GB}K1y>MZ_9Mrylduri@dy>Y69MzJ> zfvjrbcy8Ycc>Z&V3$@q)cK~_e{KtRYCrroxpdBb?(EwPQ^{S|O_c+_v7KnW|_?+q?*1 z5j=01L7xdTHGxws&kI3VMNHJUqzs7BLuEO?N*J%Q->JoYn%V5PsI+HmA-7jgx`?eF zqN{$+W>wci1`l2BVnRJ|j~vDb;XG=rcy6}?=4S|5PJgKLC2iN&?>`CM2v<*ODbYx&?++1CxZdX~qND8`_nT&nC1 z^(=@+ZJMlIT7h?V(<1Btt%2@nvPeC_0*G1*g3HX!{*NzmcPNtoE)Pe{(pIs(es7J~29KwVC)hH&bz*eQS907~#&VPMH z=uKH-oMvzi+8Ov)PIx&T#k!MdCwk!Xs{2E>JVQKhSTQcJ6*~)zHf7n1cRV0qepTXG zr$3Bv75$1842PzCs{5}Malc@#aNoC?Xs8;QH8p<{3lyu%q8!*iZX@BbkZ6$(E6DEW zYa8sNN@SiY{E-1O3*WxY)TIJV6zO@+q8RuUrSTxLyaiaP{$0Ak+6k((gS+&Xx*?OS zGm1>H2h2{4gsFV$h47(f4G!$D{ZCrX(=2KL`?{uY>SMo8=0EnaMf-8c=cB(P$vguD zTsNW?|1LtJa<5{N>l$ck{X^qV*FpCu5620WRk&~P-Qq;X9DF<79-N>%4pmx2UY`>? zfWULfFs8yA5}o@}&N9>?W$~bWcbsb(n@S4eJTiioL!FJpV<%AVD>vpJZ>EvRNlM+% z7iWMTkukvw%UKa1e**%M>uW)ZL3qiU-7Y4pu`H1$WuBsy1HRx0~+99h~v z;+S+AM$$CN&dsEKNR(!Ja$TVV*;fdrF5hfGC)N0(r3cH<*e-pSv1uyul-TLqdh`t> z)UGGj*k(Y!G0oijBc&jnnH{3_xe7KZFO?N;*TJh;qSbb@CKw&C>T6_c1;Mi=67za( z!1S3STr{W+q6q`PJi6WnSr>d$<>Q;cd3@&f*Qg4Rz93AsT*{MXMhesYJ7{=}?^ z`##Vnsqt^A$sf+gQy6Lp2H|~cL6q7l1o-WS>_<4mz|&VIwx-(w2y9<|XmovuW_lEq z5Z<>wUS1#0Y8ik|+t38@g$2kYFs0i~Sp%~2D~0zu=fMLG6;7V)gz(p9=BCy4NUHn{ zJMq96s-_Fa#H2xI!^NSaZm(4g;!LgGTJKcVm zD|;w4_DQh@?C(}-_O;c(iAy;GL+5LunM94wUaA(#3a(ma$=1SmBK>zO7i-~;x_k;z zcMa@{CrfAGzT@jtCHD>1tHFF^ZG39G3Pg)N-s-3)Lavm{%l+^yu+fj{nY)gCChj5H zX+LtH<)GQ_u1Fpz*0g*o^~?vqdL2Sq#sZ-Fn-}o~^E`rCo>g6fQikWw?Ms6|K)0!>?H_=y zA7$in-S0+3j30tqi*c^&9_N?ihLgzHlZ94xVG^xe_V&~ZZGlIvbcw(i8PYz6eV8Mz zFHZf%9Fi7lds(=j2M)e6^d{#D;MlUUfW#}z^Wj)waBM6DNyCim{7E=xbod}$@mw(^ z1Q=bZ94>+Z=QQK3kU~HzOIl~@@*abc<`^f5ZB%OF{klIYd)_JzjBai&?xiHb zC$7h?WVEm3q8ADX%DxfD z{1uf|M~KzGD~F=_dYgI2A$WN!oyIE#^FVWSj3fkc|HxqX{JYsytl>&)vc&ZG*TchLHTf zr-Ii$VNQ+ksSm%Hy3pUUiPYBjZTP&}`udVy1Cpn|FY>y$64m+>jXy{(M3FVc;}f*$ zsH|}4T`65C5*Zabucr7CS@3nhsIfObm+kayrbPm0Tj7WV=HSu1xOD7qXgahz-QDR` z#(krWTLVy*18jUxlNp@yfH3dfsIx!;NY~+$pOl+o?sWT##_okOD0q=j z#h45r^*ZwQE*U;&($7%G;@@-UU^>;dtq`tmjTO6T6oQhUZR_i|1z^`7#~6nBy_cWy zXq*hg92?QvKPHU$IpgJ}*ft)6j;P~uSr*ISwyK^$Mu>T=#4MXWvdhpG{QJzQJJUcf zeU9LF%^(ci)Vs0C)CM1fmo~$34{W%InJSZ}BYO5@h}Dd|5YgCX*|c_4BPQ{^cfXRG z(7n=FyYDz}l$UU%xYEBJ4dfiN);@~)aW;V|{#)(HTS&Cf)v6sC>xe7ePi;fTpX+yS z1mpcURX~VUtP!!F^`ly3u0y&*ndU5ys!_IFLB`tG3KU7*F%rpIib%67Uv9t6N2aIl z$Oz?RAwDf1g9V>dlu-8PxIAAhs{I+`?>P~SR9}_R8LR$4`B!3rEK&oRH2Kx9(OJSw zFTtx4erFhnqKPCO^T9nvhVu=t1L3k9fqdb55b!^lh>30ufaK5!iMT)BK;E>zl}!qm z4=oxk2e^+w@g!p{Zz=ehNfRE&_hMHL<@cs)B|s#xaOK?HQrsgP-A}87?{zoM_-2@w zL;gFGOD&`gP_fbZvqiEG)cmNjt0ShNe8$q5=i4f9f8-(w$Nbf;nw5Ae*;Qx?A&_#E zoPxej6K}6sHACOyF7l%X#W*)TaLVRHFM1QkN_?Aa96wiUu~Ifu=;rQSY2lG++{l}IO7Q0gFWVpb@8lhLw+q> zrywzD55)Y3=U+x2+1A2C{_x&l5&UubC*}m#Ky=NQ%5TFJ(0I9WpOzyJ+&i@YI9@Nn zedV@pN!l%NrH0u_kaq;^x%hWV$L2tX=``e?TZfdKZ?EM_HsF5l8EQ_8HCXfQ3>|l# zgM)-)*(yGx;4aWJMpV&=`_IRp{O5`Fz~UtLx*M&i=~-Ao1or>jyG9#)&v+btbeGUL z`f&<5&YOz#2+yEqAG<}D&>7^Ubdp-2a~hc~h&i;~pF$%+w;KAeU$N~|m!pN@C?XV1 z{yTDh0G%`r3XRC^LfswL23Go7kiS{_zpLX_h~$*S7WwHsB==o?IKV9cWlztCO%FtX z+ylixcEMac*DZ7&#@x=guKwc0!PU_1>yRktUJp&Dy?gpAo51K8wVKkMR^SOyXLEPK z^Y@R$<*pan@m!c8##E&pgu}Mf*RHgK8t9gVX0!nd1u5sQVhfB&8SN-^7lHjN17>Eb zCXjF1HlvttfC5vkkyEq{(B^c`EibqMQXkVjtkP|Sv`1<0+41-B8x9Ar-)@Fe%SV?6 ztyVqdT0n`@tGZ5u{ezlx$9SDrOkL|+-Ty9^klkZ*wrDJq* zAu>x~mVVu@L4Ov`dS{>MSI2#+CoZ=Pyd4G4aqc4<9KAqL?J-|{ya7yt2^OEV`(ggd zMo_e34I+0jc;JeCh3#XpS~X9{P@;9uB}dXplqpXT@|ST6mHXe%wBepYFN%H;9SNL7 ziIwK-edsxblRu0iWkQ= zqw|GhpO_nK&Kj^c{P_)(WzI?S@w7^-LdoMN~5tL6xx7WBK(JB{eW9-{1mCEqg zVUGk|how3b_9Q4vvFtgC^W8inNsVoxnXtI)Qe=EN3u0Z#X72#b`|@>GUR2Eh^2HRA z%B!tlt^2(xQKSu=w%C5wGqi)x_QC7-pF1E_D#I0FF2kRHKW~}Q4S@i=z->pn2@ror zqi!EG1M>4iAI2Wf!>6bG10Vh_z}>YsJ6*C%ka~9x^DviT;f*dW+Y7wz$isycf;uZMy=qUpmdv2d*Ik=u z`mrvS7+6RtJB6$ZJ53Jwaeui!72&yxQRH-$`?+W50Ls^@xpu?18xat_Tp~HqhEmuE zHtwFNMrTiCe=(QKL3#xbOjJ+XA*HepyH}M`;iTSzOl3hSyyktAXuXSjvh3)8)wws~ zp4qiubwq6-Dpj_=SkeyCLK!`70UfX}nLvL0M?1V_482C+-VA@n$||I8;2y7+PtLrd zDFdRvFR3VxcEItB=Tb{plH#Q_w2)~d8ja17~_4CjYpZe>;B&k0Na zDRfy<_GjH(emtH234w|sO+c_i4VDjW&L z@AP^|`$J3A&k9jIpZC4ptog&M5CXEPYKmKM&i7BwVFczGoZhSPNR+7pn}6BW&(%8+6987!VirUS9)wRzb{psd_GrKo|mv8}+>={(U z`WC@3xt}HZU=h@m>KkMv=V9cnFAvk+Bs?+K%NWS&$GjEb+q_l*ESmCr%9W+)n0%`A z)tYV;P9z&ItAXzY{x%!~T2n~0xig-LU>13k_IMqCIftS{Jz2k|&7uCiqoPm#&7zy> z|H9byXHcoEwx;RPDdbFd!^P zLSMG3WLaa8aO1J`AIVX$R&v{)@l!GUUNgBVi}ycam0I?VrDoU>Pc|1}?||{nr!5b= zx^Uk7iC5NC4+Pi$UjAj$2ib4aPhYX`2P2V0cE*N&NH70Zk9x zT39i+b$QlH)TJCEf-ky}E8~47;tY*?O%=qlmFrwPRSh52*J~eH;y$nul(tlYKfmdz zHBMXud;H#|_n+1PYsafL)30^FKk$HrL#-7u>rZ8ElJ zLbC?v=C!hMUz>Wo!`ob=bd( z``v(yHD>?S2tSBDGibSlUp^f@I}$wlK}<9oevTf$RHWHB4PBT+!Z z&(*Vi-{CExmsU+pBJ2<qMPBDo$OfAs_u^Ax zIWRyAUex)yz`grImewjC3SFKPt1|)2A0*c(hBQJ-P}U29^gghUYEZ0Fo&w71gTXqS zf0Rj8COR3i4mOk9n!>!x@aNhI&!&W7C`;5iZnW)z=pphI({e8w)c-*^%{qw=pQxt? ze40U#rK@sFN;7C+wp70O_axd^Ax;iEIgZ2`x*GNF4oN3_ zlNPOYz5Y=r*E)9+=`^VeU& zsOzDA%v?AqT}@j~Yf1v*)-!1;w=-dfUdbZ4JqP}n=k2ofB`x9d@p$g){?3YjUGT$Y_ZCSWwsk$DjG^0-CTznL}yR>bpfcz2AJBvj6-Da6ual=UT7Mga(KR12W{ql{MF(9&^Gqy zcqI+iu{Ma_ufA$R9eM?ov}PTsQHyq3i4JpqwybVPo$N()|MA;df5SN>(y-8wggzAe z{DVY#P%qlwxE}9S(1U)u{1uyV=tjcXYQ53Wi7Mp!udrNiM`1^-Ehyxhki}JFm6Gln zRQIhj`JG2O@=(7~u3evx!ZXLO{h>`k!CuF}7Wbp4%R0x7?-(EgV_SW#XfFun$$D}&4p(mez-}O80M;@gT=b+C5VUI2I zNB`2{Nd<*tJnjkOR8Zi1@GKe3Av;A5^NIUSqbWz&G0(o@{jn~tCMf&GO2>))SA7x} zlt1GX*np&_(A6&u;BeJ2u$Z?Io~d!G4yRzfzl!B?sTt-EIr;n+KkNZVk)Vfh%CoQ+ zsY}6VxB=H+i#_9$*n~2ZE7o_`F^@n`P5wgA5)2kb0l$$mjSz zXh~SVVtu|D0@CN29jtRfqSM1JM=loGnO>llsH{c-KN#4HsXNe?#Mhc1EPd!|lV|*M zyzbwAS2{cDJ%-+%(WCzoGJ%f2<9zRVZ3;y`5?vp*@-ddB^`N z9J!wZg>;kALvM1RfhW{4QY8nfR?X*+AI||35}nVNWzvB;Q+gz(B_8H&;%<>ERYLjY z`);kX!@%?EQKFID682%Kn|R+_2ZdYg0?lt=8_RgPSAYf7>iZZqaSz)mw*MD~* z;nj~%tB1$Xu*FO}3(pkhc3%7{g!%vH*S`6TluaV5qsRL6w8v52*!@}twPEx*cPRP( z8O(itBFkp_suQi2-@TKI^<&{upqvC%c87&@-2srHy zS9+|_&d2S;szD#P72OdSX&3|iJfYcHr_x}~dTVkvHw#3~qyx0y=fSIx^#`*ig&@Zj zrsKX`3}lUusdaQqp}A0#RaOw7dtTf*X%m3P$1}W$r3~K4Zv08{2Uu#9{!pr23c=r~ zny2_n;BxX~v2aujs#6{ZzK#XJ7QTTZAsPI9h~t$jv*FlJlA50V9H2OTlRFvnTjgwQ z8fbAYmX{{&0e3s*MYt_gnj{p!HK|RCKb*y&5?Dj?ow^K!{mFA^hO0qd!(OLXu?s9d zexyzFoCNWYR88HUD{$0hEy5DdpAW@YrJGgo`v1Gd?OyUIw3TJwpVbNhiBqH>T&p`# zZyw{~_O&tOKXtTF;|KO#sZ_rUOqxPNul$b?%}gS+Cb@HCW*q4p5tQbg9zpJV9FvCJ zm;=N^OZ>dC8;QI>Wd5Alj;fYQ`yT#oMB&4CuD(~TMmm9y7IN!KQR9F$@U3Sd;Zc=S zBMO)Uy418k%58}P+_g-u$p(P(a&G4x@_1lt9Sam{#P`xVg8)xi%st&&cl*rfr+Tu~qUpj;2H)pm9WaSv5`iDH8(C7w$ZF})fVZovI+;{w@=ZD1@x;(J_k z5PmDGdB2^Ug{>Bn<1#nafhskHQSkC6*!Vtv!t#6_T-;=~4^y!(`ei~8;j1Y;-`FU4 zjOU<6RDUa)4cp-JHSgyCVhbUBX>xRDBn(mLEQtv`uSDE;XxCi%+mLCCNQ|o+=HGG` zk?w8wBWu-CFC({M6eb}(cj~_})UEr_OuK0eDR;BXpQgrrw11`aY%;NbC``I>I2X@@ zNGUnRpA4gvs%8q;I|Ha8`X|mQ^dPfVC>2nrLGMH=s33fj*y~kfSxRT@G-wcbvnHU1N*^E)~o!7+u{!Z@7?A5SANs6OQuJB?I!KH4k56q=0VqG#TpKyyJmW71f^ zk#bH_d80mrQrUi9IR8}$imOn?xi{g-XXk7J0c=j?S9l9CG!_a%uBKHC;$3dLJ}$IH~reJ@`DJG zrxn#i5tw(yOPWU-1FHUnHtT=maW5Em&ohTah|U{RZ#o$doKh+8{#nF>o#uK^v~D3V zDh=N6SZjr+b-sMx)y65a>K-1inP?fo3j z=f4sM%i3xWqh{Yuf#I{GNVw8Q<{L~B< z!ds9*zu%is>3Srrc<=O?j4Gs^|A?XYTscaf<7(H|C_{9gq2jr%8~TU^|igI~B{!U-FN*VopEL@2^z1(&5(o$M0>hu71_q`JtXv zGMt{&zZSug2vRPt+#>4sUXvyy;F+o7F>KzZUIlfa@9_%kn9 z{SI#iUYGBI=6L=;&HT@!AY%$ne3i&k{<93Br!KZqF0H}&jn6NKG4J*{rBi5~Nk53l z5=e?`RUzu8s=7(SapeDfeCaO@)_*NEies_v_@uyPDGBSs4-&?{6n`H?U({|Xr^@yq zr-#oAWp8$%djdO~IbWKQ-^1>_0h(Hr`DG)i{C)-6Z?|IjIbVcmT!*C6*m19Hilgdf zrFcZM$wEc_Gzc$lBtT_WTv(w8ARWm_1$6<3|A`?RYyqT_=%>@2H zLlzFoOz5O#l-iC+hk~?Q_hjDU-j+_vkw?_2K%{d+@-@z_M(UeTyJST{i+1^_Bi0Rz zZ@8?7x?vr9g1V=quo&{>C#lr1e)*s4>zsCrA~-qwPe-mHx4L1gh$HcO?h-!lKR9dIzYZ_R>gIf&EW=?)$$ioL z6JW`w@RNtA1@f13cGl%1(MPctiQ*y6NEVT$^~z&?y|nQA$HGz6Ogk{GRfzMA`Gppd zT9e2xVMZ|5eH^{5TM3!GIfBMjw09qx^&^peW$|F9ZWQof=X{+^J32W~*c3M0gzmnu z<1NmvMVD!e zJq(0jJRHHnO22cQHvsnthz+KnAg4?Kp^ncT zo><@PE{GZ1!v5d0{UM4Ywu`mK|IEY`oiyzY>X#CpGoM|o$UoI!3&g~C`w(ZnCH%IuGM>-fKf zNdqY8xHSRi>wfbJoTsLUhWuBzwg*g-Al8xLN)*=Rt+u?)xzFdo)9h1>Ml-nQ+=J>F zaXkDE>>~%YZ0W|fBTVcPy``^o=Oa>1yJhqETol#D5uBW2gRkp zwsc#SSTY@wtLeB+YH&Z5eq+|fjw(1!`hG8sWE_G#J_t$eu7HlY%I_7z4LDYiN`%)U#W0}?>r{&Gw}m~Fnj$d`UFxUGN5%)AxWDo$U!UWoS-HtBEA0(_Bgp;)G+ zNEu3}_DWVxZbYZUW*7xAe};X*$BLz-8!hoI{^4c7{a?#0GnOcry{_gF&Z z7^V7=&aqU65Ow^f8AG^@!hg9EZ9(JJH;a|Q#Z*E1ZE@aUXTiCyt z`jX&3-Wp_ZL1w=#t{lk_9KUkpbP?Kp#Kp;(ihDkU?k60QC!$01{uN%lp7l|5ra#`X zN6&f>4%ctlK- zQ8Cc&nm)erJQ^7GbT#sF74mOYYAOb^G)-8{BP^R^OEBj0kJe#GBx1)}MtGCCT zof?zije=>~bay(u8qB4VI-do*Vgdiz|IGeBFQNXx2;WD;azk~-a)5i_*Dp4*T%fwJ zX4kTf?@bN8gFgB>;8@FbWX3rgx~5khZT+&~m+l^`s~CR$62saleAA)I>7*co8RqkJ z^*kYc6AN`*PUWDU0?RhO;dR%rk0FmZ6G1xU{N%k=BAx+n1Fu%4_GCct&@RlDKSms10;Uwk$2XPM zK~vzF{;<;`kPNH|*_8JJ^`@O*gH|@GgLA#E>b*%-PweVgjf^$Db|H#VQ$ zK926?Fgt{!F?3{za(2&g2t}~zwk~7;)oxn7TdGADqP95thoGwsG0rp4Tx4xTM5h=A zbzW4XzMQhE%MZ)Y^^M=EM=bJC-BnM$o(k+|`!3zYV2yK|uhpN4?|(w!il>v?wC{EYDi-!fP3Ss-HRCrk@tguLu2{xB69g<(nhJ+vn-IgP{*dKmYW%hL* zeAP~W7K1rUgo+H8)P?gQo#oIk<_PX3(O>5uB8}l-Ki8-)6BFHEfp`1U$WYP%~ze}n)0Q|2mo#i&Ys z>q`|ZsQRc_22{bd=?CH$2P>gV#yi?bzZ!fW);*jnYK4uX$3E~(j)CF;e_I0feF_P# z3#XQ>L!GssD@E!uOr580AaI!h|N42)Kb4~(H|N>Z($@(CcfZ-YH(?GkE!`jAZ|GS4 zi>?i8Q!tSk4BJU`gNCd}8jS=$!QJB1(^QvWSXHuF%ASY-$5>B~I@K8Ha`0<!;bI zp0gsqwxS@BMO6v}a_u+7PaMK4ao^U-YThRewL_Kj? z{PQ4ZPcrr~VGXX_qDXYLo`>JoFKXD2w?nWFv82nnW|ZCdc=J!!7%F+cMBsz<+)Ed} zeiGN8Mir-1B)U&dAtP1(tF6CZ?!kkdL%oyKT4($2B_c~`a#-A(=Iyv0+C zm{4r^ifbvNd);!IKqUi_x0q69*##oTl~r&^cZA>zt8c=UqoGkVa!(QGr`MKcoi{ae zV6*ixO_p^5h}7=p?zR=fPB6v&L<0a^{{Wj^RU#c9vqz0d+CGgft<^e z)V8J`cwG68#Ld@3swd-wghf5fls4=pMAZQ~f!lELR0~j;H2reEH~?osLCoKK298Xw ztQ@OZ16yKUnhm*4P}VtHvKFuoA=kCC{`oKBIYj-Y_VgsEx<^bAn-4%T3*oEB*bgL< zcF&;2H3N>dxJ3DdYdEWUw zf`s;V75$%$A<@u#1iur;(4k}GIE(ohGL(39rr2{7x$}@!HJc2h0^a%qGK`e-y3S z>SC)D2oj^BR%;LOI#RiEv~a5shQpO@MqKfH{=N1rUnlP0Y#Xyzc!7CJ@!=U%kL$t9 zeDT4QZv%X~!c?tV+yDX8!`|A;IY1W25Vzl52P)b}C)aH8`>^H``5kjBg=3%2J$1tO z<;bQvBl-^Lf2KrQx7Q0tefW(%rANW%P~&uJ@Fav$c*n%M%|Rk2787`^z}c#0SK7XH zpjcz|Jw~z#9~s<#%XV)7W9Spz2PEsTYkv5uV0s=dY3|3%|2G6Y9~y`Mvrh%dwz#X` zyBko|qZi{MMt#Wsi?_tr(_`p^_`Jer>@VRNUZZWMn?{WvSErM7XHe(I`%g8o4tywZ zla_dS28p#llGQvjgM!tWI=4cmkn7>E!#?K;q`8BsfAnL>(eZTr$jAU9ud=Jw*XTxd zRER6Jx)sUSeBKqkT#fR{$@~=0<)SsEnuq4cToGq-XZ-EyB(S*tyyJRC3A}2VmJjK# zhQsotwS59T&2#faG6rilzP13%_tkh_05c z5sQYQp$^s(t9XbsQ?*R^mI8<5)-S|y{$Q;stuw_T4^sY$q%*TsK)bf45gmOyG~^W= zbjObY_#Uq?ZCr%9V@!v(mbeFl|Ml35kU8K98>#WjZ-Ft5-=3p2jYyc0b1rIm2%XLO z%5K;{hRlApy0kUmd+%O#qk78-il={`{_6PvV#)~DQ1I(Um+yRIeS94I3}Z+WU9j)D zX8z54-7}b@ZRWzOe2$iGsdX`$D!0ks#~)B#Zrb81|z-3t$Qg25%eHypqF4aO&&X8ljEgjg8meX0S{wW0Q@?J|X|OK3kOzAeoDhG?VED;kWzs+YQ4I zEg(yt@p2B9^emUJqdk3Hbu8z z4nTvwZ}tCV;@Pc^@b(UB)U_eYbb%a^)^&T9@}@0BQ=|qe{%+7C?=8V zNxjT4l9UDO5R-m%_ofE<1)XlR|VXH9>~YJ)Y^4?2DCPaQz~beyxN$HZLt7?6VeO4U~6z_6E%b6E*V0 z`ysQfm=1=c-C!>pQ$jU~`9EAfA}VqlFm1A1^}%lyIzz~npDxb;Q@YY?Mu!n_&iyys zUe*rYrnOveF?YYOIem2dek>YsZXh$AuR`gP`pcDn+K`u8zW}RG4{8h#e_o0CSVGTh zdS6A1;Nd5~3$@`Gx;ws4`?6;Yo!5Qd!>>Pv20OgNbhJj0$))bAq4NVMMzsHu{M{co#%tj$GCtpdqTMRlA`ATo-eH7}U`Ik4Y5QK6# zB0=ScFVdT6T^IKA$M1RRZylEckg|sM?m0<66l|qROE=+*bc+_nYIW?9zDR$peb5_V zf0}r;;a)S;&4$FkIf^;LPu)Mc%+$kEhKEx7()IAmn<%p~wGRAiN!VDhN89&hgAY$Y z4Xjz5oD~``2MM)?Jl1)qoa1Z1k1! z9+UNfQ>gK97ZO}UozHq&QQJHx$BEQ>6s`SjIX(^0fci6;g1LP3{;sT4etSI1_B3+; zt!IUpw2sf6UiOD>)7Fg1t^^=?D5`h{@7J|h;)5#%uvei?@AKK+9N=IGzbxOG1JoQY zk5w?2)&9wPM8f$-Amt)-F2+8+&P|!0#1jp0{CrkU?ityr;&ZTFSR3` ziUoqA_%t>_te8E*Hy-D&oKoABN2cIXleLK;!!VrBeiXUxh*} z17sh6lP!(nZ=<8U_$bmM%lnr{KaAK2 z1B?632atLk<6$_S>)jv=m@~cAg@{xCi}gOzf;xxpE7Ek-qR4dl&Y-q3q;)DY#pzcL zDm-hmcswK)C4bH?QgU5n8`a@ZLe0?NzaK8C(1?Fb?*G&cdbTKAMTFaRH;Ls3w?X^L>thB z-9M$l-|JDXm-wE1Pc7oEcTag(SB>)`5+cIBRcMqd@K>BAAd(;C_mrwD&}3H6v6F#i zNW$~HO*LT&(*JPE=BsZZ@&xuPmBx8!s4PnPXMZ*_Ja+RXja(+OKjv8(>Yaij*V!K5 ze1M-n{@GK_aWROR%_f*ODGVvCo|F^N4MOslI|sSUd=bt2$OgGiXXHaca-$b3Qz^{)Q#+UcIFgAovwZ zzEC#OI$6W+L5bXiLy1awP4leQREF(uq4UHF342{qnq8G@19m+ zUxOG`b8r>BWGw%(jPpX0KIcCR-K_&XRhmOJ-X=I@_VtDr&H*!zxdv4HHw5k~v?L?Z zYw-2Fe1}>s-oL-Hx!aJw0=Gk@!ng}(An`xmMU#wCsIF1hyjIZzbXqnf!MI<*?e83= zsOSs#mq|u>Asf zJ?3W_lwBd$2b#YnQ*6XO(Dufb?z3PhJUKF+W>FIZNvoEQ#8L?`m})u0ubc>SL&9=? zY?%95BpT%G9R~t_ZL{5>vEV$-!c#O~377c|7dk7efy^^@lH+j&1jOoSUs@@{e1lu* zfsSRssKr&AH&_O7pQ%EsV=CY2`rut3?_*T?O=3 zIf@*__LzHh%DBL<0391XbBWu&4!!?=t?;i(8#=OC#~p?DD=JgzF3dr_XoG#d`$z%y z=1qT!HtFd@)6AB?EoiZyc`!+zF{uaL*(UmXA*Bl)*WKdq{)jn3t^AQ^OtBx;Lz*Nx zvK|#OMjt1~b7qRCic|V{ZyEWNRhvaJABl2r+c&Ofphx?uf=2ff&?-l^-A|h!w3W5T zl5K`d4byR#o%faV&sA34j2y$C0l14+2!8(1q~_$iNQc4aMtkYK{Q-C+&9NXSV-U}W8t+= zg4koC52rq-0*&LQk+xGhs17&I#+qdS!Ryl(?0hnS?p0z+eP24D-E(hg>r#PUaMpu_ z8|PXs&s>luNrVII4hL7xc!+N^B#keLhOVEqB<59ySP4jV%9&O&NSdjw1zF*YQ=Qw4G^ z8Nv6G2f$Qtl-`$o31Vz#Z>?bdk7U2w-i3oj5GbxB3D+zEg(463;&+p1jKa-Wr+yg) z@Pt`e-Csk!4$M6cbIa)L+IMUF=y_yr<<4nxV;WIP&i(p+WdxmK;ESJS=tYxzqb3iZ zwIE;RPi5CnRw3@%UwY3>G7#UuEt}MObyPfUkbCHa`GN)PQ+5)#Kbp`)d_}Yz_q1}a zxMQeH@-@CSE%#cOUFx=rV66wfs#$g)od#fg_rU6jCiaoeONLspH-Qp2k+XPf6T}QE zJPhP$hKuM%&M)p}SUNU++~;=_?hBtxc^upXkq#Mmg)q;>OXbvm4wQ|MtnkFgNVfr! z>OXI1HP^$vES+3a%+Xf)>CyWquoep1=7mq;{a3PtOZu4`{;02NT5_b!8Hp~5MA#IY zA?s%M>u0_AfbYje-k(R!K}pFYzed^#uISrXR8#rFvo>PJ0B1k&UYyD$7cxLY9f3Or zu@RuW@q?W3axd&GRVDRtEaN`#M7>+k79_tI6J+&Xgkmy8x%LMjv?gNbNx%^LHeQ}e zj&uF)Ozie_S_|m?{K-U0{&~dG*~n{EID?LnTl18&Pa^M#m6(gmL+J32qxp+Vy(lVp zYx-klE239D#rr{4etmy5HoO_oB zqVGQozs|~q7S1FQ^5sH!CzM7NU0(vL1zz!4on>&VHS0y>Y$d#MD*E?(0HTW6 zf+Dchyd?IbJs(8rUcM9(%mvzqK6Wb2S@7_m>k$8?WKcC!`|c;Ij`;GQeyq(lhN1V@ zjAWEtVBw|OldHEQfX~I^8E01_j7&ROZQ#7tscdpqb+$rio8X#k ze1S2Lp%wSYx$iDHjDoCOvp=ovG8|3kI8IXg|J?s6p=zrYSZllL1-RGM;H>KGgY!=6 zcPtHq_NI^@Njp7TaEZ1 zT2gnMug#tsJ?#y*8LAH_g5x1}|M*6iUIskd6Ii+vm<>OlsC9VTTWj9x( zYxJeMN6ZQSGa-8t`8f{O*thi6@)F?n3oET?#}uHXoEK7I&VyryHMM;_wLl!E8S~9% z1kT#jeR?6W0GCQ)2U7R&oK4aAdiawyAQakecq6(EY*M?c`Qw-etuuC0Lb)3VBA+k* z86QGc1w_JnWeeyTmolg4$}&piO5v1eT1L*||G6s+E}#~1CE4-jIplalnZ6m%cS0`P zaq@k_=lFt&RPWSbBtJ8b85R8~W1cqEE4CeN3Ntqhbl0HlvzG*_@8NmE$$8tE6RBv* zZMul8$`q`_%dcL%>j&Je&nl1+e!i3X6Ux2L1Eq_q9F$wdaCT9cL>GUL8RV~=c=xad zgoJgP%<&vq$D!5n#Iip#F1&LXR*GQ3|?bbQoeUweESB@pq$0gv{N2tPA(w9}e<-5}igX z8u^cG?o6SA8UsI~?_)^)nw5m?{xGte=XhcmH-Hw-MNAj>_9Dd|%8>^Ab9NNB7(^K` z2Zf(W&Er)qGP9+AuC`r<&NFj7y!Kx%YGC|#zwT`!vND%_5|6ph^wcK;db8i5@=ug1 z2`0|aB*Aqr+CBiNt0Omfan6A9+wCNJQ$Bhe@GQjY; z6q%fVCY<1ZROm013A+)uNcB&q0r_d+tNlEQaGd=y-S$i(q?6@OY*!~@|02V;e>@I(fk*`hTus>At{DrAaze8VKdrn-zq^!hn!WtIl}`a}eJaMijnt z0snDF$>ZADh?$1Jr|DcW664=G;IQomZdS@2TOrK*cj+>cuipax`diql zvXdzT$V7Y4(>AULNf2C6q6}$AG@2$0W$zo%HQhI>*lUTz0+sF9z7(N!19kP$VxX+Dwz z1zw{+*F119CEed?WSFef$7M#t6)^W#xJNL3-{l?vEGmPn=y{qix9hL}H-vy-} zth@&Lt0s;ORVtt_EcbQF)D(KozADtx_6E_!o%b)vL*UWO?iF#nSeUx3ML08;3R>x# z@&fGG#~f&VWwSaT0>`VT-UKxP=L+& zzMPejYkskFyIL9d0#If4Xusp3(X9EbNI?^(-`Py*Q8^7`+5c@n&?q7w7}m;&ZS zmU}A+N$|!Zz)^BL4)fv7PG(+60B4fQQ#VU-?!^1MNgjURXccxH_Zx|Yrw6lJ>Jbs} z? zG`EC3L62OY8nuARKrX{L14WRbXncQNNLFD!J z_qh3y0d)Pki2FUaUSyYkYt8v0&bN(v+K}IDM>F%fcA|z&Xh$JplBX z;_1=cX&%MsW9a8hFaI1QK+4Ge{2&R{<(lY8a)cu9-B82WDhp&qLX*??+z}`*{}-OS z8VaJOx2z`K;NQFBM=HLW1W2iG&G=xM2&2!4b6rGI;ECa}B_Ww~AgH>u5XqMTt;y0x z^{Y7d_CnX@{`+hw7UrfD(9eS5v48u)X4oTsPY^vw&HzIHZ=9chroa$u3zNolBD_zr zI>|y516#K%cesxkBZ4Y>+o9VhAzJajf7E+A5PVHnLi@WN&=Mtn2vPM1dKm)zk%a<3 z>W~+~&!5;!9Fjj6qTx19E<8LE3a6rWls+t!0qu9s857x2JpWE0vg29>?nf(pG0IyY zhm(pLmlq)`TO{uIof;?>SJ*k#*n%8MZ$}LG<2==)#e$$Qod0fj`)#t>ha^P5JQH;9 zL)_e-`;54HP)d{JN3_s^jDF|kzGY}ZGbdRu)G0O~nScLImR8mvAIFkEFU%@Xbj+2a z=8i%%^i{H$Wi1o=a6Un5Q3=R@a$o0=EEGv6sC^JHx5qid=f2D=+OXE2EHhH+4o(_m zAM7dvfHxpkMo1ODx*4Fj1s|OHtS60za)qr_^oY`kqT`u z9A5k#!q0ub%Ch{NbddNy&F?9a3e|#(guWX%S7bFw`ok&~!u=Li6yjoF<<-IBh(iph zygav|<%5BH7St}(5G zHuGs(0jg?Hk_Es7%@!5Z-U;@P{-!? zTVT2Vton-U3JffX874MPfDymc9&=SW1k1QQJ-b+mt_^H#>z(dE(?303*`08oCHkdB zQcFM5`fN}iz1feLhE8|=r0z#*Z$rY;GH{6+(cEdGI25t=9oY#WFa1f)};NSFKW8)ZcK+N&MMlqb^Q5+l@l4@ zz7P=YrqWZ!K)=n#FD@5h|GdOT;{<)a(a!$c=$Y##9sMR3h0IUPobH zu%2ffHJ&@y`(a3<_z-GJy{-9Pv=_x~`(3E*w8BA7v6lhA6^SDHgduA z0q#TF&A4y!H^JNw+XnIBW}xbQc9ZvUD_muFHF!qe26m*P7N)vwz`|&+J@pLt>Lz$U z)($m+w|;3G*-RlEzuTvF-VmX{2=b_5st^of6 zr^ZjNmGB{)d#;|V8omQT=uj1t?o`J7mWhfu6U7qtxZVg4|dAUm;wK!E94&IRiJe~DpTTP2U4LieiZw35>3Zu?eubB zj=99lMDgGfdf;SXAU(W{(uwExN@SN1s|FYI9n*RA$Ks^6~875GnAW?zT zts!)|U@84V3FZO4Jr(jKu@&`X{PB(LuR%i>3Ryn?DL@3je|Ja>MWGkbEj*oTK5!#m zuxK+n6C71}@5odY!^icxZF!3-i0W-VFN%8=5(g1>lW!W~R+4s1EPV@nvP;rg*KPwN z2YcEE%pW|$Wchu79P>9Ds47(J@xM`DZ7&OVgCo(-WRiO~WO;2z_4r^f=P6461hNhw z^U&D&a|LsKlDz3DBnsdxw^1&iS1ynofA-XkG7oY;v7S$y$OB`Wo_ily3P5$vC+yNl zAsDe+8CcI2!krsG4(bzgpfeyTKhiS^=iFE-0r<2AEU$AutgExT*xx zf4vJ(ED^%rG*Jn5drskpQ)T#G@z}TaP9FF^x%?_4JRh1LT7Dmv>ICNA_ddqAXQ7u$ z?AcrXO?Y)aY30ZKHjHU~)7h2Z09x6v1$90%&}Vp}=S3st+Z~Z24{)zXbJHqK4@7Z} z@QL0jFPK6u!(Vy&(q>U8)u-)$o^xp93-_T`p-rOG77mu3W4_?>BsDr#17@pT>yW za;ou&Pm+}&nadDOk&;F5u7v{er@)b|*J+?|PVN2clss5m>C}4ZRt#*p%#Y?M@%&Ea z>CnCQN+_l6e{6x@hneTcl+M#tLr2%+*9Lg57p*JZ--!ReM3eb?GN=lYr`msNssb=w z*8$lZ74T^B#Kn`#C162G9?5el7lIYvb@ZLBfOdVS*)pYas2%gjE8oR`heGTdn|S{5 zA1ygwJYxYo5EVZmw}L&NLyr`d*?rT(NN+?hu4Uhr;RF`B-L59TV?kAY*_mY`6NDc;>${(l z4?VdhC!E%B&X#E1J`2i0GL(sY!Ue!em&!7_sR}~m4i!&(RKxn_J4VtIHJ}}0dxYgr zHE7zbGiKed25N0T6+`_pxKeO8yO}l{&N#^Uscx5o6=RzsWdr6$pX4p%j;(|OKE0fW zIaT2HR{otiZ7md@P36uxfq7UxHz(UpwE&Ce>k-xGZNM;b`Tp8`4;ZL5PVYF4gK+2O zE%hUdK%+iOy}G^$%K=`e_{;J9$HvP!u3{ZNxvy;zGEGA;N7day+^Y@$HoEf#=N{%} zg5Ftu89`|!;b$T_rqO@N?}%;_&mv`7@9ak>W)W|5aChR?G^&66Btr4S6e@WoT1kw1 zW3S}$8h_>tBj?lH{}_+q=Tfa^^9Pe2>>XjPo5JUzD$m;=Gmkf6-`Avn^u-!Plc%rs zfv*Hbs$cic8p%XPlq~~|C? zc%9MEy(3;N^T>VY6W+M0zTfZ@sR9Pz4bMp6i&$)>&F`-@Fy6#L*-RMf}_&o~@=T|~%2Jp)(I5Ya0t z&qG^pjO<0?ET9l$V6zQ{@?@l1o|cXM_KEOg)&#Gi_WxR|_MHnuP5WMIc6^M8sy)2m_|F_QU+mK%sxq z$lbIRd+AO-EY|9P=sAC$r?p*h$8=2X!rML&Ys;X#*EI&5Nq@I_9cDq>d|KWqbP+0@ zl7&c8imI} zl{-qx+d2UzmNkxiZ0JUk4>rYG{V?zL{Wo@Tg;})n*y0);+dN{_+2t8!m`5``w_Rh$ zW)Zc;U)#$JGw61;Z}XJO6uSOs{K$LEr}U8CO<&@~J=GeE>PaJ|E?d&9<&_ z-OBB#Pcm(Z<8vd@dbFe^h4bcWIdRpK_e#)G-|~a^53`X{?U>X<(nw^j9p6PEB?emo zV#Jm45ug$I_PTv#8qnA&hkmHb16RZB7x&3ZfE~U#@!hM0e-Sqy$gov|E@!NgxIcbA zR}7Dzk*fuN`qX|MoLh@Xzd+B%Q41DVJhP=)@ZW(8?E z(rdN*#jH9Zb#%D+tX&6K?Cj-#zt{?tiEf47<4qv#jEqxzI$)04@5Cnd$3|I7ha(@h$RUWyOgyFX0EbaGC4coPTO##{^fUgZ6Ijlld=sob+s3ECD!3QQNV(P z!UEX(G70T-kHJRNw+l66IJc)sL9M6*sN;d)B}&a+v~r9oqlsZ0jXKR(rbf;nu19ND z6N>Z5>#@@I%c2F;*vS%8e{2!Sw%#QC`(XiH73SvtPKx(8^>0nbnK3s-;#Iuh8t&E8 zp0aNuA4h#(hbwl(u*Y_o=h(1iFKRpF=U9^NvTyl z+M?3&L8EGtT#Ge5Gz|0?{We3Qqg=a8M_G$|SE8&PYgw{GD%sL5?{W zqS6*Ho3r{V`xEDUD0t+Cg<3(Qx>97op%sc_j~MD(w?RwLiJlgfF8JnRkxjDD4^Pgy zu`(@Az$%;Q=O0hzA-kj5Ycy*OjF(%^&r@Um2E#Cmo6&dRDva+rk1%%(elPavtN^F% zXO)ioGti@UN|wj07xdZN1QaIHA=ys0-etZL8AqM_bf>Nh9pwI(bL!6!(o&|?qd7K( zY^~OjT;mMV=)0)>v}6v|_FRr1%*T96u5XoGxOcto{x_qi>fnRziNU)=1y0T6mr4xO#D^0fd$OcQrDaaej)L ze7L<8L=cICCTa&xvW<`#;tpt~l@yn(YKJ*VSqB!m7Vx&FHL7eX1M6RJUkndKpsq}< z$SDms6z!qWTR&%v_hFr3rW6J+#7WVm$>#(4f@eZhmZRbDrq0JF0qH<3^V9!6<};=* zF>5v5#h%IiBQ(u6ZLqUjpm57(0#0y64f<%UVovhV$Ij(VIF|b9b_(e{D2&dAd*EK+ z(I;KxUy8cWhu1^*gXZwweg6VvIP{_84)dR-iMmn1og>M5*=@)?C$-x)ssW`OkbZ^qgMUwY8HB3IIp&JHGMVgy2=$f0K zKXte-sx~}!k7B_dJ$n1%=(Ph2G*wcz+5S!zS!F#ihn>%GXr-dEOzI3;WJa=u4t}8a zp=Y=KPcS&7M0qkEgo2c@`I2o&1UwSEb?C(z2~(yIZ`{8aj_>>HWPCHhz?7tW%T7HQ z>TG`c_Js#S-;wKjy|lr=U=l63;_e6PL5DFmneL#|wBw$y;s(B3R5INU+~C1ZVibu@ zJ8)RNX{1ta2c^EBIhHTmVd3uP@J-x@sOOHa)l6)M&hw80NOAu8SemS<@?Zz(1)j~K z{oVz0vJ`uCnj_%I^7aeC=mKm>H>@osuEUKR`bHaV8?aFx`?kz!1KwphKjIAC0Nr8_ z9=-qff}7bnY5y+3(o{Li49h66KS(%9FPH^)0DLWdB*eV+PSDK36phTS9-0 z^zJyCtsvw7Vjem)EhDEUe%^b(7STj)LD;vbc|?BS`+V@$3<^9ScFdo73O!maRX;s5 zf{1MBV(6>-(M>J`E*ktECXLnoeC}y8%B}f+?Z6WAnWP#8GjYyGWaxR$+3`q3Tcf7` zL&yh?SvItds$_zGl94jaTrqS~JV~#}$9~L$X_{5bI=D;Xn)k4A2h$CJgefVxBtJw$Ay9NtWnTx@fkL$}`$`DMjFNPi&S_Xme23qd7TQH)>Z{B@s z3Ep&F_N{zV1H|GKBlowlucdWVl}K>`MJ{u!y?eQglujT0?PApG3 zsOOj)-^oPm6_sN1GqWgxKodPNS41Z>3^wcg!2~V$5R>_;rr-n|4dUO z2%PZl3QcbWo-{Guy-$r$s`ka<=eb6Z-x?#ho6!J0G*_g0uQvbzp&fZJdp*pI?rAfl zR2Y7wPPg>53I57@l=%!c!$#exr+7m>oXeatTb01MiCN83&B7vv7gTnQY*KD_IWQ6-Msm`}`BWBvf=K-10z z6DzF2zAA~rRgDE;)5r@Ywwr-JwddR1eVmO_N)!w&CKpGbjoVr;tAa;^yM>m4!I?syG@4Ilr>Hx*6O#vBQ&Pb zq1mmmK*cHKZBhBh)^Z&2a*b)mJ{?9=Mjx0F&W(yG%ClYi-Ho8$o_F{_-3Fv;w-zPFPP_VxR3 z>ZY@?zd9%6fIS&8$w_waF~*_%BwY@N^e}Y0tE$`k5cAnPm$T`f+am&JMJ}aMBFHw1 zRuC6-1ip36l{2g9u*EJvDR!nAP#1?7<*xzoKsDq9byL77$a)11OMdQG33wA}A z{d6BLf&WbW1SEf&ii<`vIE9uD~&~;c0lTps~%aht&k{@McNWl1dkJT z4+zJyA^s&jyT^V4_Jmuw7)2!lC66v4&tejYvx@Aw+`=4uDrP<&nsk_wpcL}KH*UL* zUNYM99H7-E6pH(t19Xj^4uuT`V6lDDR4TOzvP0jEU&H`7)j-6DsCf`1#h z<>?B`NLJzV?Qg$p`1*iYGoxJlXal0XUaRbKbpm~uQW92vHHVBddzHm5;6B$gEsCk( zIh1LB=T$5J3?ix2o8Y=JiF%Ti-;Ep$qfaYW*K2tD(aw$i*`_f(|3AzgPx#V|JhR@M z=~k*ib#JJiGOZS)du(%DycaUjqg#$-2?AlLiu9|~5&!47@3<)De>4)fd1cASOw-^F zTQ;9VN)E)TZ5x{<<%8iTtyHF;h43nm|I^$(?ECuZal#Gn`Jx!d*HlL6uD1t}v2hD#HaerY|d9*Ay z7bM^DQnuu0K+pITv--zy(B_jQs*A#Vo_*u+0Gn9IQF2z=5sL@Qqfr#^ixYtEO`;`Z zP$CfO$WiVSCPS!lQp<>Y9As0_zWu9b0HT9_;%9AA;UBXUPn+cc_&JsK@C2;@+e4S& z#N{n;0XZib{5~*G&Gh5k>j9Aoe~#^nI%L!fH=`NGkW$`<)B`T;7jdob3|E;&P0tp) z$--t3_N&kaM^7RBCI>wlmN6tEE9NA;Hh``zYko_;g8kT%FDOz*S`k~p{WxK>IwTcC z&%r5Dj@VSzLRwsN5TD-2^EOZ1w-$L^uf!pU9_i_cbFn1IMOe5;# zsr~Qor_iT>W*dL2aYW+w;huKMFp7Nj>l#UFKcc)y-z!tojhYlaXk_);kX32|l?QDD z;z+DfSVmQ7?vnFcdACATylA~^^fMh5XD3)48b+Y#sC8PCSOetGIOgN*=La1pL}OPB z65y=GwB7NH3?SkY`_TI#7v_oQf6HIPoB`rPxkIxH^b>TUXuit*d z-#zRtveKj!@F)UG!g#YxoXe`n<UTU9G|?8>lM6{8a>qBQIwctbxyl9ud{Uw1-y3Rfa?GhYt+qWYkOAcr zE9%X-FJNDJCX$~j3+Sn8D%%vZ;P(Oj`<$<-z(7vTRuxnM)+A4u%zB0)HIlwzmT?t~ z%sfcR$+v-}m+IGo&ML&wUmPV^9)jp}aiL%Hd1%6J>-5#yA=Jay_`dwZG+KP$E@YH3 zi}n_lIDTKAL!RTwdrv23P%2&Z5~VSoODh(Px~Y$%j+MBavRebFrEr5n=Uq2?zjr4$ zgti5dADi-&#Pc1~(0cMV++(s{sD5{$Lx0>JM;t2FT88w4xCi-}hR(GcxxDrdKB%@j?%dux zg}|u!*T_M&1g1H-tNe1ype1FbC=vJ59fHUF^=B%;KFrC4^H&Ab>^~}_BEg==*IDip zc(rMJgJ*B`O$7`&*8kbfDg%L-SJlUHkDlklwkwfS5fm<*TDl!k0L4uquGd=e=lfg1 zwmKSftlT}s|LkXg_np@kQT_3ditm^UbXR@ZA{IxtKB! zUtRv#YSC>%ioe80itaY{2d_cX+YPvv%B#LzJ_S|w6JPm_Gf^x#^^MCV(`fsZYT$C@ z61u6=txfH-h&|Vtfz(~I$Ra(&HBD^_mHv9!Wp#BF>HguD+~poXFIgXSwB5z~_jMLy zd7E}LA)GOI<3l6v1Cd%@AgDoe3}oRI#wF;~t(Wr`%CnJlk=4&t`#5xiiStj4wl}hl zbesHhULKf+_pGaUJwaBCN`4?C6d0ImO|==~ppc1IK z)X-|Oq+q+1P`3v+Pd!8No!Dc2<{|d)x#U>&!z0dm7;xr_5288GP^9>M1Qq zYykFuFHw%1o{pyVu*rPP|e&Ygr0|Z_fA!2&f0+M&0)!CW%!nK<6 zoBQgs;QGTbX}EC{&hO?u*pu3U66U-1Q=ZsEK6JyW!(kcX(~IajR;Phd{pMQf!~h(e z-jdtpXaoYr8|7zJjX|r$VD0bqMs$O(FYFP`0CE@nx=TxgJtIH+#-=|_p{f}2k3!9u zmr^#czW;Oz4R((WX$?&vBZ2P}v_J6YbYkYi6!9=p_d3fvtTBLO&UrX6iT5J=2j5#~ zKXxIy@k38)%T^S3t4@|jz5#`LME|=`Q;ix<)GgK@mZSIT488&cMTk1^)QQC2Z1gDU z?xmj2Boxlvb}6kj6!DE7wYV9jis}k2RnN(IK%bl~kDr+ryp|iwUKaO+@&VHV+D%{h z@V91gL)IU%hq{t`B>X`leqz7d)E|OJ<@N3DlQ0kNs?VxNA@+@5`EWd`1Y)?H*{B5Y zzQ3Q~?7mDXbTtvDnPHFc*`JA)iFyKIKM~ly92gD^;j+}n zaZgYGur5%Hb_V8RcUHTOZUD(go@x=s0!m!Cq^Ce7kfN2kzh*8%LT!uyuwA0OFzhf#(& zg>jb=-nX=Y!fP_zFPi%G!?d~+5uYqE$YNft8$fyxQ6}Fh6MqL$oNHhc{RW#g_z~o`zWw$)|9{r$|O*$7Q&k)_EqRNI(Zv3--0ZH&*tAN;1@oLQ9yd~JdT@C6X z_BWPPaPBs)Rg!I>4xYHpa2KvOLCf?zPomH+c$5%Zvl27}p?d0+{Vh}QgWINVy?PG( zcK*Jp+*tx;QNu_cnGKMkR=Qc1j_B<3ioZwi#L$tAw3?W=TUJ6*-MRy-xuQ4bUw+uyV$XnA z6-}JRUimQcmn>vttOPU+LTMcvi zNzcdgzTj_w%W?}m%cTvV2Gr*xgd0HgcIBw{omw~{VzZD=R|xQg{^CW)F3iilI{&(< z3wmZ+wgsPcfne4%A~wcOc>bLrvnIU**d7V|Y??@*Xw7VqKp9X6iI@UX3I!_RbY$JewQuw?qu zb!TG{B>s&*(2JOYF5z$do}Mj`ZBM#)tg;ySSER>(=dk7NL=oF04MZPDPyoSJ^oRR6ciOugFznogF2wc8PAWH{+Ou;6e~GG)Ke1uK z!Hq1;|5WW9B@{&jtFLN}-lxFfm991Qz+!mtH~f;CBKFE=-ZH*IQwK-QvTiZCHb7M7 zNB;N2O)xeuB}#!>pyfY_ZX&5x80O=BPtw?e-#6}8o8C4;;}3P$3*`7-5$iVA%+w0< z>FwH+M6GaF{IA_}xmF19IWea8p$)!L&97g2fxQnQJ12uac7R`(d=+7^;90D@~y+3KAI45B8fcW-m0h)`YxGYN5g$P!*$0-=_+~$t; z*S{~O5L>+Jr8R+Bq;WIMe+SR!`Z7Z1=8G4QcXIjo*-MLv*kM*=!C(P#X1!G*-JV0) z8Oj5pt@vJd@_NKu%u^vqX_}!m7(pQEc>Q&B9}*Aq>aX{2N5s6Pc4dS$$iQhDIjA7_UjfzDEJvUX?Lnd5Ar*^%?<``%U;>e{DRBwG+fihg*0a^uX@7?`PPx z`angVrlCe=05}YMJB_ynL4d~krc>$=R53Sd)a&#^QsTh|0e=fbf1PrfyIlq0i^sqJ z$f$;!3h1i)&r0Cs4;qo4FN1>HTvXS;0EB10`STF_CQn8#D7WyJ!{NK~FKlcT@a>#M zVh}zb`yI|$>>tH>u)CEu>a#6)E_ln%1aln}n~dt7Dy)M+q>37^;WiuylKc(bT!*op z)K?K2cuy?XV=;1f7@F=|r#-{x>Fmmd)g}Q~lz%Vbo3c(NVtOzX`WWX3xo^-32GR7P zST_@}WEn==xo?Y_OGnZEi%{k%Yn(0L&BX8?PN;-HGF56SvgcU;Ez z<6{nKhCbq*Nc4o7^o!vpbYJGLnd!+|)XzA)ec)M%{=C&wxtLpmE^m1~U_P3MEHr+2 zrb#8D*T`&aBQgjPm-$P}&Uz!~TsG3PZf{YzdqsYGmm5fmTpT?<9|^*Br>uW3B*3Df z*-@&HWT?e#f;pyCI5TLdwBDZpCVP%U>qUuB*in)(s+9)TPC;g#iAkWNHgZ9SEe;;b z5Z%7{vlXhAUuu|3wSly<`F8QkR?H|>bc%kFe>on5} z*Z!=eeZ$=7-LOv;lxJJvM06#C=F=W%X=EnUlAHsV#osEMC${mPl2*B3Y6s3gX-`Ng z*@B10_Vdce*1)&q#d^-K1z3Ok?P;~_3^<9s*?yih4(qKhM)a(M!0K{ZxTdKctkQZ7 zS20IZdP7QVmL9P0Mqzf2vlr1nM)KD_jiDQ<{?jWkjV6Oj>@FY9qM7Q`ix=bO&{IN< zd#`tAQMAT8evYmg)E}g7cLjUIMkA`wt`PQk>QY^?ro?`dOXfpuj|Wjc`_f0V!Co|Q z`s75Juf+W zF$X-ed8mxfr2{SP$NPJfnK0qtePv@K3-W~f9#T|h19ATIa2dxO$Qowc{QNW*$WGFK zo_&Y8uNgN<7#&K0qnpL#mQ^d9eBraqD>n?&jjA6CKF>k>@dNGiwCD&}6H z-xP+p5C3GJDq3pf)cG-LHz4sm| zMfKdzU+3lDbB^=9@9X+}-tW`~t19Hv$;nf0l8dIIcIXX-Ll76E@wqLW^VjSuy?X{S zA)FG0Oy4So6O7|rH%Y4Cv|jozaeQz6{^uq|pK}A8kE>)+7itD38PV$CZ>?Yu)mIkf z*AA}!!&*CXoj{u0Ja|{S3%>s#=+bTI0vlf@8@^lJplncmmdC3bDosz^c;+;ehLc6$^z=^b#;H80-ms*o<}ASXtH^pc>;q^SEBxJQkPnptMUgul`CuE& zKK_zE53(bfgc|t*;FXd5y7QL;bnR`vcu8m}GG|j#%038yevjN+u|(Z)v8d!p8{-^s z)99yMQ{04K5Bd4!O|}6rVh{Vgq&%JaI zb%kG~&GVT+A(rCaXWggJ;@i!($$yi`nc&H#y36CJr|$QlMDQ@GbKN2T$1;F;C3pUc zHTIx}E#eTTl@63TQkvPG(}W0*Tz_USTZ@PZLVINCDv(-B!|u`1e6;;QRq=&t8v5L! zp0<1^3N3vQX7U}jL30{Ux4yc1gI4uNnuVZP(4!*Z)rrr55XHXx{+KWP=J)cXSYZKl z*+tq9;5pDv^Nuh*Ln+wQSzq|4Q~}$4{2y;PRf6w1e}YavfUOknA9vp19HGz}_wX|S zV+QFpfv!rBQ>}?tDk+Bz`cG~D-ll+INAu(#|-6kjdCJyV7ZOK#GoO5uBDcsW&|M>Q0U`|VXm zjRKnwD&B3w{$G5UQ22rSr%kPoOc++-dvbA>N=HACoj%YgQ>aCzbr17@r;nqnOl9Fc zruez4=Rt3xJBKC@xxXfzpG80NeO`COOraF9pfhV8qln;Go4V&=KT`e2c_;94H%j$k zo=hQXL4N-ItgWaP85%wjc`aXtK0UXtG_J`(3+OU1e)v)Shglc&S!J^~+-O1O)tkJdPsWis znUHnO$PC&d>Pc&@ zd(?@3HB`>;>31WWd#aI6Uwe?`n8mlAxo+ecsY8>o*@Zm4?cPpDcA?arpGQhrJ5i90 zyF|Pv=Jov!;tkqvL>W#8ibL7;NWGgvWofJit^Yg9KCD-Rel0att#o1@t}Z#Hp;QhU zCHIlC3yw!M%=31`RB^bc-I22_kQ@yx4t&P6FdA6>9-Wg2#yvf669zp4uYTXV! zKQM}U?7HX^4%c;7Sj+w;fJ?~k1T*fxeUdIY+3+_H8fllVT`w;H#8M&i_d^l*=Nr6Q z!G0;Gz`F+DPv^r#>HWP%z8rYl%=d^ZAQQf~HGf6A*z>vXG1L^D4kf(r=f*X2fu$>O zQM)t;?n{1D&&6nct;Q@SseS#HI?ExtXq=#eMy{@70EG*Lpxm zRfSdb)&z)^KX3gjvOgipB)ccaFjvEktiUe40gWYY2cAA(hnW8R{)j!N3Q;(n zN#`3V!5+6itFoB;-J)}jdsaUK4Vm2z_&k${OceHljW!~XJ^e=t|0Fxq2l6w{u8weB zH2wpTTrlnvJ>g3^jDacx7UGfJB;fd${?p4*WYonVtc(G3CuFrg2bQQP>mK7Yfcp=g<5o z`U2uCwP9Rwu|ToH_G4Ho5$}acb{%e}Lgvu;(HvLIF`lNB8NF5l&vDz4khL02*H+iq zSlU4tISy#u9)VzwaBI()c`(tad19fk0ghEynxq1@;4SwH{cmbZ;Fc{|nSsv(_kU@w zJ3$6wVXc-^-l;(&aqs1#WE;>KgLXeh@)i_y+vUV<)pkTpOmf`YxE*C#_+^_$;hgRX zjmr2l%}DCO7X2lb2IRZ!w|`q1`!anCvRSCHPdWMOOs-QMda8blOeC@f!HyjPO=Jbi zsh7Fzcd7_!H7R$i|ISC9n#S`*HF>DRad?VVARF;$Vt6`t5~AWf1=Raj+9F%6!!@9s>T9OE&%pgP`t8-`54rkQcc# z_RFCKB>X8|PT_kLrw>oF{I?dc|Mth6|7t6oq>tS=eGKytPsjgpx9);AOZvbpo> zt@Sv-4|CpVkK7Etf%omPmnj2GHz7N|&cWMn8|029h=t<(ts$$S`kVKd|H(l9#du@| z@|EP<&f88v^LIr++pd_#||obj5%blgATCOd{LJXcqv5 zJ^JKS>Z!28P2b(Zkq=P>9Ze#>#n2$h6q=b?4uywFrRUyN!3wW}C#PWzl*F7Xv-PY6 zZA0DUQM}(Mb%{#~!h4t+tUE$g_Gt-+Ax=gTWd96s0O%*erwadXohmbyH#JF z{y*1<{r5LPTK=ki z3fn9c-Y1i|Tu_bs+bs7Lvbxa2;`1v~M$_nbhNV1h;Uc>5GCOXJXB81_hun#FUqy6m zkIf%u%#Xg-Dfb%QdS;P#4wgUMg`vI)1EH%GDqH z@J#%>g*xhyyOy_L_eu%+P9qj66_9`|pY$Km;dBAdCwgPY8Ss36@cgC^c`?q*|IJW~ zssdBi32n{YI{5v7zJ9K`38LDP6#Z6P!KZRpxj%jO#YT zd?(P$dH$3n9ly@F?`gz!!-Q_3NwhEio5YIN?|K)w4mG)#Uv7fyPbkhR;(aZD*u3m? zU@)RvxjI+CrZYAdLi|Hvfs{=xFb;#Vv8v|ycfH#H}>_08A_KSuIAs4M26QE zKKi$mp+TGNjD3YVRBXaGr(cA<=*yd-YeWO^!;DdzgKq^)ckfVjO>MyY+Ds1N&Kb}a zrzhc%%7Ji)#~M^JTV$%fHi*I)9cW)#)sBQ%v@4tZEiYuS<+^ zxtflc&k-7;h*WgXBFHxTzf|NP)2AdblZGyM_s$ig6m+cCfb2F=Ji5>D=Aq!;S40^$ z0dq@{XeLB!^~!D}I#no<^48WH&0Q@Jrl1i=1WPIkNBnKzda>MJToJ;6ja$lG<&2de0PJ1<;whwMvN2Z=5^!VlBJ-n2M# zAaU{VIxidx2Ii;F-sz45k55)y{Za|Q5b(ytYcmOSFS*gyOC$rUjHEgb?mty^E#*F> zPKF_$dTU;qFrc(wU*_{LK`YmOHnZlI!p}gf50{yKs z<}CO~Zk3={YK3(snEU2e?{UwUBnJ7}rc&>Xn;=Ib?VBIJ`2)pK2^UJ5SP;6^B$?2V z3gPmn?nG$kfXka<#$$)M5OkGG()&>!)M)DbupPi0p?9ewx6TyedD^E`!u&!IJGZQ5 z`ltws$7aZ%Ju8IgPczEqs0-j8`EOnd-1}1D6>C1Zl>_=wr5?4!_*~QfuR8o*7DQ@@ zH*VM`g7VIi*!Kir5nQwtq+3S!WvGAAVK)lz_J9bHlrxKNVc#uDkE<#l7R*M&}<)E{^B8~5J zGtk-k=R)2#sW>Mv!Xd93kH$=NClw5~~rE4i+qjxKqa%wRk6?mT5g$ z6!%=xZ%5SrQ`!axb6Ya@)KxG%c1QSG%m|3y%*x1U_d@<;0x{8SJxIe%L+GFMD9YHx zBBM3Tg-cQ6pv1ii4lZJ=OIN1QZ?lF^w|&M@d_jeZ)4yS)=J#K}B?ZporgQ5YDeFPG zPaU;sZgwJePJ5fi3(aW#Nt3F@W(|r>Z?a$aFGWPbtg-$Va?r{z@9oy~IAl*reqw^w z9Z|a86KZYp0y(cG#p>I!a6h$M`=b^19JQ=hG(67*!IB5F;oJEzJEQpXb`|bHTkG5J z#1w;)ppmB~Z7H}izj2FyR0Or2#c(XQRK5l0T24#fGOMO6#vZqZ zM*-!^^~|a@|5WDs|M4RiFrF`){sXR4#&WW!HvlRhXmI zL`$#sv>4~G(@HBbC#@;`a@HYbDP&0~1QR$`K&<_xj|$kwuqXF6*C%Zdgeo-74;JiGH}U6TT5wc%eG)X?UtO3=%>X9<<}+t-eluBZ-0Y<8 zIJ(71tw4`^Mic-2Nw&x%jM4>@H|ep zN#Tf>G0y3}_Fjm^eF>pg9f7k+kY`?*#^sN_m=(tsc}Eyn1mU96+O zH4W$O+kCuM*Wr#%|JOiw?17Bikq=Q^fvIf~4!P1{2&-IUlfeD@Z_EAS!>(0Glkf~V zMRpH*CLdz%Q8S8;mL@XJyG|oPeaGGNk8lr_&@5A-6MNV!N|g=grx3k~j+8IOIQGwm zioU)%ghIvjT6%+f(d%y?V|hC|P~C1)0q?U$)c5Jv1LCYI#F;-4-}1fyeZF<3U5Yjl z_pVP7-_*B9#eeFac1;9BWy*=Il$azKju-EeGr`}_3`?OIIXs68j7W1*Ed?$P`7(Kb zy!U&Qm$P{abIy~+*BXvjgUPP7#I5XV;FESg>3OOKWUmSQ~~~1@6wT~0_J%de>cnpDB)fr zFbo7p)-xNs>ws|`R@9Rd5dg9KO}e)B04n8%OQm^bK&tv;of_x0gc5!P+MH;B_FtLa z25Xbh9>1l!O|$`Ok{-mSi`y_@=5%!`b{$@BkzY`>oCbO7*E9d^)Iz0l%Cx9t4Qdjh zr96FQ0MUl}x_ptIL_|U+djWT6&~E=t3YGO4q!3H(Flj!6Y@^$zPFYSPcCosXpI0W4 zXx?ZeE6)2E%l)F0$Q?u~&njBaM)o2hNq+;HSDomD)4gt2x+X-W@NAP*wHjSA`a|$N zvJhRq@`9WCWHNdhJlgq?#ubS^7FMOE2*J&Jf#e%}Dez{Y!NnH$(>a&4qu447A(obj z>K>GW8CQu1iAE*-m6Fyc;jIFn0P_FbZL5GsVUp{eeHHvppLp@|eiiPk(+zM50-V0g zv+(6%1(-$NE#UfF3KHCIN#R9Ba8;N_qW5MlG;mDm2p8wT8IbuIg+0u&hBB+#$@!4< z!%o{Rv=CCt?ojPn6+_Kk{ir^g5^(Bg?oYNXgl9}PH;n!k1N)qx;bXl9ymwSH5mXoe zLgOppDmJs=wd-$tFti5qf;8nXHMT+M)lQ22>ov#`u1XIR7=>(;YR|RMNa#A<{4Z^` z34P1^+qKW%hr+M>Hc;*kp$O5OwE3D56!?Dd5ZFeLm}Dw_}u#~d~Q6E2i^hid?WVq;OD;DC071? zP!93=`?EX`M&e96A05X$gU%M0*E`s6BgLESE{*5QJK%4So{xsV>-_klk&BMq3Da}9 zosCE{`L0S`OGhsmh^BujB%{QcUH31J@koG_{=Tki3|i|+GrZIP4gGpB@MAD38?ibO zJ9S2tq9qquIp>c6emj&CZ`bGH_xBW&*PEN5QQ9`i#x@7?cV0X^ajY11t1Ax+NYA0v z(+BM6!U~ez>`-t5Aa6mpWmf|=d&i_aduzZ+t=E`%z6J#N0*2SKYru+x+kQ@@ z23lTE$n6DI16kAV!>ocT@c$F5_%9!OuSb*v>Q^dYIWv$&5pzh=61r zl$BJ-DXcxk!IBO{m+hXX1*OB6f3Doz(J3I}lcD<{#|h;UG30aC(d6boyrjYozm?iy%aio?o-lQiyg0hii`A3}p z9348Wch=}Z{ok30*gM-%#Zz5UC+|k=Z_`S-K~jT^cY4n&`IRD(OS%7sZ(@H@BYAAb z+XS?go=Y@&#vc(goGJXYW(tXHdU_N-AwXs(@$Rc4?lTBH2t2r(3gQieSH$jP|6jVL z;UAei;AIH?`n0M5UW{u|o^&sQhkrD)0)mU-Dw#~|eW4QAv~~XR$F2mPjyV2jBUl2T zUjLWt7GI2WH6yiL^VlPPw&dvD@w55>&X&sm?tZXooS39Zo_w3H;d>lAAgZv6r>v&(zqgv&FUo>|XkyTx| z#J_??#4H^!pnH1}-S)q*E=jY1EN6Z^OmUb);nn;mWb*hqabDn+(2YrSEJ!V%|K2cC z52%)lkLpF7RZZW=8`{uH1*LlcRV{k#VDc?lD<2ufX}c+j`=g1nYaJnv;^6N(QM4&} zAzXS#=+cROB4Z0r4$I{0p+of(LHaf9>FRrNc-^86_kb>TE6{WT!w)k$U7TaH+EeWo z!}EhW5B!z~bb~vg&oS?`Za7=nD7Vatb5k_iw(Iikpl9>w#EK*4cWidO@J-5vzF@Ut z{U^ELSWe0ob~G0}6VLg(Dd&J#lvN7B#ca?vRkU`g!}kIP0={{MJgBQ%NjVc%46^Tt zxl8PtF*nH1LgeiKx!cDyPTgDt);Ae4m6Ti9$ET*b5w;EVHw2#k7qtbq@U}a?m$*atV2Jyb+sVTt+W+wTY>5zU^#uu&9jI z0wSI!aqWDC`!O}e5ByF{p~{fAUoCLXRxXls{w&@{nrrLO{kqtSn4(szXwTOoQIBHt z1A3gN6J*_J5Kcswt?X7d-)cc_j!od^Xd-l26C6kk=R=M3_q^7Ma-jZR@mwOW8Vrow zhUhKpApbTAXI@GJ_@71s3AdZz>V>0+>N?GE?S7^A?b9ugCR${eqJn+wkvn}_iY?IV z5Wm3V)C|*0iM#%vF_(Ys{g>;H8-beeFUPP`Jy;&ThzfsK4bME9Y*XCwVd?W@t+M1+ z_%7b6oSxDOotgo6%xYReCMxr|HRfjx_)a}(JJ|uQ8Ud-_6MEpJulm;xs$sZUE&Pqb zV-nmejVL;@XMmty&S)eT^8|h$nU*VCgS)nb3d-`^kk5GWi?8|)XfHkh7Q=WbJhB1JuASkaQU$s`wV1fzEvwY*$q`m!Qb~+t#FT2Qk8zD38^Pv3#{tz$NrB@W-guy z^ogqAi-Oe*3XgLiQt6*Vmy!~lPBJYZai?!T{ykejZ){12BvR)QU1oU{8P0uL*;(!| zKb*mRPP2_{k|}gX(f>HxRm^ERshPY;Jb-LAdVF`WM~s0nzoxpV3AtJ@5w>Rl;ytlF z?(ziZ4=*&mu>Y=$F7LgQ{Qfc-G6UaGd^u7KS2oi)@BgWSPLa~nYhv~A=9?04XgB7d z%W~OK*|kE?QSwM>({{}Fp|vLr?f?dn?zGjv9kAi<7QGkSf%D@|gmK!faH4cC_9@=u zSaQo!d;Ql6%m;3lH_KXpo89r?#mg2r*?;P#%_ZFTZTRS(cG(U%xmPs0~yizK?_HMn;3!NbSj@!oOftsK+wZO9ZR z{pf4G1-B;zgR+R%L2tcLqi%i%j=j1YdatYs%-=G-`oP+YSoQL0O7dpW$+or5XZ_1) zYdS6Js?92*ebVE7?A!|GV&wf4_gO^myJxMYYUU8J<)iPtbJK{}L9uV=)C3YbJlpSs z^IQvhCz?}&dQn603lE!L?WlX1LU1;}9>si|zROKefu8sfJARhQMwHntekWW4k?46N z=~J>nKx1o0_n0yr4ryMkv=JA=BUi7x;eX39zkS+H9?v)JzYm+-+=c0Sc*+{Z-mlSh)F|_Z(|0Y%$jE1i3YV z+}Jse&!Tz2Es!ukGMa%zes2?M{7yzgfT$?xq*zz;Lku!Ezqq$M z9F4kM&YNnNMIa$5124IvBqWz-@L86q9`!CgkJ2@2L*@L|vgfq%p4e?H-rId1Bsk`1 zbI)wSDR1tp6{hnLrWhnU)a!tl-qME)ZUKHexy^<$KOzhc@YXXTT?unQ0fw0ieg63bjWt(Oj+Z_p_#=RQpFH(W3^8 z1bn$OLYK13;K-i*n+q%DK=wJmd-hue1WE?js%hf;>8-h7Uj^I?D>Pj6=EeC~Qb~3< zMSRX&A^KR4b1K|Nj;%f`3C_LoS6xR|lZ7Rym|IA3tQGzJyo`xU4U4#Tx zbm{l33Q)Xu)I_XQKC&I5bdJ4JjOHT?Q)2BfXYKk1_c!7}be&Eno43Ch36{hUjTp}W znS9uDfq@NRtu>l^Ni+kea{P}yd)9`!=Nt2M373$Y%#(YLnyaYx3}2tklSLFd_?wL5 z?=*5ete~`(7(s8ySniNvzxZpb`@F65b!h4BsW%UIbCErP_LHM^mdGgjFg|575o}51 z_2}`uCf98(w3DzL(ue8H46UnRUB9*YI7ba64Ypod5~~H96=MC;=~{@9-I$>K5A(?* zcty;Q*1-`Sz4MZ>wZLXsY+3WK1|CLzKguCc13b|&eN#`Xp^Gl{`0aaDP+}`)Tll^b ztj2#=KE8-Qr`bKe8;K=A;&y?B6t~}A64zh%AIyik|48rp^5dN5#DnT)qAZ~6E}9=( zNCAQ~7CJ#&@gP6H$a>Ez3J9xoBGU~TK=^K*Vva`xjG5)VhVllu{j#O-6+t7kikoUY z#T#Z~va(wHpS_?F4$)$ao;o2(vW0+kwmz zrN7uYjUw@sjn-n}8B|iZE^{37CSUVuCFTa;KKw+`qaV>r=uDwOHDlxwS{Yqrh;qgI z;KIySX1jS5YC}8r4rWmDz$fm>mpJc#F+P=Ca2WL*X`{F%gSqI>_vdckYDIr&##}A1 z-!%W!N7L=?R1}sxVn_GJACzm$yR81p2O*MMANtNzL$JyLhZSEVM7vQu`496pBZ#dI zQa^NoEop<>uzU|7!e>d0BfY@MFQI#hs2}d|&rr}0^h1O7bGbCUA8)tR%Qi6@0H?~R zKqY6KKbODyGsX<>xfot+9pL(f;&;I#OnJT#`#dd~{7E>VHc!(&w-~UR@98Yd#N7YC zj9W``sZcewE4b~2eRD!dVK(k%;FIrvBIH6F5QKVOIsc~@Y;AK@g(n9=`peQ}OV<>1 zteCyI%d-l{Hz-rKXtp8txL5jH*A-ZvAujJe)&&BS*?Rm}deNeAN?_sNImE|x?L}nd z3L2yBpu6F=ij2(Ki@|;wQO|HfjL-t2A3FM%A$bNFkN?t_6PrLZW_&HO34_=ZkoVHI zup4po^B&8iXhsMPe(h(dLgyQVMB}&cZB6+Pt23t`GBG#`#E&9CH;*XQ}Y6eGzKYUWNO;Gp9 zm_f4*^T}>hER3ku0>M`*i_1B=n8!J+)8^Fxn$_xi7nHF-V8G&bvv>mt%5w3Ta5lgW zZ{CW?MeMb+Y-R4oT#iqQKQ%0I1}f~NU^>h1S|BAkdPDndJLo{BZtCO^i2ut-xo0^K z6qH3iZ7;UKcm3sC(as&{j|htmOvE144Ev>b%S+&6>=@}6Jq52-f2~PX_CQ#Z<9YS6 zBFIm3s0qr;N6)y1>Q=wCA^ushKtl)Y$JB`E$-#4o6OSBe5BMjM`0vUS+ZXY3SE{fq zZ+{xqInJx8p2s}akeAnWb*ItW=t(aYqAA2xI~UWgjeTp~;^B{ZhtP~gXeA}~13cY0 z{I0s!ftX0GWekHF5L4H5)UHGYI*i_{4_Hq}(VSJ14^A4PvqZMnQnnL8tM=D;(}O}N z{d~(mz69W>mp^?7=87>KA1^+s)(8~I1*#cr*ehhpHBqgGxrDk5dNSMXaPp$$xqx&U-yGfP}!gCNRjIRpYdu&_0l5HH?aOVbG8c(tO&2ik7F-wP%^n*R41&k5&HR> zc7n57@(TmSP8bY3vVKFW6Rg$Fn6lyX`d?$Gp%34?pm3?GbFO<3nv-5|)alKF>xHQC zcHI@2E!q4}|HC?<9xL0^{2NedC#Ny_aRUnXT)gF%)**ns`_i=ED$HelK76#W09iFY zWW7_9kQkb7Iiia_%z|t+moDS`((OkHAF#K}ap>xcCc`mwZJXh=_0t(7T+K(cp)`+} zBrT4v-dscvS29*4#ugF9sfSO*Bo>j*-Kovuym=%ackuD7|13(aJXLeRIE})|zY;Mr zjH4h>OjTGIL>=R&pZ_iHLDx+jpS{QX$n>GFmwwDuqef2ms;#5BDEejcZ&L+J<9!q8$zJfz#s1dJrx`A=g6}iMb^_9<8@4{W z6l-$#fUKV+*~z#bXs!^tNg~z;L+ctn7m3S(ON*lO(c(v>Xk^>Po$(SxUD*Yu|9pa} zio!?Tl|Epa-zlo3{smSNtgOjD$HEB`$%EvoRPaf-cEu+>2a2OA62jH;fhH&1DrL78 z7M9hU?xHa;qAcfCZCHg`zP!)RK5v07abNIw)dDy__azzAt_A5cGusqRUFfOUWzH`a zqiFewS&Y=fag<9uz)1RU6mwok&z@BrMn@}^|9E!vBRU21-z%&=$Sl!Ytn6z$vTqrC z`ysdyiR??z-w&-p3u!BtYZA-RqON$tS>^&{C|=quznX?NQp~8{NkpN`D;y8hTb%Lq z$fB?{*8z-qTYCdBcfoD&zSsu#kWANqRuIJA-a=PFW=+BrFo~j~7%Ij7s5dfLW03}h zP2!57rRmV&rlAt5kpY@6S$=jS8BoFB^2OgS1K#GPMva80!;!}Fg{t^8_$x9w?{qd5 zjy*4Q`^b!Yrn|%aA`uBd6Brybt`-LdFR53A&O}2Mt^Ymd8=i>&96{PcB?lC3&g3+@ z{SMh{eW1wvrGSoU+pv}}nt?PuXFj=(8|WOad>~f|fSGXn*_S8$p*Znzf80PAYPvCD z`CZ5xUAt{`LO-h;zKBPcUeaHNWLMR%Rc_e7qmoUmJFoypKmNGLypK71LCrV+ZS*4d zi8Z4-ykFGQCKLA;oJPTtR(siUn7g_q+Ojq#78Brl2&T`|i83C`z4 zJCXSyZTCWZ^DEA))$7;9H0Q&P2N9jlWIpuCFo{^;-o(lGPfojTi;aT(IZr zaB#pm3FJ{F-Tn^eL&bO~zn7%L9NP_})OX2Xm1#I??iq(YBBm^|$3G%JvzKQHCCo5q zVEZ_enhPZMg!AXm`9o}IC2{4Ya9CiW8d|7`fsvfv)03Tv5X9wI|N252_LGqR`8$;a z#-`+svsE}BvlXYmeK-LBCMFm-Kde9pBbV0^xh;6T8tj{qz5o&$B}z&;4d7{6=8+!V ziuAizAJef6p#z78y!xqOM4wX>_0D|=O|$K1JDeUs)Fb?=TDv{ymLNNgD{m*_pq_Xx z#MF%9^n{i!Ua3Q@)z$wS?@Js|Ki)4BEs2VXe^i7ba0J^;u0lJ+pah`WFB0*gn2KzJ2ng2L`h&7 zp%TpYAQ`wTFY5ANOo0H6z2M>o{Qk{3a_|l$0VzMUKYo`4&W1C#(|JkQ`{&C-YMThe zy8nKu^~J#rp>vYkr7>W9&uhL>_ZzejPR*pAjez?nBk~g=1fETZ|GLke04yagt)pKO zpc6f_FvU4@jx(>grW#V<$@;(uZ)GY-xL=fFQBHxy?!p?<%`ZShY0Aw8mWa4tu0&}* z1o}Mq+s@Qf0sFI#3Q3<~NYHlQ9euqDgB#UR;?rAj!niEeuCd@dAjM`9rt zt7-nUpbpl5p`+5`y7&sUgA$D!yr<$2GJO#051}A zdgqr0j?Rt}oSqT8bbS!A z!gqYdVmMb|+igLZpAPEE)^*!T>2U2vckYaS8kjOhWoFnWgP+|;sbsAz$Fo2*1N_&q^pv-~!5}%NgI-fb`Q+eL>7NY^gR$bt!Matu;0; zi~2cGp|)}Rx-bZ_!@C=w(=ngLgTvNR~ZkiDG7V18dgo}-_#?E^DY&lgw;rDi1v1LN(o}z89r8XAs72k{;3QN zVt?LUQ3?WuAQb)f*f(K?C-9WH@m%OiFtmL+F&lmm3$J?}JO1Ct4$0AmR95HR_sT^Qu;u9BN%7bFV zi?e}y`C!$MlG8<70GmV4O(pE>;h!Si{Vd6GP?<20PuW|Au7alFHT?S{XUCPE!LSU` zDc#TNoVr2dHnjy*)SzeXc3()_29WDZ{cZn0qbSdJlIO^)akLXU`*YoB3?&qO#mz>zVgA`=HqJ@%Y3xD1C?`t-cdH&bDYnlUN zlVgU3q`C0kPLGaO4EIWnh8!J^W`Ws%^~cPGGH{>HPP)!E9pb{QiL+KxfIWCcDk~`g zf;71Py>NDfjra>i*M0^7@j<0QV-}BzM#RI2UdwUc%V{9{+jGl$ zItSc*rjz)8W`p|fQua@yROkzexhkJs1sgxUPD9x!@M#|sI9IKL1Lyj+zT_=XDHXMC z>{$d?{u>V!aNoW-!p|eUxEa|e={AQg3?ZqKozsCfboF~oAka=L_R1l6S{ zzE=|)L|i-#-vm$fp&ObjYXOs8sD+~%jGM<_u}Y%(N8oS zvB1eopK>%@WU_VYRvPoZEk+AlMSk=k(J>CnV`1NXzZhd`D_D{#&2npfL)!M z*<2zPmR?ecShB?;9ae3EKS>dY*OF7T3D09M<52_A1)R$WcsjM?Z-AmhKK4oknZtD| zB1_6WZ?JqY6My3I7hobtI-!fdC-yhPIH)t262W^GlUC`w&E8w! zY-UBrmb3)Zt~APJw`;(>Ls54(Y78BTVUc{Rxr9hgh9(!$EF+yw5?bNfImGa7dhX=8 zDKx?Ba>-|92)!&Sr)xdcin%?{2&VU;mF z`Jxd>Q-LRQIzbzFX@wr_%7(+(bzbHhC5d2p;PXe(IuqWriJWoa$pztG`wSa#`JfUP z5i|6t5E>;oe>j>HLEM%5b#gb0fnZzhQ)@&q_zKqYlrI(o%F~@WvQZ2?o4{OUUkrbF zsi*WCi{PoGuYAH_A^f9VyfU#+0K`=XJEtHY4BNtj*ERDX%ISvXUQZ6}X&pV4L6r?Z z$*Mk%mdAr)incLVttnLTj~;$_=m}3Rz1FdF3jz-6n`2fAAwcEfG2tN-2{URJjn?+! z;pAqeLewz+y}RVL{=GO4!r#ZBhL9|nNf)!DR?Y-%8}=o#qJCK9+aQ@~SON0DPorlX zw!qKjiEwAsA~an1(I6??2JF+Z%Qp7S$p7+T?@#VwR3aNMpw2OhhSh?V)EjNO7$=oLj-K z4F^r50XaZhgknG9-{;idlthEFnCJH{rd9QJCfGk6ZGVZ+HR)sw!~_4~zV9_xwK9|d z1b0(p&19ls!2ink{QDXBdFUxlZki3xdM65|e&>Mg=_o6G>O8pcC7+v4BOkK9l!UU- z6hgb31X(^k{@icr+-t!7%KfTi)t@J-A+wL*M<78LJXtZ?uZo@qWpDa>`hj@P@PM7k z>%lfCH%X5&Rb%deZf6x4Fum5R6 z*LVMVncCE#$0Hnhv=t@jM9Zi`L1z|W`lvLi(AY=9ypim?4E5d1WwA6;ukxL!MH-8_sw_-s94c5WMFQ202NWk zXlWT(6%2>j;2hd=``53ZewM;9(x>__B1=F$=I%*(#$qVoe;3*wg?)vm1{xKkFo$n7 SsUxo<7YL"]