Alpaca_with_LoRA.ipynb

Alpaca_with_LoRA_better_hyperparams.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "df25ccd3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install transformers datasets accelerate peft axolotl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a5ccac1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "if not os.environ.get('TRANSFORMERS_CACHE'):\n",
    "    os.environ['TRANSFORMERS_CACHE'] = '/raid/transformers_cache'\n",
    "    \n",
    "os.environ['CUDA_VISIBLE_DEVICES'] = \"6\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "2221804b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.10/dist-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import copy\n",
    "from dataclasses import dataclass, field\n",
    "from typing import Dict, Optional, Sequence\n",
    "import warnings\n",
    "\n",
    "from tqdm import tqdm\n",
    "from pdb import set_trace\n",
    "\n",
    "import torch\n",
    "import numpy as np\n",
    "import transformers\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
    "from matplotlib import pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a51d944d",
   "metadata": {},
   "source": [
    "Let's grab the dataset straight from `datasets`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4dd95b68",
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset, DatasetDict\n",
    "dataset = load_dataset(\"tatsu-lab/alpaca\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "549878ac",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:04<00:00,  2.45s/it]\n"
     ]
    }
   ],
   "source": [
    "model = AutoModelForCausalLM.from_pretrained('meta-llama/Llama-2-7b-hf')\n",
    "tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8d6ddb3d",
   "metadata": {},
   "outputs": [],
   "source": [
    "datasets = dataset['train'].train_test_split(test_size=2002, seed=42)\n",
    "datasets = DatasetDict({'train': datasets['train'], 'valid': datasets['test']})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "43b496fa",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embeding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details  about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc\n"
     ]
    }
   ],
   "source": [
    "# code from Stanford Alpaca https://github.com/tatsu-lab/stanford_alpaca\n",
    "\n",
    "PROMPT_DICT = {\n",
    "    \"prompt_input\": (\n",
    "        \"Below is an instruction that describes a task, paired with an input that provides further context. \"\n",
    "        \"Write a response that appropriately completes the request.\\n\\n\"\n",
    "        \"### Instruction:\\n{instruction}\\n\\n### Input:\\n{input}\\n\\n### Response:\"\n",
    "    ),\n",
    "    \"prompt_no_input\": (\n",
    "        \"Below is an instruction that describes a task. \"\n",
    "        \"Write a response that appropriately completes the request.\\n\\n\"\n",
    "        \"### Instruction:\\n{instruction}\\n\\n### Response:\"\n",
    "    ),\n",
    "}\n",
    "\n",
    "def smart_tokenizer_and_embedding_resize(\n",
    "    special_tokens_dict: Dict,\n",
    "    tokenizer: transformers.PreTrainedTokenizer,\n",
    "    model: transformers.PreTrainedModel,\n",
    "):\n",
    "    \"\"\"Resize tokenizer and embedding.\n",
    "\n",
    "    Note: This is the unoptimized version that may make your embedding size not be divisible by 64.\n",
    "    \"\"\"\n",
    "    num_new_tokens = tokenizer.add_special_tokens(special_tokens_dict)\n",
    "    model.resize_token_embeddings(len(tokenizer))\n",
    "\n",
    "    if num_new_tokens > 0:\n",
    "        input_embeddings = model.get_input_embeddings().weight.data\n",
    "        output_embeddings = model.get_output_embeddings().weight.data\n",
    "\n",
    "        input_embeddings_avg = input_embeddings[:-num_new_tokens].mean(dim=0, keepdim=True)\n",
    "        output_embeddings_avg = output_embeddings[:-num_new_tokens].mean(dim=0, keepdim=True)\n",
    "\n",
    "        input_embeddings[-num_new_tokens:] = input_embeddings_avg\n",
    "        output_embeddings[-num_new_tokens:] = output_embeddings_avg\n",
    "        \n",
    "special_tokens_dict = dict()\n",
    "special_tokens_dict[\"pad_token\"] = \"[PAD]\"\n",
    "\n",
    "smart_tokenizer_and_embedding_resize(special_tokens_dict, tokenizer, model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ca648e3d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1, 32000]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.encode('[PAD]')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5f3b7326",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[PAD]'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.decode([32000])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "edfd9e7b",
   "metadata": {},
   "outputs": [],
   "source": [
    "def process_example(example):\n",
    "    template = PROMPT_DICT[\"prompt_input\"]\n",
    "    if not example['input']:\n",
    "        template = PROMPT_DICT[\"prompt_no_input\"] + '\\n\\n'\n",
    "\n",
    "    prompt = template.format_map(example)\n",
    "    prompt_toks = tokenizer(prompt)['input_ids']\n",
    "    input_ids = tokenizer(prompt + example[\"output\"] + tokenizer.eos_token, return_tensors='pt')['input_ids'][0]\n",
    "    labels = input_ids.clone().detach()\n",
    "    labels[:len(prompt_toks)] = -100 # loss will not be calculated for labels set to -100\n",
    "    return input_ids, labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "36c9cd51",
   "metadata": {},
   "outputs": [],
   "source": [
    "class SupervisedDataset(Dataset):\n",
    "    def __init__(self, dataset):\n",
    "        super().__init__()\n",
    "        discarded_examples_count = 0\n",
    "        self.examples = []\n",
    "        for example in tqdm(dataset):\n",
    "            input_ids, labels = process_example(example)\n",
    "            if input_ids.shape[0] > 512:\n",
    "                discarded_examples_count += 1\n",
    "            else:\n",
    "                self.examples.append((input_ids, labels))\n",
    "        print(f'Discarded {discarded_examples_count} examples due to length > 512.')\n",
    "            \n",
    "    def __getitem__(self, idx):\n",
    "        return {\"input_ids\": self.examples[idx][0], \"labels\": self.examples[idx][1]}\n",
    "    def __len__(self):\n",
    "        return len(self.examples)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4a4bf62b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50000/50000 [00:37<00:00, 1330.85it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Discarded 94 examples due to length > 512.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2002/2002 [00:01<00:00, 1132.66it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Discarded 3 examples due to length > 512.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "train_ds = SupervisedDataset(datasets['train'])\n",
    "valid_ds = SupervisedDataset(datasets['valid'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5e3628de",
   "metadata": {},
   "outputs": [],
   "source": [
    "def collate_fn(examples):\n",
    "    input_ids, labels = tuple([example[key] for example in examples] for key in (\"input_ids\", \"labels\"))\n",
    "    input_ids = torch.nn.utils.rnn.pad_sequence(\n",
    "        input_ids, batch_first=True, padding_value=tokenizer.pad_token_id\n",
    "    )\n",
    "    labels = torch.nn.utils.rnn.pad_sequence(labels, batch_first=True, padding_value=-100)\n",
    "    return dict(\n",
    "        input_ids=input_ids,\n",
    "        labels=labels,\n",
    "        attention_mask=input_ids.ne(tokenizer.pad_token_id)\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "436ff501",
   "metadata": {},
   "outputs": [],
   "source": [
    "from peft import LoraConfig, TaskType\n",
    "from peft import get_peft_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4f19f221",
   "metadata": {},
   "outputs": [],
   "source": [
    "# source: https://github.com/OpenAccess-AI-Collective/axolotl/blob/bde3c5a478100fd205822a139ec1c9cade73c9c1/src/axolotl/utils/models.py#L465\n",
    "\n",
    "def find_all_linear_names(model):\n",
    "    cls =torch.nn.Linear\n",
    "    lora_module_names = set()\n",
    "    for name, module in model.named_modules():\n",
    "        if isinstance(module, cls):\n",
    "            names = name.split(\".\")\n",
    "            lora_module_names.add(names[0] if len(names) == 1 else names[-1])\n",
    "\n",
    "    if \"lm_head\" in lora_module_names:  # needed for 16-bit\n",
    "        lora_module_names.remove(\"lm_head\")\n",
    "\n",
    "    return list(lora_module_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "1a959720",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['gate_proj', 'v_proj', 'q_proj', 'k_proj', 'down_proj', 'up_proj', 'o_proj']"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "find_all_linear_names(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "1644c00e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "trainable params: 79,953,920 || all params: 6,818,377,728 || trainable%: 1.1726237998177387\n"
     ]
    }
   ],
   "source": [
    "peft_config = LoraConfig(\n",
    "    inference_mode=False,\n",
    "    r=32,\n",
    "    lora_alpha=16,\n",
    "    lora_dropout=0.05,\n",
    "    target_modules=find_all_linear_names(model)\n",
    ")\n",
    "\n",
    "model = get_peft_model(model, peft_config)\n",
    "model.print_trainable_parameters()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f6f21cfb",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_batch_size = 2\n",
    "lr = 2e-4\n",
    "num_epochs = 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "c07a2e76",
   "metadata": {},
   "outputs": [],
   "source": [
    "from accelerate import Accelerator\n",
    "\n",
    "accelerator = Accelerator(mixed_precision='bf16', gradient_accumulation_steps=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "bc81f95f",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dl = DataLoader(train_ds, batch_size=train_batch_size, shuffle=True, collate_fn=collate_fn)\n",
    "valid_dl = DataLoader(valid_ds, batch_size=2*train_batch_size, shuffle=False, collate_fn=collate_fn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "aa58ff68",
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = torch.optim.AdamW(model.parameters(), lr=lr, weight_decay=0)\n",
    "lr_scheduler = torch.optim.lr_scheduler.OneCycleLR(\n",
    "    optimizer,\n",
    "    lr,\n",
    "    epochs=num_epochs,\n",
    "    steps_per_epoch=len(train_dl)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "eb6dd55a",
   "metadata": {},
   "outputs": [],
   "source": [
    "model, train_dl, valid_dl, optimizer, lr_scheduler = accelerator.prepare(\n",
    "    model, train_dl, valid_dl, optimizer, lr_scheduler\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "4e622a19",
   "metadata": {},
   "outputs": [],
   "source": [
    "lrs = []\n",
    "train_losses = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "6a88692a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Epoch:  0\tTrain loss: 1.03:  55%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████                                                                                                                                         | 13826/24953 [50:23<39:02,  4.75it/s]IOPub data rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_data_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "                                                                                                                                                                                                                                                                                                                                                                                          \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train loss: 1.04\tval loss: 1.08\ttoken accuracy: 0.00\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Epoch:  1\tTrain loss: 1.02:  38%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                                                                                                                                              | 9542/24953 [36:53<59:52,  4.29it/s]IOPub data rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_data_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "                                                                                                                                                                                                                                                                                                                                                                                          \r"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train loss: 0.98\tval loss: 1.08\ttoken accuracy: 0.00\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Epoch:  2\tTrain loss: 0.68:  65%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎                                                                                                         | 16303/24953 [1:01:40<32:52,  4.38it/s]IOPub data rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_data_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_data_rate_limit=1000000.0 (bytes/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 500/500 [01:34<00:00,  5.24it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train loss: 0.67\tval loss: 1.14\ttoken accuracy: 0.00\n",
      "CPU times: user 4h 41min 51s, sys: 5min 40s, total: 4h 47min 31s\n",
      "Wall time: 4h 46min 49s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                                                                                                                                                                                                                                                                                                                          "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train loss: 0.67\tval loss: 1.14\ttoken accuracy: 0.00\n",
      "CPU times: user 4h 41min 51s, sys: 5min 40s, total: 4h 47min 31s\n",
      "Wall time: 4h 46min 49s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": []
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "for i in range(num_epochs):\n",
    "    model.train()\n",
    "    pbar = tqdm(train_dl, leave=False)\n",
    "    for batch in pbar:\n",
    "        outputs = model(**batch)\n",
    "        loss = outputs.loss\n",
    "\n",
    "        train_losses.append(loss.item())\n",
    "        lrs.append(optimizer.param_groups[0]['lr'])\n",
    "\n",
    "        accelerator.backward(loss)\n",
    "        \n",
    "        optimizer.step()\n",
    "        optimizer.zero_grad()\n",
    "        lr_scheduler.step()\n",
    "        pbar.set_description(f'Epoch: {i:2d}\\tTrain loss: {np.mean(train_losses[-20:]) :.2f}')\n",
    "\n",
    "    model.eval()\n",
    "    preds = []\n",
    "    labels = []\n",
    "    val_losses = []\n",
    "    for batch in tqdm(valid_dl, leave=False):\n",
    "        with torch.no_grad():\n",
    "            outputs = model(**batch)\n",
    "\n",
    "        logits = outputs.logits\n",
    "        val_losses.append(outputs.loss.item())\n",
    "\n",
    "        preds.append(outputs.logits.argmax(-1).cpu().detach())\n",
    "        labels.append(batch['labels'].cpu().detach())\n",
    "\n",
    "    hits = 0\n",
    "    chances = 0\n",
    "    for p, l in zip(preds, labels):\n",
    "        hits += (p == l).sum().item()\n",
    "        chances += (l != -100).sum().item()\n",
    "    print(f'Train loss: {np.mean(train_losses):3.02f}\\tval loss: {np.mean(val_losses):3.02f}\\ttoken accuracy: {hits/chances:3.02f}')\n",
    "    train_losses = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "673395f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7fc92c0f84f0>]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7fc92c0f84f0>]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAk8AAAGdCAYAAAAL2ZfXAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAABv+ElEQVR4nO3de1xUdfoH8M9cmBlAYUDkpoCoIIp4D6K81EphWUnbprKsqVlWa1utW6tu66Vf7Wrabm2uZbWV7bZp2kVbvEV4V0TDGxdFUMwrECAzoFxnnt8f6NQkXsaAA8Pn/XqdF3HOMzOfMxDzeM73fI9KRAREREREdEPUSgcgIiIiakvYPBERERE5gM0TERERkQPYPBERERE5gM0TERERkQPYPBERERE5gM0TERERkQPYPBERERE5QKt0AGdjtVpx9uxZdOzYESqVSuk4REREdANEBBUVFQgMDIRafe1jS2yemtjZs2cRFBSkdAwiIiK6CadOnULXrl2vWcPmqYl17NgRQMOb7+HhoXAaIiIiuhFmsxlBQUG2z/FrYfPUxC6fqvPw8GDzRERE1MbcyJAbDhgnIiIicgCbJyIiIiIHsHkiIiIicgCbJyIiIiIHsHkiIiIicgCbJyIiIiIHsHkiIiIicgCbJyIiIiIHsHkiIiIicsBNNU9LlixBt27dYDAYEBMTgz179lyzftWqVYiIiIDBYEBUVBTWrVtnt11EMGfOHAQEBMDV1RVxcXHIy8uzqykrK0NSUhI8PDxgNBoxZcoUVFZW2rZv2bIFY8aMQUBAANzd3TFgwAD897//bZYsRERE1H453Dx9+umnmD59OubOnYt9+/ahf//+iI+PR3FxcaP1u3btQmJiIqZMmYL9+/cjISEBCQkJyMrKstUsXLgQb775JpYuXYr09HS4u7sjPj4e1dXVtpqkpCRkZ2cjJSUFycnJ2LZtG6ZOnWr3Ov369cPnn3+OQ4cOYfLkyXjkkUeQnJzc5FmIiIioHRMHRUdHy7Rp02zfWywWCQwMlPnz5zdaP3bsWBk9erTdupiYGHniiSdERMRqtYq/v78sWrTItr28vFz0er0sX75cRERycnIEgOzdu9dWs379elGpVHLmzJmrZr333ntl8uTJTZrlekwmkwAQk8l0Q/VERESkPEc+vx26MXBtbS0yMjIwa9Ys2zq1Wo24uDikpaU1+pi0tDRMnz7dbl18fDxWr14NACgoKEBhYSHi4uJs2z09PRETE4O0tDSMHz8eaWlpMBqNGDJkiK0mLi4OarUa6enpePDBBxt9bZPJhN69ezdplp+qqalBTU2N7Xuz2dxoFqKmVlNvwcFTJhwpNKPIXI3qOiu0GhUMWg1cdRq46zTo3FGPzh0N8O2oh5+HATothzkSEf1cDjVPJSUlsFgs8PPzs1vv5+eHI0eONPqYwsLCRusLCwtt2y+vu1aNr6+vfXCtFt7e3raan1q5ciX27t2Ld955p0mz/NT8+fPx0ksvNbqNqDlknjbhg50FSMkpQmVN/Q0/TqNWIcTbDT18O6BH5w7o28UDg4K9EOBpuKG7iBMRUQOHmqe2YvPmzZg8eTLee+89REZGNutrzZo1y+5oltlsRlBQULO+JrVP35VewLyvsrE593vbOp8OevTv6okgbzfoXdSwWARVdRZU11lRWVOH7ytqUHxpqa234njJBRwvuYAUFNmew89Dj8EhXri9pw9GhHdGVy83JXaPiKjNcKh58vHxgUajQVFRkd36oqIi+Pv7N/oYf3//a9Zf/lpUVISAgAC7mgEDBthqfjogvb6+HmVlZVe87tatW3H//ffj9ddfxyOPPNLkWX5Kr9dDr9c3uo2oKYgI/rW9AIu+zkVtvRUatQr39wvAhNgQDAzyglp9/aNGIoIicw3yiyuRX1yBo8WVOHiqHEcKK1BkrsG6zEKsy2w4utrTtwPu7NUZo/sFon9XTx6VIiL6CYcGQOh0OgwePBipqam2dVarFampqYiNjW30MbGxsXb1AJCSkmKrDw0Nhb+/v12N2WxGenq6rSY2Nhbl5eXIyMiw1WzatAlWqxUxMTG2dVu2bMHo0aPx6quv2l2J15RZiFqSuboOT/wnA39Zdxi19VYM7emDlN8PxxvjB2JwiPcNNU4AoFKp4O9pwNAwH0y6PRR/fTAKa58Zhsx5d+PTqbdi+l3hGBLiBbUKyC+uxHvbC5CwZCeGL9qMVzccwdGiimbeUyKiNsTR0egrVqwQvV4vy5Ytk5ycHJk6daoYjUYpLCwUEZEJEybIzJkzbfU7d+4UrVYrr732mhw+fFjmzp0rLi4ukpmZaatZsGCBGI1GWbNmjRw6dEjGjBkjoaGhUlVVZasZNWqUDBw4UNLT02XHjh0SFhYmiYmJtu2bNm0SNzc3mTVrlpw7d862lJaWNnmWa+HVdtRUis3VMuqNbRIyI1nC/rRO/pN2QqxWa7O+ZvmFWkk+eFZ+98k+ifjzegmZkWxbHnprp3yx75RU1dY3awYiIiU48vntcPMkIrJ48WIJDg4WnU4n0dHRsnv3btu2ESNGyMSJE+3qV65cKeHh4aLT6SQyMlLWrl1rt91qtcrs2bPFz89P9Hq9jBw5UnJzc+1qSktLJTExUTp06CAeHh4yefJkqaiosG2fOHGiALhiGTFiRJNnuRY2T9QUTp+/KCMWbpKQGcky+OUUOXDyfItnuFBTJ/87eEYe+2ivdJ+11tZE9X9po8xfd1iKzDf2DwoiorbAkc9vlYiIYoe9nJDZbIanpydMJhM8PDyUjkNtUGllDR5emobjJRfQ1csVH0+JQTcfd0UzFZmrsXLvKSzfcxJnTQ0Txuq0ajw0qCueGN5d8XxERD+XI5/fbJ6aGJsn+jkqa+rx6/d249BpE7oYXfHZU7EI8HRVOpaNxSpIPVyEpVuPYd/JcgCAWgU80D8Q0+/qheBOvFKPiNomNk8KYvNEN8tqFTz5cQa+zimCt7sOq56MRY/OHZSO1SgRwd4T57F06zFsOtJwJaxWrUJidDB+N7InfDsaFE5IROQYNk8KYvNEN+ufm/Lw2tdHodOq8enUWzEw2EvpSDck87QJi77OxbajDfNPubpoMHV4dzx1Rw8YXDQKpyMiujGOfH7zXg1ErcDWo9/jbylHAQCvjOnbZhonAIjq6ol/PxqN5Y/fioHBRlTVWfCP1DzE/X0rNmYXgv8+IyJnw+aJSGGllTX4w8oDEAF+HROMsbe0zRnqY3t0whdP3YYlvx6EQE8DTp+vwhP/ycAjH+xBQckFpeMRETUZNk9EChIR/OnLTJRU1iLcrwPm3NdH6Ug/i0qlwuh+AfjmDyPw9J09odOosT2vBKPe2IZ3th5DvcWqdEQiop+NzRORgj7fdwYbs4vgolHh9XEDnGaMkJtOi+fje+Hr3w/HsDAf1NRbMX/9ETz09i7kFnK2ciJq29g8ESmkuKIaL/0vGwDwXFw4IgM9FU7U9Lr5uOPfj0Zj4a/6oaNBi4OnTbhv8Xb8c1MeLFaOhSKitonNE5FC/rL2MCqq69GvqyeeHNFD6TjNRqVSYeyQIHwzfQTievuhziJ47eujSHx3N86UVykdj4jIYWyeiBSwM78Eaw6chVoF/CUhCpobvMFvW+bnYcB7jwzG3x7uD3edBntOlOGeN7Zh7aFzSkcjInIImyeiFlZTb8Hs1VkAgAm3hiCqq/OdrrsalUqFhwZ3xbpnh6F/kBHm6npM+2QfZnx2CNV1FqXjERHdEDZPRC1s2c4TOF5yAZ076vGH+F5Kx1FESCd3fPZkLKbd2QMqFfDpt6fwy7d24VTZRaWjERFdF5snohZ0/kIt/rk5HwDwx/he8DC4KJxIOS4aNV6Ij8DHU2LQyV2HnHNm3Ld4BzbnFisdjYjomtg8EbWgf27OR0V1PSL8O+KXg7oqHadVuL2nD/73u6HoH2SEqaoOjy7bi398kwcrr8YjolaKzRNRCzlZehH/TjsBAPjTvb3bxSDxGxVodMXKJ27Fb24Nhgjw+jdH8dv/7kNVLcdBEVHrw+aJqIUs+joXdRbBsDAfDA/vrHScVkev1eCVhCgs+lU/6DRqbMguxNh30lBkrlY6GhGRHTZPRC3gaFEFkg+dBQDMuqe3wmlat4eHBOG/j8fA212HzDMmjPnnTmSdMSkdi4jIhs0TUQt4MzUPIsA9ff3RJ9BD6Tit3i3dvLH6t7ejp28HFJqr8fDSNKTkFCkdi4gIAJsnomaXV1SBtZkNE0E+MzJM4TRtR3AnN3z+1G0YFuaDqjoLnvjPt1ix56TSsYiI2DwRNbc3N+VDBIiP9EPvAB51coSnqws+mHQLxg7pCqsAM7/IxJLN+RDhlXhEpBw2T0TNKL/4h7FOPOp0c1w0arz6UD/89o6G+/8t2piLl/6Xw6kMiEgxbJ6ImtHbW45DBLirjx8iA9vPbViamkqlwh9HRWDOfX0AAMt2ncCznx5Abb1V4WRE1B6xeSJqJkXmanx18AwA2I6a0M/z6NBQ/GP8AGjVKvzv4Fk89XEG74lHRC2OzRNRM1m26wTqLILobt4YGOyldBynMWZAF7w/6RbotWqkHinG4//+lg0UEbUoNk9EzaCyph7/3f0dAODx4d0VTuN8RoR3xoeTb4Griwbb80ow+cO9uFhbr3QsImon2DwRNYOVe0/BXF2P7j7uGBnhq3Qcp3RbDx989Gg03HUapB0vxaQP9qKyhg0UETU/Nk9ETazeYsUHOwsAAFOGhULNe9g1m+hQb/znsRh0NGix50QZJryfjorqOqVjEZGTY/NE1MS+zinC6fNV8HbX4aFBXZWO4/QGBXvhk8duhaerC/afLMejy3gKj4iaF5snoib277QTAICkmGAYXDTKhmknorp64r+XjkDtPXGeg8iJqFmxeSJqQnlFFdh9vAwatQq/jglWOk670reLp20M1M78Uvz2v/s4DxQRNQs2T0RN6ONLV9jF9fZFgKerwmnan0HBXnh/0i0wuKix6Ugxnl2xH/UWNlBE1LRuqnlasmQJunXrBoPBgJiYGOzZs+ea9atWrUJERAQMBgOioqKwbt06u+0igjlz5iAgIACurq6Ii4tDXl6eXU1ZWRmSkpLg4eEBo9GIKVOmoLKy0ra9uroakyZNQlRUFLRaLRISEq7IMWnSJKhUqiuWyMhIW828efOu2B4REXET7xK1N5U19fh8X8OkmI/EdlM2TDt2a/dOeHfCEOg0aqzPKsTzqw7yVi5E1KQcbp4+/fRTTJ8+HXPnzsW+ffvQv39/xMfHo7i4uNH6Xbt2ITExEVOmTMH+/fuRkJCAhIQEZGVl2WoWLlyIN998E0uXLkV6ejrc3d0RHx+P6upqW01SUhKys7ORkpKC5ORkbNu2DVOnTrVtt1gscHV1xTPPPIO4uLhGs/zjH//AuXPnbMupU6fg7e2Nhx9+2K4uMjLSrm7Hjh2Ovk3UDq3efwaVNfXo3tkdt/XopHScdm14eGe8lTQIWrUKqw+cxf8l5/BmwkTUdMRB0dHRMm3aNNv3FotFAgMDZf78+Y3Wjx07VkaPHm23LiYmRp544gkREbFareLv7y+LFi2ybS8vLxe9Xi/Lly8XEZGcnBwBIHv37rXVrF+/XlQqlZw5c+aK15w4caKMGTPmuvvy5ZdfikqlkhMnTtjWzZ07V/r373/dx16NyWQSAGIymW76OajtsVqtEv/6VgmZkSzvbz+udBy6ZM2BMxIyI1lCZiTLPzflKR2HiFoxRz6/HTryVFtbi4yMDLsjO2q1GnFxcUhLS2v0MWlpaVccCYqPj7fVFxQUoLCw0K7G09MTMTExtpq0tDQYjUYMGTLEVhMXFwe1Wo309HRHdsHO+++/j7i4OISEhNitz8vLQ2BgILp3746kpCScPHnyqs9RU1MDs9lst1D78+1353GksAKuLho8NJjTE7QWD/QPxNz7G24mvGhjLj7de/X/l4mIbpRDzVNJSQksFgv8/Pzs1vv5+aGwsLDRxxQWFl6z/vLX69X4+trP0qzVauHt7X3V172es2fPYv369Xjsscfs1sfExGDZsmXYsGED3n77bRQUFGDYsGGoqKho9Hnmz58PT09P2xIUFHRTeahtW7HnFICGD2tPVxeF09CPTb491HZj5llfZCIlp0jhRETU1rXbq+0++ugjGI3GKwaW33PPPXj44YfRr18/xMfHY926dSgvL8fKlSsbfZ5Zs2bBZDLZllOnTrVAempNKqrrsC7zHABg7C1snlujF+J7YeyQrrAK8PQn+7D3RJnSkYioDXOoefLx8YFGo0FRkf2/3IqKiuDv79/oY/z9/a9Zf/nr9Wp+OiC9vr4eZWVlV33daxERfPDBB5gwYQJ0Ot01a41GI8LDw5Gfn9/odr1eDw8PD7uF2pe1h86hqs6CHp3dMSjYqHQcaoRKpcJfH4zCyAhf1NRbMWXZXuQXN340mYjoehxqnnQ6HQYPHozU1FTbOqvVitTUVMTGxjb6mNjYWLt6AEhJSbHVh4aGwt/f367GbDYjPT3dVhMbG4vy8nJkZGTYajZt2gSr1YqYmBhHdgEAsHXrVuTn52PKlCnXra2srMSxY8cQEBDg8OtQ+7Dy24ajjWOHBEGl4n3sWiutRo1//noQBod4wVxdj8nL9qKkskbpWETUBjl82m769Ol477338NFHH+Hw4cN46qmncOHCBUyePBkA8Mgjj2DWrFm2+meffRYbNmzA3/72Nxw5cgTz5s3Dt99+i6effhpAw78In3vuObzyyiv46quvkJmZiUceeQSBgYG2U2q9e/fGqFGj8Pjjj2PPnj3YuXMnnn76aYwfPx6BgYG218rJycGBAwdQVlYGk8mEAwcO4MCBA1fsw/vvv4+YmBj07dv3im3PP/88tm7dihMnTmDXrl148MEHodFokJiY6OhbRe1AfnEF9p0sh0atwoODuigdh67DVafBuxMGI6STG06VVfE2LkR0c27mcr7FixdLcHCw6HQ6iY6Olt27d9u2jRgxQiZOnGhXv3LlSgkPDxedTieRkZGydu1au+1Wq1Vmz54tfn5+otfrZeTIkZKbm2tXU1paKomJidKhQwfx8PCQyZMnS0VFhV1NSEiIALhi+bHy8nJxdXWVd999t9F9GzdunAQEBIhOp5MuXbrIuHHjJD8//4bfG05V0L78dW2OhMxIlinL9l6/mFqN/OIK6Tdvo4TMSJbffpwhFotV6UhEpDBHPr9VIpw5rimZzWZ4enrCZDJx/JOTq7NYETt/E0oqa/DuhMG4O9Lx8XeknN3HSzHh/XTUWQS/vaMH/jiKdxIgas8c+fxut1fbEf1cW3K/R0llDXw66HBnhO/1H0Ctyq3dO2HBL/sBAN7acoxzQBHRDWPzRHSTPs84DQB4cGAXuGj4v1Jb9NDgrnhmZBgA4MUvs7Arv0ThRETUFvAvPtFNMF2sw6YjDdNn/HIQZxRvy34fF4YxAwJRbxX89pN9OFl6UelIRNTKsXkiugnrs86h1mJFL7+O6B3AsW1tmUqlwqsP9UP/rp4ov1iHx//9LS7U1Csdi4haMTZPRDdh9YEzAIAxAwOvU0ltgcFFg3cmDEHnjnrkFlVg+soDsFp5LQ0RNY7NE5GDzpmqkF7QcHuPB/qzeXIW/p4GvDNhMHQaNTZmF+EfqXlKRyKiVorNE5GDvjpwFiJAdDdvdPVyUzoONaFBwV74y4MNk+f+IzUPG7LOKZyIiFojNk9EDlp94CwAnrJzVg8PCcKjt4cCAKavPIgjhWaFExFRa8PmicgBR4sqcPicGS4aFUZH8X6HzupP90ZgaE8fXKy14PF/fwvTxTqlIxFRK8LmicgBq/c3DBQfEe4Lo5tO4TTUXBpuIjwQwd4N98D7PQeQE9GPsHkiukEigjWXTtkl8JSd0zO66fD2bwZBr1Vj05FiLNmcr3QkImol2DwR3aD9p8pxprwK7joN4nr7KR2HWkBkoCdeTmgYQP73b45ie973CiciotaAzRPRDVp7qOHKq5G9/WBw0SichlrK2CFBGH9LEESAZ5bvx5nyKqUjEZHC2DwR3QCrVbA+s6F5upcDxdudeQ9Eom8XD5y/WIff/ncfauotSkciIgWxeSK6AQdOl+OsqRruOg3u6NVZ6TjUwgwuGrydNBieri44eKocLyfnKB2JiBTE5onoBqy7dMruFzxl124FebvhjfEDoFIBH+8+iS/2nVY6EhEphM0T0XWICNZnFQIARkf5K5yGlHRnL1/87hdhAIAXv8xCfnGlwomISAlsnoiu48Clq+zcdBrc0ctX6TiksGdHhuG2Hp1QVWfB05/sQ3Udxz8RtTdsnoiuY10mr7KjH2jUKrwxbgA6uetwpLCC45+I2iE2T0TXICJYl8lTdmTP18OA18cNAAD8N/2kbRoLImof2DwRXcPB0yaesqNGDQ/vjN/e0QMAMPPzQzhZelHhRETUUtg8EV3D5VN2v4jw5Sk7usL0u8IxOMQLFTX1eHr5PtTWW5WOREQtgM0T0VU0XGXX0DyN5sSY1AitRo03EwfC09UFh06bsHDDEaUjEVELYPNEdBVHCitwqqwKeq0aIzgxJl1FF6MrXnu4PwDgXzsK8E1OkcKJiKi5sXkiuoqvsxs+BIeFdYabTqtwGmrN7urjh8m3dwMAvPDZQRSbq5UNRETNis0T0VV8ndNwld3dkX4KJ6G2YOY9EegT0HD/uz+sOgirVZSORETNhM0TUSNOn7+I7LNmqFXAyAheZUfXp9dq8GbiAOi1amzPK8GyXSeUjkREzYTNE1EjUi6NWxnSzRudOugVTkNtRU/fjvjzfX0AAAvWH8Hhc2aFExFRc2DzRNSIy+Od7u7DU3bkmN/EBGNkhC9qLVY8t+IAb99C5ITYPBH9xPkLtdhzogwAcHcfzipOjlGpVHj1V/3g00GH3KIKvMrpC4icDpsnop/YdKQYFqsgwr8jgju5KR2H2iCfDnosujR9wYc7T2BLbrHCiYioKd1U87RkyRJ069YNBoMBMTEx2LNnzzXrV61ahYiICBgMBkRFRWHdunV220UEc+bMQUBAAFxdXREXF4e8vDy7mrKyMiQlJcHDwwNGoxFTpkxBZWWlbXt1dTUmTZqEqKgoaLVaJCQkXJFjy5YtUKlUVyyFhYU/a//IufxwlR2POtHNu7OXLybd1g0A8PyqQyitrFE2EBE1GYebp08//RTTp0/H3LlzsW/fPvTv3x/x8fEoLm78X1a7du1CYmIipkyZgv379yMhIQEJCQnIysqy1SxcuBBvvvkmli5divT0dLi7uyM+Ph7V1T/MlZKUlITs7GykpKQgOTkZ27Ztw9SpU23bLRYLXF1d8cwzzyAuLu6a+5Cbm4tz587ZFl/fH66mcnT/yLlU11mw7WgJAI53op9v5j0RCPfrgJLKGsz4PBMinL6AyCmIg6Kjo2XatGm27y0WiwQGBsr8+fMbrR87dqyMHj3abl1MTIw88cQTIiJitVrF399fFi1aZNteXl4uer1eli9fLiIiOTk5AkD27t1rq1m/fr2oVCo5c+bMFa85ceJEGTNmzBXrN2/eLADk/PnzTbZ/P2UymQSAmEymG6qn1iUlu1BCZiTLbfNTxWq1Kh2HnED2GZOE/WmdhMxIluXp3ykdh4iuwpHPb4eOPNXW1iIjI8PuyI5arUZcXBzS0tIafUxaWtoVR4Li4+Nt9QUFBSgsLLSr8fT0RExMjK0mLS0NRqMRQ4YMsdXExcVBrVYjPT3dkV0AAAwYMAABAQG46667sHPnzp+1fzU1NTCbzXYLtV2XT9nd1ccPKpVK4TTkDPoEeuD5+HAAwMvJOThVdlHhRET0cznUPJWUlMBiscDPz/50hp+f3xXjhi4rLCy8Zv3lr9er+fGpNQDQarXw9va+6us2JiAgAEuXLsXnn3+Ozz//HEFBQbjjjjuwb9++m96/+fPnw9PT07YEBQXdcB5qXSxWwTeHG07PclZxakpThnZHdDdvXKi14HnOPk7U5rWrq+169eqFJ554AoMHD8Ztt92GDz74ALfddhtef/31m37OWbNmwWQy2ZZTp041YWJqSQdOnUfZhVp4GLS4pZu30nHIiWjUKrz2cH+46TRILyjDh5x9nKhNc6h58vHxgUajQVGR/V3Di4qK4O/f+JVJ/v7+16y//PV6NT8dsF1fX4+ysrKrvu6Nio6ORn5+PoCb2z+9Xg8PDw+7hdqmTUcafsdG9PKFi6Zd/buCWkBwJze8OLo3AGDhhiPIL668ziOIqLVy6BNCp9Nh8ODBSE1Nta2zWq1ITU1FbGxso4+JjY21qweAlJQUW31oaCj8/f3tasxmM9LT0201sbGxKC8vR0ZGhq1m06ZNsFqtiImJcWQXrnDgwAEEBATc9P6R80i9dMqO97Kj5vLr6GAMD++Mmnor/rDyAOotVqUjEdFN0Dr6gOnTp2PixIkYMmQIoqOj8cYbb+DChQuYPHkyAOCRRx5Bly5dMH/+fADAs88+ixEjRuBvf/sbRo8ejRUrVuDbb7/Fu+++C6BhNt7nnnsOr7zyCsLCwhAaGorZs2cjMDDQNldT7969MWrUKDz++ONYunQp6urq8PTTT2P8+PEIDAy0ZcvJyUFtbS3KyspQUVGBAwcOAGgYIA4Ab7zxBkJDQxEZGYnq6mr861//wqZNm/D111/f8P6RczpTXoUjhRVQq4AR4Z2VjkNOSqVSYeFD/XD361tx8LQJb285ht+NDFM6FhE56mYu51u8eLEEBweLTqeT6Oho2b17t23biBEjZOLEiXb1K1eulPDwcNHpdBIZGSlr16612261WmX27Nni5+cner1eRo4cKbm5uXY1paWlkpiYKB06dBAPDw+ZPHmyVFRU2NWEhIQIgCuWy1599VXp0aOHGAwG8fb2ljvuuEM2bdrk0P5dD6cqaJv+k3ZCQmYky0Nv7VQ6CrUDX+47LSEzkqXHrLWSebpc6ThEJI59fqtEOGtbUzKbzfD09ITJZOL4pzbk0WV7selIMf44qhd+e0dPpeOQkxMRPPXxPmzILkQvv4746ne3Q6/VKB2LqF1z5PObo2Kp3auqtWBnfsOs4r/geCdqASqVCn95sK/t5sGvp+Rd/0FE1GqweaJ2L+14CWrqrehidEUvv45Kx6F2olMHPf7yYBQA4N1tx7Dv5HmFExHRjWLzRO3e5avsfhHhy1nFqUXFR/rjlwO7wCrAHz87hOo6i9KRiOgGsHmidk1EbPM78ZQdKWHO/X3g00GP/OJKvJnK03dEbQGbJ2rXjhRW4JypGgYXNWJ7dFI6DrVDRjcdXknoCwB4Z9txZJ42KZyIiK6HzRO1a5ePOt3ewwcGF17tRMoY1dcf9/ULgMUqeOGzg6it5+SZRK0Zmydq11IPN9yK5xe9ecqOlPXSA5HwdtfhSGEF3tqSr3QcIroGNk/UbpVdqMX+U+UAON6JlNepgx4vPRAJAPjnpnwcPmdWOBERXQ2bJ2q3tuQWQwToHeCBAE9XpeMQ4b5+Abi7jx/qrYI/fnaI974jaqXYPFG7lXqENwKm1kWlUuGVhL7wdHVB5hkT3t1+XOlIRNQINk/ULtVbrNh+9HsAwJ0RvBEwtR6+HgbMua8PAOCNlDzkF1conIiIforNE7VLB0+Xw1xdD09XF/TvalQ6DpGdXw7qgjt7dUatxYoXPjsEi5W3ICVqTdg8Ubu0NbfhqNPQMB9oNfzfgFoXlUqFv/4yCh31Wuw/WY4PdxYoHYmIfoSfGtQubb10ym5EOE/ZUesU4OmKF0f3BgD87eujOFV2UeFERHQZmydqd0ora3DoTMMszmyeqDUbd0sQbu3ujao6C15cnQURnr4jag3YPFG7syO/BCJAhH9H+HkYlI5DdFUqlQrzf9kPOq0a245+j9UHzigdiYjA5onaocvjnUb04lEnav1Cfdzx7MgwAMDLyYdRdqFW4URExOaJ2hWrVbAtj+OdqG2ZOrw7Ivw7ouxCLV5JzlE6DlG7x+aJ2pWcc2aUVNbCTafBkBBvpeMQ3RAXjRoLHuoHlQr4Yv8ZbLt0wQMRKYPNE7Url6+yu62HD3Ra/vpT2zEgyIhJt3UDALy4OhMXa+uVDUTUjvHTg9oV2xQFHO9EbdDzd/dCF6MrTpVV4Y1v8pSOQ9RusXmidsNcXYd9350HAIwIY/NEbY+7XotXEvoCAP61/TiyLk25QUQti80TtRu78ktRbxV093FHcCc3peMQ3ZQ7I3xxf/9AWAWY8fkh1FusSkcianfYPFG7cfmU3XBeZUdt3Jz7+sDT1QXZZ814fwdv3ULU0tg8UbsgIrYrlDjeidq6zh31+POlW7e8/s1RnCzlrVuIWhKbJ2oXjn1fiTPlVdBp1bg1tJPScYh+tl8N7orbe3ZCdZ0Vf/oyk7duIWpBbJ6oXdhyaVbxmFBvuOo0Cqch+vlUKhX++mAU9Fo1duSX4KuDZ5WORNRusHmidsE2RQHHO5ETCenkjt/9oicA4OXkHJgu1imciKh9YPNETq+q1oL0gjIAwB0c70ROZurwHujp2wEllbVYuPGI0nGI2gU2T+T0dheUorbeii5GV/To3EHpOERNSqdV4y+X5n76ZM9J7Dt5XuFERM6PzRM5va25P0xRoFKpFE5D1PRiunfCrwZ3hQjwpy8yOfcTUTO7qeZpyZIl6NatGwwGA2JiYrBnz55r1q9atQoREREwGAyIiorCunXr7LaLCObMmYOAgAC4uroiLi4OeXn2tx4oKytDUlISPDw8YDQaMWXKFFRWVtq2V1dXY9KkSYiKioJWq0VCQsIVOb744gvcdddd6Ny5Mzw8PBAbG4uNGzfa1cybNw8qlcpuiYiIcPAdotZkR34JAGB4mI/CSYiaz5/u7Q2jmwuOFFbgw50nlI5D5NQcbp4+/fRTTJ8+HXPnzsW+ffvQv39/xMfHo7i4uNH6Xbt2ITExEVOmTMH+/fuRkJCAhIQEZGVl2WoWLlyIN998E0uXLkV6ejrc3d0RHx+P6upqW01SUhKys7ORkpKC5ORkbNu2DVOnTrVtt1gscHV1xTPPPIO4uLhGs2zbtg133XUX1q1bh4yMDNx55524//77sX//fru6yMhInDt3zrbs2LHD0beJWolzpirkF1dCrWq4GTCRs/J21+FP9zTM/fT3lKM4U16lcCIiJyYOio6OlmnTptm+t1gsEhgYKPPnz2+0fuzYsTJ69Gi7dTExMfLEE0+IiIjVahV/f39ZtGiRbXt5ebno9XpZvny5iIjk5OQIANm7d6+tZv369aJSqeTMmTNXvObEiRNlzJgxN7Q/ffr0kZdeesn2/dy5c6V///439NjGmEwmASAmk+mmn4Oazsq9JyVkRrI88M8dSkchanZWq1UefnuXhMxIlsc+2nv9BxCRjSOf3w4deaqtrUVGRobdkR21Wo24uDikpaU1+pi0tLQrjgTFx8fb6gsKClBYWGhX4+npiZiYGFtNWloajEYjhgwZYquJi4uDWq1Genq6I7tgx2q1oqKiAt7e3nbr8/LyEBgYiO7duyMpKQknT5686nPU1NTAbDbbLdR6XD5lN6wnjzqR81OpVPjLg32hVauQklOEr7MLlY5E5JQcap5KSkpgsVjg5+dnt97Pzw+FhY3/T1pYWHjN+stfr1fj6+trt12r1cLb2/uqr3sjXnvtNVRWVmLs2LG2dTExMVi2bBk2bNiAt99+GwUFBRg2bBgqKioafY758+fD09PTtgQFBd10HmpaVqtg56XmaSjHO1E7EebXEVOHdwcAzPsqGxdq6hVOROR82u3Vdp988gleeuklrFy50q4xu+eee/Dwww+jX79+iI+Px7p161BeXo6VK1c2+jyzZs2CyWSyLadOnWqpXaDrOFJYgZLKWrjpNBgU7KV0HKIW87tfhCHI2xVnTdV445ujSschcjoONU8+Pj7QaDQoKiqyW19UVAR/f/9GH+Pv73/N+stfr1fz0wHp9fX1KCsru+rrXsuKFSvw2GOPYeXKlVcdXH6Z0WhEeHg48vPzG92u1+vh4eFht1DrsCP/h1uy6LTt9t8J1A656jT4vzENcz99sPMEcs5yOAFRU3LoE0Wn02Hw4MFITU21rbNarUhNTUVsbGyjj4mNjbWrB4CUlBRbfWhoKPz9/e1qzGYz0tPTbTWxsbEoLy9HRkaGrWbTpk2wWq2IiYlxZBewfPlyTJ48GcuXL8fo0aOvW19ZWYljx44hICDAodch5W3Pu3zKjrOKU/tzZy9fjI4KgMUq+NOXmbBYeeNgoqbi8D/Hp0+fjvfeew8fffQRDh8+jKeeegoXLlzA5MmTAQCPPPIIZs2aZat/9tlnsWHDBvztb3/DkSNHMG/ePHz77bd4+umnATQMcHzuuefwyiuv4KuvvkJmZiYeeeQRBAYG2uZq6t27N0aNGoXHH38ce/bswc6dO/H0009j/PjxCAwMtL1WTk4ODhw4gLKyMphMJhw4cAAHDhywbf/kk0/wyCOP4G9/+xtiYmJQWFiIwsJCmEwmW83zzz+PrVu34sSJE9i1axcefPBBaDQaJCYmOvpWkYKq6yzYc+mWLMM43onaqTn390EHvRYHTpVj+Z6rX/hCRA66mcv5Fi9eLMHBwaLT6SQ6Olp2795t2zZixAiZOHGiXf3KlSslPDxcdDqdREZGytq1a+22W61WmT17tvj5+Yler5eRI0dKbm6uXU1paakkJiZKhw4dxMPDQyZPniwVFRV2NSEhIQLgiuXH2Rrb/uO848aNk4CAANHpdNKlSxcZN26c5Ofn3/B7w6kKWoftR7+XkBnJEv2XFLFarUrHIVLMhzuOS8iMZOk7d4MUmauUjkPUajny+a0SER7LbUJmsxmenp4wmUwc/6Sg+esP452tx/HLQV3w97EDlI5DpBiLVZCwZCcyz5iQMCAQb4wfqHQkolbJkc9vjqIlp7Qj7/ItWTjeido3jbph7ieVClh94CzSjpUqHYmozWPzRE6ntLIG2ZeuLrqdk2MSoV9XI5JiggEAc9ZkoY43Dib6Wdg8kdPZeelf1hH+HdG5o17hNEStwwt3R6CTuw55xZX4YEeB0nGI2jQ2T+R0duQ1zO/Eq+yIfuDp5oKZ90QAAP6RmodzJt44mOhmsXkipyIitvFOnN+JyN5Dg7piSIgXLtZa8HJyjtJxiNosNk/kVI6XXMBZUzV0GjWiu3lf/wFE7YharcLLCX2hUauwLrMQ245+r3QkojaJzRM5lctHnYZ084KrTqNwGqLWp3eABybGdgMAzP0qGzX1FmUDEbVBbJ7IqfxwSxaOdyK6mt/fFQbfjnoUlFzAu1uPKx2HqM1h80ROo85ixe7jDVfaDevJ8U5EV9PR4IIXR/cGAPxzcz5OlV1UOBFR28LmiZzGwVPlqKyph5ebCyIDObs70bU80D8Qsd07oabeipf+l610HKI2hc0TOY1tl07Z3dbTB2q1SuE0RK2bSqXCywmRcNGo8M3hYqTkFCkdiajNYPNETsM2vxNnFSe6IT19O2LK0O4AgHlfZaOqloPHiW4EmydyCubqOhw8bQLAweJEjnhmZE8EehpwprwKSzbnKx2HqE1g80ROIe1YKSxWQaiPO7p6uSkdh6jNcNNpMef+PgCAd7cdx/HvKxVORNT6sXkip2CbVZyn7IgcFh/pjxHhnVFrsWLuV9kQEaUjEbVqbJ7IKezI5/xORDdLpVLhpQciodOqsT2vBOsyC5WORNSqsXmiNu/0+YsoKLkAjVqF2B6dlI5D1CZ183HHkyN6AABeTs5BZU29womIWi82T9TmXT5lNyDICA+Di8JpiNqu397RA8Hebig0V+PN1Dyl4xC1WmyeqM3bns/xTkRNweCiwUsPRAIAPthRgNzCCoUTEbVObJ6oTbNaBbsuNU/DON6J6Ge7M8IXd/fxQ71VMGdNFgePEzWCzRO1adlnzTh/sQ4d9Fr0DzIqHYfIKcy5vw8MLmqkF5RhzYGzSschanXYPFGbtj2/YVbxW7t3gouGv85ETaGrlxt+94swAMBf1h2GubpO4URErQs/bahNuzxYnKfsiJrWY8NC0d3HHd9X1OD1lKNKxyFqVdg8UZtVVWvBtyfOA+D8TkRNTa/VYN6lweMf7TqBnLNmhRMRtR5snqjN2nOiDLUWKwI9Deju4650HCKnMzy8M+6N8odVwMHjRD/C5onarO1HG8Y7DQ3zgUqlUjgNkXP68+g+cNNp8O135/H5vjNKxyFqFdg8UZv1wy1ZOiuchMh5BRpd8czIhsHj89cdhqmKg8eJ2DxRm1RcUY0jlybwu523ZCFqVo/eHoqevh1QeqEWf/86V+k4RIpj80Rt0s5LR50iAz3QqYNe4TREzk2nVeP/Lg0e/8/u75B1xqRwIiJlsXmiNml73uVTdrzKjqgl3NbTB/f3D4RVgNlrsmC1cvA4tV9snqjNEZEf5nfqyfFORC3lxXt7w12nwf6T5fgs47TScYgUc1PN05IlS9CtWzcYDAbExMRgz54916xftWoVIiIiYDAYEBUVhXXr1tltFxHMmTMHAQEBcHV1RVxcHPLy7O/oXVZWhqSkJHh4eMBoNGLKlCmorKy0ba+ursakSZMQFRUFrVaLhISERrNs2bIFgwYNgl6vR8+ePbFs2bKfvX/UsvKLK1FcUQO9Vo0h3byUjkPUbvh7GvD7u8IBAAs2HEH5xVqFExEpw+Hm6dNPP8X06dMxd+5c7Nu3D/3790d8fDyKi4sbrd+1axcSExMxZcoU7N+/HwkJCUhISEBWVpatZuHChXjzzTexdOlSpKenw93dHfHx8aiurrbVJCUlITs7GykpKUhOTsa2bdswdepU23aLxQJXV1c888wziIuLazRLQUEBRo8ejTvvvBMHDhzAc889h8ceewwbN2686f2jlnf5lF10qDcMLhqF0xC1LxNv64Zwvw4ou1CLRRs5eJzaKXFQdHS0TJs2zfa9xWKRwMBAmT9/fqP1Y8eOldGjR9uti4mJkSeeeEJERKxWq/j7+8uiRYts28vLy0Wv18vy5ctFRCQnJ0cAyN69e20169evF5VKJWfOnLniNSdOnChjxoy5Yv0f//hHiYyMtFs3btw4iY+Pv+n9+ymTySQAxGQy3VA9OW7yh3skZEayLN2Sr3QUonYp7ViJhMxIlm4zk+XgqfNKxyFqEo58fjt05Km2thYZGRl2R3bUajXi4uKQlpbW6GPS0tKuOBIUHx9vqy8oKEBhYaFdjaenJ2JiYmw1aWlpMBqNGDJkiK0mLi4OarUa6enpN5z/elluZv9qampgNpvtFmo+tfVW7D5eCoCDxYmUcmv3TnhwYBeIALNXZ8HCwePUzjjUPJWUlMBiscDPz89uvZ+fHwoLCxt9TGFh4TXrL3+9Xo2vr6/ddq1WC29v76u+riNZzGYzqqqqbmr/5s+fD09PT9sSFBR0w3nIcftPnsfFWgs6uevQ299D6ThE7daseyPQUa/FwdMmfLr3lNJxiFoUr7b7mWbNmgWTyWRbTp3iH5HmdHl+p9t6+kCt5i1ZiJTi2/GHweMLNx5B2QUOHqf2w6HmycfHBxqNBkVFRXbri4qK4O/v3+hj/P39r1l/+ev1an46YLu+vh5lZWVXfV1Hsnh4eMDV1fWm9k+v18PDw8NuoeazPf/yFAU8ZUektEdiQxDh3xHlF+uwcMMRpeMQtRiHmiedTofBgwcjNTXVts5qtSI1NRWxsbGNPiY2NtauHgBSUlJs9aGhofD397erMZvNSE9Pt9XExsaivLwcGRkZtppNmzbBarUiJibmhvNfL8vN7B+1HFNVHQ6eKgfA8U5ErYFWo8YrCX0BACv2nsK+k+cVTkTUQhwdjb5ixQrR6/WybNkyycnJkalTp4rRaJTCwkIREZkwYYLMnDnTVr9z507RarXy2muvyeHDh2Xu3Lni4uIimZmZtpoFCxaI0WiUNWvWyKFDh2TMmDESGhoqVVVVtppRo0bJwIEDJT09XXbs2CFhYWGSmJholy07O1v2798v999/v9xxxx2yf/9+2b9/v2378ePHxc3NTV544QU5fPiwLFmyRDQajWzYsOGG9+96eLVd81mfeU5CZiTLna9tVjoKEf3IH1YekJAZyTL6zW1Sb7EqHYfopjjy+e1w8yQisnjxYgkODhadTifR0dGye/du27YRI0bIxIkT7epXrlwp4eHhotPpJDIyUtauXWu33Wq1yuzZs8XPz0/0er2MHDlScnNz7WpKS0slMTFROnToIB4eHjJ58mSpqKiwqwkJCREAVyw/tnnzZhkwYIDodDrp3r27fPjhhw7t3/WweWo+L355SEJmJMvs1ZnXLyaiFvN9RbX0nbtBQmYky793FSgdh+imOPL5rRIRXmPahMxmMzw9PWEymTj+qYndsWgzTpRexLsTBuPuyBsf60ZEze/faScwZ002PAxabHr+Dvjwht3Uxjjy+c2r7ahNOFV2ESdKL0KjVuHWHp2UjkNEP5EUE4LIQA+Yq+uxYD0Hj5NzY/NEbcLlKQoGBBnhYXBROA0R/ZRGrcLLlwaPf5ZxGt+eKFM4EVHzYfNEbcLlKQqGcooColZrULAXxg1pmCh49pps1FusCiciah5snqjVs1oFuy7P78QpCohatRn3RMDT1QWHz5nxn93fKR2HqFmweaJWL/usGecv1qGDXov+QUal4xDRNXi76/DHUb0AAH//+iiKK6oVTkTU9Ng8Uau3Pf97AMCt3b3houGvLFFrN/6WYPTr6omKmnosWMfB4+R8+ElErd5OjncialM0ahVeHtMXKhXwxf4zSD9eqnQkoibF5olateo6C/aeaLjlw9CwzgqnIaIb1T/IiMToYADAnDXZqOPgcXIibJ6oVdtTUIbaeisCPA3o0dld6ThE5IA/xveCl5sLcosq8NGuE0rHIWoybJ6oVdtx6ZTd7T19oFKpFE5DRI4wuukw854IAMAb3+ShyMzB4+Qc2DxRq7Y9j1MUELVlDw8OwsBgIypr6vGXtYeVjkPUJNg8Uav1fUUNDp8zA2g48kREbY/60uBxtQr46uBZ7DpWonQkop+NzRO1Wpf/yPYO8OBNRonasL5dPPGbW0MANAwer63n4HFq29g8Uau1g6fsiJzGH+7qhU7uOuQXV+LDnQVKxyH6Wdg8UaskIrbB4pzfiajt83Rzwax7ewMA/pGah3OmKoUTEd08Nk/UKh37/gLOmaqh06hxSzdvpeMQURP45cAuGBLihYu1FrySzMHj1HaxeaJWaUdewy1ZhnTzgqtOo3AaImoKarUK/3dp8PjazHPYfun/c6K2hs0TtUo78htu5zCU452InEqfQA9MvK0bAGDummzU1FuUDUR0E9g8UatTZ7Fi96V7YQ3ryVuyEDmb398Vjs4d9ThecgH/2s7B49T2sHmiVmf/yXJU1tTDy80FkYEeSschoibmYXDBi5cGjy/elIcz5Rw8Tm0LmydqdbYdbRgHMTSsM9Rq3pKFyBmNGRCI6FBvVNdZ8X//y1Y6DpFD2DxRq7Pt0iDS4RzvROS0VKqGmcc1ahU2Zhdhc26x0pGIbhibJ2pVyi7UIvOMCQAwPJzjnYicWS//jnj09m4AgHlfZaO6joPHqW1g80Styo78EogAEf4d4edhUDoOETWzZ+PC4eehx3elF/HutuNKxyG6IWyeqFW5PN6JR52I2ocOei1eHN0HALBkcz5OlV1UOBHR9bF5olZDRGyT5g0PY/NE1F7c3y8At/XohJp6K176X47ScYiui80TtRq5RRUoMtfA4KLGkG5eSschohaiUqnwf2MioVWr8M3hIqQeLlI6EtE1sXmiVuPyKbtbu3eCwYW3ZCFqT3r6dsSUYaEAgHn/4+Bxat3YPFGrse1oCQCesiNqr575RRgCPA04VVaFt7ccUzoO0VWxeaJWoarWgj0nygBwsDhRe+Wu12L2fQ2Dx9/eegzflV5QOBFR49g8Uauwu6AUtfVWdDG6okdnd6XjEJFC7unrj2FhPqitt2LuV9kQEaUjEV3hppqnJUuWoFu3bjAYDIiJicGePXuuWb9q1SpERETAYDAgKioK69ats9suIpgzZw4CAgLg6uqKuLg45OXl2dWUlZUhKSkJHh4eMBqNmDJlCiorK+1qDh06hGHDhsFgMCAoKAgLFy60237HHXdApVJdsYwePdpWM2nSpCu2jxo16mbeJnLAD1MU+ECl4i1ZiNorlUqFlx6IhItGhS253+PrHA4ep9bH4ebp008/xfTp0zF37lzs27cP/fv3R3x8PIqLG59af9euXUhMTMSUKVOwf/9+JCQkICEhAVlZWbaahQsX4s0338TSpUuRnp4Od3d3xMfHo7q62laTlJSE7OxspKSkIDk5Gdu2bcPUqVNt281mM+6++26EhIQgIyMDixYtwrx58/Duu+/aar744gucO3fOtmRlZUGj0eDhhx+2yzxq1Ci7uuXLlzv6NpGDbM0TxzsRtXvdO3fA1OHdAQD/978cVNVy8Di1MuKg6OhomTZtmu17i8UigYGBMn/+/Ebrx44dK6NHj7ZbFxMTI0888YSIiFitVvH395dFixbZtpeXl4ter5fly5eLiEhOTo4AkL1799pq1q9fLyqVSs6cOSMiIm+99ZZ4eXlJTU2NrWbGjBnSq1evq+7L66+/Lh07dpTKykrbuokTJ8qYMWOu9zZclclkEgBiMplu+jnam9PnL0rIjGTpPmutlF+sVToOEbUCF2vq5bb5qRIyI1kWbTiidBxqBxz5/HboyFNtbS0yMjIQFxdnW6dWqxEXF4e0tLRGH5OWlmZXDwDx8fG2+oKCAhQWFtrVeHp6IiYmxlaTlpYGo9GIIUOG2Gri4uKgVquRnp5uqxk+fDh0Op3d6+Tm5uL8+fONZnv//fcxfvx4uLvbj7HZsmULfH190atXLzz11FMoLS296ntSU1MDs9lst5BjLh91GhBkhKeri8JpiKg1cNVpMOf+hsHj7247juPfV17nEUQtx6HmqaSkBBaLBX5+fnbr/fz8UFhY2OhjCgsLr1l/+ev1anx9fe22a7VaeHt729U09hw/fo0f27NnD7KysvDYY4/ZrR81ahT+/e9/IzU1Fa+++iq2bt2Ke+65BxZL44eN58+fD09PT9sSFBTUaB1dHU/ZEVFj7u7jhzt6dUatxYo5azh4nFqPdnu13fvvv4+oqChER0fbrR8/fjweeOABREVFISEhAcnJydi7dy+2bNnS6PPMmjULJpPJtpw6daoF0juPeosVO/Ib5ncaFu6jcBoiak0uDx7Xa9XYkV+C1QfOKB2JCICDzZOPjw80Gg2KiuyvfigqKoK/v3+jj/H3979m/eWv16v56YD0+vp6lJWV2dU09hw/fo3LLly4gBUrVmDKlCnX3mEA3bt3h4+PD/Lz8xvdrtfr4eHhYbfQjTt4uhwV1fXwdHVB/65GpeMQUSsT0skdz4wMAwC8nHwY5y/UKpyIyMHmSafTYfDgwUhNTbWts1qtSE1NRWxsbKOPiY2NtasHgJSUFFt9aGgo/P397WrMZjPS09NtNbGxsSgvL0dGRoatZtOmTbBarYiJibHVbNu2DXV1dXav06tXL3h52d8nbdWqVaipqcFvfvOb6+7z6dOnUVpaioCAgOvWkuO2XppVfGhPH2jUnKKAiK70+LDuCPfrgLILtViw/ojScYgcv9puxYoVotfrZdmyZZKTkyNTp04Vo9EohYWFIiIyYcIEmTlzpq1+586dotVq5bXXXpPDhw/L3LlzxcXFRTIzM201CxYsEKPRKGvWrJFDhw7JmDFjJDQ0VKqqqmw1o0aNkoEDB0p6errs2LFDwsLCJDEx0ba9vLxc/Pz8ZMKECZKVlSUrVqwQNzc3eeedd67Yh6FDh8q4ceOuWF9RUSHPP/+8pKWlSUFBgXzzzTcyaNAgCQsLk+rq6ht6f3i1nWPG/HOHhMxIlhV7vlM6ChG1YnsLSiVkRrKEzEiW3cdKlI5DTsiRz2+HmycRkcWLF0twcLDodDqJjo6W3bt327aNGDFCJk6caFe/cuVKCQ8PF51OJ5GRkbJ27Vq77VarVWbPni1+fn6i1+tl5MiRkpuba1dTWloqiYmJ0qFDB/Hw8JDJkydLRUWFXc3Bgwdl6NChotfrpUuXLrJgwYIrsh85ckQAyNdff33FtosXL8rdd98tnTt3FhcXFwkJCZHHH3/c1hjeCDZPN660ska6zWz4Y3iuvOr6DyCidm3WF4ckZEay/OK1zVJdV690HHIyjnx+q0R4+UJTMpvN8PT0hMlk4vin61i9/wye+/QAegd4YP2zw5SOQ0StnOliHUb+fStKKmvw+7hwPBsXpnQkciKOfH6326vtSHmbcxsuArizF6coIKLr83RzwdxLcz8t2ZzPuZ9IMWyeSBEWq2Drpfmd7ozwvU41EVGD+/oFYER4w9xPL36ZxbmfSBFsnkgRB06Vo/xiHTwMWgwMMiodh4jaCJVKhVcS+sLgokba8VJ8vo9zP1HLY/NEithy6ZTd8PDO0Gr4a0hENy7I2w3PxYUDAP6yNgdlnPuJWhg/tUgRP4x34ik7InLclKGhiPDviPMX6/CXtYeVjkPtDJsnanHF5mpknWm4gfLwcA4WJyLHuWjU+Osvo6BSAZ/vO41dx0qUjkTtCJsnanFbLg0U79fVE5076hVOQ0Rt1aBgL/wmJgQA8Ocvs1Bd1/gN3ImaGpsnanGXxzvdwVN2RPQzvTCqF3w76nG85ALe2nJM6TjUTrB5ohZVZ7Fi+6X72XF+JyL6uTwMLpj3QCQA4O0t+cgrqlA4EbUHbJ6oRe377jwqaurh7a5Dv65GpeMQkRO4p68/Rkb4os4imPH5IVisnPuJmhebJ2pRm3MbxjuNCO8MjVqlcBoicgYqlQovJ/RFB70W+06W499pJ5SORE6OzRO1qB/GO/GUHRE1nUCjK2beEwEAWLQxF6fKLiqciJwZmydqMWfLq3CksAJqFTA8jM0TETWtX0cHIzrUGxdrLfjTl5m8dQs1GzZP1GK2XDplNzDYC17uOoXTEJGzUatVWPDLKOi0amzPK8EXvHULNRM2T9RiNh0pAgDcwYkxiaiZdO/cAc/FhQEA/i85B99X1CiciJwRmydqEVW1FmzPa5iiIK6Pn8JpiMiZPT6sOyIDPWCqqsO8/2UrHYecEJsnahE78ktQU29FF6MrIvw7Kh2HiJyYi0aNVx/qB41ahbWHzmFjdqHSkcjJsHmiFpF6uOGUXVxvX6hUnKKAiJpX3y6emDq8OwBg9uosmKrqFE5EzoTNEzU7q1XwzeGGKQp4yo6IWsqzI8MQ6uOO4ooaLFh/WOk45ETYPFGzO3i6HCWVNeig1yImtJPScYionTC4aLDgl1EAgOV7TmHXsRKFE5GzYPNEzS710lGnEeGdodPyV46IWk5M905IigkGAMz6IhNVtRaFE5Ez4CcZNbtvLo936uOrcBIiao9m3hOBAE8Dviu9iNe+zlU6DjkBNk/UrE6VXcSRwgpo1Crc2YvNExG1vI4GF/z1wYbTdx/sLMDeE2UKJ6K2js0TNavLV9kNDvGC0Y2zihORMu6M8MXDg7tCBHhh1UGevqOfhc0TNavLV9nd1ZtX2RGRsv58Xx8EeBpwovQiFm48onQcasPYPFGzMVfXYffxUgCcooCIlOfp6oIFD/UDAHy48wTSL/19InIUmydqNtuOfo96q6BHZ3eE+rgrHYeICCPCO2P8LUEAgBc+O4SLtfUKJ6K2iM0TNZtvci7PKs6jTkTUerw4ujcCPQ04WXYRr67n6TtyHJsnaha19VakHuGs4kTU+nQ0uODVXzWcvvso7TukHePpO3IMmydqFmnHS1FRXY/OHfUYHOyldBwiIjvDwjrj15cmz3zhs4O4UMPTd3Tj2DxRs9iQ1XAX87v7+EGt5o2Aiaj1+dO9vdHF6IrT56uwgKfvyAE31TwtWbIE3bp1g8FgQExMDPbs2XPN+lWrViEiIgIGgwFRUVFYt26d3XYRwZw5cxAQEABXV1fExcUhLy/PrqasrAxJSUnw8PCA0WjElClTUFlZaVdz6NAhDBs2DAaDAUFBQVi4cKHd9mXLlkGlUtktBoPB4Sx0bRarICWnoXka1ddf4TRERI3roNdi4aXTd//Z/R125fPed3RjHG6ePv30U0yfPh1z587Fvn370L9/f8THx6O4uLjR+l27diExMRFTpkzB/v37kZCQgISEBGRlZdlqFi5ciDfffBNLly5Feno63N3dER8fj+rqaltNUlISsrOzkZKSguTkZGzbtg1Tp061bTebzbj77rsREhKCjIwMLFq0CPPmzcO7775rl8fDwwPnzp2zLd99953d9hvJQteW8d15lFTWwsOgxa3deSNgImq9bu/pg9/cevn03SGYq+sUTkRtgjgoOjpapk2bZvveYrFIYGCgzJ8/v9H6sWPHyujRo+3WxcTEyBNPPCEiIlarVfz9/WXRokW27eXl5aLX62X58uUiIpKTkyMAZO/evbaa9evXi0qlkjNnzoiIyFtvvSVeXl5SU1Njq5kxY4b06tXL9v2HH34onp6eV923G8lyPSaTSQCIyWS6oXpn9NJX2RIyI1l+/+l+paMQEV1XZXWdDHt1U8PfrRX7lY5DCnHk89uhI0+1tbXIyMhAXFycbZ1arUZcXBzS0tIafUxaWppdPQDEx8fb6gsKClBYWGhX4+npiZiYGFtNWloajEYjhgwZYquJi4uDWq1Genq6rWb48OHQ6XR2r5Obm4vz58/b1lVWViIkJARBQUEYM2YMsrOzbdtuJMtP1dTUwGw22y3tmYhgY/alU3aRPGVHRK2fu16L18f1h1oFfLH/DNYeOqd0JGrlHGqeSkpKYLFY4Odnf+m5n58fCgsLG31MYWHhNesvf71eja+v/U1ltVotvL297Woae44fv0avXr3wwQcfYM2aNfj4449htVpx22234fTp0zec5afmz58PT09P2xIUFNRoXXuRdcaMM+VVcHXRYHh4Z6XjEBHdkMEh3vjtHT0BAC+uzkSRmUM16Ora1dV2sbGxeOSRRzBgwACMGDECX3zxBTp37ox33nnnpp9z1qxZMJlMtuXUqVNNmLjt2ZDd8C+2OyM6w+CiUTgNEdGNe2ZkGPp28UD5xTq88NkhiIjSkaiVcqh58vHxgUajQVFRkd36oqIi+Ps3forG39//mvWXv16v5qcD0uvr61FWVmZX09hz/Pg1fsrFxQUDBw5Efn7+DWf5Kb1eDw8PD7ulvRIRrL80RUE8T9kRURuj06rxxrgB0GvV2Hb0e/xn93fXfxC1Sw41TzqdDoMHD0ZqaqptndVqRWpqKmJjYxt9TGxsrF09AKSkpNjqQ0ND4e/vb1djNpuRnp5uq4mNjUV5eTkyMjJsNZs2bYLVakVMTIytZtu2bairq7N7nV69esHLq/FJGi0WCzIzMxEQEHDDWejq8osrcfz7C9Bp1PhFhO/1H0BE1Mr09O2IWfdEAAD+uu4w8osrr/MIapccHY2+YsUK0ev1smzZMsnJyZGpU6eK0WiUwsJCERGZMGGCzJw501a/c+dO0Wq18tprr8nhw4dl7ty54uLiIpmZmbaaBQsWiNFolDVr1sihQ4dkzJgxEhoaKlVVVbaaUaNGycCBAyU9PV127NghYWFhkpiYaNteXl4ufn5+MmHCBMnKypIVK1aIm5ubvPPOO7aal156STZu3CjHjh2TjIwMGT9+vBgMBsnOznYoy7W056vt/vHNUQmZkSyTPkhXOgoR0U2zWKzym3/tlpAZyXL/4u1SW29ROhK1AEc+vx1unkREFi9eLMHBwaLT6SQ6Olp2795t2zZixAiZOHGiXf3KlSslPDxcdDqdREZGytq1a+22W61WmT17tvj5+Yler5eRI0dKbm6uXU1paakkJiZKhw4dxMPDQyZPniwVFRV2NQcPHpShQ4eKXq+XLl26yIIFC+y2P/fcc7bcfn5+cu+998q+ffscznIt7bl5uvvvWyVkRrJ8uuek0lGIiH6Wc+VV0m/eRgmZkSx/23hE6TjUAhz5/FaJcERcUzKbzfD09ITJZGpX45+OFlXg7te3wUWjwrcv3gVPNxelIxER/SzJh87i6U/2Q60CVj15GwaH8D6dzsyRz+92dbUdNZ/kg2cBAMPDOrNxIiKncF+/QCQMCIRVgOc+3c/Zx8mGzRP9bCKC5EuTyt3XP0DhNERETef/Evqiq5crTpVV4c9fZnH6AgLA5omaQM45M46XXIBeq0Zcb7/rP4CIqI3wMLjgH+MHQqNW4auDZ/H5vjNKR6JWgM0T/WyXjzrd2csXHQ08ZUdEzmVwiBem3xUOAJizJgvHv+f0Be0dmyf6WUQE/7s03un+/oEKpyEiah5PjuiB2O6dcLHWgt8t34+aeovSkUhBbJ7oZzl42oTT56vgptNwYkwicloatQqvjxsALzcXZJ81Y+GGXKUjkYLYPNHPcvkqu5G9/eCq473siMh5+XsasOhX/QEA7+8owOYjxdd5BDkrNk9006xWwdrMhvFO9/fjVXZE5Pzi+vhh0m3dAADPrzqIYnO1soFIEWye6KalF5ThnKkaHQ1aDA/vrHQcIqIWMfOeCET4d0TphVpMX3kQFiunL2hv2DzRTfti32kAwH39AmBw4Sk7ImofDC4a/PPXA+HqosGO/BL8c1O+0pGohbF5optSVWvB+qxCAMCDA7sqnIaIqGX19O2IlxP6AgDeSD2KnfklCieilsTmiW7K1zmFqKypR1cvVwzh/Z6IqB361eCuGDckCCLAsyv2o4jjn9oNNk90U77c3zDL7i8HdoFarVI4DRGRMl4aE4neAR4oqazF7z7Zj3qLVelI1ALYPJHDiiuqsT2v4RD1g4N4yo6I2i+DiwZvJQ1CB70We06UYdHXnP+pPWDzRA776sBZWKyCAUFGhPq4Kx2HiEhRoT7uWPirfgCAd7Yexzc5RQonoubG5okcdvmU3UODuiichIiodbg3KsA2/9MfVh3EqbKLygaiZsXmiRySW1iB7LNmuGhUuK8f72VHRHTZn+7tjQFBRpiq6jDtk32oruP975wVmydyyKd7TwEA7uzlCy93ncJpiIhaD51WjSVJg2B0c8Gh0ybMXZMNEU6g6YzYPNENq66z4Iv9DRNjJkYHK5yGiKj16WJ0xeLEgVCrgE+/PYWP008qHYmaAZsnumFf5xSh/GIdAjwNvB0LEdFVDAvrjD+OigAAvPRVNvaeKFM4ETU1Nk90w1bsafgX1MNDgqDh3E5ERFf1xPDuuK9fAOqtgqc+3odCEyfQdCZsnuiGfFd6AbuOlUKlAsYO4dxORETXolKpsPBX/RDh3xEllTV48uMM1NRzALmzYPNEN+TyQPFhYZ3R1ctN4TRERK2fm06LdycMgaerCw6cKsec1RxA7izYPNF11VusWJXRMFB8/C1BCqchImo7gju5cQC5E2LzRNeVeqQY31fUoJO7DnG9/ZSOQ0TUpgwPtx9Aviu/ROFE9HOxeaLr+mjXCQANA8V1Wv7KEBE56onh3TFmQCDqrYInP87A8e8rlY5EPwM/Cema8ooqsOtYKdQq4De3cm4nIqKboVKp8OpD/TAo2AhzdT0eXbYX5y/UKh2LbhKbJ7qmj9JOAADu6uPHgeJERD+DwUWDdx8Zgi5GV5wovYin/puB2nqr0rHoJrB5oqsyV9fhi30NNwGeGNtN2TBERE7Ap4MeH0y6BR30Wuw+XobZq7N4BV4bxOaJruqzb0/jYq0FYb4dENujk9JxiIicQi//jnZX4P1re4HSkchBbJ6oUVar4D+7vwMAPHJbN6hUnFGciKip3Bnhi9n39QEA/HX9YWzIKlQ4ETnippqnJUuWoFu3bjAYDIiJicGePXuuWb9q1SpERETAYDAgKioK69ats9suIpgzZw4CAgLg6uqKuLg45OXl2dWUlZUhKSkJHh4eMBqNmDJlCior7a9WOHToEIYNGwaDwYCgoCAsXLjQbvt7772HYcOGwcvLC15eXoiLi7si+6RJk6BSqeyWUaNGOfoWtXmbjhSjoOQCOuq1+OXALkrHISJyOpNu64bf3BoMEeDZFfvxLe+B12Y43Dx9+umnmD59OubOnYt9+/ahf//+iI+PR3FxcaP1u3btQmJiIqZMmYL9+/cjISEBCQkJyMrKstUsXLgQb775JpYuXYr09HS4u7sjPj4e1dU/3AsoKSkJ2dnZSElJQXJyMrZt24apU6fatpvNZtx9990ICQlBRkYGFi1ahHnz5uHdd9+11WzZsgWJiYnYvHkz0tLSEBQUhLvvvhtnzpyxyzxq1CicO3fOtixfvtzRt6nNW7r1GADg17cGw12vVTgNEZHzUalUmHd/JOJ6+6Km3oopH32L/OIKpWPRjRAHRUdHy7Rp02zfWywWCQwMlPnz5zdaP3bsWBk9erTdupiYGHniiSdERMRqtYq/v78sWrTItr28vFz0er0sX75cRERycnIEgOzdu9dWs379elGpVHLmzBkREXnrrbfEy8tLampqbDUzZsyQXr16XXVf6uvrpWPHjvLRRx/Z1k2cOFHGjBlzvbfhqkwmkwAQk8l008+htL0FpRIyI1nC/rROCk1VSschInJqF2vqZcw/d0jIjGS5bX4q/+4qxJHPb4eOPNXW1iIjIwNxcXG2dWq1GnFxcUhLS2v0MWlpaXb1ABAfH2+rLygoQGFhoV2Np6cnYmJibDVpaWkwGo0YMmSIrSYuLg5qtRrp6em2muHDh0On09m9Tm5uLs6fP99otosXL6Kurg7e3t5267ds2QJfX1/06tULTz31FEpLS6/6ntTU1MBsNtstbd07244DAB4c2AV+HgaF0xAROTdXnQYfTLoFoT7uOFNehUkf7kVFdZ3SsegaHGqeSkpKYLFY4Odnf4sOPz8/FBY2PtitsLDwmvWXv16vxtfX1267VquFt7e3XU1jz/Hj1/ipGTNmIDAw0K5xGzVqFP79738jNTUVr776KrZu3Yp77rkHFkvjd8OeP38+PD09bUtQUNu+91t+cSVScooAAI8P765wGiKi9sHbXYePJkfDp4MOh8+Z8eTHnAOqNWu3V9stWLAAK1aswJdffgmD4YejK+PHj8cDDzyAqKgoJCQkIDk5GXv37sWWLVsafZ5Zs2bBZDLZllOnTrXQHjSPd7c1jHW6q48fevp2UDgNEVH7EdzJDR9OioabToOd+aWYvvIALFbOAdUaOdQ8+fj4QKPRoKioyG59UVER/P39G32Mv7//Nesvf71ezU8HpNfX16OsrMyuprHn+PFrXPbaa69hwYIF+Prrr9GvX79r7nP37t3h4+OD/Pz8Rrfr9Xp4eHjYLW3VqbKLtkkxnxzBo05ERC0tqqsn3v7NYLhoVEg+dA4vfpnJSTRbIYeaJ51Oh8GDByM1NdW2zmq1IjU1FbGxsY0+JjY21q4eAFJSUmz1oaGh8Pf3t6sxm81IT0+31cTGxqK8vBwZGRm2mk2bNsFqtSImJsZWs23bNtTV1dm9Tq9eveDl5WVbt3DhQrz88svYsGGD3Riqqzl9+jRKS0sREBBw3dq2bvGmPNRbBcPCfDA4xPv6DyAioiY3Irwz3hjXMInmir2n8Mraw2ygWhtHR6OvWLFC9Hq9LFu2THJycmTq1KliNBqlsLBQREQmTJggM2fOtNXv3LlTtFqtvPbaa3L48GGZO3euuLi4SGZmpq1mwYIFYjQaZc2aNXLo0CEZM2aMhIaGSlXVD1ccjBo1SgYOHCjp6emyY8cOCQsLk8TERNv28vJy8fPzkwkTJkhWVpasWLFC3Nzc5J133rF7HZ1OJ5999pmcO3fOtlRUVIiISEVFhTz//POSlpYmBQUF8s0338igQYMkLCxMqqurb+j9aatX2xV8XyndZ62VkBnJ8u2JMqXjEBG1e5/uPSkhM5IlZEay/P3rXKXjOD1HPr8dbp5ERBYvXizBwcGi0+kkOjpadu/ebds2YsQImThxol39ypUrJTw8XHQ6nURGRsratWvttlutVpk9e7b4+fmJXq+XkSNHSm6u/S9KaWmpJCYmSocOHcTDw0MmT55sa3ouO3jwoAwdOlT0er106dJFFixYYLc9JCREAFyxzJ07V0RELl68KHfffbd07txZXFxcJCQkRB5//HFbY3gj2mrzNP3TAxIyI1keeT9d6ShERHTJhzuO2xqod7ceUzqOU3Pk81slwmOBTclsNsPT0xMmk6nNjH86/n0l4v6+FVYBVk+7HQOCjEpHIiKiS5ZszseijbkAgFcS+uI3t4YonMg5OfL53W6vtqMfvLrhCKwCjIzwZeNERNTK/PaOHnhyRA8AwJ9XZ+HjS/cdJeWweWrn0o+XYmN2EdQqYMY9EUrHISKin1CpVJgxqhceGxoKoKGB+k/aCWVDtXNsntoxq1Xw13WHAQDjo4MR7tdR4URERNQYlUqFF0f3xtRLkxfPXpONj3adUDZUO8bmqR3736GzOHjaBHedBr+PC1c6DhERXYNKpcKseyLwxKV5+OZ+lY0PdxYonKp9YvPUTlVU19mOOj11Rw907qhXOBEREV2PSqXCzFEReOqOhjFQL/0vx3ZnCGo5bJ7aqb99fRRF5hp06+SGx4ZxNnEiorZCpVLhj/G9MO3Ohgbqr+uOYNHGI5xIswWxeWqHMk+b8O9Lgw1fTugLg4tG2UBEROQQlUqF5+/uhT+O6gUAWLL5GF5cncV74bUQNk/tTJ3FillfHoJVgAf6B2JYWGelIxER0U1QqVT47R098dcHo6BSAZ+kn8QzK/ajtt6qdDSnx+apnfnnpnxknTHDw6DFn+/rrXQcIiL6mX4dE4zFiQPholFh7aFzeOzf3+JCTb3SsZwam6d2ZP/J8/jn5nwAwCsPRsG3o0HhRERE1BTu6xeIf028Ba4uGmw7+j3GvpOGInO10rGcFpundqKyph7TVx6ExSp4oH8gHugfqHQkIiJqQiPCO+OTx2PQyV2H7LNmJCzZiZyzZqVjOSU2T+2AiOCFVQdRUHIBAZ4GvDymr9KRiIioGQwM9sKXv70dPTq745ypGg8v3YUtucVKx3I6bJ7agXe2Hcf6rEK4aFRYkjQInm4uSkciIqJmEtzJDV88dTtiu3fChVoLpnz0Lf6TdoJTGTQhNk9ObmN2IRZuOAIAmPdAJAYFeymciIiImpunmws+ejQavxrcFRarYPaabMz8PBPVdRalozkFNk9OLP14KX63fD+sAiRGB+PX0cFKRyIiohai06qx6Ff9MGNUBNQq4NNvT2Hcu7txzlSldLQ2j82Tk8r4rgyPffQtauutuKuPH14eEwmVSqV0LCIiakEqlQpP3dEDyyZHw9PVBQdPleP+xTuQfrxU6WhtGpsnJ7QjrwS/+dceVNTUIzrUG4sTB0Kr4Y+aiKi9Gh7eGf97eigi/DuipLIWSf9Kx9Ktx2DljOQ3hZ+oTkREsGxnASZ9uAdVdRYMD++MjyZH8/YrRETUMJD8t7dhzIBA1FsFC9YfwcQP9+D7ihqlo7U5bJ6cRHFFNaZ9sg/z/peD+ktzOb33yGC46tg4ERFRAzedFm+MG4AFv4yCwUWN7XkluOcf27Dt6PdKR2tTVMJrF5uU2WyGp6cnTCYTPDw8mv31LtTU4+Pd3+GtLcdgqqqDRq3Cn+7tjUdv78YxTkREdFV5RRX43fL9OFJYAQCYMjQUz9/dq93+o9uRz282T02sOZsnEUFVnQWllbXIOmPC5txirM8qREV1wz2M+nbxwIJf9kPfLp5N+rpEROScquss+Ou6w/h32ncAgFAfdyz6VT8M6eatcLKWx+ZJQc3VPJmr6zDk5W9Qa7nybtmhPu747R098ODALhwYTkREDtt8pBizvshEobkaKhXw6O3t7ygUmycFNVfzZLUKery4DiKAi0aFMN+OGBzihXujAhAd6g2NmqfoiIjo5pmq6vBKcg5WZZwGAAR7u2HeA33wiwg/hZO1DDZPCmrO03Zny6vg6eoCN52G45mIiKhZbM4txp++yMQ5UzUAIK63H+be3wdB3m4KJ2tebJ4U1NIDxomIiJpaZU09Fqfm4f0dBai3CvRaNZ66owceH9Yd7nqt0vGaBZsnBbF5IiIiZ5FXVIE5a7KRdmlGcp8OejwbF4bxtwTBxcnG2LJ5UhCbJyIiciYigrWZ57BwQy5Oll0EAHTr5Ibpd/fC6KgApxlzy+ZJQWyeiIjIGdXWW7Fi70m8mZqHkspaAEB3H3c8OaIHEgZ2gU7bto9EsXlSEJsnIiJyZpU19Xh/ewE+2FkAU1UdACDA04ApQ0Px8OAgeLq5KJzw5rB5UhCbJyIiag8qa+qxPP0k3tt+HMWX7o+n16pxf/9ATLg1BP2DjMoGdBCbJwWxeSIiovakpt6CL/edwUdp3+HwObNtfYR/R4wZ0AX39w9AV6/WP82BI5/fN3WCcsmSJejWrRsMBgNiYmKwZ8+ea9avWrUKERERMBgMiIqKwrp16+y2iwjmzJmDgIAAuLq6Ii4uDnl5eXY1ZWVlSEpKgoeHB4xGI6ZMmYLKykq7mkOHDmHYsGEwGAwICgrCwoULmyULERERNdBrNRgfHYx1zwzF50/dhl8O7AKdRo0jhRV4dcMRDH11M3719i78a/tx5BdXwCmO2YiDVqxYITqdTj744APJzs6Wxx9/XIxGoxQVFTVav3PnTtFoNLJw4ULJycmRP//5z+Li4iKZmZm2mgULFoinp6esXr1aDh48KA888ICEhoZKVVWVrWbUqFHSv39/2b17t2zfvl169uwpiYmJtu0mk0n8/PwkKSlJsrKyZPny5eLq6irvvPNOk2e5FpPJJADEZDLd8HtKRETkTM5fqJFP0r+Tce/skm4zkyVkxg/L7QtS5cUvD8maA2fk9PmLYrValY4rIo59fjt82i4mJga33HIL/vnPfwIArFYrgoKC8Lvf/Q4zZ868on7cuHG4cOECkpOTbetuvfVWDBgwAEuXLoWIIDAwEH/4wx/w/PPPAwBMJhP8/PywbNkyjB8/HocPH0afPn2wd+9eDBkyBACwYcMG3HvvvTh9+jQCAwPx9ttv48UXX0RhYSF0Oh0AYObMmVi9ejWOHDnSZFmuh6ftiIiIflBoqsa6zHPYnFuM9ONlV9yj1c9DjwFBRvTy64iefh0R5tsBwd5uLT4ZpyOf3w4lq62tRUZGBmbNmmVbp1arERcXh7S0tEYfk5aWhunTp9uti4+Px+rVqwEABQUFKCwsRFxcnG27p6cnYmJikJaWhvHjxyMtLQ1Go9HWOAFAXFwc1Go10tPT8eCDDyItLQ3Dhw+3NU6XX+fVV1/F+fPn4eXl1SRZfqqmpgY1NTW2781m8xU1RERE7ZW/pwGPDg3Fo0NDcbG2HmnHSrE9rwT7Tp5H9lkzisw12JhdhI3ZRXaP66jXwtdDD9+OBnQwaOGm08BNp4Feq4GLRoUXR/dRaI8cbJ5KSkpgsVjg52d/k0A/Pz/b0Z2fKiwsbLS+sLDQtv3yumvV+Pr62gfXauHt7W1XExoaesVzXN7m5eXVJFl+av78+XjppZca3UZEREQ/cNNpMbK3H0b2bvicraq14NDpcmSeMeHY95XIK6rE0aIKmKvrUVFTj4rv63Hs+wtXPI9eq247zRNdadasWXZHs8xmM4KCghRMRERE1Da46jSI6d4JMd072a2vrKlHkbkaReZqfF9Rg8qaelTVWlBVa0FNvVXxWc0dap58fHyg0WhQVGR/aK2oqAj+/v6NPsbf3/+a9Ze/FhUVISAgwK5mwIABtpri4mK756ivr0dZWZnd8zT2Oj9+jabI8lN6vR56vb7RbUREROS4DnotOnTugB6dOygdpVEOTVWg0+kwePBgpKam2tZZrVakpqYiNja20cfExsba1QNASkqKrT40NBT+/v52NWazGenp6baa2NhYlJeXIyMjw1azadMmWK1WxMTE2Gq2bduGuro6u9fp1asXvLy8miwLERERtXOOXsq3YsUK0ev1smzZMsnJyZGpU6eK0WiUwsJCERGZMGGCzJw501a/c+dO0Wq18tprr8nhw4dl7ty5jU4PYDQaZc2aNXLo0CEZM2ZMo1MVDBw4UNLT02XHjh0SFhZmN1VBeXm5+Pn5yYQJEyQrK0tWrFghbm5uV0xV0BRZroVTFRAREbU9jnx+O9w8iYgsXrxYgoODRafTSXR0tOzevdu2bcSIETJx4kS7+pUrV0p4eLjodDqJjIyUtWvX2m23Wq0ye/Zs8fPzE71eLyNHjpTc3Fy7mtLSUklMTJQOHTqIh4eHTJ48WSoqKuxqDh48KEOHDhW9Xi9dunSRBQsWXJG9KbJcC5snIiKitqdZ53mia+M8T0RERG1Ps9+ehYiIiKi9YvNERERE5AA2T0REREQOYPNERERE5AA2T0REREQOYPNERERE5AA2T0REREQOYPNERERE5AA2T0REREQO0CodwNlcnrDdbDYrnISIiIhu1OXP7Ru58QqbpyZWUVEBAAgKClI4CRERETmqoqICnp6e16zhve2amNVqxdmzZ9GxY0eoVKomfW6z2YygoCCcOnWqXdw3j/vr/NrbPnN/nVt721/AufZZRFBRUYHAwECo1dce1cQjT01MrVaja9euzfoaHh4ebf6X1BHcX+fX3vaZ++vc2tv+As6zz9c74nQZB4wTEREROYDNExEREZED2Dy1IXq9HnPnzoVer1c6Sovg/jq/9rbP3F/n1t72F2if+wxwwDgRERGRQ3jkiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHMDmqQ1ZsmQJunXrBoPBgJiYGOzZs0fpSFfYtm0b7r//fgQGBkKlUmH16tV220UEc+bMQUBAAFxdXREXF4e8vDy7mrKyMiQlJcHDwwNGoxFTpkxBZWWlXc2hQ4cwbNgwGAwGBAUFYeHChVdkWbVqFSIiImAwGBAVFYV169Y1+f7Onz8ft9xyCzp27AhfX18kJCQgNzfXrqa6uhrTpk1Dp06d0KFDBzz00EMoKiqyqzl58iRGjx4NNzc3+Pr64oUXXkB9fb1dzZYtWzBo0CDo9Xr07NkTy5YtuyJPc/+OvP322+jXr59tQrzY2FisX7/eKfe1MQsWLIBKpcJzzz1nW+dM+zxv3jyoVCq7JSIiwin39bIzZ87gN7/5DTp16gRXV1dERUXh22+/tW13tr9Z3bp1u+JnrFKpMG3aNADO+TNuFkJtwooVK0Sn08kHH3wg2dnZ8vjjj4vRaJSioiKlo9lZt26dvPjii/LFF18IAPnyyy/tti9YsEA8PT1l9erVcvDgQXnggQckNDRUqqqqbDWjRo2S/v37y+7du2X79u3Ss2dPSUxMtG03mUzi5+cnSUlJkpWVJcuXLxdXV1d55513bDU7d+4UjUYjCxculJycHPnzn/8sLi4ukpmZ2aT7Gx8fLx9++KFkZWXJgQMH5N5775Xg4GCprKy01Tz55JMSFBQkqamp8u2338qtt94qt912m217fX299O3bV+Li4mT//v2ybt068fHxkVmzZtlqjh8/Lm5ubjJ9+nTJycmRxYsXi0ajkQ0bNthqWuJ35KuvvpK1a9fK0aNHJTc3V/70pz+Ji4uLZGVlOd2+/tSePXukW7du0q9fP3n22Wdt651pn+fOnSuRkZFy7tw52/L999875b6KiJSVlUlISIhMmjRJ0tPT5fjx47Jx40bJz8+31Tjb36zi4mK7n29KSooAkM2bN4uI8/2MmwubpzYiOjpapk2bZvveYrFIYGCgzJ8/X8FU1/bT5slqtYq/v78sWrTItq68vFz0er0sX75cRERycnIEgOzdu9dWs379elGpVHLmzBkREXnrrbfEy8tLampqbDUzZsyQXr162b4fO3asjB492i5PTEyMPPHEE026jz9VXFwsAGTr1q0i0rB/Li4usmrVKlvN4cOHBYCkpaWJSEPDqVarpbCw0Fbz9ttvi4eHh20f//jHP0pkZKTda40bN07i4+Nt3yv1O+Ll5SX/+te/nHpfKyoqJCwsTFJSUmTEiBG25snZ9nnu3LnSv3//Rrc5276KNPzdGDp06FW3t4e/Wc8++6z06NFDrFarU/6MmwtP27UBtbW1yMjIQFxcnG2dWq1GXFwc0tLSFEzmmIKCAhQWFtrth6enJ2JiYmz7kZaWBqPRiCFDhthq4uLioFarkZ6ebqsZPnw4dDqdrSY+Ph65ubk4f/68rebHr3O5prnfL5PJBADw9vYGAGRkZKCurs4uS0REBIKDg+32OSoqCn5+fnZZzWYzsrOzb2h/lPgdsVgsWLFiBS5cuIDY2Fin3tdp06Zh9OjRV+Ryxn3Oy8tDYGAgunfvjqSkJJw8edJp9/Wrr77CkCFD8PDDD8PX1xcDBw7Ee++9Z9vu7H+zamtr8fHHH+PRRx+FSqVyyp9xc2Hz1AaUlJTAYrHY/bICgJ+fHwoLCxVK5bjLWa+1H4WFhfD19bXbrtVq4e3tbVfT2HP8+DWuVtOc75fVasVzzz2H22+/HX379rXl0Ol0MBqNV83yc/bHbDajqqqqRX9HMjMz0aFDB+j1ejz55JP48ssv0adPH6fcVwBYsWIF9u3bh/nz51+xzdn2OSYmBsuWLcOGDRvw9ttvo6CgAMOGDUNFRYXT7SsAHD9+HG+//TbCwsKwceNGPPXUU3jmmWfw0Ucf2WV21r9Zq1evRnl5OSZNmmTL4Gw/4+aiVToAkbOYNm0asrKysGPHDqWjNKtevXrhwIEDMJlM+OyzzzBx4kRs3bpV6VjN4tSpU3j22WeRkpICg8GgdJxmd88999j+u1+/foiJiUFISAhWrlwJV1dXBZM1D6vViiFDhuCvf/0rAGDgwIHIysrC0qVLMXHiRIXTNb/3338f99xzDwIDA5WO0ubwyFMb4OPjA41Gc8UVD0VFRfD391coleMuZ73Wfvj7+6O4uNhue319PcrKyuxqGnuOH7/G1Wqa6/16+umnkZycjM2bN6Nr16629f7+/qitrUV5eflVs/yc/fHw8ICrq2uL/o7odDr07NkTgwcPxvz589G/f3/84x//cMp9zcjIQHFxMQYNGgStVgutVoutW7fizTffhFarhZ+fn9Pt848ZjUaEh4cjPz/fKX++AQEB6NOnj9263r17205VOvPfrO+++w7ffPMNHnvsMds6Z/wZNxc2T22ATqfD4MGDkZqaaltntVqRmpqK2NhYBZM5JjQ0FP7+/nb7YTabkZ6ebtuP2NhYlJeXIyMjw1azadMmWK1WxMTE2Gq2bduGuro6W01KSgp69eoFLy8vW82PX+dyTVO/XyKCp59+Gl9++SU2bdqE0NBQu+2DBw+Gi4uLXZbc3FycPHnSbp8zMzPt/gCnpKTAw8PD9of9evuj5O+I1WpFTU2NU+7ryJEjkZmZiQMHDtiWIUOGICkpyfbfzrbPP1ZZWYljx44hICDAKX++t99++xVTixw9ehQhISEAnPNv1mUffvghfH19MXr0aNs6Z/wZNxulR6zTjVmxYoXo9XpZtmyZ5OTkyNSpU8VoNNpd8dAaVFRUyP79+2X//v0CQP7+97/L/v375bvvvhORhst+jUajrFmzRg4dOiRjxoxp9LLfgQMHSnp6uuzYsUPCwsLsLvstLy8XPz8/mTBhgmRlZcmKFSvEzc3tist+tVqtvPbaa3L48GGZO3dus1z2+9RTT4mnp6ds2bLF7vLfixcv2mqefPJJCQ4Olk2bNsm3334rsbGxEhsba9t++dLfu+++Ww4cOCAbNmyQzp07N3rp7wsvvCCHDx+WJUuWNHrpb3P/jsycOVO2bt0qBQUFcujQIZk5c6aoVCr5+uuvnW5fr+bHV9s52z7/4Q9/kC1btkhBQYHs3LlT4uLixMfHR4qLi51uX0Uapp/QarXyl7/8RfLy8uS///2vuLm5yccff2yrcba/WSINV7YFBwfLjBkzrtjmbD/j5sLmqQ1ZvHixBAcHi06nk+joaNm9e7fSka6wefNmAXDFMnHiRBFpuPR39uzZ4ufnJ3q9XkaOHCm5ubl2z1FaWiqJiYnSoUMH8fDwkMmTJ0tFRYVdzcGDB2Xo0KGi1+ulS5cusmDBgiuyrFy5UsLDw0Wn00lkZKSsXbu2yfe3sX0FIB9++KGtpqqqSn7729+Kl5eXuLm5yYMPPijnzp2ze54TJ07IPffcI66uruLj4yN/+MMfpK6uzq5m8+bNMmDAANHpdNK9e3e717isuX9HHn30UQkJCRGdTiedO3eWkSNH2honZ9vXq/lp8+RM+zxu3DgJCAgQnU4nXbp0kXHjxtnNeeRM+3rZ//73P+nbt6/o9XqJiIiQd9991267s/3NEhHZuHGjALhiP0Sc82fcHFQiIooc8iIiIiJqgzjmiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHMDmiYiIiMgBbJ6IiIiIHPD/4rXiiE+kNeoAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(lrs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "a88dc232",
   "metadata": {},
   "outputs": [],
   "source": [
    "accelerator.free_memory()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "87ddc33d",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save_pretrained('/raid/models/lora_apaca_llama2_better_hyperparams')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2ec39dd3",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os._exit(00)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}