diff --git a/.gitignore b/.gitignore index e19a231..1d97f12 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,6 @@ .env lightning_logs/ +outputs/ *.arrow squad_* diff --git a/README.md b/README.md index 7aa2f1f..d5b0115 100644 --- a/README.md +++ b/README.md @@ -34,3 +34,19 @@ When using microsoft/phi-2 we get this amount of perplexity reduction by includi As you can see, some of these are probobly in the training set + +# Citing + +If you like our work and end up using this code for your reseach give us a shout-out by citing or acknowledging + +``` +@misc{wassname2024, + author = {Clark, M.J.}, + title = {BS Writing Detector}, + year = {2024}, + publisher = {GitHub}, + journal = {GitHub repository}, + howpublished = {\url{https://github.com/wassname/detect_bs_text}}, + commit = {} +} +``` diff --git a/nbs/02_use_lora_transformertrain_WORK.ipynb b/nbs/02_use_lora_transformertrain_WORK.ipynb new file mode 100644 index 0000000..c38c13f --- /dev/null +++ b/nbs/02_use_lora_transformertrain_WORK.ipynb @@ -0,0 +1,1611 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "https://github.com/huggingface/peft/blob/main/examples/fp4_finetuning/finetune_fp4_opt_bnb_peft.py" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-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": [ + "from torch import optim\n", + "import lightning as pl\n", + "from matplotlib import pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import transformers\n", + "from datasets import load_dataset\n", + "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig\n", + "import numpy as np\n", + "from tqdm.auto import tqdm\n", + "import pandas as pd\n", + "import warnings\n", + "from peft import LoraConfig, get_peft_model, IA3Config" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "plt.style.use('ggplot')\n", + "torch.set_float32_matmul_precision('medium')\n", + "warnings.filterwarnings(\"ignore\", \".*does not have many workers.*\")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n", + "\n", + "model_name = \"microsoft/phi-2\"\n", + "\n", + "# model = AutoModelForCausalLM.from_pretrained(\n", + "# model_name,\n", + "# # max_memory=max_memory,\n", + "# quantization_config=BitsAndBytesConfig(\n", + "# load_in_4bit=True,\n", + "# llm_int8_threshold=6.0,\n", + "# llm_int8_has_fp16_weight=False,\n", + "# bnb_4bit_compute_dtype=torch.float16,\n", + "# bnb_4bit_use_double_quant=True,\n", + "# bnb_4bit_quant_type=\"nf4\",\n", + "# ),\n", + "# torch_dtype=torch.float16,\n", + "# trust_remote_code=True,\n", + "# )\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "model_name = \"TheBloke/phi-2-GPTQ\"\n", + "# model_name = \"microsoft/phi-2\"\n", + "\n", + "def load_model():\n", + "\n", + " # model = AutoModelForCausalLM.from_pretrained(\n", + " # model_name,\n", + " # # quantization_config=BitsAndBytesConfig(\n", + " # # load_in_4bit=True,\n", + " # # llm_int8_threshold=6.0,\n", + " # # llm_int8_has_fp16_weight=False,\n", + " # # bnb_4bit_compute_dtype=torch.float16,\n", + " # # bnb_4bit_use_double_quant=True,\n", + " # # bnb_4bit_quant_type=\"nf4\",\n", + " # # ),\n", + " # torch_dtype=torch.float16,\n", + " # trust_remote_code=True,\n", + " # )\n", + "\n", + "\n", + " config = AutoConfig.from_pretrained(model_name, trust_remote_code=True,)\n", + " config.quantization_config['use_exllama'] = False\n", + " config.quantization_config['disable_exllama'] = True\n", + " model = AutoModelForCausalLM.from_pretrained(\n", + " model_name,\n", + " torch_dtype=torch.bfloat16,\n", + " trust_remote_code=True,\n", + " config=config,\n", + " )\n", + " return model\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "CUDA extension not installed.\n", + "CUDA extension not installed.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n" + ] + } + ], + "source": [ + "base_model = load_model()\n", + "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True,)\n", + "tokenizer.pad_token = tokenizer.eos_token" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "def reset_model(base_model):\n", + " peft_config = LoraConfig(\n", + " # task_type=TaskType.TOKEN_CLS, \n", + " target_modules=[ \"fc2\", \"Wqkv\",],\n", + " inference_mode=False, r=4, lora_alpha=4, \n", + " # lora_dropout=0.1, \n", + " # bias=\"all\"\n", + " )\n", + " # peft_config = IA3Config(\n", + " # target_modules=[ \"fc2\", \"Wqkv\",], \n", + " # feedforward_modules=[\"fc2\"],\n", + " # inference_mode=False,\n", + " # )\n", + " model = get_peft_model(base_model, peft_config)\n", + " model.config.use_cache = False\n", + " return model\n", + "\n", + "model = reset_model(base_model)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "MAX_LEN = 2000\n", + "samples = json.load(open(\"../samples.json\"))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "# modified from https://github.dev/huggingface/evaluate/blob/8dfe05784099fb9af55b8e77793205a3b7c86465/measurements/perplexity/perplexity.py#L154\n", + "\n", + "# from evaluate.measurements.perplexity import Perplexity\n", + "import evaluate\n", + "from evaluate import logging\n", + "from torch.nn import CrossEntropyLoss\n", + "\n", + "# @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)\n", + "def perplexity_compute(\n", + " data, model, tokenizer, batch_size: int = 16, add_start_token: bool = True, device=None, max_length=None\n", + "):\n", + "\n", + " if device is not None:\n", + " assert device in [\"gpu\", \"cpu\", \"cuda\"], \"device should be either gpu or cpu.\"\n", + " if device == \"gpu\":\n", + " device = \"cuda\"\n", + " else:\n", + " device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "\n", + " # model = AutoModelForCausalLM.from_pretrained(model_id)\n", + " model = model.to(device)\n", + "\n", + " # tokenizer = AutoTokenizer.from_pretrained(model_id)\n", + "\n", + " # # if batch_size > 1 (which generally leads to padding being required), and\n", + " # # if there is not an already assigned pad_token, assign an existing\n", + " # # special token to also be the padding token\n", + " # if tokenizer.pad_token is None and batch_size > 1:\n", + " # existing_special_tokens = list(tokenizer.special_tokens_map_extended.values())\n", + " # # check that the model already has at least one special token defined\n", + " # assert (\n", + " # len(existing_special_tokens) > 0\n", + " # ), \"If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1.\"\n", + " # # assign one of the special tokens to also be the pad token\n", + " # tokenizer.add_special_tokens({\"pad_token\": existing_special_tokens[0]})\n", + "\n", + " # if add_start_token and max_length:\n", + " # # leave room for token to be added:\n", + " # assert (\n", + " # tokenizer.bos_token is not None\n", + " # ), \"Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False\"\n", + " # max_tokenized_len = max_length - 1\n", + " # else:\n", + " max_tokenized_len = max_length\n", + "\n", + " encodings = tokenizer(\n", + " data,\n", + " add_special_tokens=False,\n", + " padding=True,\n", + " truncation=True if max_tokenized_len else False,\n", + " max_length=max_tokenized_len,\n", + " return_tensors=\"pt\",\n", + " return_attention_mask=True,\n", + " ).to(device)\n", + "\n", + " encoded_texts = encodings[\"input_ids\"]\n", + " attn_masks = encodings[\"attention_mask\"]\n", + "\n", + " # check that each input is long enough:\n", + " if add_start_token:\n", + " assert torch.all(torch.ge(attn_masks.sum(1), 1)), \"Each input text must be at least one token long.\"\n", + " else:\n", + " assert torch.all(\n", + " torch.ge(attn_masks.sum(1), 2)\n", + " ), \"When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings.\"\n", + "\n", + " ppls = []\n", + " loss_fct = CrossEntropyLoss(reduction=\"none\")\n", + "\n", + " for start_index in logging.tqdm(range(0, len(encoded_texts), batch_size)):\n", + " end_index = min(start_index + batch_size, len(encoded_texts))\n", + " encoded_batch = encoded_texts[start_index:end_index]\n", + " attn_mask = attn_masks[start_index:end_index]\n", + "\n", + " # if add_start_token:\n", + " # bos_tokens_tensor = torch.tensor([[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)).to(device)\n", + " # encoded_batch = torch.cat([bos_tokens_tensor, encoded_batch], dim=1)\n", + " # attn_mask = torch.cat(\n", + " # [torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(device), attn_mask], dim=1\n", + " # )\n", + "\n", + " labels = encoded_batch\n", + "\n", + " with torch.no_grad():\n", + " out_logits = model(encoded_batch, attention_mask=attn_mask).logits\n", + " # print(out_logits.shape)\n", + "\n", + " shift_logits = out_logits[..., :-1, :].contiguous()\n", + " shift_labels = labels[..., 1:].contiguous()\n", + " shift_attention_mask_batch = attn_mask[..., 1:].contiguous()\n", + "\n", + " perplexity_batch = torch.exp(\n", + " (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch).sum(1)\n", + " / shift_attention_mask_batch.sum(1)\n", + " )\n", + " # perplexity_batch = torch.exp(\n", + " # (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch)\n", + " # / shift_attention_mask_batch.sum(1)\n", + " # )\n", + " # print(perplexity_batch.shape)\n", + "\n", + " ppls += perplexity_batch.tolist()\n", + "\n", + " return {\"perplexities\": ppls, \"mean_perplexity\": torch.tensor(ppls).mean()}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [], + "source": [ + "# perplexity_compute(\n", + "# second_half, model, tokenizer\n", + "# )" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Training" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "from torch.nn import functional as F\n", + "from torch.utils.data import DataLoader, TensorDataset" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Lightning helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "\n", + "\n", + "# def str2xya(s, tokenizer):\n", + "# max_len = min(MAX_LEN, len(s))\n", + "# input_ids = tokenizer(s, return_tensors=\"pt\")[\"input_ids\"][0]\n", + "\n", + "# pad = tokenizer.bos_token_id\n", + "# data = []\n", + "# for i in range(1, len(input_ids)):\n", + "# x = input_ids[:i][-max_len:]\n", + "# padding = max_len - len(x)\n", + "# x = torch.tensor([pad]*padding + x.tolist())\n", + "\n", + "# labels = input_ids[i:i+1]\n", + "# attention_mask = (x==pad)*1\n", + "# data.append(dict(input_ids=x, labels=labels, attention_mask=attention_mask, return_loss=True))\n", + " \n", + "# return data\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "def eval(model, tokenizer, second_half):\n", + " model.eval();\n", + " with torch.no_grad():\n", + " with model.disable_adapter():\n", + " results = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " results2 = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " return dict(before=results['mean_perplexity'].item(), after=results2['mean_perplexity'].item())\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Train" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "from datasets import Dataset\n", + "\n", + "\n", + "def compute_metrics(eval_prediction):\n", + " return {}" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trainer docs\n", + "\n", + "- https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "def learn_sample(sample):\n", + " # device = 'cuda'\n", + " # lr = 4e-3\n", + " # epochs = 3\n", + " # accum_steps = 1\n", + " batch_size = 6\n", + " verbose = True\n", + "\n", + " s = sample['text']\n", + " first_half = s[:len(s)//2]\n", + " second_half = s[len(s)//2:]\n", + " ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + " ds_val = Dataset.from_dict(tokenizer([second_half]))\n", + "\n", + " os.environ['CUDA_VISIBLE_DEVICES']=\"1\"\n", + " model = reset_model(base_model)\n", + " eval(model, tokenizer, second_half)\n", + "\n", + " # https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer\n", + " trainer = transformers.Trainer(\n", + " model=model,\n", + " train_dataset=ds_train,\n", + " eval_dataset=ds_val,\n", + " compute_metrics=compute_metrics, # without this it wont even give val loss\n", + " args=transformers.TrainingArguments(\n", + " label_names=['labels',],\n", + " per_device_train_batch_size=batch_size,\n", + " gradient_accumulation_steps=8,\n", + " warmup_steps=0,\n", + " max_steps=3,\n", + " learning_rate=3e-4,\n", + " fp16=True,\n", + " logging_steps=1,\n", + " output_dir=\"outputs\",\n", + " log_level='error',\n", + " # do_eval=True,\n", + " evaluation_strategy=\"epoch\",\n", + " eval_steps=1,\n", + " \n", + " # disable_tqdm=not verbose,\n", + " ),\n", + " data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),\n", + " )\n", + " trainer._signature_columns = ['input_ids', 'attention_mask', 'labels',]\n", + " model.config.use_cache = False # silence the warnings. Please re-enable for inference!\n", + " train_output = trainer.train()\n", + "\n", + " df_hist = pd.DataFrame(trainer.state.log_history)\n", + " df_hist_epoch = df_hist.groupby('epoch').last().dropna(axis=1).drop(columns=['step'])\n", + " df_hist_step = df_hist.set_index('step').dropna(thresh=2, axis=1)\n", + " if verbose:\n", + " df_hist_epoch[['eval_loss', 'loss']].plot()\n", + " # for c in df_hist_epoch.columns:\n", + " # df_hist_epoch[[c]].plot()\n", + "\n", + "\n", + " result_train = {f'train/{k}':v for k,v in eval(model, tokenizer, first_half).items()}\n", + " result = eval(model, tokenizer, second_half)\n", + " result['hist'] = df_hist_epoch\n", + " result.update(result_train)\n", + " return result\n" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "bad_ml\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 3.50it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 4.88it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + " 0%| | 0/3 [00:00 4\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43mlearn_sample\u001b[49m\u001b[43m(\u001b[49m\u001b[43msample\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;28mdict\u001b[39m(before\u001b[38;5;241m=\u001b[39mr[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbefore\u001b[39m\u001b[38;5;124m'\u001b[39m], after\u001b[38;5;241m=\u001b[39mr[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mafter\u001b[39m\u001b[38;5;124m'\u001b[39m]))\n\u001b[1;32m 6\u001b[0m data\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;28mdict\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mr, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39msample))\n", + "Cell \u001b[0;32mIn[15], line 17\u001b[0m, in \u001b[0;36mlearn_sample\u001b[0;34m(sample)\u001b[0m\n\u001b[1;32m 15\u001b[0m os\u001b[38;5;241m.\u001b[39menviron[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCUDA_VISIBLE_DEVICES\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m1\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 16\u001b[0m model \u001b[38;5;241m=\u001b[39m reset_model(base_model)\n\u001b[0;32m---> 17\u001b[0m \u001b[38;5;28;43meval\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msecond_half\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;66;03m# https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer\u001b[39;00m\n\u001b[1;32m 20\u001b[0m trainer \u001b[38;5;241m=\u001b[39m transformers\u001b[38;5;241m.\u001b[39mTrainer(\n\u001b[1;32m 21\u001b[0m model\u001b[38;5;241m=\u001b[39mmodel,\n\u001b[1;32m 22\u001b[0m train_dataset\u001b[38;5;241m=\u001b[39mds_train,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 42\u001b[0m data_collator\u001b[38;5;241m=\u001b[39mtransformers\u001b[38;5;241m.\u001b[39mDataCollatorForLanguageModeling(tokenizer, mlm\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m),\n\u001b[1;32m 43\u001b[0m )\n", + "Cell \u001b[0;32mIn[13], line 6\u001b[0m, in \u001b[0;36meval\u001b[0;34m(model, tokenizer, second_half)\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m model\u001b[38;5;241m.\u001b[39mdisable_adapter():\n\u001b[1;32m 5\u001b[0m results \u001b[38;5;241m=\u001b[39m perplexity_compute(data\u001b[38;5;241m=\u001b[39msecond_half, model\u001b[38;5;241m=\u001b[39mmodel, tokenizer\u001b[38;5;241m=\u001b[39mtokenizer, device\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcuda\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 6\u001b[0m results2 \u001b[38;5;241m=\u001b[39m \u001b[43mperplexity_compute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msecond_half\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mcuda\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mdict\u001b[39m(before\u001b[38;5;241m=\u001b[39mresults[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmean_perplexity\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mitem(), after\u001b[38;5;241m=\u001b[39mresults2[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmean_perplexity\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mitem())\n", + "Cell \u001b[0;32mIn[9], line 85\u001b[0m, in \u001b[0;36mperplexity_compute\u001b[0;34m(data, model, tokenizer, batch_size, add_start_token, device, max_length)\u001b[0m\n\u001b[1;32m 82\u001b[0m labels \u001b[38;5;241m=\u001b[39m encoded_batch\n\u001b[1;32m 84\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[0;32m---> 85\u001b[0m out_logits \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mencoded_batch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattn_mask\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mlogits\n\u001b[1;32m 86\u001b[0m \u001b[38;5;66;03m# print(out_logits.shape)\u001b[39;00m\n\u001b[1;32m 88\u001b[0m shift_logits \u001b[38;5;241m=\u001b[39m out_logits[\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m, :\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, :]\u001b[38;5;241m.\u001b[39mcontiguous()\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/peft/peft_model.py:536\u001b[0m, in \u001b[0;36mPeftModel.forward\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 532\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs: Any, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any):\n\u001b[1;32m 533\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 534\u001b[0m \u001b[38;5;124;03m Forward pass of the model.\u001b[39;00m\n\u001b[1;32m 535\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 536\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_base_model\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/TheBloke/phi-2-GPTQ/8c61fa56159b3e69e768afcbebaf14bdb11532f2/modeling_phi.py:953\u001b[0m, in \u001b[0;36mPhiForCausalLM.forward\u001b[0;34m(self, input_ids, past_key_values, attention_mask, labels, **kwargs)\u001b[0m\n\u001b[1;32m 945\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m 946\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 947\u001b[0m input_ids: torch\u001b[38;5;241m.\u001b[39mLongTensor,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 951\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 952\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m CausalLMOutputWithPast:\n\u001b[0;32m--> 953\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtransformer\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 954\u001b[0m lm_logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlm_head(hidden_states)\n\u001b[1;32m 956\u001b[0m loss \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/TheBloke/phi-2-GPTQ/8c61fa56159b3e69e768afcbebaf14bdb11532f2/modeling_phi.py:915\u001b[0m, in \u001b[0;36mPhiModel.forward\u001b[0;34m(self, input_ids, past_key_values, attention_mask)\u001b[0m\n\u001b[1;32m 912\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membd(input_ids)\n\u001b[1;32m 914\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m layer \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mh:\n\u001b[0;32m--> 915\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[43mlayer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 916\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 917\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 918\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 919\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m hidden_states\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/TheBloke/phi-2-GPTQ/8c61fa56159b3e69e768afcbebaf14bdb11532f2/modeling_phi.py:770\u001b[0m, in \u001b[0;36mParallelBlock.forward\u001b[0;34m(self, hidden_states, past_key_values, attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 767\u001b[0m residual \u001b[38;5;241m=\u001b[39m hidden_states\n\u001b[1;32m 768\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mln(hidden_states)\n\u001b[0;32m--> 770\u001b[0m attn_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmixer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 771\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 772\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 773\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 774\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 775\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(attn_outputs, \u001b[38;5;28mtuple\u001b[39m):\n\u001b[1;32m 776\u001b[0m attn_outputs \u001b[38;5;241m=\u001b[39m attn_outputs[\u001b[38;5;241m0\u001b[39m]\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/TheBloke/phi-2-GPTQ/8c61fa56159b3e69e768afcbebaf14bdb11532f2/modeling_phi.py:722\u001b[0m, in \u001b[0;36mMHA.forward\u001b[0;34m(self, x, past_key_values, attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 719\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_head \u001b[38;5;241m==\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_head_kv:\n\u001b[1;32m 720\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m past_key_values \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 721\u001b[0m \u001b[38;5;66;03m# If `past_key_values` are not supplied, we run self-attention\u001b[39;00m\n\u001b[0;32m--> 722\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward_self_attn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 723\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 724\u001b[0m \u001b[38;5;66;03m# If `past_key_values` are supplied, it means that we might have cached values and\u001b[39;00m\n\u001b[1;32m 725\u001b[0m \u001b[38;5;66;03m# could take advantage of cross-attention\u001b[39;00m\n\u001b[1;32m 726\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_cross_attn(x, past_key_values, attention_mask)\n", + "File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/TheBloke/phi-2-GPTQ/8c61fa56159b3e69e768afcbebaf14bdb11532f2/modeling_phi.py:593\u001b[0m, in \u001b[0;36mMHA._forward_self_attn\u001b[0;34m(self, x, key_padding_mask)\u001b[0m\n\u001b[1;32m 590\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_forward_self_attn\u001b[39m(\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28mself\u001b[39m, x: torch\u001b[38;5;241m.\u001b[39mFloatTensor, key_padding_mask: Optional[torch\u001b[38;5;241m.\u001b[39mBoolTensor]\n\u001b[1;32m 592\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m torch\u001b[38;5;241m.\u001b[39mFloatTensor:\n\u001b[0;32m--> 593\u001b[0m qkv \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mWqkv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 594\u001b[0m qkv \u001b[38;5;241m=\u001b[39m rearrange(qkv, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m... (three h d) -> ... three h d\u001b[39m\u001b[38;5;124m\"\u001b[39m, three\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m3\u001b[39m, d\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhead_dim)\n\u001b[1;32m 596\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrotary_dim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1516\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1525\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1526\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1530\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n", + "File \u001b[0;32m/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/peft/tuners/lora/gptq.py:58\u001b[0m, in \u001b[0;36mQuantLinear.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 56\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m requires_conversion:\n\u001b[1;32m 57\u001b[0m expected_dtype \u001b[38;5;241m=\u001b[39m result\u001b[38;5;241m.\u001b[39mdtype\n\u001b[0;32m---> 58\u001b[0m x \u001b[38;5;241m=\u001b[39m \u001b[43mx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlora_A\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 60\u001b[0m output \u001b[38;5;241m=\u001b[39m lora_B(lora_A(dropout(x)))\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m requires_conversion:\n", + "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAG0CAYAAADKEdZ4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABOA0lEQVR4nO3deXgUVfr28e+pLJAEQgiLIQMEwiKMIogICKhsCkJUUEAMjiKKuM/4G1fcHXEEF0DAV1QcwVEhoKgsIrKpLOKGo2ERFXdEghDCEkJCnfePJq1NWJKQpLsr9+e6vKSrq6qfp6sDd06dqjbWWouIiIhImHOCXYCIiIhIWVCoEREREU9QqBERERFPUKgRERERT1CoEREREU9QqBERERFPUKgRERERT1CoEREREU9QqBERERFPiAx2ARVtx44dFBQUlPl+69SpQ1ZWVpnvN1Sov/Dn9R693h94v0f1F/7Ko8fIyEhq1qxZvHXL9JXDQEFBAfn5+WW6T2OMf99e/NYJ9Rf+vN6j1/sD7/eo/sJfKPSo008iIiLiCQo1IiIi4gkKNSIiIuIJCjUiIiLiCZVuorCIiEhF2bNnDwUFBRhjyM3NZf/+/cEuqVyVtsfY2FgiI48/kijUiIiIlIO8vDyMMdSoUQOAqKioMr/6NtSUpkfXddm1axdxcXHHHWx0+klERKQc5OXlERMTE+wyQp7jOFSvXp29e/ce/77KoB4RERE5jMJ7t8jROU7ZxBGFGhEREfEEhRoRERHxBIUaERER8QSFGhEREQGgVq1axMfHB7uMUivVtVMLFixgzpw5ZGdnk5KSwrBhw2jatOkxt1uxYgXjx4+nXbt23H777f7lGRkZrFy5kt9//53IyEhSU1MZPHgwzZo1869zww03FPnmz/T0dPr161eaFsqUu3YNtm6dYJchIiJSqZU41KxcuZJp06YxfPhwmjVrxrx58xg1ahTjxo3zX4t/OFu3buWll16iZcuWRZ5LTk5m2LBhnHDCCezfv5958+bx8MMPM2HChIDEOGjQIHr27Ol/XLVq1ZKWX+bsj9/ijr2PX1+djO11EXTsiomMCnZZIiIilU6JQ83cuXPp0aMH3bp1A2D48OF89tlnLF269IijJq7rMmHCBAYNGsT69evZs2dPwPNdunQJeHz55ZezZMkSfvjhB1q1auVfHhMTQ0JCQklLLl/bs6B6DQ5s+QWmToC5MzDnDcB06oGJUrgRERGw1mLz9mGDcfO96CqlurS88MaBhQMI+/fvZ+fOnRw4cACAiIgIatSoQXR0NAAHDhxg79695Ofn+7etUqUKjuNw4MABdu3aRW5ubtn1dRglCjUFBQVs2rQpILw4jkOrVq3YuHHjEbebNWsW8fHxdO/enfXr1x/zNRYtWkRsbCwpKSkBz73xxhu89tpr1K5dmy5dutC3b18iIiIOu5/8/PyAuxoaY/w3QSrL+waYU8/AOakt1T5bTvbMqfD7Vux/n8bOy8A5bwDmzHMwUdFl9nrBUPh+efV+C17vD7zfo9f7A+/36PX+2J9H3o2DgvLSzsQMqFLyMxsJCQlERkayfft2XNclPj6eWrVqsXXrVgD/2Zlt27ZhrSUyMtL/b3J8fDxRUVH+bSMiIop1bI/3+Jco1OTk5OC6bpHRkoSEBDZv3nzYbTZs2MCSJUsYM2bMUff96aefMm7cOPbv309CQgL33HNPwKmn8847j8aNG1OtWjW++uorXn31VXbs2MEVV1xx2P3Nnj2bWbNm+R83btyY0aNHU6dOOc19SWlEXJ8B7HnnDXbNmsqB37NwX3kGZ8Esql98OXG9L8IJgdNlxyMpKSnYJZQrr/cH3u/R6/2B93v0Un+5ublEHRyxt+4B8oJUR1RUVLHPHBhjcByHqlWrEhMTw44dO7DWYoxh9+7d1KpVi7i4OPbv309kZKT/qyCMMbiui+u6REVFERkZSUFBAeAb/LDWYq31vx+HEx0dTb169Y6r13L97qfc3FwmTJjAiBEjjjmb+qSTTuKxxx4jJyeHxYsXM3bsWB555BF/EkxLS/Ovm5KSQmRkJM899xzp6emHfZP69+8fsE1h+svKyvK/0WXFGENSUhJbd2RjTz8b2pyBs3wR7tszcbdvI/u5J8me/gJO7/6Yrn0wpUjMwVTY35YtW7DWBrucMuf1/sD7PXq9P/B+j17sb//+/f4zBtY4VJk8Oyjf/ZRvHEwxX9dai+u6/hBy6Omiwi/nzM/PZ/fu3dSoUYOoqCjy8vLIzc0NeK5mzZr+4JObm3vM3vfv38+vv/5aZHlkZGSxByRKFGri4+NxHIfs7OyA5dnZ2Yed6/Lbb7+RlZXF6NGj/csKP6yDBw9m3Lhx/lRetWpVkpKSSEpKonnz5tx8880sWbKE/v37H7aWZs2aceDAAbKyskhOTi7yfFRU1BETYXn9wBR+CIiMwnQ9D6dLT+zKJdj5M+H3rbgz/wNvv4Y5tx+mWx9M1dhyqaO8+PvzKK/3B97v0ev9gfd79Gp/xhhMdFWMc/gpE+Fo79697Nu3j6pVq1KlShXq1KnD7t27yc/PJy8vj61bt1KlShWqVKlC7dq12bNnDzk5OUfd5/Ee+xKFmsLLrTMzM2nfvj3gmwScmZlJ7969i6yfnJzM448/HrBs+vTp7Nu3j6FDh1K7du0jvpa19qip7vvvv8cYE9LX05vIKMxZvbCdemBXL8POy4CsLdjXp2HfmY3peQGmexomNi7YpYqIiPgVjsj8+Vu3jTFEREQEnO1wXZe9e/eyd+9eqlevTkxMDLt27fI/l5ubS25uLvv37yc+Pv6YoeZ4lfj0U1paGpMmTSI1NZWmTZsyf/588vLy6Nq1KwATJ04kMTGR9PR0oqOjadiwYcD2cXG+f8ALl+/bt4/XX3+ddu3aUbNmTXbt2sWCBQvYvn07Z5xxBgAbN27k66+/5qSTTiImJoaNGzcydepUzjzzTKpVq3Y8/VcIExmJ6dwT27Eb9qP3feHmt1+wb76MXfgGpuf5mB4XYOJCvxcREfG+AwcOkJubS0JCAjt37vRPFHZdl3379gG+szd5eXkUFBTgOA5VqlTxB57q1av7L9gxxlC1atUyn/pxOCUONZ06dSInJ4eMjAyys7Np1KgRI0eO9J9+2rZtW4lmLzuOw+bNm3niiSfYtWsX1atXp0mTJjz44IM0aNDAV2RkJCtXrmTmzJnk5+dTt25d+vbtGzBnJhyYiAjMGd2wHc7CfrzcF25+/Qk7Zzr23Tcx3c/HnHMBplrojj6JiEjlkJ2dTY0aNUhMTAR8c15+//33gHVq1KhBREQEruuSl5fH3r17Ad/ZlurVq/uvhsrLy2PHjh3lXrOxXjx5eRRZWVllPlHLGEO9evX49ddfS3Q+0LoufLYSd+4M+OUH38IqMb75NudciIlPKNM6S6u0/YULr/cH3u/R6/2B93v0Yn85OTkBUyT+fCrHq46nx0Pfrz/vs1wmCkvZMo4D7brgtO0En6/GnTsdfvoOu+A17JK5mK7nYc7tj6lRM9ilioiIhDyFmhBgHAfanoFzakf44mPcOdPhh2+wC9/ALp2POasXpvdFmIRawS5VREQkZCnUhBBjDLRuj3PK6bD2M1+42fQVdvEc7HsLMF3OwfS+GFNLX54pIiJyKIWaEGSMgZNPwzmpLaz/ny/cfLMOu2w+9oOFmM49fN8vVfuEYJcqIiISMhRqQpgxBv7aBqdla/jqS9+E4q++xL7/DnbFIkzHbpg+AzF1j++20iIiUj4Kv2JAjs513TLZj0JNGDDGQItTiGhxCnbjWtx5M2Dd59gVi7CrlmA6nI3pMwiT9JdglyoiIgdVqVKF3NxcYmPD6+7xFc11XXbt2uW/j93xUKgJM6b5SUQ0fwj77QbfyE3mp9hVS7Efvoc5/UxM34GY5IbH3pGIiJSrKlWqsGfPHnbu3IkxhujoaPbv3x/ssspVaXuMi4sjMvL4I4lCTZgyTVoQ8ff7sd997Ru5+d9H2I/ew378Pua0zpi+gzD1GwW7TBGRSq1w9MGL9+E5VCj0qFAT5kzjZkTceA/2h2994WbNh9hPlmM/We67TLzvJZiGqcEuU0REpNwp1HiESWlCxPUjsT9/h52bgf1sJXy2CvezVb7LxNMuwTRqFuwyRUREyo1CjceY+o0x196B/eVH7PwM7McfwP8+wv3fR9CqHU7fQZgmLYJdpoiISJlTqPEo85eGmOG3YtMGY+fPxK5+D778BPfLT+Cvp+Kcfwmm6V+DXaaIiEiZUajxOFOvPuaqW7DnX+ILN6uWwro1uOvWQItTcNIGY048OdhlioiIHDeFmkrC1E3GDP07tu8l2LdnYVcugQ1f4G74ApqfhJM2GFqcoptEiYhI2HKCXYBULFMnCefyG3FGPYPpeh5ERsLGtbhP3os7+g5s5meevdxQRES8TaGmkjK16uIMuQ5n1LOY7mkQFQ3fbsAd/wDuI7di//exwo2IiIQVhZpKziTWxrn0GpxHnsWccyFER8P3X+NO/Bfuw7dg13yILaPv5BARESlPCjUCgElIxBl0Fc6/n8f0ugiqVIUfN+E+/QgHHvo7e5cvUrgREZGQplAjAUx8As6Aob5w02cgVI2Bn7/n93/fyYEHbsL96H2seyDYZYqIiBShUCOHZarH4/T/G86jz2POH4yJqwabf8Q+9zju/TfifrgUe0DhRkREQodCjRyViatOxIVDSH5hDs6FQyC2Gmz5BTtlLO591+OuWIwtKAh2mSIiIgo1UjxOteo45w/2jdz0/xtUqw5bf8W+OB733utwP1iILcgPdpkiIlKJKdRIiZiYWJw+A31zbgYMheo1YNtv2GkTce++FnfZ29h8hRsREal4CjVSKqZqDE6vi3zhZtBVUKMmbM/Cvvz/cEdeg7tkLjZ/f7DLFBGRSkShRo6LqVIF55wLffe5GXwNJCRC9u/YV5/Fvesa3EVvYvPygl2miIhUAgo1UiZMdBWcHmm+cDPkWkisDTu3Y2dMwb3ratx3Xsfuyw12mSIi4mEKNVKmTFQ0Ttc+OKMmYy6/EWrVhV07sbNe9IWb+TOxuXuDXaaIiHiQvqVbyoWJjMKceS72jO7Y1cuw8zIgawt29kvYd2ZjzrkA0z0NE1st2KWKiIhHKNRIuTKRkZjOPbEdu2E/ft8Xbrb8gn3zFezCNzE9zsf0PB8TVz3YpYqISJhTqJEKYSIiMB27Ydufhf1kBXbuDPj1J+zc6dhFb/pGbXpeiKkeH+xSRUQkTCnUSIUyTgSm/VnYdl1gzSrcOdPhlx+w82diF8/BdO2DObcfJj4h2KWKiEiYUaiRoDCOA6d1xjn1DPjfR7hzp8OPm7DvvI5dOhdz9nmYc/tjEhKDXaqIiIQJhRoJKuM4cGpHnDYd4ItPfOHm+6+x776JXfY25qxemF4XYWrWCnapIiIS4hRqJCQYY6D16TintIO1n/lOS236Crt4Dva9tzFdzsX0vhhTq06wSxURkRClUCMhxRgDJ5+Gc1JbWP8/X7j5Zh122XzsBwsxnXv4wk2dpGCXKiIiIUahRkKSMQb+2ganZWvYmOkLN199iX3/HezydzFndMP0GYipmxzsUkVEJEQo1EhIM8bAia2IOLEVduNa3HkzYN3n2BWLsauWYjqc7Qs3SfWDXaqIiASZQo2EDdP8JCKaP4T9dgPu3BmQ+Sl21VLsh+9hTj8T03cgJrlhsMsUEZEgUaiRsGOatCDi7/djv/vaN3Lzv4+wH72H/fh9TNtOmLRBmPqNg12miIhUMIUaCVumcTMibrwH++O3uPMy4LNV2E9XYD9d4btMPO0STMMmwS5TREQqiEKNhD3TsAkR192F/fl77LwMX6hZ8yHumg+hdXucvpdgGjcLdpkiIlLOFGrEM0z9RpgRt2M3/4idNxP78Qe+uxX/7yPfZeJpl2CatAh2mSIiUk4UasRzTHJDzPB/Ys+/xPedUqvfg8xPcTM/9V0mnjYY0+yvwS5TRETKmEKNeJZJqo8Zdgs27RLs/FnYD5fCus9x130OJ7bCOX8wND/Zd9m4iIiEPYUa8TxTNxkz9GZs30HYBa9hVyyGr77E/epLaPZXOP9SbJLuUCwiEu6cYBcgUlFMnSScv92AM2oypmsfiIyEr9fhPnkvW2+9CjfzU6y1wS5TRERKSSM1UumYWnUwQ67F9hmIfed17PvvsH/DF7DhC2jUDCdtMJzSTqelRETCjEZqpNIyNWvhDB5OxL+fo1r/IRAdDd9/jTvxX7gP34L9bBXWdYNdpoiIFJNCjVR6JiGRmlffQsSjUzC9LoIqVeHHTbj/79+4D/0d+8lyhRsRkTCgUCNykIlPwBkwFOffz2P6DIKqMfDLD7iTx+A+cBPu6vew7oFglykiIkegUCNyCFM9Hqf/ZTiPPo9JGwwxcfDrT9jnn8C9/0bcVUuxBxRuRERCjUKNyBGYuOo4F6bjPPoc5sIhEFsNtvyCfWEs7r3X4a5YhC0oCHaZIiJykEKNyDGY2Go4aZf4Rm4uuhyqVYesLdgXn8K951rc99/BFuQHu0wRkUpPoUakmExMLM55A3xzbgZcCdVrwO9bsS9Nwr17BO6y+dh8hRsRkWBRqBEpIVM1BqdXf1+4ueQqqFETtm/DvvwM7shrcBfPxe7PC3aZIiKVjkKNSCmZKlVwel6I88izmEuvgYRakP07dvqzvnDz7pvYPIUbEZGKolAjcpxMdBWc7mm+cDPkOkisAzt3YDOm4N51Ne47r2P35Qa7TBERz1OoESkjJioKp+t5OKOewVx+I9Q+AXbtxM560Rdu5s/E5u4NdpkiIp6l734SKWMmMgpz5rnYM7pjV7+HnZ8BW3/Fzn4J+85sTM8LMD3SMLHVgl2qiIinKNSIlBMTGYnp3APbsSv24/ex8zJ897l56xXsu29iepyP6Xk+Jq56sEsVEfEEhRqRcmYiIjAdu2Hbn4X9ZAV27gzfHYrnTscuehPTrS/mnH6Y6vHBLlVEJKwp1IhUEONEYNqfhW3XBdaswp07A37+Hvv2LOySuZiu52HO7YeJrxnsUkVEwpJCjUgFM44Dp3XGOfUM+OIj3Dkz4Mdvse/Mxi6dhznrPEyv/piExGCXKiISVhRqRILEOA606YjTugN8+QnunOnw/dfYRW9il83HnNUL0+siTGLtYJcqIhIWFGpEgswYA6ecjtOqHaxdgzt3Ony7AbtkLvb9BZgu52B6D8DUqhPsUkVEQppCjUiIMMbAyW1xTjoVNnyBO+dV+Hoddtnb2A/exXTqjjlvAKZOUrBLFREJSQo1IiHGGAMtWxPRsjX2q0zfyM2GL7AfLMSuWIQ5oxumz0BM3eRglyoiElIUakRCmDnxZCJOfBj79Trf1VLr1mBXLMauXIrpcDam70BMUv1glykiEhIUakTCgGn2VyJueRD77QbceRnw5SfYD5diVy/DnH4mps8gzF8aBrtMEZGgKlWoWbBgAXPmzCE7O5uUlBSGDRtG06ZNj7ndihUrGD9+PO3ateP222/3L8/IyGDlypX8/vvvREZGkpqayuDBg2nWrJl/nd27d/PCCy/w6aefYoyhQ4cOXHnllVStWrU0LYiEJdOkBRE334f9/mvfyM3/PsJ+9D724w8wbTth0gZh6jcOdpkiIkFR4i+0XLlyJdOmTWPAgAGMHj2alJQURo0axc6dO4+63datW3nppZdo2bJlkeeSk5MZNmwYjz/+OA899BB16tTh4YcfJicnx7/OU089xU8//cQ999zDnXfeyfr165k8eXJJyxfxBNOoGRE33oNz71hoewZYi/10Be6Df+fApEewP3wb7BJFRCpciUPN3Llz6dGjB926daN+/foMHz6c6Oholi5desRtXNdlwoQJDBo0iLp16xZ5vkuXLpxyyimccMIJNGjQgMsvv5zc3Fx++OEHAH7++Wc+//xzrr32Wpo1a0aLFi0YNmwYK1euZPv27SVtQcQzTMMmRFx3F879T2HadQFj4PMPcR++hQMT/oX9bmOwSxQRqTAlOv1UUFDApk2b6Nevn3+Z4zi0atWKjRuP/JfnrFmziI+Pp3v37qxfv/6Yr7Fo0SJiY2NJSUkBYOPGjcTFxdGkSRP/eq1atcIYwzfffEP79u2L7Cc/P5/8/Hz/Y2MMMTEx/j+XpcL9lfV+Q4X6C32mQWO49g7s5p9w52VgP3ofvvgY94uPMSe3xTn/UqhXL6x7PBovHMNj8XqP6i/8hUKPJQo1OTk5uK5LQkJCwPKEhAQ2b9582G02bNjAkiVLGDNmzFH3/emnnzJu3Dj2799PQkIC99xzD/Hxvi/4y87O9v+5UEREBNWqVSM7O/uw+5s9ezazZs3yP27cuDGjR4+mTp3yu4FZUpK37x+i/sJAvXpwWnvyf/mBnBkvsHfpAmzmZxzI/IytbdpT89LhVDn51GBXWW48cQyPwes9qr/wF8wey/Xqp9zcXCZMmMCIESOKhJJDnXTSSTz22GPk5OSwePFixo4dyyOPPEKNGjVK9dr9+/cnLS3N/7gwOWZlZVFQUFCqfR6JMYakpCS2bNmCtbZM9x0K1F8YcqLh0muJ6H4B7tuzsKuWkPf5R2z9/CPMia0w5w/2/d8jvzV68hgewus9qr/wV149RkZGFntAokShJj4+HsdxioyOZGdnFxm9Afjtt9/Iyspi9OjR/mWFjQ4ePJhx48b5E13VqlVJSkoiKSmJ5s2bc/PNN7NkyRL69+9PQkJCwKRhgAMHDrB79+7Dvi5AVFQUUVFRh32uvD5Q1lrPflhB/YWluvVwrrgJ0i6h6nvz2bPwLexXX2K/+hKa/hXn/EugZRvPhBtPHsNDeL1H9Rf+gtljiUJN4eXWmZmZ/nksruuSmZlJ7969i6yfnJzM448/HrBs+vTp7Nu3j6FDh1K79pG/qM9a658T07x5c/bs2cOmTZtITU0FIDMzE2ttsS4lF6nsTO0TSLxxJPu6pflGbj5YCN+swx17P6SeiJM2GE5u65lwIyKVU4lPP6WlpTFp0iRSU1Np2rQp8+fPJy8vj65duwIwceJEEhMTSU9PJzo6moYNA28IFhcXB+Bfvm/fPl5//XXatWtHzZo12bVrFwsWLGD79u2cccYZANSvX582bdowefJkhg8fTkFBAS+88AKdOnUiMTHxePoXqVRMYh2c9Gux5w3EvvM69v13YNNXuE89CClNcc4fDKecrnAjImGpxKGmU6dO5OTkkJGRQXZ2No0aNWLkyJH+00Dbtm0r0V+IjuOwefNmnnjiCXbt2kX16tVp0qQJDz74IA0aNPCvd/PNNzNlyhQeeugh/833hg0bVtLyRQQwNWthBg/HnjcAu3A2dtnb8MM3uBMfhgaNfSM3bTpgnBLf9UFEJGiM9frJvUNkZWUFXOpdFowx1KtXj19//dWT50rVX/g7Vo82Jxv77pvYpfMgb59v4V9SMH0vwZx2BsaJqOCKS0bHMPypv/BXXj1GRUUVe6Kwfg0TEUx8As7FV+D8+3lMn0FQNQZ++QH77BjcB27GXf0e1j0Q7DJFRI5KoUZE/Ez1eJz+l+E8OgVz/mCIiYNff8I+/wTufTfirlyCPaBwIyKhSaFGRIowcdVwLkjHefR5zIVDILYa/PYL9j/jcO+9Dnf5u9gyvt+TiMjxUqgRkSMysXE4aZfgjH4ec9HlUC0esrZgp07Aveda3PcXYAvKdo6aiEhpKdSIyDGZqrE45w3A+fdzmAFXQvUa8PtW7EtP4949AnfpfGz+/mCXKSKVnEKNiBSbqRqD06u/b0LxJVdBjUTYvg37yjO4I6/BXTwHuz8v2GWKSCWlUCMiJWaqVMHpeSHOv5/FpI+AmrUhezt2+nO4dw3HXfgGtvDScBGRCqJQIyKlZqKicbr1xRk1GXPZ9ZBYB3KysTNf8IWbBa9h9+UGu0wRqSQUakTkuJmoKJyze+OMegZz+Y1Q+wTYtRP72lTcu67GnZeBzd0b7DJFxONK/DUJIiJHYiKjMGeeiz2jO/aj97DzMmDrr9g3/otdOBvT80JMjzRMbLVglyoiHqRQIyJlzkRGYjr1wHboiv34A1+42fIz9q1XsO++gelxPqbnBZi46sEuVUQ8RKFGRMqNiYjAdOyKbX8m9tOV2LkzYPOP2LkzsO++heneF3NOP0z1+GCXKiIeoFAjIuXOOBGY08/EntYZ1nyIO3c6/Pw99u1Z2CVzMWefh+nVDxNfM9ilikgYU6gRkQpjHAdO64Rzakf44iPcOTPgx2+xC2djl83DnNUb06s/JqFWsEsVkTCkUCMiFc44DrTpiNO6A3z5Ce7cGfDdRuyit7DL3saceS6m98WYxNrBLlVEwohCjYgEjTEGTjkdp1U7WLvGd1rq2w3YpfOwH7yD6dwTc94ATK26wS5VRMKAQo2IBJ0xBk5ui3PSqbDhC1+42bgW+94C7PJ3MZ16+MJNnaRglyoiIUyhRkRChjEGWrYmomVr7FeZvnCz4QvsBwuxKxZhOnbD9BmIOSE52KWKSAhSqBGRkGROPJmIEx/GfrPON+dm7RrsysXYVUsxHc7C9BmEqVc/2GWKSAhRqBGRkGaa/pWIfzyI3fSVL9x8+Qn2w2XY1e9h2nXB9L0EUz8l2GWKSAhQqBGRsGBSTyTi5vuwP3zjCzefr/bdrfjjD7CndWL/0BshRncoFqnM9IWWIhJWTEpTIm64G+fecdC2EwD205X89vfLcFctDW5xIhJUGqkRkbBkGqYScd2d2F9+8H1h5uercV8Yh8HidOwW7PJEJAg0UiMiYc38JQXn+pHE9e4P1sW+MB73Q43YiFRGCjUiEvaM41DzhrswZ/c+GGzGKdiIVEIKNSLiCcZxcIZchzmrN1jrCzaaYyNSqSjUiIhnGMfBDLn2j2DzHwUbkcpEoUZEPMUfbM5WsBGpbBRqRMRzjONg0g8JNiuXBLssESlnCjUi4kn+YNP1PF+weXG8go2IxynUiIhnGcfBXDqCwGCzONhliUg50c33RMTTjONA+rUA2GVvY198ChdwOvUIbmEiUuY0UiMinmeMOeRU1FO4KzRiI+I1GqkRkUrBGBM4YjP14IhNZ43YiHiFRmpEpNL4Y8Smj2/EZupTuCsWBbssESkjGqkRkUrFN2IzAgC7bD526oSDIzY9g1uYiBw3jdSISKXjG7EZgelWOGIzQSM2Ih6gUCMilZIxxne595+DzfJ3g12WiBwHhRoRqbT+CDZ9fcFm2kQFG5Ewpjk1IlKpGWPg0msAsEvn+YIN4HQ5J7iFiUiJaaRGRCo934jNNZjuaRqxEQljCjUiIhwMNoOH/xFspk7A/WBhsMsSkRJQqBEROSgg2IBvxEbBRiRsKNSIiPyJP9j0OB9QsBEJJwo1IiKHMMZgLrlawUYkzCjUiIgchoKNSPhRqBEROYLDBpv33wlyVSJyJAo1IiJH4Q82PS8AwL40ScFGJEQp1IiIHIMxBjPoqkOCzYIgVyUih1KoEREphqLB5mkFG5EQo1AjIlJMfwSbCwEFG5FQo1AjIlICvmAzLDDYvKdgIxIKFGpERErIH2zOORhs/qtgIxIKFGpERErBGIMZeEiwWfZ2kKsSqdwUakRESskfbM7tB4B9+f8p2IgEkUKNiMhxMMZgBlx5SLCZH9yiRCophRoRkeP0R7DpD4B9+RkFG5EgUKgRESkDvmAzNDDYLFWwEalICjUiImWkSLB5RcFGpCIp1IiIlCF/sOmlYCNS0RRqRETKmDEGc/GhwWZekKsS8T6FGhGRcvBHsLkIAPvKZAUbkXKmUCMiUk58weYKBRuRCqJQIyJSjvzBpvfFgIKNSHlSqBERKWfGGMxFlwcGmyVzg1yViPco1IiIVIAiwebVZxVsRMqYQo2ISAXxB5vzFGxEyoNCjYhIBTLGYPofEmwWK9iIlAWFGhGRCvZHsBkAgJ2uYCNSFhRqRESCwBds/nZIsJkT5KpEwltkaTZasGABc+bMITs7m5SUFIYNG0bTpk2Pud2KFSsYP3487dq14/bbbwegoKCA6dOns2bNGrZu3UpsbCytWrUiPT2dxMRE/7Y33HADWVlZAftLT0+nX79+pWlBRCTojDHQ/29gDHb+TOz053ABp8f5wS5NJCyVONSsXLmSadOmMXz4cJo1a8a8efMYNWoU48aNo0aNGkfcbuvWrbz00ku0bNkyYPn+/fv57rvvuPjii2nUqBG7d+/mxRdfZMyYMTz66KMB6w4aNIiePXv6H1etWrWk5YuIhBRjDPS7DOCPYGMtTs8LglyZSPgpcaiZO3cuPXr0oFu3bgAMHz6czz77jKVLlx5x1MR1XSZMmMCgQYNYv349e/bs8T8XGxvLvffeG7D+sGHDGDlyJNu2baN27dr+5TExMSQkJBSrzvz8fPLz8/2PjTHExMT4/1yWCvdX1vsNFeov/Hm9x3DvzxiD7f83XGOw8zKwM57HGhMQbMK9x2NRf+EvFHosUagpKChg06ZNAeHFcRxatWrFxo0bj7jdrFmziI+Pp3v37qxfv/6Yr7N3716MMcTGxgYsf+ONN3jttdeoXbs2Xbp0oW/fvkRERBx2H7Nnz2bWrFn+x40bN2b06NHUqVPnmK9fWklJSeW271Cg/sKf13sM9/7sdbeRU60aOTNewJ3+HPHx8VS/8NKAdcK9x2NRf+EvmD2WKNTk5OTgum6R0ZKEhAQ2b9582G02bNjAkiVLGDNmTLFeY//+/bz88st07tw5INScd955NG7cmGrVqvHVV1/x6quvsmPHDq644orD7qd///6kpaX5Hxcmx6ysLAoKCopVS3EZY0hKSmLLli1Ya8t036FA/YU/r/fopf5sz36Y3bux8zLIfvYJcnbuxDnnQk/1eDjqL/yVV4+RkZHFHpAo1UTh4srNzWXChAmMGDGC+Pj4Y65fUFDA2LFjAbj66qsDnvtzQElJSSEyMpLnnnuO9PR0oqKiiuwrKirqsMuBcvtAWWs9+2EF9ecFXu/RK/2ZC4cAYOdl4M54Hosl4px+vmUe6fFI1F/4C2aPJQo18fHxOI5DdnZ2wPLs7OzDznX57bffyMrKYvTo0f5lhY0OHjyYcePG+YepCgPNtm3buO+++4qcejpUs2bNOHDgAFlZWSQnJ5ekDRGRkGaMgT8FGztjCq4FrrguuIWJhLgShZrIyEhSU1PJzMykffv2gG8ScGZmJr179y6yfnJyMo8//njAsunTp7Nv3z6GDh3qnwRcGGi2bNnC/fffT/Xq1Y9Zy/fff48xplgjQCIi4cYfbIzBzp2BmzGFXfHx0LF7sEsTCVklPv2UlpbGpEmTSE1NpWnTpsyfP5+8vDy6du0KwMSJE0lMTCQ9PZ3o6GgaNmwYsH1cXByAf3lBQQFPPvkk3333HXfccQeu6/pHgqpVq0ZkZCQbN27k66+/5qSTTiImJoaNGzcydepUzjzzTKpVq3Yc7YuIhC5jDFyQDoCdO4Ps58fi5ORgzrkwyJWJhKYSh5pOnTqRk5NDRkYG2dnZNGrUiJEjR/pPP23btq1El3Nt376dTz75BMB/Q75C999/PyeddBKRkZGsXLmSmTNnkp+fT926denbt2/APBsRES/yBxtjsHOm42ZMwViLc26/YJcmEnKM9fqMpUNkZWUF3L+mLBhjqFevHr/++qsnJ4Cpv/Dn9R693l+huCVzyHn1OQDMwGGeCjZeP4Ze7w/Kr8eoqKhiX/2k734SEQkDxhhqXDYCc77vvjV25gu4C2cHuSqR0KJQIyISRiIuTMecPxgAO/M/CjYif6JQIyISZpwLDgk27yjYiIBCjYhIWAoINrMUbERAoUZEJGwVDTavB7kikeBSqBERCWO+YHNw8vCsFxVspFJTqBERCXPOBZcGBpsFrwW5IpHgUKgREfEA54JLMYV3H35tqoKNVEoKNSIiHuGcP1jBRio1hRoREQ8pEmzeVrCRykOhRkTEY5zzB2MuPBhsXlewkcpDoUZExIOctEODzawgVyRS/hRqREQ8yhdshgBgX5+mYCOep1AjIuJhTtolgcFm/swgVyRSfhRqREQ8zkm7BNPvMgDs7JcUbMSzFGpERCoBp+8gBRvxPIUaEZFKokiwmZcR5IpEypZCjYhIJRIQbN74r4KNeIpCjYhIJaNgI16lUCMiUgk5fQdh+v8NULAR71CoERGppJw+AwODzdwZQa5I5Pgo1IiIVGJOn4GYiy4HwL75soKNhDWFGhGRSs45b4CCjXiCQo2IiBwMNlcAhcFmepArEik5hRoREQHAOe/iPwWbVxRsJOwo1IiIiF+RYDNHwUbCh0KNiIgEcM67GHPxwWDzloKNhA+FGhERKcLpfUiweevVIFckcmwKNSIiclhO74sxA4YCYOe8qmAjIU+hRkREjsjpddEhweaV4BYkchQKNSIiclS+YHMlAHbOdAUbCVkKNSIickxOr/4KNhLyFGpERKRYnF79MQMVbCR0KdSIiEixOecq2EjoUqgREZESKRJs3nwFa22QqxJRqBERkVLwBZthANi507FvvapgI0GnUCMiIqXinNvvkGCjERsJLoUaEREpNefcfphBVwFg585QsJGgUqgREZHj4pxzoYKNhASFGhEROW5Fgs2bLyvYSIVTqBERkTLhnHMh5pKDwWZehoKNVDiFGhERKTNOz0OCzRsKNlJxFGpERKRMBQSb+Qo2UnEUakREpMz5gs3VQGGw+a+CjZQ7hRoRESkXTs8L/hRsZirYSLlTqBERkXLj9LwAM3g4oGAj5U+hRkREypXT4/zAYDP7JQUbKRcKNSIiUu58weYaAOzbsxRspFwo1IiISIVweqQdEmymKdhImVKoERGRCuP0SMNcWhhsXlOwkTKlUCMiIhXK6X5IsHldwUbKhkKNiIhUuIBgs+A13NemKtjIcYsMdgEiIlI5Od3TcI3BvjIZu+A1dlarhu11cbDLkjCmkRoREQkap1tfTPoIAHbNmqoRGzkuCjUiIhJUTre+OOnXAr5TUVbBRkpJoUZERILO6d6XhOvuAMC+8zr2tRcVbKTEFGpERCQkVE8biDPk4IjNO7MVbKTEFGpERCRkON36Yv4cbGYp2EjxKdSIiEhIcbr2+SPYLFSwkeJTqBERkZBTNNj8R8FGjkmhRkREQpIv2FwHgF34hoKNHJNCjYiIhCyn63kKNlJsCjUiIhLSnK7nYS67HjgYbGa+oGAjh6VQIyIiIc85u/cfwebdNxVs5LAUakREJCw4Z/fG/O1PwSZDwUYCKdSIiEjYcM76U7BZpGAjgRRqREQkrBQNNlMUbARQqBERkTAUGGzeUrARQKFGRETClC/Y3AAo2IhPZGk2WrBgAXPmzCE7O5uUlBSGDRtG06ZNj7ndihUrGD9+PO3ateP2228HoKCggOnTp7NmzRq2bt1KbGwsrVq1Ij09ncTERP+2u3fv5oUXXuDTTz/FGEOHDh248sorqVq1amlaEBERD3DO6oUL2JcmYRe9BdbCJVdjjAl2aRIEJR6pWblyJdOmTWPAgAGMHj2alJQURo0axc6dO4+63datW3nppZdo2bJlwPL9+/fz3XffcfHFFzN69Gj++c9/snnzZsaMGROw3lNPPcVPP/3EPffcw5133sn69euZPHlyScsXERGPcc7qhbn8RgDs4jnYGc9rxKaSKnGomTt3Lj169KBbt27Ur1+f4cOHEx0dzdKlS4+4jeu6TJgwgUGDBlG3bt2A52JjY7n33nvp1KkTycnJNG/enGHDhrFp0ya2bdsGwM8//8znn3/OtddeS7NmzWjRogXDhg1j5cqVbN++vaQtiIiIxzhnnqtgIyU7/VRQUMCmTZvo16+ff5njOLRq1YqNGzcecbtZs2YRHx9P9+7dWb9+/TFfZ+/evRhjiI2NBWDjxo3ExcXRpEkT/zqtWrXCGMM333xD+/bti+wjPz+f/Px8/2NjDDExMf4/l6XC/Xl1uFP9hT+v9+j1/sD7PZZFfxFn9cI1BnfqBOziOb79DR4eEu+Z148fhEaPJQo1OTk5uK5LQkJCwPKEhAQ2b9582G02bNjAkiVLipxOOpL9+/fz8ssv07lzZ3+oyc7OJj4+PmC9iIgIqlWrRnZ29mH3M3v2bGbNmuV/3LhxY0aPHk2dOnWKVUdpJCUlldu+Q4H6C39e79Hr/YH3ezzu/gZdwe4aNdgxYRR28Rxi4uJIuOafIRMmvH78ILg9lmqicHHl5uYyYcIERowYUSSUHE5BQQFjx44F4Oqrrz6u1+7fvz9paWn+x4Uf6KysLAoKCo5r34cyxpCUlMSWLVs8Odyp/sKf13v0en/g/R7LtL9TOuBccRPu1Ansfms6e3bvxrn0mqAGG68fPyi/HiMjI4s9IFGiUBMfH4/jOEVGR7Kzs4uM3gD89ttvZGVlMXr0aP+ywkYHDx7MuHHj/ImuMNBs27aN++67zz9KA76RoJycnIB9HzhwgN27dx/2dQGioqKIioo67HPl9YGy1nr2wwrqzwu83qPX+wPv91hW/ZnOPTHWYqdNxC6Zi0tonIry+vGD4PZYolATGRlJamoqmZmZ/nksruuSmZlJ7969i6yfnJzM448/HrBs+vTp7Nu3j6FDh1K7dm3gj0CzZcsW7r//fqpXrx6wTfPmzdmzZw+bNm0iNTUVgMzMTKy1xbqUXEREKh+nyzm+y70PBhsAQiDYSPkp8emntLQ0Jk2aRGpqKk2bNmX+/Pnk5eXRtWtXACZOnEhiYiLp6elER0fTsGHDgO3j4uIA/MsLCgp48skn+e6777jjjjtwXdc/ElStWjUiIyOpX78+bdq0YfLkyQwfPpyCggJeeOEFOnXqFHAvGxERkT8rEmyshSCfipLyU+JQ06lTJ3JycsjIyCA7O5tGjRoxcuRI/2mgbdu2lejDsn37dj755BMA/w35Ct1///2cdNJJANx8881MmTKFhx56yH/zvWHDhpW0fBERqWScLufgGoOdOgG7dJ5voYKNJxnr9ZN7h8jKygq41LssGGOoV68ev/76qyfPlaq/8Of1Hr3eH3i/x4roz12xCDt1AliL6dYHc+mICgs2Xj9+UH49RkVFFXuisL77SUREKgWnc0/MFTeDMdil87GvTvZswKisFGpERKTScDr3CAw2ryjYeEm53qdGREQk1Dide/gmD099Crtsvm9hesWdipLyo5EaERGpdJzOPTBDD47YLJuPfeUZjdh4gEZqRESkUnI6HRyxefEp7LK3fQvTr9WITRhTqBERkUrrsMHm0hEYRycywpGOmoiIVGpOpx6YoX8/eCrqbd9VUa4b7LKkFBRqRESk0nM6dQ8MNq88o2AThhRqREREOBhsrvyHL9i8t0DBJgwp1IiIiBzknNEtMNi8rGATThRqRERE/sQ5oxtm2D98weZ9BZtwoqufREREDuF07Oa7KuqFcdj3F/gWDrlWV0WFOIUaERGRw/gj2Iw/GGwsDLlOwSaEKdSIiIgcQWCwece3UMEmZOmoiIiIHIXTsXCOjYN9/x3sf5/WHJsQpZEaERGRY3A6dv1jjs0HC30LL7teIzYhRkdDRESkGJyOXTFX3eIbsflgoUZsQpBGakRERIrJ6XC2b8RmyliN2IQghRoREZESULAJXQo1IiIiJaRgE5r07ouIiJSC0+HswDk2L03SHJsg00iNiIhIKQWM2Cx/17fwbzdoxCZI9K6LiIgcB6fD2Zir/883YrP8Xey0iRqxCRKN1IiIiBwnp/1ZvhGb55/ErljkW3j5jRqxqWB6t0VERMqA0/4szPB/+kZsVizCTpugEZsKppEaERGRMuKcfubBEZsnsCsW+xZefhMmIiKodVUWCjUiIiJl6HDBxl5xc3CLqiR0+klERKSMOaefibn6n+A42BWLcafqVFRFUKgREREpB75gc+vBYLOI7eP/hXUPBLssT1OoERERKSfO6V38wWbvojm4L05QsClHmlMjIiJSjpzTu2Adg/vs49iVi8FaGHoTxtHk4bKmkRoREZFy5rTrQq3bR/lORa1agtWITblQqBEREakAsWf2xLnmtj8Fm6cUbMqYTj+JiIhUEKddFwDcZx/DrlrqWzj0Zp2KKiMaqREREalA5rTOfxqxWaoRmzKkUCMiIlLBfMHm9j+CzX8UbMqCQo2IiEgQmNM6/RFsPlSwKQsKNSIiIkHiDzYREQo2ZUChRkREJIjMaZ1wht/2p2AzXsGmlBRqREREgsw3YlMYbJYp2JSSQo2IiEgIMG0PCTYvjFOwKSGFGhERkRDhCzYH59isfk/BpoQUakREREKIaXuGgk0pKdSIiIiEmCLBZoqCTXEo1IiIiISggGDz0cFgc0DB5mgUakREREKUaXsGzog7/gg2LyjYHI1CjYiISAgzp3Y8JNiMVbA5AoUaERGREGdO7YhzbWGweV/B5ggUakRERMKAaVMYbCIVbI5AoUZERCRM+ILN7X8EmylPKtj8iUKNiIhIGAkYsfn4AwWbP1GoERERCTOmTQcFm8NQqBEREQlDCjZFKdSIiIiEKdOmA851dyrYHKRQIyIiEsZM6/aBweb5JyptsFGoERERCXMBweaT5ZU22CjUiIiIeIAv2Nz1R7B57vFKF2wUakRERDzCtD7dF2wiI7Gfrqh0wUahRkRExENM69Nxrj0k2BQUBLusCqFQIyIi4jFFgs3zT1SKYKNQIyIi4kGHnopyn/f+iI1CjYiIiEeZU/4INny60vPBRqFGRETEw8wpp+NcP/KPYOPhOTYKNSIiIh5nWrX7I9h85t1go1AjIiJSCVSGYKNQIyIiUkn4gs3dng02CjUiIiKViGl12sFgE3Uw2DzmmWCjUCMiIlLJmFan4dww8mCwWeWZYKNQIyIiUgmZkw8JNs+OCftgE1majRYsWMCcOXPIzs4mJSWFYcOG0bRp02Nut2LFCsaPH0+7du24/fbb/ctXr17Nu+++y6ZNm9i9ezdjxoyhUaNGAds+8MADrFu3LmBZz549ueaaa0rTgoiISKVXGGzcSY/Amg9xnx2Dc81tmMioYJdWKiUeqVm5ciXTpk1jwIABjB49mpSUFEaNGsXOnTuPut3WrVt56aWXaNmyZZHn8vLyaNGiBUOGDDnqPnr06MGzzz7r/++yyy4rafkiIiLyJwEjNms+xH32MWxBfrDLKpUSh5q5c+fSo0cPunXrRv369Rk+fDjR0dEsXbr0iNu4rsuECRMYNGgQdevWLfL8WWedxYABA2jVqtVRX7tKlSokJCT4/4uNjS1p+SIiInIIX7C5O+yDTYlOPxUUFLBp0yb69evnX+Y4Dq1atWLjxo1H3G7WrFnEx8fTvXt31q9fX+piP/jgAz744AMSEhI47bTTuPjii6lSpcph183Pzyc//48DYowhJibG/+eyVLi/st5vqFB/4c/rPXq9P/B+j+ov+Eyr0+DGe3AnPgxrPsQ++xhmxO3FPhUVCj2WKNTk5OTgui4JCQkByxMSEti8efNht9mwYQNLlixhzJgxpS4SoEuXLtSuXZvExER++OEHXn75ZTZv3sytt9562PVnz57NrFmz/I8bN27M6NGjqVOnznHVcTRJSUnltu9QoP7Cn9d79Hp/4P0e1V+Q1etLbmIi2/71T+yaD4me+hS17vg3Jqr4c2yC2WOpJgoXV25uLhMmTGDEiBHEx8cf17569uzp/3PDhg2pWbMmDz30EFu2bDnsG9i/f3/S0tL8jwuTY1ZWFgVlPLvbGENSUhJbtmzBWlum+w4F6i/8eb1Hr/cH3u9R/YWQ5EY4N96NO+Fhclct45cH/oFz7R3HHLEprx4jIyOLPSBRolATHx+P4zhkZ2cHLM/Ozi4yegPw22+/kZWVxejRo/3LChsdPHgw48aNK3WiK7za6kihJioqiqgjJMvy+kBZa0P/w3oc1F/483qPXu8PvN+j+gsN5q+n4tx4D+6kUdjPV3PgmdE4xTwVFcweSxRqIiMjSU1NJTMzk/bt2wO+ScCZmZn07t27yPrJyck8/vjjAcumT5/Ovn37GDp0KLVr1y514d9//z0ANWvWLPU+RERE5PDMSafi3HA37qRR8Plq3Mljih1sgqXEp5/S0tKYNGkSqampNG3alPnz55OXl0fXrl0BmDhxIomJiaSnpxMdHU3Dhg0Dto+LiwMIWL579262bdvG9u3bAfzzcwqvctqyZQvLly+nbdu2VKtWjR9//JGpU6fSsmVLUlJSStW4iIiIHF2RYPPM6GKdigqWEoeaTp06kZOTQ0ZGBtnZ2TRq1IiRI0f6Tz9t27atxDOfP/nkE55++mn/43HjxgEwYMAABg0aRGRkJF9++aU/QNWqVYsOHTpw0UUXlbR8ERERKQFz0qm+OTYTR8H/PgrpYGNsOJzcK0NZWVkBl3qXBWMM9erV49dffw2Lc6Ulpf7Cn9d79Hp/4P0e1V/os+vW+IJN/n5o3b5IsCmvHqOiooo9UVjf/SQiIiLHVDh5mKho/4hNqN2gT6FGREREisX8tU3RYFPGZz+Oh0KNiIiIFFuRYDM5dIKNQo2IiIiUiPlrG5yb7v3TiM2jIRFsFGpERESkxEzL1n8Emy8+xv1//8bm7w9qTQo1IiIiUir+YBMdjf3iY7aNuj2ok4cVakRERKTUTMvWODf6gk1k0l8goly/VvKogvfKIiIi4gmmZWsi7h1Hwqmnsy+IX9qpkRoRERE5bqZegxJ/o0BZU6gRERERT1CoEREREU9QqBERERFPUKgRERERT1CoEREREU9QqBERERFPUKgRERERT1CoEREREU9QqBERERFPUKgRERERT1CoEREREU9QqBERERFPUKgRERERT4gMdgEVLTKy/Fouz32HAvUX/rzeo9f7A+/3qP7CX1n3WJL9GWutLdNXFxEREQkCnX4qA7m5udxxxx3k5uYGu5Ryof7Cn9d79Hp/4P0e1V/4C4UeFWrKgLWW7777Dq8Oeqm/8Of1Hr3eH3i/R/UX/kKhR4UaERER8QSFGhEREfEEhZoyEBUVxYABA4iKigp2KeVC/YU/r/fo9f7A+z2qv/AXCj3q6icRERHxBI3UiIiIiCco1IiIiIgnKNSIiIiIJyjUiIiIiCd4/0soSmjdunW89dZbfPfdd+zYsYNbb72V9u3bH3WbtWvXMm3aNH766Sdq1arFxRdfTNeuXQPWWbBgAXPmzCE7O5uUlBSGDRtG06ZNy7GTwytpf6tXr2bhwoV8//33FBQUUL9+fQYOHEibNm3862RkZDBr1qyA7ZKTkxk3blw5dXF0Je1x7dq1PPjgg0WWP/vssyQkJPgfh+sxnDRpEu+9916R5fXr1+fJJ58EQusYzp49m48++ohffvmF6OhomjdvzmWXXUZycvJRt1u1ahUzZswgKyuLpKQkhgwZQtu2bf3PW2vJyMhg8eLF7NmzhxYtWnD11VdTr1698m4pQGn6W7RoEe+//z4//fQTAKmpqVx66aUBn7/DHefWrVtz9913l08jR1GaHpctW8bTTz8dsCwqKoqXX37Z/zicj+EDDzzAunXriiw/9dRTueuuu4DQOYYLFy5k4cKFZGVlAb6/KwYMGMCpp556xG1C5edPoeYQeXl5NGrUiO7du/P4448fc/2tW7fy6KOPcs4553DTTTeRmZnJM888Q0JCgv8f/pUrVzJt2jSGDx9Os2bNmDdvHqNGjWLcuHHUqFGjnDsKVNL+1q9fzymnnMKll15KXFwcS5cuZfTo0TzyyCM0btzYv16DBg249957/Y8dJ3iDgCXtsdC4ceOIjY31P46Pj/f/OZyP4ZVXXsmQIUP8jw8cOMBtt91Gx44dA9YLlWO4bt06evXqRZMmTThw4ACvvvoqDz/8ME8++SRVq1Y97DZfffUV48ePJz09nbZt27J8+XIee+wxRo8eTcOGDQF48803efvtt7nhhhuoW7cuM2bMYNSoUTz55JNER0eHdH/r1q2jc+fOnHjiiURFRfHmm2/6t0lMTPSv16ZNG66//nr/42B9eWJpegSIiYlh/PjxR3w+nI/hrbfeSkFBgf/xrl27uO222zjjjDMC1guFY5iYmEh6ejr16tXDWst7773HmDFjGDNmDA0aNCiyfkj9/Fk5ooEDB9rVq1cfdZ2XXnrJ/t///V/AsrFjx9qHH37Y//iuu+6yzz//vP/xgQMH7DXXXGNnz55dpvWWVHH6O5xbbrnFzpw50/94xowZ9tZbby3L0spMcXrMzMy0AwcOtLt37z7iOl46hqtXr7aDBg2yW7du9S8L5WO4c+dOO3DgQLt27dojrvPkk0/af//73wHLRo4caSdPnmyttdZ1XTt8+HD75ptv+p/fs2ePTU9Pt8uXLy+fwoupOP0d6sCBA/byyy+3y5Yt8y+bOHGiHT16dHmUeNyK0+PSpUvtFVdcccTnvXYM586day+//HKbm5vrXxbKx3Do0KF28eLFh30ulH7+NFJznL7++mtatWoVsKx169a8+OKLABQUFLBp0yb69evnf95xHFq1asXGjRsrsNKy4bouubm5VKtWLWD5li1bGDFiBFFRUTRv3pz09HRq164dpCpL5/bbbyc/P58GDRowcOBAWrRoAXjvGC5ZsoRWrVpRp06dgOWhegz37t0LUOQz92cbN24kLS0tYFnr1q35+OOPAd+IanZ2Nqeccor/+djYWJo2bcrGjRvp3LlzOVRePMXp71B5eXkUFBQU2WbdunVcffXVxMXFcfLJJzN48GCqV69epvWWRnF73LdvH9dffz3WWho3bsyll17qHxnw2jFcsmQJnTp1KjKyE2rH0HVdVq1aRV5eHs2bNz/sOqH086dQc5yys7OLnH6oUaMGubm57N+/n927d+O6bsDcDICEhAQ2b95cgZWWjTlz5rBv376AIdNmzZpx/fXXk5yczI4dO5g1axb33XcfTzzxBDExMUGstnhq1qzJ8OHDadKkCfn5+SxevJgHH3yQUaNGkZqaSk5OjmeO4fbt2/n888+5+eabA5aH6jF0XZcXX3yRE0880T+MfThH+jnMzs72P1+47EjrBENx+zvUyy+/TGJiYsAvVG3atKFDhw7UrVuXLVu28Oqrr/LII48watSooJ4OLm6PycnJXHfddaSkpLB3717eeust7rnnHp588klq1arlqWP4zTff8NNPP3HdddcFLA+lY/jjjz9y9913k5+fT9WqVbn11lupX7/+YdcNpZ8/hRoptuXLlzNr1ixuu+22gA/nnyePpaSk+P+BXLVqFd27dw9GqSWSnJwcMMHvxBNP5LfffmPevHncdNNNQays7L333nvExcUVmVgcqsdwypQp/PTTTzz00ENBq6E8laa/N954gxUrVvDAAw8EzEX482+7DRs2JCUlhZtuuom1a9cWGU2uSMXtsXnz5gEjAc2bN+eWW27h3XffZfDgweVdZqmV5hguWbKEhg0bFrnQIJSOYXJyMo899hh79+7lww8/ZNKkSTz44INHDDahQpd0H6eEhAR27twZsGznzp3ExMQQHR1NfHw8juMUSaPZ2dlFfvMPZStWrOCZZ57hlltuCRhCPJy4uDiSk5PZsmVLBVVX9po2beqv3yvH0FrL0qVLOfPMM485+TAUjuGUKVP47LPPuP/++6lVq9ZR1z3Sz2Hh8Sn8/9HWqWgl6a/QW2+9xRtvvME999xDSkrKUdc94YQTqF69etgcw0NFRkbSuHFjf/1eOYb79u1jxYoVxfplIZjHMDIykqSkJFJTU0lPT6dRo0bMnz//sOuG0s+fQs1xatasGV9++WXAsi+++ML/G0dkZCSpqalkZmb6n3ddl8zMzCOenww1y5cv5+mnn+bvf/97wCV6R7Jv3z62bNkSVv/gH+r777+nZs2agDeOIfjO1W/ZsqVYf5kG8xhaa5kyZQofffQR9913H3Xr1j3mNs2bNz/sz2GzZs0AqFu3LgkJCQHr7N27l2+++abCj2Fp+gPf1SOvvfYaI0eOpEmTJsdc//fff2f37t3+z3FFKm2Pf+a6Lj/++KO/fi8cQ4APP/yQgoICzjzzzGOuG8xjeCjXdcnPzz/sc6H086fTT4co/Mu80NatW/n++++pVq0atWvX5pVXXmH79u3ceOONAJx77rm88847/Pe//6Vbt25kZmayatUq7rzzTv8+0tLSmDRpEqmpqTRt2pT58+eTl5dX5F42FaGk/S1fvpxJkyYxdOhQmjVr5h+tiI6O9l/+PG3aNNq1a0ft2rXZsWMHGRkZOI5Dly5dKrw/KHmP8+bNo27dujRo0ID9+/ezZMkSMjMzueeee/z7COdjWGjJkiU0a9bssOf9Q+kYTpkyheXLl3P77bcTExPj/8zFxsb6T7dMnDjRf9kpQJ8+fXjggQeYM2cObdu2ZcWKFXz77bdcc801ABhj6NOnD6+//jr16tWjbt26TJ8+nZo1a3L66aeHfH9vvPEGGRkZ3HzzzdStW9e/TdWqValatSr79u1j5syZdOjQgYSEBH777Tf++9//kpSUROvWrSu0v9L2OGvWLJo1a0ZSUhJ79uzhrbfeIisrix49egDhfwwLLVmyhNNPP73I5N9QOoavvPIKbdq0oXbt2uzbt4/ly5ezbt06//1yQvnnT6HmEN9++23AjdimTZsGwNlnn80NN9zAjh072LZtm//5unXrcueddzJ16lTmz59PrVq1uPbaawNuTtepUydycnLIyMggOzubRo0aMXLkyKD8FlzS/hYtWsSBAweYMmUKU6ZM8S8vXB98k0/Hjx/Prl27iI+Pp0WLFowaNSrgPi8VqaQ9FhQUMG3aNLZv306VKlVISUnh3nvv5eSTT/avE87HEHy/Fa1evZqhQ4cedp+hdAwXLlwI+G5W9mfXX3+9P0Ru27YNY4z/uRNPPJGbb76Z6dOn8+qrr1KvXj1uu+22gAB34YUXkpeXx+TJk9m7dy8tWrRg5MiRFXp/Eyhdf++++y4FBQX+myUWGjBgAIMGDcJxHH788Ufee+899uzZQ2JiIqeccgqXXHIJUVFR5drP4ZSmx927dzN58mSys7OJi4sjNTWVhx9+OGAORzgfQ4DNmzezYcOGgF+YCoXSMdy5cyeTJk1ix44dxMbGkpKSwt133+2fehDKP3/GWmvLdI8iIiIiQaA5NSIiIuIJCjUiIiLiCQo1IiIi4gkKNSIiIuIJCjUiIiLiCQo1IiIi4gkKNSIiIuIJCjUiIiLiCQo1IiJARkYGgwYNIicnJ9iliEgpKdSIiIiIJyjUiIiIiCco1IiIiIgn6Fu6RaRCbd++nenTp7NmzRr27NlDUlISaWlpdO/eHYC1a9fy4IMP8o9//IPvv/+epUuXsm/fPk4++WSuuuoqateuHbC/VatW8cYbb/Dzzz9TtWpVWrduzWWXXUZiYmLAer/88gszZsxg7dq17Nu3j9q1a9OxY0cuvfTSgPX27t3LSy+9xMcff4y1lg4dOnDVVVdRpUqV8n1jROS4KdSISIXJzs7m7rvvBqBXr17Ex8fz+eef88wzz5Cbm0vfvn39677++usYY7jwwgvJyclh3rx5/Otf/+Kxxx4jOjoagGXLlvH000/TpEkT0tPT2blzJ/Pnz+err75izJgxxMXFAfDDDz9w3333ERkZSY8ePahbty5btmzh008/LRJqxo4dS506dUhPT2fTpk0sWbKE+Ph4Lrvssgp6l0SktBRqRKTCTJ8+Hdd1efzxx6levToA5557LuPGjWPmzJmcc845/nV3797N2LFjiYmJAaBx48aMHTuWRYsW0adPHwoKCnj55Zdp0KABDz74oD/otGjRgkcffZR58+YxaNAgAF544QUARo8eHTDSM2TIkCI1NmrUiOuuuy6gjqVLlyrUiIQBzakRkQphrWX16tWcdtppWGvJycnx/9emTRv27t3Lpk2b/OufddZZ/kAD0LFjR2rWrMmaNWsA2LRpEzt37qRXr17+QAPQtm1b/vKXv/DZZ58BkJOTw/r16+nWrVuRU1fGmCJ1/jlYgS8k7dq1i7179x7/myAi5UojNSJSIXJyctizZw+LFi1i0aJFR1yn8JRRvXr1Ap4zxpCUlERWVhaA///JyclF9pOcnMyGDRsA+O233wBo0KBBseo8NPhUq1YNgD179hAbG1usfYhIcCjUiEiFsNYCcOaZZ3L22Wcfdp2UlBR+/vnniiyrCMc5/AB2Yf0iEroUakSkQsTHxxMTE4PrupxyyilHXK8w1Pz6668By621bNmyhYYNGwJQp04dADZv3szJJ58csO7mzZv9z59wwgkA/PTTT2XTiIiELM2pEZEK4TgOHTp0YPXq1fz4449Fnj/06wnef/99cnNz/Y8//PBDduzYwamnngpAamoqNWrU4N133yU/P9+/3po1a/jll19o27Yt4AtTLVu2ZOnSpWzbti3gNTT6IuItGqkRkQqTnp7O2rVrufvuu+nRowf169dn9+7dbNq0iS+//JL//Oc//nWrVavGfffdR9euXdm5cyfz5s0jKSmJHj16ABAZGcmQIUN4+umneeCBB+jcuTPZ2dm8/fbb1KlTJ+Dy8CuvvJL77ruPO+64w39Jd1ZWFp999hmPPfZYhb8PIlI+FGpEpMIkJCTwyCOPMGvWLFavXs0777xD9erVadCgQZHLq/v3788PP/zAG2+8QW5uLq1ateLqq68OuAle165diY6O5s033+Tll1+mSpUqnH766Vx22WX+Ccfgu0x71KhRzJgxg3fffZf9+/dTp04dzjjjjArrXUTKn7EafxWREFJ4R+H/+7//o2PHjsEuR0TCiObUiIiIiCco1IiIiIgnKNSIiIiIJ2hOjYiIiHiCRmpERETEExRqRERExBMUakRERMQTFGpERETEExRqRERExBMUakRERMQTFGpERETEExRqRERExBP+P5pVcfWHeGWHAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAG0CAYAAADKEdZ4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABe+ElEQVR4nO3dd3gVZd7G8e8zKZBACoGEEOkGRFYUscMiIGtZRcEVG6Agil0U267YsKBiA1Zw1bUgCgKigCBiQSwolhUboiBCFIRIICQhPSfzvH9EzmskKAlJ5pzJ/bkuL8nJnMn9YxK4mWfmHGOttYiIiIiEOcfrACIiIiK1QaVGREREfEGlRkRERHxBpUZERER8QaVGREREfEGlRkRERHxBpUZERER8QaVGREREfEGlRkRERHwh0usA9W3Hjh0EAoFa329ycjJZWVm1vt9Q4ff5wP8zar7w5/cZ/T4f+H/GupgvMjKSZs2a7d22tfqVw0AgEKCsrKxW92mMCe7bj+864ff5wP8zar7w5/cZ/T4f+H/GUJhPy08iIiLiCyo1IiIi4gsqNSIiIuILKjUiIiLiCw3uQmEREak/BQUFBAKB4EWkf6SoqIjS0tJ6SOUdv8+4L/PFxsYSGblvtUSlRkRE6kRJSQnGGBISEvZq+6ioqFq/OzXU+H3Gms7nui47d+6kSZMm+1RsavTMJUuWsHDhQnJycmjXrh0jR44kPT29ym03btzI7Nmz2bBhA1lZWQwfPpxTTjml0jau6zJnzhzef/99cnJySEpKok+fPpxxxhmV2v2mTZuYMWMGq1evxnVdWrduzXXXXUeLFi1qMoaIiNShkpIS4uLivI4hYcBxHOLi4sjPzyc+Pr7G+6l2qfnwww+ZPn06o0aNolOnTrz66quMHz+eSZMmVdnGS0pKaNmyJccccwzPPvtslfucP38+b775JldccQWtW7dm/fr1PProo8TGxnLyyScDkJmZyW233cZxxx3HWWedRUxMDJs2bSIqKqq6I4iISD3Zm2UnEagoNvuq2qVm0aJF9O/fn379+gEwatQoVq5cybJlyxg0aNBu26enpwfP4sycObPKfa5du5bDDz+cHj16AJCSksLy5ctZt25dcJtZs2Zx6KGHMmzYsOBjqamp1Y0vIiIiPlWtUhMIBFi/fn2l8uI4Dt26dWPt2rU1DtG5c2eWLl3K5s2bSUtLIyMjgzVr1nD++ecDFctTK1eu5LTTTmP8+PFs2LCBlJQUBg0axJFHHlnlPsvKyiqt6xljiImJCf66Nu3an1//ReL3+cD/M2q+8NcQZhSBffser1apycvLw3VdEhMTKz2emJjI5s2baxxi0KBBFBUVMWbMGBzHwXVdzjnnHHr37h38usXFxSxYsICzzz6boUOH8sUXX/DQQw9x++2307Vr1932OW/ePObOnRv8uEOHDkyYMIHk5OQa5/wzfj9z5Pf5wP8zar7wF04zFhUVVfsSgYZwSYHfZ9yX+aKjo2nVqlWNnx8Sdz+tWLGC5cuXM3r0aNq0aUNGRgbTpk2jWbNm9O3bF9d1ATj88MMZMGAAAO3bt2fNmjW88cYbVZaa008/Pbgt/H/zy8rKqvU3tDTGkJqaSmZmpm/fz8PP84H/Z9R84S8cZywtLa3WnTB+vzMIKmaMjIwkISGBzMxMr+NUqXnz5pSVlZGXl1ft5+7rMSwtLWXLli2VHouMjNzrExLVKjXx8fE4jkNOTk6lx3NycnY7e1Mdzz//PAMHDqRXr14AtG3blqysLObPn0/fvn2Jj48nIiKC1q1bV3refvvtx5o1a6rcZ1RU1B7bYl39gWCtDZs/bGrC7/OB/2f083y2tMTX8+3SEGaU+hEdHU2LFi3YsmVLpe+p7OxsD1Pt29/R1brUODIyko4dO7Jq1argY67rsmrVKjp37lzjECUlJbtd9ew4TnCwyMhI9t9//92WuLZs2aLbuUUE9/WX2XRmH8pfnq6/8EX2UTgX52ovPw0YMICpU6fSsWNH0tPTWbx4MSUlJfTt2xeAKVOmkJSUxJAhQ4CKi4s3bdoU/HV2djYZGRk0btw4uDZ82GGH8fLLL9OiRQtat25NRkYGixYtCt5hBXDaaacxceJEDjzwQA466CC++OILPvvsM8aNG7ePvwUiEs7sjz/gvjwdysuxi1+EkmI4+yJdUBtirLVQWvLH27jl2LpYfopuVO3vh6ZNmxIbG0tERASBQICdO3dSXFxMy5Yt2blzJ4WFhcFtdy2PbN26lfLycpo0aRJ8rrWW4uJi8vLyalQU4uLiaNy4MQUFBTRt2pSIiAi2bNlCSkoKBQUFFBQUBLdNTk6muLiYnTt3ApCWlkZOTg6NGjWiUaNGuK5Lbm4uJSUlREREBE8K7LqGpbCwkJycnN2Wn1JSUigsLCQyMpLGjRsH91NWVkZCQgKNGjWivLx8t1Wc6Oho4uLiiI6OxnVdioqK2LlzZ50WpmqXmp49e5KXl8ecOXPIycmhffv2jB07Nrj8tG3btkrfPNnZ2dx4443BjxcuXMjChQvp2rVrsJCMHDmS2bNn8+STT5Kbm0tSUhLHH388gwcPDj7vyCOPZNSoUcyfP59nnnmGtLQ0rrvuOrp06VLD0UUk3NmyMtxnJkF5OVHt9qfsxx+wSxdW/OU57HJMLbzuhdSS0hLcK8/6w03+uPLUnDNlDjRqvNfbN23alJiYGHJzcwkEAkRHR9OsWTO2b99OUVERMTExlUpNbGwspaWllJeXBx/Lzc2lvLyciIgIEhISiI+PJzc3t0b5IyIiaNy4cY2WheLi4sjLyyMvL48mTZrQrFkzfvnlF8rLy8nOziYpKYlffvnlT8/ONG3alLy8PHbu3EnTpk1p1qwZpaWlFBYWkpeXR3x8PImJicFiExERQVJSEjt37iQnJwfHcUhISCAhIWG38lObanSh8EknncRJJ51U5ed+f+YkJSWFOXPm/OH+YmJiGDFiBCNGjPjD7Y477jiOO+646kQVER+zi2bDzz9CXALJ9z5G5puv4k77N/b9N6CsDEaMxkREeB1TwkzTpk3Zvn178ILXoqIioqOjiY2NJT8/n+TkZCIiIoIlJiYmJnh2BKh09qS8vJydO3eSkJBQ41JjjCEnJyd400x1FBYWUlRUBBAsJNHR0ZSUlAT357run549KS4uDha5XW9nUFZWRnFxMUDw92XXSY2mTZtSVFQU/L0oLy8nLy+P5s2bh16pERHxms34Hruk4mUbnGGXEZHQDKdXf2xUFPbJh7AfLYOyUrjoOsw+vkme1ILoRhVnTP5And39FN1orzeNjIzEcRyaN29e6XFjDGVlZQQCAQKBADExMeTn5xMdHY3jOMHiAP+/7BIZGYkxptJ/NVFeXl6jQgNU+v201uK6bo1eufe3+9mVparHdu171806u14fbhdjDJGRkbV+F/Iu+kkXkbBjy8pwn54Eros5ojfOYb2Cn3OO6I2NiMR94gHsZx9gywM4F9+I8flrg4Q6Y8yfLgGZqCiM4+2ZtV3FIzs7u9JyEvz/XTm7lqDy8/OJiYmhpKQk+LmIiAiaN29OQUFB8LXddi1f1VQ4XrRrjNntmp9dfv/7Wpu04CwiYccunAlbNkJcAubcS3b7vOlxDM4VN0NUNHzxMe6j47F/cpGqCFTc0GKtDS4v/fa/XWcjioqKiIyMDJ6J+O31NbteSiQvL4+ysrLgdTW1zXXdSvs1xlT769RlWSorKyMqKmq338O6LDSgUiMiYcauX4NdMg8AZ9jlmLiq39HXdDsM56pbK5YeVq3E/fed2OKiKrcV2cVaG3yn6JiYGCIiIoiKiqJJkybBpZTy8nJKS0uDN8jsuq4EKkqRMYYmTZoQERFBTEwMTZo0qfWcJSUlxMTEEB0dTWRkZI1eK668vBxrLY0bN8ZxnFq9YzA/P5+oqCgSEhKIjIwMXuxc1Rtf1yaVGhEJG7asFPeZyWBdzFF9MD2O+cPtzYGH4FxzBzSOgTVf404ehy3c/XS4yG/t3LmT/Px8mjZtSkpKCklJScHblnfZ9RYQvy00UFFqcnNzadq0KcnJycTExNTolXn/TH5+PqWlpSQlJZGUlERxcXG1z4K4rsvOnTuJj4+nZcuWtVo4AoEA27dvD946npycTFxcXJ2fqdE1NSISNuyCGZC5CRKaYc69eK+eYzp1xbn2LtxJt8O6b3EfvhVnzB2YJnF1nFbC2Z6uB9mlsLCw0rLTnz33txcSFxUVVfr4j+zcubPSnVW7WGvZsWPHHr8GUOV7Mv7+rRny8/PJz8+v9Nj27dsrfbx169bd9vP7fZeXl7N58+ZKr+RfVlZW769OrDM1IhIW7LpvsW/MB8A574pqlRLToTPOdXdD0zj4cR3ug7dgd9bs9loRCV0qNSIS8mxJya/LThZzTD/MIUdWex+m7f44198L8YmwaQPuA2OxOd6+x41IcnIyqampVf73+9uh5c+p1IhIyLPzn4etmyExCXP2qBrvx+zXFueGe6FZC9iyEfeBm7DZWbWYVKR6srOzycrKqvK/31+vI39OpUZEQppd+w126SsAOOdfiWnSdJ/2Z1L3w7nhHmieAlu34N5/EzYr88+fKFIHqrrledd/4fj6NF5TqRGRkGVLinGf/XfFslOvv2G6HV4r+zXJqTg33gspabB9a0WxydxUK/sWkZrb1yKnUiMiIcvOew62boFmLTBnXVir+zZJyRVnbFq1gZztFdfY/PxjrX6Nhs4YQ2lpqdcxJAxYaykoKCByH9/SRLd0i0hIsmtWVbzjNr8uO8XW/guYmcQknBvuwX34toqLhx8cizPmTkzb/Wv9azVETZs2JT8/f6+vDYmOjvZ9CfL7jPsyX6NGjWjUaO/fp6sqKjUiEnJscRHutMkAmN4nYA7qUWdfy8Ql4Fw/vuJ1bDK+x33oFpyrx2E6HlBnX7OhMMYQF7d3t94bY2jVqhVbtmzx7bUkfp8xFObT8pOIhBz78rOw7RdISsacObLOv55p0hTn2rsg/UAoLMCdeBt27Td1/nVFpHap1IhISLHffoldthgAZ/hVmJjYevm6JiYW5+pxcEA3KC6qeEuFb7+sl68tIrVDpUZEQoYtLsR99hEATJ+TMF271+vXN41jcEbfBgf1gNKSijfB/Pp/9ZpBRGpOpUZEQoZ9cRps3wrNUzCDR3iSwUQ3wrn8Zuh+FATKcKfeg125wpMsIlI9KjUiEhLs6s+x7y0BwBkxGtO4fpadqmKionAu+Sfm8L9CeQD38Qm4n7znWR4R2TsqNSLiOVv0m2WnfqdguhzscSIwkZGYUddhjukHrot98mHcD5Z6HUtE/oBKjYh4zr74NGRvg+RUzBnDvY4TZJwIzIirMceeCNbFTpuM+85rXscSkT1QqRERT9lVn2HffwP4ddmpUWOPE1VmHAcz7HJM/1MBsDP+g/vWAo9TiUhVVGpExDO2MB/32SkAmP6nYjof5HGiqhljMGdfhDnpDADs7KdwF7/ocSoR+T2VGhHxjJ3zFORsh5RWmNPP9zrOHzLGYP5xPubUc4GK96VyF8z05SvDioQrlRoR8YT96lPsB0vBGJwLrsbs43u+1AdjDM5p5wav+7GLZmFfmqZiIxIiVGpEpN7Zgnzc6VMBMH87DZPe1eNE1eOcdAbmnFEA2NfnYV94Auu6HqcSEZUaEal3dtZ/ITcbWu6HGTTM6zg14vQ/FXPe5WAMdtmr2OcfxbrlXscSadBUakSkXtkvPsZ+tAyMU7HsFB36y0574hx7EmbE1WAc7PtvYJ+ZjC1XsRHxikqNiNQbm5+H+/yjAJgTBmH27+Jxon3n9DwOM+p6iIjAfvQO9r8PYgMBr2OJNEgqNSJSb+wL/4XcHdCqDWbgEK/j1BrniL/iXPpPiIzEfvYB7mP3YctKvY4l0uCo1IhIvbArP8R+8u7/LztFRXsdqVaZ7kfjXHEzREXDl5/gThmPLSnxOpZIg6JSIyJ1zu7Mw33+PwCYk/6B6dDZ40R1wxx0GM5Vt0J0I1j9Oe4jd2KLi7yOJdJgqNSISJ2zLzwOO3MhrW3wxev8yhx4CM6YO6BxDKz5GnfS7djCAq9jiTQIKjUiUqfs/5ZjP30fHAdn5DWYqCivI9U5k94V59q7IbYp/PAd7sO3Ygt2eh1LxPdUakSkzti8HNwZjwFg/j4Y0y7d40T1x3TohHP9eGgaDz+uw33wZmxejtexRHxNpUZE6oS1tqLQ5OdB6/aYAWd7HanemTYdcG64BxKawaYM3AfGYnO2ex1LxLdUakSkTtj/LYeVH0JERMXdTpH+X3aqiklri3PDvdCsBWRuwr3/Juz2LK9jifiSSo2I1DqbuwO7a9np5LMwbff3OJG3TMu0ijM2LVpCVibuAzdht27xOpaI76jUiEitstZWvGpwwU5o0wFz8pleRwoJJjm14oxNy/1g+9aKYpO5yetYIr6iUiMitcp+/C588TFEROJccA0mMtLrSCHDJLWoOGOT1hZysiuWojZleB1LxDdUakSk1ticbOwLTwBgBpyNadPB40ShxyQ0w7n+HmjTAXbmVtwV9eMPXscS8QWVGhGpFcFlp8J8aJeOOekMryOFLBMXj3PdeOjQGQp24j50C/aH77yOJRL2VGpEpFbYFcvgy08gMvLXu5207PRHTJOmOGPuhPSuUFSAO/F27NpVXscSCWsqNSKyz+yO7dhZ/wXAnHouZr92HicKDyYmFueacdDlYCgpwp08Drv6C69jiYQtlRoR2SfWWtzpU6CoANp3wpz4D68jhRXTqHHFm2B2OxxKS3EfuQv71adexxIJSyo1IrJP7IdLYdVnEBlVsewUEeF1pLBjohvhXHYTdD8aAmW4j96LXfmh17FEwo5KjYjUmM3Ows5+EgAzaCgmra3HicKXiYrCueRGzBG9oTyA+/j9uB+/63UskbCiUiMiNWKtxX12ChQVQscDMMcP9DpS2DORkZiLrsUccxy4Lvaph3E/eMvrWCJhQ6VGRGrEvv8GrP4coqIrlp0cLTvVBuNEYEaMxvQ5CazFTvs37juLvY4lEhZUakSk2uz2rdgXnwbADBqGSW3tcSJ/MY6DGXoZ5m+nAWBnPIb7xnxvQ4mEAb2QhIhUS8Wy0yNQXATpB2L+dqrXkXzJGANnXQhR0djX5uLOeYq8xo3g2L97HU0kZOlMjYhUi313CXz7JURH44zQslNdMsZgTj8PM3AIALnTH6V8/vNYaz1OJhKaVGpEZK/ZrEzs3GcAMKefj2mZ5nEi/zPG4Aw4B2fwBQDYRbOxc59RsRGpgkqNiOwV67oVy04lxdCpK+a4AV5HalCck/5B4qU3AGDfmI994XGs63qcSiS0qNSIyF6x774Ga76G6Ea/Ljvpj4/6Fnfq2TjnXwnGYJctxj43FeuWex1LJGToTyUR+VN26xbs3GkAmMEjMCmtvA3UgDnHnogZeQ0YB7v8TezTk7DlKjYioFIjIn/Cui7utMlQWgIHdMP00d03XnOO7odz8fUQEYH9+F3cJx7ABsq8jiXiOZUaEflD9u1F8P1qaNQYZ/hVWnYKEebwv+Jc+i+IjISVH+L+5z5sWanXsUQ8pT+dRGSP7C+bsfOmA2AGX4BJTvU4kfyW6X4UzhW3QFQ0fPUp7pS7sSUlXscS8YxKjYhUybrlvy47lcKBh1S8bL+EHHNQD5yrb4dGjWH1F7j/vgNbXOh1LBFPqNSISJXsWwth3bfQOKZi2ckYryPJHpgDuuFccwfExMLaVbiTxmEL872OJVLvVGpEZDc2cxN2/vMAmDNHYpqneJxI/oxJPxDn2rsgtin88B3uQ7di8/O8jiVSr1RqRKQS65bjPjMZykqh66GY3id4HUn2kmnfCef68RCXAD/9gPvgzdi8HV7HEqk3KjUiUol9cwGsXwMxsTjDr9SyU5gxbTpUFJuEJPj5R9wHbsbu2O51LJF6oVIjIkF280/Y+TMAMGdfhElK9jiR1IRJa4tzwz2Q1AIyN+E+cBN2+1avY4nUOZUaEQHAlv+67BQog26HY3r29zqS7APTMg3nhnshORWyMnHvvwm7dYvXsUTqVGRNnrRkyRIWLlxITk4O7dq1Y+TIkaSnp1e57caNG5k9ezYbNmwgKyuL4cOHc8opp1TaxnVd5syZw/vvv09OTg5JSUn06dOHM844o8pT30888QRvvfVWlfsSkZqxr78MGd9DTBOc867QspMPmBYtcW64F/ehW+CXn3HvvwnnursxrVp7HU2kTlT7TM2HH37I9OnTGTx4MBMmTKBdu3aMHz+e3NzcKrcvKSmhZcuWDBkyhMTExCq3mT9/Pm+++SYXXnghEydOZOjQobzyyiu89tpru237ySef8P3339OsWbPqRheRPbA//4hd+AIA5pxRmGbNPU4ktcU0a16xFJXWFnKzK5aiNmV4HUukTlT7TM2iRYvo378//fr1A2DUqFGsXLmSZcuWMWjQoN22T09PD57FmTlzZpX7XLt2LYcffjg9evQAICUlheXLl7Nu3bpK22VnZ/P0009z8803c9999/1hzrKyMsrK/v+9UIwxxMTEBH9dm3btz6//svX7fOD/Gf9oPhsI/LrsFMAcciROz+PC7vfB78cP9m1Gk5iEueEeyifeBj+tx33wZiLG3IlpX/UZdi/oGIa/UJivWqUmEAiwfv36SuXFcRy6devG2rVraxyic+fOLF26lM2bN5OWlkZGRgZr1qzh/PPPD27jui6PPPIIp512Gm3atPnTfc6bN4+5c+cGP+7QoQMTJkwgObnuLnxMTfX3S8j7fT7w/4xVzZc760nyflyH0zSe1OvvJCKphQfJaoffjx/sw4ytWuHe/yRZt4+mdM0q3Im3knzHv2l04MG1G3Af6RiGPy/nq1apycvLw3Xd3ZaREhMT2bx5c41DDBo0iKKiIsaMGYPjOLiuyznnnEPv3r2D2yxYsICIiAj+/ve9e4fg008/nQEDBgQ/3tUcs7KyCAQCNc5aFWMMqampZGZmYq2t1X2HAr/PB/6fcU/z2Y0bKJ/5ZMUH54xia0kZbAm/i0n9fvyg9ma0V90Kk+/Efv8NW2++gojRt2IO6FaLSWtGxzD81dV8kZGRe31CokYXCte2FStWsHz5ckaPHk2bNm3IyMhg2rRpNGvWjL59+7J+/XoWL17MhAkT9vq0VlRUFFFRUVV+rq6+may1vvxG3cXv84H/Z/ztfDYQwH16IpQHoPvRcOSxYT+7348f1MKMjWJwrr4dd+p4+PZLyiePw7n8ZsxfDq29kPtAxzD8eTlftUpNfHw8juOQk5NT6fGcnJw9XgS8N55//nkGDhxIr169AGjbti1ZWVnMnz+fvn378u2335KXl8fll18efI7rukyfPp3FixczderUGn9tkYbKLn4RNm6ApnE4513m23V+2Z1p1Bjnqltx/3MffP0/3Cl34Vx6E+aQI7yOJrJPqlVqIiMj6dixI6tWreLII48EKsrFqlWrOOmkmr+Db0lJCY5T+UYsx3GCTe/YY4+lW7fKp0fHjx/PscceG7xgWUT2nv3pB+ziOQCYIZdi4nU3YUNjoqJxLr8J94kH4POPcP9zD86oGzCH9fQ6mkiNVXv5acCAAUydOpWOHTuSnp7O4sWLKSkpoW/fvgBMmTKFpKQkhgwZAlRcXLxp06bgr7Ozs8nIyKBx48bBi4kOO+wwXn75ZVq0aEHr1q3JyMhg0aJFwcISFxdHXFxc5eCRkSQmJpKWllbj4UUaIhsow316EpSXQ4+emMP/6nUk8YiJjMK5+EbsM5Own7yH+8T9mJFjcI7q43U0kRqpdqnp2bMneXl5zJkzh5ycHNq3b8/YsWODy0/btm2rdBo7OzubG2+8MfjxwoULWbhwIV27dmXcuHEAjBw5ktmzZ/Pkk0+Sm5tLUlISxx9/PIMHD9636URkN3bRbPj5R2gajzP0Ui07NXAmMhIuHANRUdgPlmKfehi3rBTnr8d7HU2k2oz189VKVcjKyqr0+jW1wRhDq1at2LJliy8v/vL7fOD/GXfNt3nF+5Tfcx24Ls4lN/rmLI3fjx/U/YzWdbEvPI59p+JFT82QS3D61d8rtusYhr+6mi8qKmqv737Sez+JNBC2rJTypyeC62KO6O2bQiO1wzhOxfVVfxsIgJ35OO4b8zxOJVI9KjUiDUTuzP/C5p8gLgFz7iVex5EQZIzBnDUSc/KZANgXn8FdNNvjVCJ7T6VGpAGw69eyc+6zADjDLsfExXucSEKVMQbn9PMwA4cCYBfMwJ33vC+XS8R/VGpEfM6WlVL+zKSKZaej+mB6HON1JAkDzoCzMWdeAIBdPAf74tMqNhLyVGpEfM4umAlbNuI0a45z7sVex5Ew4pxwOmZIxVKlfXMBduZjWNf1OJXInqnUiPiY/eE77BvzAUi6ciymqZadpHqcfqdgzr8SjMG+8xp2+iNYt9zrWCJVUqkR8SlbWoL7zGSwLuaYfsQcrRdUk5pxep+AGXkNGOfX17KZhC1XsZHQo1Ij4lN2wQz45WdISMI5R8tOsm+co/vhXHIDRERgP3kX94n7sYHafc0vkX2lUiPiQ3bdauybCwBwzr8C06Spx4nED8xhvXAuuwkiI2HlCtxH78WWlXodSyRIpUbEZ2zJrmUni+nVH3Ow3nlZao855EicK2+F6OiKd/h+5C5sSbHXsUQAlRoR37HzpsPWLZDYHHPWhV7HER8yfzkUZ/Q4aNQYvv0Sd/I4bHGh17FEVGpE/MSuXYVduhAAZ/iVmFgtO0ndMAcchHPNHRATC9+vxp14O7Yw3+tY0sCp1Ij4hC0pxp32bwBM7xMwBx3mcSLxO5N+IM51d0OTOFi/BvehW7H5eV7HkgZMpUbEJ+xLz0JWJiS1wJw50us40kCYduk4198NcQnw0w+4D96MzdvhdSxpoFRqRHzAfvcVdtmrADjDR2NiYj1OJA2Jad0B54Z7ICEJfv4R94Gx2B3bvY4lDZBKjUiYs8VF/7/sdOxJmK7dvQ0kDZJp1QbnxnsgKRkyf8Z94Cbs9q1ex5IGRqVGJMzZl6bB9q3QPAVz5giv40gDZlLScG68F5JTISsT9/5/Ybdu9jqWNCAqNSJhzK7+AvvOawA4w6/CNNayk3jLNE/BueFeSN0Psrfh3j8Wu2Wj17GkgVCpEQlTtqgQ99lHADD9TsYceIjHiUQqmGbNK66x2a8d5GZXXGOzcYPXsaQBUKkRCVP2xachOwtatMT8Y7jXcUQqMfHNcK4fD233h525FXdFZXzvdSzxOZUakTBkV63Evv8GAM6IqzGNYzxOJLI70zQe57q7oOMBUJiP+/Ct2HXfeh1LfEylRiTM2MIC3OlTADD9T8UccJDHiUT2zMQ2xRlzB3T+CxQV4k66Hbvma69jiU+p1IiEGTvnKdixDVJaYU4/z+s4In/KNI6teK+ort2hpBh38h3Ybz73Opb4kEqNSBixX/8P+8FbYEzFslOjxl5HEtkrplEjnCtvgYOPgLJS3Cl3Yb/8xOtY4jMqNSJhwhbk/2bZ6TRMp64eJxKpHhMVjXPZv6BHTwgEcP9zL/Z/y72OJT6iUiMSJuzsJyEnG1ruhxk0zOs4IjViIqNwLr4Bc2QfKC/HfeJB3I+WeR1LfEKlRiQM2C8/wa54G4yDc8HVmEaNvI4kUmMmIgJz4TWYXn8D62KfnoT73utexxIfiPQ6gIj8MVuwE/e5qQCYEwZi9u/icSKRfWecCDj/SoiKxr6zGHf6FHY2iYXDensdTcKYztSIhDj7whOQuwNSW2MGDvU6jkitMY6DGXIJ5oRBAOT8537c11/2NpSENZUakRBmP/8I+/G7/7/sFBXtdSSRWmWMwQy+ADPgbADcF5/BXTQLa63HySQcqdSIhCi7M+//l51OOh3T8QCPE4nUDWMMEYOGkXDeZQDYBTOx855TsZFqU6kRCVH2hcdhZy6ktcWcOsTrOCJ1Lv6cC3HOuhAA+9pc7JynVGykWlRqREKQ/ewD7Kfvg7Nr2SnK60gi9cI5YRBmyKUA2Ldewc74D9Z1PU4l4UKlRiTE2J25uDMeA8CcNBjTvpPHiUTql9PvZMzwq8AY7LtLsM8+gnXLvY4lYUClRiTE2BmPVSw77dcuePGkSEPj/PV4zIXXguNgP1yKffJhbCDgdSwJcSo1IiHE/XQ59rMPICIC54JrtOwkDZpzVB+ci2+EiEjsp+/jPnE/tqzM61gSwlRqREKEzduBnfkfAMzJZ2La7e9xIhHvmcN64lx2E0RGwucfVbxfVFmp17EkRKnUiIQAay3u8/+B/J3QugPm5DO9jiQSMswhR+BcdStER8PX/8N95C5sSbHXsSQEqdSIhAD7yXvw+UcVy04jr8FEatlJ5LdM10NxRo+DRjHw7Ze4k8dhiwq9jiUhRqVGxGM2Jxs783EAzICzMW06eJxIJDSZAw7CGXMHxDSB71fjTrwNW5DvdSwJISo1Ih6qWHZ6FArzoe3+mJMGex1JJKSZ/bvgXHc3NImDDWtxH7oZuzPP61gSIlRqRDxkP3oHvvwEIiJ/XXaK9DqSSMgz7fbHuX48xCXAxg24D47F5u7wOpaEAJUaEY/YnO3YWU8AYE49B7NfO48TiYQP07o9zg33QmISbP4J94Gx2OxtXscSj6nUiHjAWos7fSoUFkC7dMxJZ3gdSSTsmFatK4pNUjL88jPuAzdht/3idSzxkEqNiAfsh2/D1/+DyF+XnSIivI4kEpZMSiucG++D5FTY9ktFsflls9exxCMqNSL1zGZvw87+LwBm4FBMWluPE4mEN9M8GefGeyG1NWRvqyg2m3/yOpZ4QKVGpB5VLDs9AkWF0KEz5oRBXkcS8QWT2Bznhntgv3aQu6PiGpuNG7yOJfVMpUakHtnlb8I3n0NkVMV7OzladhKpLSY+seKuqHbpkJ+H++DN2A3fex1L6pFKjUg9sduzsHOeAsCcPgzTqrXHiUT8xzSNx7n2Tti/CxTm4068FbtutdexpJ6o1IjUA2st7rP/huIi2L8L5m+neR1JxLdMbFOca8ZB54OgqBB30jjsd195HUvqgUqNSD2w770O334JUdE4I67WspNIHTONY3FG3w5dD4WSYtx/34ld9ZnXsaSOqdSI1DG77Rfsi88AYP5xHiZ1P48TiTQMplEjnCtvhkOOhLJS3KnjsV985HUsqUMqNSJ1yLou7rOPQEkRdOqKOe5UryOJNCgmKhrn0n9Cj54QCOA+NgH7v+Vex5I6olIjUofsu0vgu68guhHOiNEYRz9yIvXNREbhXHwD5qg+UF6O+8SDuCuWeR1L6oD+hBWpIzYrEzv312WnM4ZjUtI8TiTScJmICMzIazC9TwDrYp+ZhPve617HklqmUiNSB6zr4k6bDKUlcEA3TN+TvY4k0uAZJwIz7HJMv5PBWuxzU3GXLvI6ltQilRqROmCXLYa130CjxjjDr9Kyk0iIMI6DOfcSzAmnA2BnPYG75CWPU0lt0Z+0IrXMbt2MfXkaAGbwCExyqreBRKQSY0zFz+aAswGwLz2Lu3AW1lqPk8m+UqkRqUXWLcd9ZjKUlsKBh2COPcnrSCJSBWMMzsChmEHDALCvzMTOm65iE+ZUakRqkV26CNZ9C41itOwkEgacU87CnH0hAPa1l7Czn1SxCWP6E1ekltjMn7HzngPAnHUBpnmKx4lEZG84fxuIGXopAHbpQuzz/8G6rseppCZUakRqgXXLK+52KiuFrt0xvU/0OpKIVIPT92TMiNFgDPa9Jdhp/8a65V7HkmpSqRGpBfbNV+CH7yAmtmLZyRivI4lINTm9/oa58FpwHOyKt7FPPowNBLyOJdWgUiOyj+yWjdj5zwNgzroQk5TscSIRqSnnqD44l9wIEZHYT9/Hffx+bFmZ17FkL6nUiOwDW/7r3U6BMjjoMEyvv3kdSUT2kenRE+eKsRAZBV98hPvoPdjSEq9jyV6IrMmTlixZwsKFC8nJyaFdu3aMHDmS9PT0KrfduHEjs2fPZsOGDWRlZTF8+HBOOeWUStu4rsucOXN4//33ycnJISkpiT59+nDGGWdgjCEQCDBr1iw+//xztm7dSmxsLN26dWPIkCEkJSXVZASRWmHfmA8b1kJME5zzrtCyk4hPmG6H41x1K+7Uu2HVZ7iP3IVz5S2YRo29jiZ/oNpnaj788EOmT5/O4MGDmTBhAu3atWP8+PHk5uZWuX1JSQktW7ZkyJAhJCYmVrnN/PnzefPNN7nwwguZOHEiQ4cO5ZVXXuG1114DoLS0lA0bNnDGGWcwYcIErrvuOjZv3sz9999f3fgitcb+/BP2lRkAmHMuwiS18DiRiNQm07U7ztV3QKMY+O4r3Em3Y4sKvY4lf6DapWbRokX079+ffv360bp1a0aNGkV0dDTLllX9jqfp6emcd9559OrVi6ioqCq3Wbt2LYcffjg9evQgJSWFo48+moMPPph169YBEBsby6233krPnj1JS0ujc+fOjBw5kvXr17Nt27bqjiCyz2wggPvMJAgE4OAjMMcc53UkEakDpvNfcMbcATFNYN23uBNvwxbkex1L9qBay0+BQID169czaNCg4GOO49CtWzfWrl1b4xCdO3dm6dKlbN68mbS0NDIyMlizZg3nn3/+Hp9TWFiIMYbY2NgqP19WVkbZby7uMsYQExMT/HVt2rU/vy49+H0+qP6M9vWX4cd1ENuEiPOvCPkX2fP7MfT7fOD/GUN5PpN+IOb6uymfeBtsWIv70C1EXHsnJi6hevsJ4RlrQyjMV61Sk5eXh+u6uy0jJSYmsnnz5hqHGDRoEEVFRYwZMwbHcXBdl3POOYfevXtXuX1paSkzZsygV69eeyw18+bNY+7cucGPO3TowIQJE0hOrrs7U1JT/f0eP36fD/ZuxtKMdfyyaBYASZf9kyYHHlTXsWqN34+h3+cD/88YsvO1akXphP+SdfMVuBvXYybeRsr4R4mowbJzyM5YS7ycr0YXCte2FStWsHz5ckaPHk2bNm3IyMhg2rRpNGvWjL59+1baNhAIMHHiRAAuuuiiPe7z9NNPZ8CAAcGPdzXHrKwsArX8ugPGGFJTU8nMzPTly2v7fT7Y+xltIED5hLEQCGC6H0Vul+7kbdlSj0lrxu/H0O/zgf9nDIv5GjXBXH83PHQLgZ/Ws/n6kURcd/dev4xDWMy4D+pqvsjIyL0+IVGtUhMfH4/jOOTk5FR6PCcnZ48XAe+N559/noEDB9KrVy8A2rZtS1ZWFvPnz69UanYVmm3btnHbbbft8SwNQFRU1B6v4amrbyZrrS+/UXfx+3zw5zO6i1+En9ZDkzjMsMuDzwkXfj+Gfp8P/D9jyM/Xcj+cG+7FfegW+GUz5RP+hXPd3ZjkvT87EfIz7iMv56vWhQCRkZF07NiRVatWBR9zXZdVq1bRuXPnGocoKSnB+d01CY7jVPpN2VVoMjMzufXWW4mLi6vx1xOpCfvTeuyrswEwQy7BJDTzOJGIeMEkp+LccC+ktILtW3EfGIvN/NnrWEIN7n4aMGAAS5cu5Z133mHTpk08+eSTlJSUBM+oTJkyhZkzZwa3DwQCZGRkkJGRQSAQIDs7m4yMDDIzM4PbHHbYYbz88susXLmSrVu38sknn7Bo0SKOOOKI4D4efvhh1q9fz1VXXYXruuTk5JCTk1PrS0kiVbGBsooX2Ssvhx7HYI6o+novEWkYTPNknBvugVZtYMc23AfHYjf/5HWsBq/a19T07NmTvLw85syZQ05ODu3bt2fs2LHB5adt27ZVuvI5OzubG2+8MfjxwoULWbhwIV27dmXcuHEAjBw5ktmzZ/Pkk0+Sm5tLUlISxx9/PIMHDw7u43//+x9ApX0B3H777fzlL3+p7hgi1WJffRE2bYCm8ThDL/Pt3QsisvdMYnOc68fjTrwNNmXgPjAWZ8ydmLYdvY7WYBnr54W9KmRlZVW61bs2GGNo1aoVW7Zs8eU6qd/ngz+e0f74A+4914Hr4lxyI+bwv3qUsub8fgz9Ph/4f8Zwns8W7MSdeHvwZR6ca+7AdNj9koxwnnFv1NV8UVFRe32hcGi/uIaIx2xZWcWL7Lku5vC/hmWhEZG6ZZrE4Vx7F+zfBQoLcB++Ffv9aq9jNUgqNSJ/wC6aBT//CHEJmCGXeB1HREKU+fUMDQd0g+KiirdU+PZLr2M1OCo1IntgN3yPXfISQMV1NNV89VARaVhM4xicq26DrodCaQnuI3dhV33mdawGRaVGpAq2rPT/l52OPBZzWE+vI4lIGDCNGuFceQscciSUleJOGY/94iOvYzUYKjUiVbCvvABbNkJ8Iubci72OIyJhxERF4Vz6L8xhvaA8gPvYBNxP3/c6VoOgUiPyO/aH77CvzwPAOe9yTNN4jxOJSLgxkZGYUddjju4H5eXY/z6E+8FSr2P5Xki895NIqLClJbjT/g3WxRzdF9P9aK8jiUiYMhERcMHVEBWFff8N3Gcmkd8kFrof43U039KZGpHfcBfMgMxNkJCEOWeU13FEJMwZx8EMuxzT7xQAdky5B/etVzxO5V8qNSK/Kln9JfaN+QA4512BaaL3FxORfWccB3PuxZgT/wGAO+u/uK+95HEqf1KpEQFsSTHZE+8AazE9+2MOOcLrSCLiI8YYnMEjiB9ScQbYvvws7iszffnKwl5SqREB3HnPEdj8EzRrjjn7Qq/jiIgPGWNIGHoJzj/OB8AunIV96VkVm1qkUiMNnl37DXbpQgCc86/ExDb1OJGI+Jlz8pnBfzzZ11/Gzn5SxaaWqNRIg2ZLinGnTQZraXLCQJxuh3sdSUQaAOdvAzFDLwPALl2Iff5RrOt6nCr8qdRIg2Zfng5ZmZDUgsSLxngdR0QaEKfv3zEXXA3Gwb73OnbaZGx5udexwppKjTRYds3X2LcXAeAMH43TRMtOIlK/nJ79MaOuA8fBrliGffIhbCDgdaywpVIjDZItLqp4kT3AHHsizl8O9TiRiDRUzhG9cS75J0REYv+3HPfxCdiyMq9jhSWVGmmQ7EvPwrZfoHkK5swLvI4jIg2c6XEMzhVjITIKvvgY99Hx2NISr2OFHZUaaXDst19i31kMgDP8KkzjWI8TiYiA6XY4zujbILoRrFqJ++87scVFXscKKyo10qDY4kLcZx8BwPQ9GXPgId4GEhH5DXPgIThXj4PGMbDma9zJ47CFBV7HChsqNdKg2Benwfat0KIl5ozhXscREdmN6fwXnGvvgtgmsO5b3Im3YQt2eh0rLKjUSINhv/kc+94SAJwRozGNYzxOJCJSNdOhM851d0PTOMj4HvfBW7A7c72OFfJUaqRBsIUFuNN/XXY6bgDmgG4eJxIR+WOm7f44198L8YmwaQPuA2OxOdlexwppKjXSINgXn4bsbZCcivn1fVdEREKd2a8tzg33QmJz2LIR94GbsNlZXscKWSo14nv268+wy98EY3BGXI1p1NjrSCIie82k7odz473QPAW2bsG9/yZsVqbXsUKSSo34mi3Mx50+BQDT/1RM5794nEhEpPpMcmpFsUlJg+1bK4pN5s9exwo5KjXia3b2U5CzHVLSMIPO8zqOiEiNmaRknBvugVZtIGd7xVLUzz96HSukqNSIb9kvP8V+uLRi2emCqzGNGnkdSURkn5jEpIpi07oD5OXgPjgW+9MPXscKGSo14ku2IB/3uakAmOMHYdIP9DiRiEjtMHEJONffDe07Qf5O3Iduwa5f43WskKBSI75kZ/0XcrMhdT/MwCFexxERqVWmSRzOmDsh/UAoLKh4gb7vV3sdy3MqNeI79ouPsB8tA+NU3O0UrWUnEfEfE9uk4i0VDugGxUW4k27Hfvul17E8pVIjvmLz83CfexQAc+LpmP27eJxIRKTumMYxFW+CeVAPKC2peBPMr//ndSzPqNSIr9gXnoC8HGjVBnPauV7HERGpcya6Ec7lN0P3oyBQhjv1HuzKFV7H8oRKjfiGXfkh9pP3wHFwLrgGExXtdSQRkXphoqJwLvkn5vC/QnkA9/EJuJ+853WseqdSI75gd+biPv8fAMxJZ2A6dPI4kYhI/TKRkZiLrsMc0w9cF/vkw7gfLvU6Vr1SqRFfsDMfh525sF87zIBzvI4jIuIJExGBGXE15tgTwbrYZybjvvOa17HqjUqNhD330+XY/y3/zbJTlNeRREQ8YxwHM+xyTP9TAbAz/oP71gKPU9UPlRoJazYvBzvzMQDMyWdh2u3vcSIREe8ZYzBnX4Q56Qyg4i1j3MUvepyq7qnUSNiy1uLOeAzy86B1B8wpZ3odSUQkZBhjMP84H3NqxZ2gdt5zuAtmYq31OFndUamRsGU/fR9WfggRERXv7RSpZScRkd8yxuCcdi7mH8MBsItmYV+a5ttio1IjYcnm7qi4OBgwp5yNadvR40QiIqHL+fsZmHNGAWBfn4d94Qms63qcqvap1EjYsdbiPv8oFOyEth0xfx/sdSQRkZDn9D8Vc97lYAx22avY5x/FuuVex6pVKjUSduzH78IXH0NEZMXdTpGRXkcSEQkLzrEnYUZcDcbBvv8G9pnJ2HL/FBuVGgkrNmd7xVshAObUczCt23sbSEQkzDg9j8OMug4cB/vRO9j/PogNBLyOVStUaiRsWGsr3qyyMB/apQdvVRQRkepxjuiNc+m/ICIS+9kHuI/dhy0r8zrWPlOpkbBhV7wNX30Kkb8uO0VEeB1JRCRsmUOPxrnyZoiKhi8/wZ16N7akxOtY+0SlRsKC3bEdO+tJAMxpQzH7tfU4kYhI+DMHHYZz1a0Q3Qi++Rz3kTuxxUVex6oxlRoJedZa3OlToKgAOnTGnDDI60giIr5hDjwEZ8wd0DgG1nyNO+l2bGGB17FqRKVGQp794C1Y9RlERlW8yJ6WnUREapVJ74pz7V0Q2wR++A734VuxBTu9jlVtKjUS0uz2LOycpwAwg4ZhWrXxOJGIiD+ZDp1xrhsPTePhx3W4D96MzcvxOla1qNRIyKpYdnoEigph/y6Y40/zOpKIiK+Zth1xrr8HEprBpoyKYpOz3etYe02lRkKWff8NWP0FREXjjLga42jZSUSkrpn92uLccC80awFbNuI+MBa7PcvrWHtFpUZCkt2+FTvnaQDM6edhUvfzOJGISMNhWqbh3HAPtGgJW7fgPnATdusWr2P9KZUaCTnWdXGn/RtKiiC9K6b/AK8jiYg0OCY5teKMTUoabN9aUWwyN3kd6w+p1EjIse8tge++guhonAtGa9lJRMQjJqlFxRmbVm0gJ7tiKernH72OtUcqNRJSbFYmdu40AMw/RmBS0rwNJCLSwJnEpIpi06YD5OXgPjgW++MPXseqkkqNhAzrurjPPgIlxdD5IEy/k72OJCIigIlLqLjdu0NnyN+J+9At2B++8zrWblRqJGTYdxbDmq+hUWOcEaMxjr49RURChWnSFGfMnZDeFYoKcCfejl27yutYlehvDQkJdutm7EvPAmDOGIFJTvU4kYiI/J6JicW5Zhx0ORhKinAnj8Ou/sLrWEEqNeK54N1OpSXQ5WBMn5O8jiQiIntgGjWueBPMgw6D0lLcR+7CfvWp17EAlRoJAfbtRfD9amgUgzP8Ki07iYiEOBPdCOfysdD9aAiU4T56L+7KFV7HUqkRb9nMn7HzpgNgzrwA06Klx4lERGRvmKgonEtuxBzRG8oDuI/dR8E7SzzNpFIjnrFuOe60yVBaCgcegjn2RK8jiYhINZjISMxF12KOOQ5cl+yHbsNu3uhZnkjPvrI0ePatV+CH76BxDM7w0RhjvI4kIiLVZJwIGDEaoqOJ75BOQVobrLWeZFGpEU/YLZuw854HwJx1IaZ5sseJRESkpozjYIZdTnxaGgVbvHuPKC0/Sb2zbjnuM5MgUAYH9cD89XivI4mIyD4KhbPtKjVS7+wb82HDWohpgnPelSHxgyAiIuGvRstPS5YsYeHCheTk5NCuXTtGjhxJenp6ldtu3LiR2bNns2HDBrKyshg+fDinnHJKpW1c12XOnDm8//775OTkkJSURJ8+fTjjjDOCf+FZa5kzZw5Lly6loKCALl26cNFFF9GqVauajCAesZt/wi6YAYA5+yJMUguPE4mIiF9U+0zNhx9+yPTp0xk8eDATJkygXbt2jB8/ntzc3Cq3LykpoWXLlgwZMoTExMQqt5k/fz5vvvkmF154IRMnTmTo0KG88sorvPbaa8FtFixYwGuvvcaoUaO45557aNSoEePHj6e0tLS6I4hHbHk57tOTIBCAbodjeh7ndSQREfGRap+pWbRoEf3796dfv34AjBo1ipUrV7Js2TIGDRq02/bp6enBszgzZ86scp9r167l8MMPp0ePHgCkpKSwfPly1q1bB1ScpVm8eDH/+Mc/OOKIIwC48sorGTVqFJ9++im9evXabZ9lZWWUlZUFPzbGEBMTE/x1bdq1P78uo9TWfPaNefDjOohtQsTwK0PqRfZ0DMOb3+cD/8/o9/nA/zOGwnzVKjWBQID169dXKi+O49CtWzfWrl1b4xCdO3dm6dKlbN68mbS0NDIyMlizZg3nn38+AFu3biUnJ4eDDz44+JzY2FjS09NZu3ZtlaVm3rx5zJ07N/hxhw4dmDBhAsnJdXeXTWqqv9+vaF/mK81Yxy+vVJTapMtupMmBB9VWrFqlYxje/D4f+H9Gv88H/p/Ry/mqVWry8vJwXXe3ZaTExEQ2b95c4xCDBg2iqKiIMWPG4DgOrutyzjnn0Lt3bwBycnIASEhIqPS8hISE4Od+7/TTT2fAgAHBj3c1x6ysLAKBQI2zVsUYQ2pqKpmZmZ7dm1+X9nU+GwhQPuFmCAQw3Y8it8uh5Hl4y19VdAzDm9/nA//P6Pf5wP8z1tV8kZGRe31CIiRep2bFihUsX76c0aNH06ZNGzIyMpg2bRrNmjWjb9++NdpnVFQUUVFRVX6urr6ZrLW+/Ebdpabzua+9CD/9AE3iMMMuD+4rFOkYhje/zwf+n9Hv84H/Z/RyvmqVmvj4eBzH2e3sSE5Ozh4vAt4bzz//PAMHDgwuI7Vt25asrCzmz59P3759g/vOzc2lWbNmwefl5ubSvn37Gn9dqXt24wbsojkAmHMvxiQ0+5NniIiI1Ey1rtSMjIykY8eOrFq1KviY67qsWrWKzp071zhESUkJzu8uGnUcJ9j0UlJSSExM5Ouvvw5+vrCwkHXr1u3T15W6ZQNlFS+yVx6AQ4/GHHms15FERMTHqr38NGDAAKZOnUrHjh1JT09n8eLFlJSUBJeJpkyZQlJSEkOGDAEqLi7etGlT8NfZ2dlkZGTQuHHj4MVEhx12GC+//DItWrSgdevWZGRksGjRouAdVsYYTj75ZF5++WVatWpFSkoKs2bNolmzZsG7oST02MUvwsYN0DQOZ9hlvr3iX0REQkO1S03Pnj3Jy8tjzpw55OTk0L59e8aOHRtcItq2bVulv7yys7O58cYbgx8vXLiQhQsX0rVrV8aNGwfAyJEjmT17Nk8++SS5ubkkJSVx/PHHM3jw4ODzBg4cSElJCY8//jiFhYV06dKFsWPHEh0dXcPRpS7ZH3+oKDWAGXIZJl7LTiIiUreM9fPVSlXIysqq9Po1tcEYQ6tWrdiyZYsvL/6q7nw2UIZ797Xw84+Yw3rhXPrPeki5b3QMw5vf5wP/z+j3+cD/M9bVfFFRUXt991PovPqZ+IZdNBt+/hHiEjBDL/U6joiINBAqNVKrbMb32NcqXvTQGXoZJi7hT54hIiJSO1RqpNbYsrKK93ZyXcwRvTGH9fQ6koiINCAqNVJr7MKZsGUjxCdihlzidRwREWlgVGqkVtgNa7FL5gHgnHc5pmm8x4lERKShUamRfWbLSiuWnayLOaoPpvvRXkcSEZEGSKVG9pldMAMyN0FCM8y5F3sdR0REGiiVGtkndt232DfmA+CcdwWmSZy3gUREpMFSqZEas6UluNP+DdZijjkOc8iRXkcSEZEGTKVGaszOfx5++RkSkzDnXOR1HBERaeBUaqRG7PersW+9AoBz/pWY2KYeJxIRkYZOpUaqzZYU406bXLHs1OtvmG6Hex1JREREpUaqz857DrZugWYtMGdd6HUcERERQKVGqsmuWYVduhAAZ/hVmNgmHicSERGpoFIje80WF+E++28ATO8TMH851ONEIiIi/0+lRvaa+9KzkJUJScmYM0d6HUdERKQSlRrZK8Vffopd9irw67JTTKzHiURERCpTqZE/ZYsLyZ58FwCm798xXbt7mkdERKQqkV4HkNDnvjgN+8tmaJGCOWOE13FERESqpDM18ofs6s+x774GgDPiakzjGI8TiYiIVE2lRvbIFhXiPvsIAE0HnIXT5WCPE4mIiOyZSo3skX3xacjeBsmpJFxwlddxRERE/pBKjVTJrlqJff8NMIaIC67B0bKTiIiEOJUa2Y0tzA8uO5njBmA6/8XjRCIiIn9OpUZ2Y+c8BTnbIaUV5vTzvY4jIiKyV1RqpBL71afYD5aCMTgXXI1p1MjrSCIiIntFpUaCbEE+7nNTATDHD8Skd/U4kYiIyN5TqZEgO/u/kJMNqfthBg71Oo6IiEi1qNQIAPaLj7ErloFxKl5kL1rLTiIiEl5UagSbn4f7/KMAmBMGYfbv4nEiERGR6lOpEewL/4XcHdCqDWbgEK/jiIiI1IhKTQNnV67AfvIuOA7OBddgoqK9jiQiIlIjKjUNmN35m2WnE/+B6dDJ40QiIiI1p1LTgNkXHoeduZDWFnPquV7HERER2ScqNQ2U/ewD7KfvVyw7jbwGExXldSQREZF9olLTANm8HNzn/wOAOflMTLt0jxOJiIjsO5WaBsZaizvjMcjPg9btMaec5XUkERGRWqFS08DY/y2HlR9CRETFeztFatlJRET8QaWmAbF5O7AzHwPAnHwWpu3+HicSERGpPSo1DYS1tuI6mvyd0KYD5uQzvY4kIiJSq1RqGgj7yXvw+UcQEVlxt1NkpNeRREREapVKTQNgc7KxMx8HwAw4G9O6g8eJREREap9Kjc9VLDs9CoX50C4dc9IZXkcSERGpEyo1PmdXLIMvP4HIyF/vdtKyk4iI+JNKjY/ZHduxs/8LgDltCGa/dh4nEhERqTsqNT5lrcV9bioUFkCHzpgTTvc6koiISJ1SqfEp++FS+Pp/EBmFM2I0JiLC60giIiJ1SqXGh2x2Fnb2kwCYQUMxaW09TiQiIlL3VGp8xlqLO30KFBVCxwMwxw/0OpKIiEi9UKnxGbv8Tfjmc4iKrrjbydGyk4iINAwqNT5it2/FznkKADNoGCa1tceJRERE6o9KjU9Ya3GffQSKiyD9QMzfTvU6koiISL1SqfEJ++4S+PZLiI7GGaFlJxERaXhUanzAZmVi5z4DgPnHcEzLNI8TiYiI1D+VmjBnXbdi2amkGDr/BdPvFK8jiYiIeEKlJszZd1+DNV9DdCOc4aMxjg6piIg0TPobMIzZrVuwc6cBYAaPwKS08jaQiIiIh1RqwlTFstO/obQEDuiG6fN3ryOJiIh4SqUmTNllr8Lab6BRY5zhV2nZSUREGjz9TRiG7C+bsS8/C4AZfAEmOdXjRCIiIt5TqQkz1i3HnTYZSkvhwEMwfU7yOpKIiEhIUKkJM3bpIlj3LTSOqVh2MsbrSCIiIiFBpSaM2MxN2HnPAWDOuhDTPMXjRCIiIqFDpSZMWLcc95nJUFYKfzkU89fjvY4kIiISUlRqwoR9cwGsXwMxsTjnX6llJxERkd+JrMmTlixZwsKFC8nJyaFdu3aMHDmS9PT0KrfduHEjs2fPZsOGDWRlZTF8+HBOOaXyS/lfccUVZGVl7fbcE044gYsuugiAnJwcnnvuOb766iuKi4tJS0vj9NNP5+ijj67JCGHFbtmInT8DAHP2RZikZI8TiYiIhJ5ql5oPP/yQ6dOnM2rUKDp16sSrr77K+PHjmTRpEgkJCbttX1JSQsuWLTnmmGN49tlnq9znvffei+u6wY9/+ukn7r77bo455pjgY1OmTKGgoIB//vOfxMXFsXz5ciZOnMh9991Hhw4dqjtG2LDlvy47Bcqg2+GYnv29jiQiIhKSqr38tGjRIvr370+/fv1o3bo1o0aNIjo6mmXLllW5fXp6Oueddx69evUiKiqqym3i4+NJTEwM/rdy5UpatmxJ165dg9usWbOGv//976Snp9OyZUvOOOMMmjRpwvr166s7Qlixb8yDDWshpgnOeVdo2UlERGQPqnWmJhAIsH79egYNGhR8zHEcunXrxtq1a2slUCAQ4P333+eUU06p9Bf4AQccwIcffkiPHj2IjY1lxYoVlJWV8Ze//KXK/ZSVlVFWVhb82BhDTExM8Ne1adf+anu/9ucfsa/MBMA592KcpBa1uv+9VVfzhRK/z6j5wp/fZ/T7fOD/GUNhvmqVmry8PFzXJTExsdLjiYmJbN68uVYCffLJJxQUFNC3b99Kj48ZM4ZJkyYxcuRIIiIiiI6O5vrrryc1tepX0503bx5z584NftyhQwcmTJhAcnLdXY+ypyw1YQMBfrnvRsoDARof2ZsW/xji+Q9Cbc4Xqvw+o+YLf36f0e/zgf9n9HK+Gl0oXJeWLVtG9+7dSUpKqvT47NmzKSgo4NZbbyUuLo5PP/2UiRMncuedd9K2bdvd9nP66aczYMCA4Me7CkFWVhaBQKBWMxtjSE1NJTMzE2ttrezTXTQbd923ENuUsrMuIjMzs1b2WxN1MV+o8fuMmi/8+X1Gv88H/p+xruaLjIzc6xMS1So18fHxOI5DTk5OpcdzcnJ2O3tTE1lZWXz11Vdcf/31lR7PzMxkyZIlPPTQQ7Rp0waA9u3b891337FkyRIuvvji3fYVFRW1x2t46uqbyVpbK/u2mzbgLpwFgBlyCSQ0C4kfgNqaL5T5fUbNF/78PqPf5wP/z+jlfNW6UDgyMpKOHTuyatWq4GOu67Jq1So6d+68z2GWLVtGQkICPXr0qPR4aWkpsPs6neM4vvvGsIEA7tOToDwA3Y/GHHms15FERETCQrXvfhowYABLly7lnXfeYdOmTTz55JOUlJQEr4GZMmUKM2fODG4fCATIyMggIyODQCBAdnY2GRkZuy2nuK7LO++8Q58+fYiIiKj0ubS0NFJTU/nvf//LunXryMzMZOHChXz11VccccQRNRg7dNnFL8LGDdA0Due8yzy/jkZERCRcVPuamp49e5KXl8ecOXPIycmhffv2jB07Nrj8tG3btkp/EWdnZ3PjjTcGP164cCELFy6ka9eujBs3Lvj4119/zbZt2+jXr9/uISMjuemmm5gxYwYTJkyguLiY1NRUrrjiit3O6oQz+9N67OI5AJghl2Lim3mcSEREJHwY67f1mz+RlZVV6Vbv2mCMoVWrVmzZsqXGy2E2UIY7/jrYlAGH9cS55J8hc5amNuYLdX6fUfOFP7/P6Pf5wP8z1tV8UVFRe32hsN77KUTYV+dUFJqm8ThDLg2ZQiMiIhIuVGpCgP1xXcW1NIAz9FJMfKK3gURERMKQSo3HbFlZxd1Oros5ojfm8L96HUlERCQsqdR4zC6aBZt/grgEzLmXeB1HREQkbKnUeMhu+B772ksAOMMux8TFe5xIREQkfKnUeMSWleI+MwmsizmyD6bHMV5HEhERCWsqNR6xC2bClo2Q0Axz7iiv44iIiIQ9lRoP2B++w74xH/h12amplp1ERET2lUpNPbOlJbjTJlcsOx3TD9P9KK8jiYiI+IJKTT2zC2ZA5s+QmIQ5W8tOIiIitUWlph7Zdauxby4AwDnvCkyTph4nEhER8Q+VmnpiS0pwn5kM1mJ69ccc7K93FxcREfGaSk09sfOfg61boFkLzFkXeh1HRETEd1Rq6oFduwq7dCEAzvlXYmK17CQiIlLbVGrqmC0pxp3274plp94nYA7q4XUkERERX1KpqWP2pWchKxOSWmDOHOl1HBEREd9SqalDds3X2GWvAuAMH42JifU4kYiIiH+p1NQRW1xUcbcTYPqchOna3dtAIiIiPqdSU0fsS9Ng+1ZonoIZPMLrOCIiIr6nUlMH7OovsO+8BoAz/CpMYy07iYiI1DWVmlpmiwpxn30EANPvZMyBh3icSEREpGFQqalldu4zkJ0FyamYfwz3Oo6IiEiDoVJTi9xvVmLfex0AZ8RoTOMYjxOJiIg0HCo1tcQtyMed9uuyU/9TMZ0P8jiRiIhIw6JSU0ty/vsw7NgGKa0wp5/ndRwREZEGR6WmFrhf/4+CN18BY3BGXI1p1NjrSCIiIg2OSs0+sgX5/3+3098GYjp19TiRiIhIwxTpdYCwV7AT4hKJbNIUe/owr9OIiIg0WCo1+8iktCLi5gdJjoogyzpYa72OJCIi0iBp+akWmMgoIlP38zqGiIhIg6ZSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyIiIr4Q6XWA+hYZWXcj1+W+Q4Hf5wP/z6j5wp/fZ/T7fOD/GWt7vursz1hrba1+dREREREPaPmpFhQVFfHPf/6ToqIir6PUCb/PB/6fUfOFP7/P6Pf5wP8zhsJ8KjW1wFrLhg0b8OtJL7/PB/6fUfOFP7/P6Pf5wP8zhsJ8KjUiIiLiCyo1IiIi4gsqNbUgKiqKwYMHExUV5XWUOuH3+cD/M2q+8Of3Gf0+H/h/xlCYT3c/iYiIiC/oTI2IiIj4gkqNiIiI+IJKjYiIiPiCSo2IiIj4gr/fgKIGVq9ezSuvvMKGDRvYsWMH119/PUceeeQfPuebb75h+vTpbNy4kebNm3PGGWfQt2/fStssWbKEhQsXkpOTQ7t27Rg5ciTp6el1OMmeVXfGjz/+mDfeeIOMjAwCgQCtW7fmzDPPpHv37sFt5syZw9y5cys9Ly0tjUmTJtXRFHtW3fm++eYb7rjjjt0ef+KJJ0hMTAx+HCrHsLrzTZ06lXfffXe3x1u3bs3DDz8MhNbxmzdvHp988gk///wz0dHRdO7cmWHDhpGWlvaHz1uxYgWzZ88mKyuL1NRUhg4dSo8ePYKft9YyZ84cli5dSkFBAV26dOGiiy6iVatWdT3Sbmoy41tvvcV7773Hxo0bAejYsSPnnntupe/Bqo71IYccws0331w3g+xBTeZ75513ePTRRys9FhUVxYwZM4Ifh8oxrMl848aNY/Xq1bs9fuihh3LTTTcBoXP8AN544w3eeOMNsrKygIo/LwYPHsyhhx66x+eEws+gSs3vlJSU0L59e4477jgefPDBP91+69at3HfffRx//PFcddVVrFq1iscee4zExMTgX/offvgh06dPZ9SoUXTq1IlXX32V8ePHM2nSJBISEup4ot1Vd8Zvv/2Wgw8+mHPPPZcmTZqwbNkyJkyYwD333EOHDh2C27Vp04Zbb701+LHjeHMisLrz7TJp0iRiY2ODH8fHxwd/HUrHsLrzXXDBBQwdOjT4cXl5OTfccANHH310pe1C5fitXr2aE088kf3335/y8nJeeOEF7r77bh5++GEaN25c5XPWrFnD5MmTGTJkCD169GD58uU88MADTJgwgbZt2wKwYMECXnvtNa644gpSUlKYPXs248eP5+GHHyY6Oro+R6zRjKtXr6ZXr14ccMABREVFsWDBguBzkpKSgtt1796dyy+/PPixF2+eWJP5AGJiYpg8efIePx8qx7Am811//fUEAoHgxzt37uSGG27gmGOOqbRdKBw/gKSkJIYMGUKrVq2w1vLuu+9y//33c//999OmTZvdtg+Zn0Ere3TmmWfajz/++A+3ee655+y1115b6bGJEyfau+++O/jxTTfdZJ988sngx+Xl5fbiiy+28+bNq9W8NbE3M1ZlzJgx9sUXXwx+PHv2bHv99dfXZrRasTfzrVq1yp555pk2Pz9/j9uE6jGsyfH7+OOP7VlnnWW3bt0afCxUj5+11ubm5tozzzzTfvPNN3vc5uGHH7b33ntvpcfGjh1rH3/8cWutta7r2lGjRtkFCxYEP19QUGCHDBlily9fXjfBq2FvZvy98vJye/7559t33nkn+NiUKVPshAkT6iLiPtmb+ZYtW2aHDx++x8+H8jGsyfFbtGiRPf/8821RUVHwsVA9fruMGDHCLl26tMrPhcrPoM7U7KPvv/+ebt26VXrskEMOYdq0aQAEAgHWr1/PoEGDgp93HIdu3bqxdu3aekxae1zXpaioiKZNm1Z6PDMzk0suuYSoqCg6d+7MkCFDaNGihUcpq+/GG2+krKyMNm3acOaZZ9KlSxfAf8fw7bffplu3biQnJ1d6PFSPX2FhIcBu32+/tXbtWgYMGFDpsUMOOYRPP/0UqDijmpOTw8EHHxz8fGxsLOnp6axdu5ZevXrVQfK9tzcz/l5JSQmBQGC356xevZqLLrqIJk2acNBBB3HOOecQFxdXq3mra2/nKy4u5vLLL8daS4cOHTj33HODZwVC+RjW5Pi9/fbb9OzZc7czO6F4/FzXZcWKFZSUlNC5c+cqtwmVn0GVmn2Uk5Oz2/JDQkICRUVFlJaWkp+fj+u6la7NAEhMTGTz5s31mLT2LFy4kOLi4kqnTTt16sTll19OWloaO3bsYO7cudx222089NBDxMTEeJj2zzVr1oxRo0ax//77U1ZWxtKlS7njjjsYP348HTt2JC8vzzfHMDs7my+++ILRo0dXejxUj5/rukybNo0DDjggeAq7Knv6OczJyQl+ftdje9rGK3s74+/NmDGDpKSkSv+o6t69O0cddRQpKSlkZmbywgsvcM899zB+/HjPlhP3dr60tDQuu+wy2rVrR2FhIa+88gq33HILDz/8MM2bNw/ZY1iT47du3To2btzIZZddVunxUDt+P/30EzfffDNlZWU0btyY66+/ntatW1e5baj8DKrUSLUsX76cuXPncsMNN1T65vztxWPt2rUL/iW5YsUKjjvuOC+i7rW0tLRKF/gdcMAB/PLLL7z66qtcddVVHiarfe+++y5NmjTZ7cLiUD1+Tz31FBs3buTOO+/0LENdq8mM8+fP54MPPmDcuHGVrkX47b9227ZtS7t27bjqqqv45ptvdjujXF/2dr7OnTtXOgvQuXNnxowZw5tvvsk555xT1zFrrCbH7+2336Zt27a73WgQascvLS2NBx54gMLCQj766COmTp3KHXfcscdiEwp0S/c+SkxMJDc3t9Jjubm5xMTEEB0dTXx8PI7j7NZEc3JydvuXf6j74IMPeOyxxxgzZkylU4hVadKkCWlpaWRmZtZTutqVnp4ezO6XY2itZdmyZfTu3ftPLz4MheP31FNPsXLlSm6//XaaN2/+h9vu6edw1/HZ9f8/2sYL1Zlxl1deeYX58+dzyy230K5duz/ctmXLlsTFxXl2HGsy3y6RkZF06NAhmD0Uj2FN5isuLuaDDz7Yq38seH38IiMjSU1NpWPHjgwZMoT27duzePHiKrcNlZ9BlZp91KlTJ77++utKj3311VfBf3FERkbSsWNHVq1aFfy867qsWrVqj2uToWj58uU8+uijXH311ZVu0duT4uJiMjMzw+ov/d/KyMigWbNmgH+O4erVq8nMzNyrP0y9PH7WWp566ik++eQTbrvtNlJSUv70OZ07d67y57BTp04ApKSkkJiYWGmbwsJC1q1b58kxrMmMUHH3yEsvvcTYsWPZf//9/3T77du3k5+fH/xeri81ne+3XNflp59+CmYPpWO4L/N99NFHBAIBevfu/afbenX89sR1XcrKyqr8XKj8DGr56Xd2/WG+y9atW8nIyKBp06a0aNGCmTNnkp2dzZVXXgnACSecwOuvv87zzz9Pv379WLVqFStWrOBf//pXcB8DBgxg6tSpdOzYkfT0dBYvXkxJSclur2VTX6o74/Lly5k6dSojRoygU6dOwTMW0dHRwVugp0+fzuGHH06LFi3YsWMHc+bMwXEc/vrXv4b8fK+++iopKSm0adOG0tJS3n77bVatWsUtt9wS3EcoHcPqzrfL22+/TadOnapc9w+l4/fUU0+xfPlybrzxRmJiYoLfb7GxscGllilTpgRvOQU4+eSTGTduHAsXLqRHjx588MEH/PDDD1x88cUAGGM4+eSTefnll2nVqhUpKSnMmjWLZs2accQRR4TFjPPnz2fOnDmMHj2alJSU4HMaN25M48aNKS4u5sUXX+Soo44iMTGRX375heeff57U1FQOOeSQkJ9v7ty5dOrUidTUVAoKCnjllVfIysqif//+QGgdw5rMt8vbb7/NEUccsdvFv6F0/ABmzpxJ9+7dadGiBcXFxSxfvpzVq1cHXzMnVH8GVWp+54cffqj0QmzTp08HoE+fPlxxxRXs2LGDbdu2BT+fkpLCv/71L5599lkWL15M8+bNufTSSyu9MF3Pnj3Jy8tjzpw55OTk0L59e8aOHevZWYzqzvjWW29RXl7OU089xVNPPRV8fNf2UHEB6uTJk9m5cyfx8fF06dKF8ePHV3qtl/pS3fkCgQDTp08nOzubRo0a0a5dO2699VYOOuig4DahdAyrOx9U/Ivo448/ZsSIEVXuM5SO3xtvvAFUvFjZb11++eXBErlt2zaMMcHPHXDAAYwePZpZs2bxwgsv0KpVK2644YZKBW7gwIGUlJTw+OOPU1hYSJcuXRg7dmy9v0YN1GzGN998k0AgEHzBxF0GDx7MWWedheM4/PTTT7z77rsUFBSQlJTEwQcfzNlnn01UVFSdzvN7NZkvPz+fxx9/nJycHJo0aULHjh25++67K12/ESrHsCbzAWzevJnvvvuu0j+Ydgml4wcVy0JTp05lx44dxMbG0q5dO26++ebgpQeh+jNorLW21vYmIiIi4hFdUyMiIiK+oFIjIiIivqBSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyIiIr6gUiMiIiK+oFIjIiIivqBSIyICzJkzh7POOou8vDyvo4hIDanUiIiIiC+o1IiIiIgvqNSIiIiIL+hdukWkXmVnZzNr1iw+//xzCgoKSE1NZcCAARx33HEAfPPNN9xxxx1cc801ZGRksGzZMoqLiznooIO48MILadGiRaX9rVixgvnz57Np0yYaN27MIYccwrBhw0hKSqq03c8//8zs2bP55ptvKC4upkWLFhx99NGce+65lbYrLCzkueee49NPP8Vay1FHHcWFF15Io0aN6vY3RkT2mUqNiNSbnJwcbr75ZgBOPPFE4uPj+eKLL3jssccoKirilFNOCW778ssvY4xh4MCB5OXl8eqrr3LXXXfxwAMPEB0dDcA777zDo48+yv7778+QIUPIzc1l8eLFrFmzhvvvv58mTZoA8OOPP3LbbbcRGRlJ//79SUlJITMzk88++2y3UjNx4kSSk5MZMmQI69ev5+233yY+Pp5hw4bV0++SiNSUSo2I1JtZs2bhui4PPvggcXFxAJxwwglMmjSJF198keOPPz64bX5+PhMnTiQmJgaADh06MHHiRN566y1OPvlkAoEAM2bMoE2bNtxxxx3BotOlSxfuu+8+Xn31Vc466ywAnn76aQAmTJhQ6UzP0KFDd8vYvn17Lrvssko5li1bplIjEgZ0TY2I1AtrLR9//DGHHXYY1lry8vKC/3Xv3p3CwkLWr18f3P7YY48NFhqAo48+mmbNmvH5558DsH79enJzcznxxBODhQagR48e7LfffqxcuRKAvLw8vv32W/r167fb0pUxZrecvy1WUFGSdu7cSWFh4b7/JohIndKZGhGpF3l5eRQUFPDWW2/x1ltv7XGbXUtGrVq1qvQ5YwypqalkZWUBBP+flpa2237S0tL47rvvAPjll18AaNOmzV7l/H3xadq0KQAFBQXExsbu1T5ExBsqNSJSL6y1APTu3Zs+ffpUuU27du3YtGlTfcbajeNUfQJ7V34RCV0qNSJSL+Lj44mJicF1XQ4++OA9brer1GzZsqXS49ZaMjMzadu2LQDJyckAbN68mYMOOqjStps3bw5+vmXLlgBs3LixdgYRkZCla2pEpF44jsNRRx3Fxx9/zE8//bTb53//9gTvvfceRUVFwY8/+ugjduzYwaGHHgpAx44dSUhI4M0336SsrCy43eeff87PP/9Mjx49gIoydeCBB7Js2TK2bdtW6Wvo7IuIv+hMjYjUmyFDhvDNN99w8803079/f1q3bk1+fj7r16/n66+/5plnnglu27RpU2677Tb69u1Lbm4ur776KqmpqfTv3x+AyMhIhg4dyqOPPsq4cePo1asXOTk5vPbaayQnJ1e6PfyCCy7gtttu45///Gfwlu6srCxWrlzJAw88UO+/DyJSN1RqRKTeJCYmcs899zB37lw+/vhjXn/9deLi4mjTps1ut1effvrp/Pjjj8yfP5+ioiK6devGRRddVOlF8Pr27Ut0dDQLFixgxowZNGrUiCOOOIJhw4YFLziGitu0x48fz+zZs3nzzTcpLS0lOTmZY445pt5mF5G6Z6zOv4pICNn1isLXXnstRx99tNdxRCSM6JoaERER8QWVGhEREfEFlRoRERHxBV1TIyIiIr6gMzUiIiLiCyo1IiIi4gsqNSIiIuILKjUiIiLiCyo1IiIi4gsqNSIiIuILKjUiIiLiCyo1IiIi4gv/B2xhthWG0ma6AAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiwAAAG0CAYAAAARqnxaAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABiCUlEQVR4nO3dd3wUdf7H8dd3spveCSFEuoDoT0A8O9jgznZ4VhSxgBVFsZ3YEKyooCIoeOKJIhaKOQv2BqIi9nIiKHZUCATSe5nv74+YPSIE0mezeT8fDx9md2dn35/MLvvJfL8zY6y1FhEREZEg5ngdQERERGRn1LCIiIhI0FPDIiIiIkFPDYuIiIgEPTUsIiIiEvTUsIiIiEjQU8MiIiIiQU8Ni4iIiAQ9NSwiIiIS9HxeB2hOOTk5VFZWNvt6O3bsSFZWVrOvN1iEen0Q+jWqvrYv1GsM9fog9Gtsifp8Ph9JSUn1W7ZZX9ljlZWVVFRUNOs6jTGBdYfiVQxCvT4I/RpVX9sX6jWGen0Q+jUGQ30aEhIREZGgp4ZFREREgp4aFhEREQl6alhEREQk6IXUpFsREaieGFhcXOx1jAYpKSmhvLzc6xgtJtTrg9CvsSn1RUdH4/M1reVo0LMXL15MRkZGrfvS09OZMWNGnc8pKipiwYIFfPTRRxQWFtKxY0dGjx7N3nvv3eh1iojUpbKykqKiIuLi4nCctrMT2e/3N/tRjsEk1OuD0K+xsfW5rktBQQExMTFNaloa/MyuXbsyadKkwO0d/YNQWVnJbbfdRnx8PFdeeSXJycls3ryZ6OjoRq9TRGRHiouL21yzIhLKHMchLi6OwsJC4uPjG72eBjcsjuOQmJhYr2WXLl1KYWEht956a6CrSk1NbdI6RUR2Rs2KSHBpjs9kgxuWzMxMxo4di9/vp2/fvowaNYqUlJTtLvvpp5/Sp08f5s6dyyeffEJ8fDyDBw/m+OOPrxW+IesEqKioqLVbyhhDVFRU4OfmVLO+5l5vsAj1+iD0a1R9ItJWNOVzbGwDTln3+eefU1paSnp6Ojk5OWRkZJCdnc0999wTaBi2dvnll5OVlcWQIUM48sgjyczM5OGHH+boo49mxIgRjVonbDvvpWfPnkydOrWhtYtICPrxxx+Ji4vzOoaI/ElBQQG9evVq9PMb1LD8WVFREePGjWP06NEMHTp0m8cvu+wyysvLmT17dmCPyosvvsiSJUt46KGHGrVOqHsPS1ZWVrNfS8gYQ1paGpmZmSF7uuVQrg9Cv0bVV1teXl6Txsm9ogmbbV+o19jU+vLz80lISKh1n8/no2PHjvV6fpOOMYqJiSE9PZ3MzMztPp6YmIjP56s1/LPLLruQm5tLZWXldmcL72ydUP1L8/v9232spf7BttaG5JdBjVCvD0K/RtUnOxIVFUVCQsIO/20NdqFQQygKDw8nJSWFDRs27PQz2pTPcJNmwZSWlpKZmVnnhNnddtuNzMxMXNcN3LdhwwaSkpLqPLRpZ+tsbbYgj7JvvvI6hoiISLvWoIZl/vz5rF69mk2bNvHtt99y11134TgOQ4YMAWDWrFk89dRTgeWPOOIICgsLmTdvHuvXr+ezzz7j2Wef5cgjj6z3Or1kf/uZqsmXsPnWf2IL8ryOIyIi0m41aEgoOzubmTNnUlBQQHx8PP369WPKlCmB8eLNmzfXmgGckpLCxIkTeeyxx5gwYQLJyckcffTRHH/88fVep6c67QLxCbi//4J5ag7OBRO8TiQiDWSthfKy1n/h8IgGHxERGxtLdHQ0YWFhVFZWUlBQQGlpKZ06daKgoKDW2Xtrxv43bdpEVVUVMTExgedaayktLSU/P79Ru+B9Ph8JCQmBoffKykry8vKoqKjAGENCQgIREdX1VVVVUVhYSElJSeD5HTp0CMx1iI6OxlpLcXExlZWVJCQkEBkZieu65OXlUVZWvW1qhhW2bNlCfHw8Pp+PioqKwBSCukRGRhIbG4vf76eqqori4mIKCwsDj8fFxREVFUVYWBiu61JSUkJ+fv5OfwepqakUFxfj8/mIjIzEWrvNNjDGEB8fT2RkJMYYKisra+WNi4sjMjKSoqIiYmNjCQsLY8OGDTt83cjISOLi4vD5fFhrqaioIDs7O7Ado6OjAydgqzlJ4taZHMcJZPrztqt5fk2WqqoqCgoKam279PR0cnNziYiIICIiYpvtBBAREUFCQgJhYWGUl5e32lmlG9SwXH755Tt8/Kabbtrmvr59+zJlypRGr9NLxu8n7OzLqbr9KuzH72L3PhCzj/d7fkSkAcrLcC85pdVf1pm1GCIi6718dHQ04eHh5OXlUVlZSXh4OElJSWzZsoWSkhKioqJqfTFER0dTXl5OVVVV4L68vDyqqqoICwsjISGB+Ph48vIavnc4KSmJiooK8vLysNbi9/sDX5jGGCoqKigsLMRaS2RkJImJiVRWVtaakBkdHU1hYSFZWVlERUURFxeH3++ntLSUgoICYmNjSUxMZNOmTbWaqvj4ePLz86mqqiI+Pp7k5GQ2bdq03Zzh4eEkJiaSl5dHeXl5oNECKCwsJDIykpiYGHJycqisrMRxnDrnP25PbGxsoIbIyEgSEhKoqqoKfHknJydjrSU7OxvXdYmLi6NDhw61agoLCyMyMpLs7Oydvp7jOCQlJZGfn09paSnGGMLDwwOP1/weaxoQv99PYmIi1lpKSkowxpCSkkJVVRXZ2dlUVVXVqremhpoGpGbbVVVV1TrlflxcHPn5+eTn5xMTE0NSUhIbN24MZExOTqaoqIiioiLCw8NbbQeDzq60E6ZHb+JPORsA98kHsfm53gYSkZAUHR1Nbm4uZWVlVFVVUVJSQnFxMdHR0RQXFxMeHk5YWFhg+aioqFp/GRcVFQUamPLycgoKCgJ/ZTdUWFgYZWVlVFZWUlVVRWlpaWCvgeu6FBUVBR4rKiqirKxsm9NQ1DQ1NXtgap5bXFwc+Ms+LCxsm/mMBQUFgdfOycnBcZw666g5e2pJSUmgkag5BXxNHa7rBn6nFRUVDdobUF5eHqihqKiI0tLSwLrDw8Px+/1kZ2dTUVERWMZaW+t3YYwJ7HXZ2VGsYWFhGGMoLS2lqqoqcE2smuanppGoeby0tJTCwsJApqioKBzHITs7O/BeKC0tDTSSsbGxFBcXB7ZBTU2xsbG1chQXFwd+pwUFBTiOE2icYmJiqKysDDSVNe/T1qCLH9ZD/MhzyX/vTfjtZ9wnH8S58BqdxEqkrQiPqN7b4cHr1pfP58MYQ4cOHWrdX7M3o+bLLioqisLCQsLDw3Ecp1bDEh4eHhhKMMbU+q+hw0JFRUUkJiYSHR1NWVlZ4MurRmxsbGCYpSbnn1/jz1/OruvW2gNTczDGn8+AuvUy1lqqqqrqPEjD5/MRHh5e6wt367pLSkqIiYmhU6dOlJaWUlZWRmlpab1/D3++0F95eXmgOaj5PaelpdV6baBWY1lVVVXrwJMdqaiooKysjI4dO1JWVhb43VtrMcYE9iBtfWiwMSaw/prDjuva3j6fj6Kiojpr2jpHDWstruviOA6u6waG6upaviWpYakH4/cTds4VVE25Ej57H/vJe5h9D/Y6lojUgzGmQUMzXqj5oqvZjb+1mi+fmmGhwsJCoqKiKCsrqzXs0KFDB4qKisjPz8d13cCQUmPUzNWIjIwkIiKCuLg4cnJyAn+Nx8TEkJ+fH/hy/PO5NbbOXd/aG8NxnG3mYGz9+tZaNm3aFJiPkZCQQGxsLJs3b270a2792q7r1lpXzbySrWtvaLO4ZcsWwsPDiYiIICYmhri4ODZv3hxYT83w1/aE+mH/GhKqJ9OtF+bvpwJgn3wQm5fjcSIRCRU1X3I1EyG3/q/mr+eSkhJ8Ph9+v3+b+Sw18xRqmoiaeSxNUTNkkJ2dTUlJSeCiteHh4ZSWllJSUhIYFmrKFXj/bOs5F8aYwATk7amoqNju7+zPTV9ZWRn5+fls3rw5MJRTH1vPH6nJVpOloqIisHdo623VkD0qdakZ0svKygIITFKu2a511Vszr6WuJrBmbtSfa2zICVcrKyu3+f01ZF5QU6hhaQBz9MnQrRcUFeA+8UDId7Mi0jpqjqKJj48PDLX4/X5iYmIC8yFq5qbUnKNq66GNyspKjDHExMQQFhZGVFTUNrv5GyIhISEwZyY8PJzw8PDAbv/KykoiIiLw+/2BIYrmvNhkXFwc4eHh+Hw+EhMTcV23zmGcgoKCwFEvPp8vcERPzaUZoqKiiI6OxufzERYWRnR0NK7r1vsLuma4qea5UVFRgSGVsrIyysvLSU5OJiIiIjAfp2ZycWP4/f7AEU81k3UdxwnkrZmsXLOdfT5frW1dUlKC67okJycHtl9kZGQgT2FhIdHR0YGjyWJiYoiMjKx1VNXO1Bw5FR8fH3iv1TSzLU1DQg1gfD6csy/Dve2f8MWH2A+XYw44zOtYIhICag77rfnyrZnzsfWXSUlJCYmJidtMcqw5dDU2Npa4uDjKy8vJz89v9JCQMYbExMRahwIXFBQABCbLdujQIdBo1RzR0hxqTt9eM1diR0fXlJWVkZ2dTVxcXGAeS81EVahuBGNiYgJHsVRWVtY6RHhnCgsLA02EtZb8/Pxah/fWvHZiYmJgiKhmgm9jWGsJDw8nJiYGx3GoqqqqdUhxzQTc2NhY4uPjA4c9bz0vpeaw8OTk5EDNNUeKlZaWBt4nNUc85ebm1jnEtD01RyAlJCQQExPT5PdaQzTpWkLBJisrq9kn/xhj6Ny5c61TDrsvLcY+9wREx+LcPAuTmNysr9matldfqAn1GlVfbfn5+cFxHqcGau/XoWnI6d1bQ2pqauDQ3fpq79twZ7b32fT7/fW+lpCGhBrBHHUSdO8NxYUaGhIREWkFGhJqBBMWhnP25bi3XQ5ffoRduQxz0PavLC0iEmw6duxY56TcvLy87R51E0rCw8MDQybb01IXVwwLC9vh3oSsrKxGDye1B2pYGsns0g3zj1HYZ+ZjF/4bu/tATFKHnT9RRMRjO5oX0tQjXBqrvLyc9evXt9pr1RyBU5e6zq7bFFVVVTt8XTUrO6YhoSYwR5wAPftCSRHu/FkaGhKRNmF7h8XW/Nde/h3b0e8gFF83FKhhaYLqoaHLwOeHVZ9i33/L60gi7V57+cIVaWua+tlUw9JEpnNXzPGnA2AXPYzN3vFuRhFpWTWnH1fjIhIcrLUUFRU1+QSDmsPSDMzfjsN+thJ+/Bb3sVk4l9+kaw2JeCQmJiZwEby2JDw8vEHnw2hrQr0+CP0am1JfzeURmkINSzMwTvXQkHvL5bD6c+y7r2MOOdLrWCLtVnP849iadC6dti/UawyG+jQk1ExMWhfMCWcCYJ9+BLul+WeYi4iItFdqWJqRGTYceu8BpSW4j90fkl22iIiIF9SwNKPqoaFLITwc1nyJXf6q15FERERCghqWZmZS0zEnjgbAZjyKzWqZMyaKiIi0J2pYWoA5/O/Q9/+grLR6aMijM0eKiIiECjUsLcA4Ds6YyyAiEr79Crv8Fa8jiYiItGlqWFqI6ZiGOalmaGgedtMGjxOJiIi0XWpYWpA59GjYrT+Ul+HOm6mhIRERkUZSw9KCqoeGLoWIKPhuNXbpi15HEhERaZPUsLQwk9IJM+JsAOyz87EbW+fy6SIiIqFEDUsrMIccCbsPhPLyP4aGdBlxERGRhlDD0gqMMTijx0NkFHy/BvvmC15HEhERaVPUsLQS0yEVc8q5ANjnnsBm/uZxIhERkbZDDUsrMkP+Bv83CCrKcR/V0JCIiEh9qWFpRcYYnLPGQ1QM/Pgt9o3nvY4kIiLSJqhhaWUmOQVzas3Q0JPY9es8TiQiIhL81LB4wBw0DPrvA5UV1UNDVRoaEhER2RE1LB4wxuCceTFEx8DP32Ffe8brSCIiIkFNDYtHTFIHzMgLALAvLMD+/ovHiURERIKXGhYPmQMOg4H7QWVl9dBQZaXXkURERIKSGhYPGWNwzhgH0bHwy/fYV//jdSQREZGgpIbFYyYxGTNqLAD2xUXY337yOJGIiEjwUcMSBMx+h8CgA6CqEveRGRoaEhER+RM1LEGgemjoIoiNg19/wr78tNeRREREgooaliBh4pMwoy4EwL68GLvuB48TiYiIBA81LEHE7DME/nIQVFX9MTRU4XUkERGRoKCGJYgYY3BOvwjiEuD3X7AvLvI6koiISFBQwxJkTFxCddMC2FcysL9873EiERER76lhCULmLwdh9j0YXLd6aKhCQ0MiItK+qWEJUua0sdVDQ+vXYV9Y4HUcERERT6lhCVImLr76LLiAffUZ7E9rPU4kIiLiHTUsQczsfSBm/0PButXXGqoo9zqSiIiIJ9SwBDlz2gWQkAQbfsU+/5TXcURERDyhhiXImZi4/w0Nvf4c9odvPE4kIiLS+tSwtAFmr/0xBx7+v6Gh8jKvI4mIiLQqNSxthDn1fEhMho2/Y597wus4IiIirUoNSxthYmJxzroEAPvmEuz3qz1OJCIi0np8DVl48eLFZGRk1LovPT2dGTNm1PmcoqIiFixYwEcffURhYSEdO3Zk9OjR7L333oFlXn31VV544QVyc3Pp3r0755xzDr17925YJe2A6b8PZvAw7Iq3cB+diTP5PkxEhNexREREWlyDGhaArl27MmnSpMBtx6l7J01lZSW33XYb8fHxXHnllSQnJ7N582aio6MDy7z//vvMnz+f888/nz59+vDSSy8xZcoUZsyYQUJCQkPjhTxzyrnY1V/Cpg3YZ+djRp7vdSQREZEW1+AhIcdxSExMDPwXHx9f57JLly6lsLCQCRMm0K9fP1JTU9ljjz3o0aNHYJkXX3yRYcOGcfjhh9OlSxfOP/98wsPDWbZsWaMKCnUmequhobdewK5d5XEiERGRltfgPSyZmZmMHTsWv99P3759GTVqFCkpKdtd9tNPP6VPnz7MnTuXTz75hPj4eAYPHszxxx+P4zhUVlby448/cvzxxwee4zgO/fv3Z+3aus/sWlFRQcVW19cxxhAVFRX4uTnVrK+519sUpv9fsIcciX3nNdx59xF20/2YiMjGrSsI62tuoV6j6mv7Qr3GUK8PQr/GYKivQQ1Lnz59GDduHOnp6eTk5JCRkcHkyZO55557Ag3D1jZu3EhWVhZDhgzhuuuuIzMzk4cffpiqqipGjBhBfn4+ruuSmJhY63mJiYmsX7++zhzPPvtsrbk0PXv2ZOrUqXTs2LEh5TRIWlpai627Mdzx15G55kuqsjKJeuVpki66uknrC7b6WkKo16j62r5QrzHU64PQr9HL+hrUsAwaNCjwc/fu3QMNzMqVKxk6dOg2y1triY+PZ+zYsTiOQ69evcjOzmbJkiWMGDGi0aFPOOEEhg8fHrhd0/FlZWVRWVnZ6PVujzGGtLQ0MjMzsdY267qbyp55MUyfROGLiynuNxCn34AGryOY62suoV6j6mv7Qr3GUK8PQr/GlqrP5/PVe2dDg4eEthYTE0N6ejqZmZnbfTwxMRGfz1drYu4uu+xCbm4ulZWVxMfH4zgOubm5tZ6Xm5u7zV6Xrfn9fvx+/3Yfa6k3irU26N6EZveBmEOPwi5/FffRmXDTfZjI6J0/cTuCsb7mFuo1qr62L9RrDPX6IPRr9LK+Jp2HpbS0lMzMzDqbi912243MzExc1w3ct2HDBpKSkvD5fPh8Pnr16sWqVf+bOOq6LqtWraJv375NidZumJPHQIdU2LIJmzHP6zgiIiItokENy/z581m9ejWbNm3i22+/5a677sJxHIYMGQLArFmzeOqp/12g74gjjqCwsJB58+axfv16PvvsM5599lmOPPLIwDLDhw/nrbfe4u233+a3337j4YcfpqysjMMOO6x5KgxxJjIaZ8ylANjlr2JXf+FtIBERkRbQoCGh7OxsZs6cSUFBAfHx8fTr148pU6YEDm3evHlzrRnEKSkpTJw4kccee4wJEyaQnJzM0UcfXeuooIMOOoj8/HwWL15Mbm4uPXr04Prrr9/hkJDUZvoNwBx+DHbZy7iP3Y9z0/2YqMYNDYmIiAQjY0NosC0rK6vW4c7NwRhD586d2bBhQ1CPS9rSEtxbLoOsTMzBRwTO1bIzbaW+pgj1GlVf2xfqNYZ6fRD6NbZUfX6/v96TbnUtoRBhIqP+NzT07uvYVZ95nEhERKT5qGEJIabvnphhxwLgzp+FLS7yOJGIiEjzUMMSYswJZ0FqZ8jZjF081+s4IiIizUINS4gxERE4Yy4DY7Ar3sR+9YnXkURERJpMDUsIMn32wPz1H8AfQ0NFhR4nEhERaRo1LCHKHH8GdNoFcrOxi/7tdRwREZEmUcMSokx4BM7Zl4FxsCuXYb/8yOtIIiIijaaGJYSZXfthjjgOAPfx2diiAo8TiYiINI4alhBnjjsd0rpAXg52wUNexxEREWkUNSwhzvjDcc65vHpo6MPl2M8/8DqSiIhIg6lhaQdMz76Yo04A/hgaKsj3OJGIiEjDqGFpJ8yxoyC9GxTkYRfM8TqOiIhIg6hhaSeM31991JDjYD9+F/vpCq8jiYiI1JsalnbE9OiDOfpkANwn/oXNz/U2kIiISD2pYWlnzPBToUsPKMzHfepBr+OIiIjUixqWdsb4/hgaCguDT9/H/fhdryOJiIjslBqWdsh02xVzzAgA3Cf/RVXOFo8TiYiI7JgalnbKHDMCuvaEwgJyZt+JtdbrSCIiInVSw9JOVQ8NXQ5hPkpWLsN+tNzrSCIiInVSw9KOma49cYafCoD75BxsbrbHiURERLZPDUs7Z44+Gf+u/aC4EPeJBzQ0JCIiQUkNSztnfD6Sr7wJwnzw5UfYD972OJGIiMi21LAI4T164xw3CgC78CGsjhoSEZEgo4ZFADBHngg9+kBxUfUFEjU0JCIiQUQNiwBgwsKqTyjn88FXn2DfX+p1JBERkQA1LBJg0rthjjsdALvo39jszR4nEhERqaaGRWoxRxwPvXaDkmLc+fdraEhERIKCGhapxTh/DA35w+Hrz7HvveF1JBERETUssi2T1gVz/B9DQ4vnYrdkeZxIRETaOzUssl3mr/+AXftBaQnuY/dpaEhERDylhkW2yzhhOGMug/BwWPMl9p3XvI4kIiLtmBoWqZNJ2wVzwlkA2KcfxW7e6HEiERFpr9SwyA6ZocOhzx5QVoL72P1Y1/U6koiItENqWGSHjOPgjLkUwiPgm/9il7/qdSQREWmH1LDITpnUdMxJowGwGY9iszI9TiQiIu2NGhapF3PYMbBbfygvw503U0NDIiLSqtSwSL0Yx8EZPR4iImHt19hlL3kdSURE2hE1LFJvpmMa5uQxANhnHsNuWu9tIBERaTfUsEiDmEOOgt0HQnk57qMzsW6V15FERKQdUMMiDfK/oaEo+H4N9q0XvY4kIiLtgBoWaTDTIRVzyjkA2Gcfx2b+5nEiEREJdWpYpFHMwUfAHoOgohx33n0aGhIRkRalhkUaxRiDM/oSiIqGH77BvrHE60giIhLC1LBIo5nkjphTzgXAPvcEdsOvHicSEZFQpYZFmsQM/ivs+ReorKg+aqhKQ0MiItL81LBIkxhjcM66BKJi4Ke12Nef9TqSiIiEIDUs0mQmqQNm5HkA2CVPYX9f53EiEREJNWpYpFmYA4fCgH2hshL30RnYykqvI4mISAhRwyLNwhiDc+Y4iI6FX77HvvaM15FERCSEqGGRZmMSO2BOuwAA+8JC7G8/eZxIRERChRoWaVZm/0Nhr/2hqrL6qCENDYmISDNQwyLNyhiDc8Y4iImDdT9iX8nwOpKIiIQAX0MWXrx4MRkZtb+A0tPTmTFjxnaXf/vtt3nggQdq3ef3+3nyyScDt2fPns3y5ctrLTNw4EAmTpzYkGgSRExCEmbUWOy/78a+tAg7cD9Mt15exxIRkTasQQ0LQNeuXZk0aVLgtuPseCdNVFQUM2fO3OEye+21F+PGjftfKF+DY0mQMfsejP30ffjsfdxHZ+BMvAfj83sdS0RE2qgGdwaO45CYmFjv5Y0xO13e5/M1aJ0S/IwxOKdfiLt2Ffz2M/alxZjjTvc6loiItFENblgyMzMZO3Ysfr+fvn37MmrUKFJSUupcvrS0lHHjxmGtpWfPnpx22ml07dq11jKrV6/mvPPOIyYmhj333JORI0cSFxdX5zorKiqoqKgI3DbGEBUVFfi5OdWsr7nXGyxasj6TkARnXIT74FTsy0/DoAMw3Xs3++vsNIe2YZsW6vVB6NcY6vVB6NcYDPUZa62t78Kff/45paWlpKenk5OTQ0ZGBtnZ2dxzzz2BhmFra9euZcOGDXTv3p3i4mKWLFnCmjVrmD59Oh06dABgxYoVREREkJqaSmZmJgsWLCAyMpIpU6bUOdz057k0PXv2ZOrUqQ2tXVrJ5juvo+TdN/B335VOMx/H+MO9jiQiIg3glpViwnwYD6dsNKhh+bOioiLGjRvH6NGjGTp06E6Xr6ys5IorrmDw4MGMHDlyu8ts3LiR8ePHM2nSJPr377/dZeraw5KVlUVlMx9Ga4whLS2NzMxMmvCrClqtUZ8tyKNq8iVQkIs5ZgRhJ57VIq9TF23Dti3U64PQrzHU64PQrtGWFOPOupWozl0oP30cNONeFp/PR8eOHeu3bFNeKCYmhvT0dDIzM+sdrGfPnjtcvlOnTsTFxZGZmVlnw+L3+/H7tz+Bs8W+dK0NuTfh1lq0vth4nDMuwv3XHdhX/oO71wGYnn1a5rV2QNuwbQv1+iD0awz1+iD0arSF+bgzb4afv6Nk3U84fz0OOu3iSZYmnYeltLSUzMzMek+YdV2XdevWkZSUVOcyW7ZsobCwcIfLSNtj9j4Qs98hYN3qaw1VlHsdSUREdsDmZuPedT38/B3ExpF6x4OYtC6e5WnQHpb58+ezzz77kJKSQk5ODosXL8ZxHIYMGQLArFmzSE5OZtSoUQBkZGTQp08f0tLSKCoqYsmSJWRlZTFs2DCguuF5+umn2X///UlMTGTjxo088cQTpKWlMXDgwGYuVbxmTrsA+81/YcOv2CULMCeN9jqSiIhsh928EXf6JMjKhMRkwq68lfA+u8OGDZ5lalDDkp2dzcyZMykoKCA+Pp5+/foxZcoU4uPjAdi8eXOtGcSFhYXMmTOH3NxcYmJi6NWrF7fddhtdulR3aI7jsG7dOpYvX05RURHJyckMGDCAU089tc4hH2m7TGw8zpnjcGffjn3tWexe+2N27ed1LBER2Yrd8BvuvZMhZzOkdMK58lZMamevYzVt0m2wycrKqjUZtzkYY+jcuTMbNmwIqXHJGl7U5869F/vBMkjbBWfSDEx4RIu+nrZh2xbq9UHo1xjq9UHo1GjX/YA74yYoyIPOXXGuuAWT1KHF6vP7/fWedKtrCUmrMyPPh4RkyPwd+/yTO3+CiIi0OPv9Gty7b6huVrrtijPhDkxSB69jBahhkVZnYmJxzrwYAPvG89jv13icSESkfbOrP68eBiopgt574PzzNkxcvNexalHDIp4wA/fFHDQMrMV9dCa2rMzrSCIi7ZL9/APc+2+F8jL4v0E4l9+MiY7xOtY21LCIZ8yp50JiB9i0Hvvc417HERFpd9wPluE+eCdUVsLeB+FcfAMmomXnFTaWGhbxjImOxTnrEgDsWy9g137tcSIRkfbDfftl7Nx7wXUxBw7FuWACJoiP0FXDIp4y/f+CGfK36qGheTOxZaVeRxIRCXnuKxnYJx8EwAwdjhlzKSYszONUO6aGRTxnRpwDySmQlYl9Zr7XcUREQpa1FveZ+YF/a80xp2BGno+p42LDwST4E0rIM9ExOKPHA2CXvoj99iuPE4mIhB7rutgFc7CvZABgThqNc8IZtU74GszUsEhQMHsMwhxyFED1UUOlJR4nEhEJHbaqCjtvJnbZy2AM5vSLcI46yetYDaKGRYKGGTEGOqTClk3Y/8zzOo6ISEiwFRW4c6ZiVy4Dx8GccwXOYUd7HavB1LBI0DCR0f8bGnr7FeyaLz1OJCLSttmyUtxZt8HnH4DPh3PRtTgHHOZ1rEZRwyJBxew+EHPYMQC48+7DlhR7G0hEpI2yxUW4M26E1Z9DRCTOpTdi9jrA61iNpoZFgo45aTSkdILsLGzGo17HERFpc2xBHu49E+H7NRAdU30Rw90Heh2rSdSwSNAxkVE4Yy4FwL7zGvbrzz1OJCLSdticLbjTroN1P0JcAs4/p2B27ed1rCZTwyJByezWHzN0OADu/PuxxUUeJxIRCX520wbcqddA5m+QlIJz9R2Ybr28jtUs1LBI0DInngUd0yB7M/bpR7yOIyIS1Ozv66r3rGzZBKmdca65E5PWxetYzUYNiwQtExGJM+YyMAb73hvYrz71OpKISFCyP3+He/d1kJcNu3THufpOTIdUr2M1KzUsEtRM3//DDDsW+GNoqKjQ40QiIsHFrl2Fe88NUFgAPfviTLgdk5Dkdaxmp4ZFgp45/kxITYfcbOyih72OIyISNOxXn+LOuAlKS2C3/jhX3oKJifM6VotQwyJBz0RE4Jz9x9DQyqXYLz/2OpKIiOfsJ+/hzp4CFeXQfx+cSydjIqO9jtVi1LBIm2B674752/EAuI/PxhYVeBtIRMRD7oo3cR+6G6oqMfsejDPuekx4hNexWpQaFmkzzHGjIK0L5GVjF/7b6zgiIp5w33oBO+8+sC7m4CMw512J8fm8jtXi1LBIm2HCa4aGHOwHb2O/+MDrSCIircZai/viosAfbOZvx2HOvBjjhHmcrHWoYZE2xfTaDXPkCQC4jz+ALcz3OJGISMuz1mIz5mGffxIA849RmBHnYIzxOFnrUcMibY75x2nQuSvk52IXPOR1HBGRFmXdKuwT/8K+/iwA5tRzcY4d2a6aFVDDIm2Q8YfjnH05OA72o3ewn77vdSQRkRZhKyuxc+/FvvMqGIM56xKcvx7ndSxPqGGRNsn07IM56iQA3Cf/hS3I8ziRiEjzshXluA/eif3oHQgLw5x/Fc7BR3gdyzNqWKTNMsNHwi7doSAP++SDXscREWk2trQE975b4MuPwB+OM+56nH0P9jqWp9SwSJtl/P7/DQ19ugL34/e8jiQi0mS2qBD33snwzX8hIgrnspswA/b1Opbn1LBIm2a674o55hQA7FP/wubneJxIRKTxbH4O7t3Xw4/fQnQszj9vxey2p9exgoIaFmnzzN9HQJeeUFiA+8S/sNZ6HUlEpMHslizcqdfBbz9DQhLO1Xdgevb1OlbQUMMibZ7x+atPKBcWBp9/UD1BTUSkDbGZv+NOuwY2rYcOqdXNyi7dvY4VVNSwSEgw3Xph/n4qAHbBQ9g8DQ2JSNtgf/sJd9q1kL0Z0napblZS072OFXTUsEjIMEefDN16QVEB7hMPaGhIRIKe/fFb3Luuh4I86NoTZ8IdmOSOXscKSmpYJGQYn6/6qKEwH3zxIfbDt72OJCJSJ/vNf3GnT4LiIti1H85VUzDxiV7HClpqWCSkmC49MMeOBP4YGsrd4nEiEZFt2S8/wp15M5SVwu4DcS6/GRMd63WsoKaGRUKOOeok6N4biotw58/W0JCIBBX3o3dw/3UHVFbAXvvjjJ+EiYzyOlbQU8MiIceEhVUPDfl88NUn2PeXeh1JRAQA951XsQ/fA1VVmAMOwxl7DcYf7nWsNkENi4Qks0s3zD9OB8Bd+G8qN2/0OJGItHfu689iH38ArMUcdjTm7MsxPp/XsdoMNSwSsswRx0PPvlBSRM59UzQ0JCKesNbiPv8k9ulHgephazPqQoyjr+CG0G9LQlb10NBl4PNT+un72Pfe8DqSiLQz1nWxix7GvrgIAHPCmTgnjcYY43GytkcNi4Q007krzglnAOAunovdkuVxIhFpL6xbhZ0/C/vWCwCYUWNxjhnhcaq2Sw2LhDzzt+MI7zcASopx59+voSERaXG2sgL70N3YFW+CcTBnX4Zz+N+9jtWmqWGRkGecMJKvvBH84bD6C+y7r3kdSURCmC0rw519O/bTFRDmw7nwapyDhnkdq81TwyLtgn+X7jgnnAmAXfwoVkcNiUgLsCXFuPfdBKs+hfBwnEtuwOx9kNexQoIaFmk3zF+Phd57QFkJ7mP3Y13X60giEkKq8nOpumcirP0aoqJxLr8Fs+feXscKGWpYpN0wThjO2ZdCeDh881/sO696HUlEQoTNzWbTtRfAz99DbDzOP6dg+uzhdayQooZF2hWTmo45cQwANmMeNivT20Ai0ubZrEyqpl5D5S8/QmIyztV3YLrv6nWskKOGRdodc/gx0HdPKCvFnXefhoZEpNHsht9wp10HWZmEpe1C2DVTMZ27eh0rJKlhkXbHOA7OmEshIhLWrsIue9nrSCLSBtl1P+BOuxZyt0B6VzpNexjTMc3rWCFLDYu0S6ZjGuakMQDYZx7DblrvbSARaVPs96tx774BCvOhe2/CJtxBWIeOXscKaWpYpN0yhx4F/QZAeRnuoxoaEpH6sas/x733Rigpgj574PzzNkxcgtexQl6DLhO5ePFiMjIyat2Xnp7OjBkztrv822+/zQMPPFDrPr/fz5NPPhm4ba1l8eLFvPXWWxQVFdGvXz/OO+88Onfu3JBoIg1mHAdn9Hjcmy6F71djl76A+etxXscSkSBmP1uJ+++7oLIS9twb58LrMBERXsdqFxp8XeuuXbsyadKkwG1nJ1ebjIqKYubMmXU+/vzzz/PKK69w8cUXk5qayqJFi5gyZQrTp08nPDy8ofFEGsSkdMKMOBv7xAPYZx7H7rkPJm0Xr2OJSBByVy7DzpsJrgt/OQjnvH9ifH6vY7UbDR4SchyHxMTEwH/x8fE7XN4YU2v5xMTEwGPWWl5++WVOPPFE9t13X7p3784ll1xCTk4OH3/8cYOLEWkMc8iRsPtAqCjHnTcT61Z5HUlEgoy77GXsI/eC62IOGoZz/gQ1K62swXtYMjMzGTt2LH6/n759+zJq1ChSUlLqXL60tJRx48ZhraVnz56cdtppdO1afcjXpk2byM3NZcCAAYHlo6Oj6d27N2vXrmXw4MHbXWdFRQUVFRWB28YYoqKiAj83p5r1heqlwEO9Pth5jcYYzJhLqbrxEvjhG3jzBcyRJ7RmxCYJ9W0Y6vVB6NfY1utzX34a+8x8AMywY3FOPQ/zp9GFtl7jzgRDfcY24NK1n3/+OaWlpaSnp5OTk0NGRgbZ2dncc889gYZha2vXrmXDhg10796d4uJilixZwpo1a5g+fTodOnTg22+/ZdKkScyZM4ekpKTA86ZPn44xhiuuuGK7Of48l6Znz55MnTq1IXWLbKPwtefIue828IeTdv9T+Lv28DqSiHjIWkveY7MpeHoeAPEjzyX+jAtDtikJdg3awzJo0KDAz927d6dPnz6MGzeOlStXMnTo0G2W79u3L3379q11+4orruCNN95g5MiRjQ59wgknMHz48MDtmjdPVlYWlZWVjV7v9hhjSEtLIzMzkwb0dm1GqNcH9a/R9t8Ps+fe2FWfkTn1esKunYYJC2vFpI0T6tsw1OuD0K+xLdZnXRd3wZzAeZqck8+m+K/HU5y5/bNjt8UaG6Kl6vP5fHTsWL/DwRs8JLS1mJgY0tPTyaxjA24vWM+ePQPL18xnycvLq7WHJS8vjx49etS5Hr/fj9+//bHDlnqjWGtD8k1YI9Trg/rVaM68BHvTePhpLe5rz+IcfVIrpWu6UN+GoV4fhH6NbaU+W1WFnXcf9oNlYAzm9Iswhx5Vr+xtpcbG8rK+Jp2HpbS0lMzMzFoTaXfEdV3WrVsXaE5SU1NJTEzkq6++CixTXFzM999/X2vPjEhrMckpmFPPA8AueRK7fp3HiUSkNdmKCtw5U6ubFcfBnHslzqFHeR1LaOAelvnz57PPPvuQkpJCTk4OixcvxnEchgwZAsCsWbNITk5m1KhRAGRkZNCnTx/S0tIoKipiyZIlZGVlMWzYMKB6F9MxxxzDM888Q+fOnUlNTWXhwoUkJSWx7777NnOpIvVjDhqK/XQFfPUJ7iMzcK67q00MDYlI09iyUtwHbofVX4DPjzP2asxe+3sdS/7QoIYlOzubmTNnUlBQQHx8PP369WPKlCmBQ5s3b95cazJSYWEhc+bMITc3l5iYGHr16sVtt91Gly5dAsscd9xxlJWVMWfOHIqLi+nXrx/XX3+9zsEinjHG4Jx1Me6Nl8Av32Nf/Q/m76d4HUtEWpAtLsS975bqIwUjInEunojZfaDXsWQrDTpKKNhlZWXVOty5ORhj6Ny5Mxs2bAjJcclQrw8aX6O7cln1eRfCfDg3TMd06dFyIZsg1LdhqNcHoV9jsNdnC/Jw750Mv/4E0TE4l96I2bVfg9YR7DU2VUvV5/f76z3pVtcSEqmDOeAwGLgfVFXiPjoT28xHoImI92z2Ztxp11U3K3EJOFfd3uBmRVqHGhaROhhjcM68GGLiYN0P2Fczdv4kEWkz7KYNuNOuhczfIDkF5+o7MV17eh1L6qCGRWQHTEIS5rQLALAvLsKu+9HjRCLSHOzvv1TvWdmyCVI741w9VdcRC3JqWER2wux3CAw6AKqq/hgaat55UiLSuuxP3+HedT3kZcMu3av3rHSo3zwK8Y4aFpGdMMbgnHERxMbBbz9hX3ra60gi0kh27Src6TdAUQH07Isz4XZMQtLOnyieU8MiUg8mPgkz6iIA7CtPY3/5weNEItJQ9qtPcGfcBKUlsFt/nCtvwcTEeR1L6kkNi0g9OfsOwfxl8B9DQzOwzXwIvYi0HPvJe7izp0BFOQzYF+fSyZjIaK9jSQOoYRFpAHP6hRCXAL//gn1xkddxRKQe3PfewH3obqiqwux7MM5F12HCI7yOJQ2khkWkAUxcAs7pfwwNvZqB/fk7jxOJyI64bz6Pfex+sC7m4CMw512J8TXpur/iETUsIg1k/nIQZt+DwXVxH9HQkEgwstbivrgQu2guAOaI4zFnXoxxdF2wtkoNi0gjmFFjIT4RNvyKfeEpr+OIyFastdiMR7HPV382zXGjMCefXetad9L2qGERaQQTG49zxjgA7KvPYn/81uNEIgJg3Srs47Oxrz8HgDn1PJzhI9WshAA1LCKNZAYdgNn/ULBu9Qnlysu8jiTSrtnKSuzD07Hvvg7GwYwej/PXf3gdS5qJGhaRJjCnXQAJSZD5W2D3s4i0PltehvuvO7Afv1t9hfULrsIZ8jevY0kzUsMi0gQmJq76AomAfeM57PdrPE4k0v7Y0mLc+26B/34M/nCciydi9hnidSxpZmpYRJrIDNwPc+DhYG310FCZhoZEWostKsCdPhm+/Qoio3AuuwnT/y9ex5IWoIZFpBmYU8+HxGTYtB773BNexxFpF2xeTvVFDH9aCzFxOFfehtltT69jSQtRwyLSDExMLM5ZlwBg31qCXfu1x4lEQpvdkoU77Tr4/RdISKq+iGHPPl7HkhakhkWkmZj++2AG/7V6aOix+7BlpV5HEglJNvN33GnXwKb10CEV5+o7Mbt09zqWtDA1LCLNyJxyLiSlwKYN2Gcf9zqOSMixv/6EO+1ayN4MaV2qm5XUzl7HklaghkWkGZnomK2Ghl7AfrvK40QiocP+8A3u3ddDQR507Vk9DJSc4nUsaSVqWESamdlzb8zBRwDgzpuJLS3xOJFI22fXfIl772QoLoJd++FcNQUTn+h1LGlFalhEWoAZcQ4kd4TNG7H/eczrOCJtmv3yo+rzrJSVwh574VxxCyY61utY0srUsIi0ABMVjTN6PAD27Zexa770OJFI2+R+uBz3gduhsgL2OgDnkkmYiEivY4kH1LCItBCzx16YQ48CwH3sfmxpsceJRNoW951XsXOng+tiDjgc58JrMH6/17HEI2pYRFqQOXkMdEiFLZuwT8/zOo5Im+G+9gz28QfAWsxhx2DOvgwTFuZ1LPGQGhaRFmQio3HGXAqAfedV7OrPPU4kEtystbjPPYHNmAeAOfokzKixGEdfV+2d3gEiLcz0G4A5/O/AH0NDJRoaEtke67rYRQ9jX1oMgDnxLJwTR2OM8TiZBAM1LCKtwJw0GjqmQfZm7NOPeB1HJOjYqirsY/dj33oBADPqQpyjT/Y4lQQTNSwircBERP5vaOjd17GrPvU4kUjwsJUVuP++C/v+W+A4mHOuwDn8GK9jSZBRwyLSSkzfPTHDjgXAfWwWtrjQ40Qi3rNlZbizp8Cn74PPhzP2GpwDD/c6lgQhNSwirciccBakdobcLdhFc72OI+IpW1KMO/NGWPUZhEfgjJ+E2ftAr2NJkFLDItKKTEQEztmXgTHY99/C/vdjryOJeMIW5OPecwN8txqionGuuBmzxyCvY0kQU8Mi0spM7z0wf/0HAO782dgiDQ1J+2Jzt+DedR388j3ExldfF6j3Hl7HkiCnhkXEA+b4M6DTLpCXjV34b6/jiLQam5WJO+062PArJHbAufoOTLddvY4lbYAaFhEPmPCaoSEH+8Ey7Bcfeh1JpMXZ9b/iTrsWsjKhYxrONXdiOnf1Opa0EWpYRDxidu2HOeJ4ANwnHsAW5nsbSKQFlX//DVXTroXcbOjctXrPSkonr2NJG6KGRcRD5rhR0Lkr5OVgF2hoSEKT/e5rNl03FgrzoXtvnAl3YBI7eB1L2hg1LCIeMv7w/w0NfbQc+9n7XkcSaVZ21WdU3TsZW1wEff8P55+3YeLivY4lbZAaFhGPmZ59MUedCID7xL+wBXkeJxJpHvaz93Fn3Qbl5UTucxBhl92EiYr2Opa0UWpYRIKAOfY0SO8GBXnYp+Z4HUekydz3l+I+OA2qKjH7DCblhnswEZFex5I2TA2LSBAwfj/OOZeD42A/eQ/7yXteRxJpNHfZS9hHZ4B1MYOH4VwwAeP3ex1L2jg1LCJBwnTvjfnj6rTukw9i83O9DSTSCO7LTwf2Epphx2LOGo9xwjxOJaFADYtIEDHDT4UuPaAwv7ppsdbrSCL1Yq3F/c9j2GcfB8AMH4k59TyMo68ZaR56J4kEEePzVx81FBYGn72P/fhdryOJ7JR1XexTD2Jf/Q8AZsTZOMeNwhjjcTIJJWpYRIKM6bYr5phTALBPzcHm5XicSKRutqoK++gM7NuvgDGYM8fhHHGC17EkBKlhEQlC5pgR0LUnFBVUnwVXQ0MShGxFOe6Dd2I/eBvCwjDnXolzyFFex5IQpYZFJAgZnw/n7MshzAdffIj9cLnXkURqsWWluPffCl98CD4/zkXX4ex/qNexJISpYREJUqZrz+pJuIBd8BA2d4vHiUSq2eJC3Hsnw5ovISIS57IbMQP38zqWhDg1LCJBzBx1EnTvDcWFuI9raEi8Z/Nzce+eCD98A9ExOFfcguk3wOtY0g6oYREJYtVDQ5eBzwf//Ri7cpnXkaQds9lZuHddB7/+BPGJOBNux+zaz+tY0k6oYREJcmaX7tWn7gfswn9jczQ0JK3PblqPO+06yPwdklOqr7jcpafXsaQd8TVk4cWLF5ORkVHrvvT0dGbMmLHT565YsYKZM2eyzz77cPXVVwfunz17NsuX155QOHDgQCZOnNiQaCIhzRx5IvbzD+Dn73Dnz8K5dLLOcSGtxv7+S/WclbwcSE3HufJWTIeOXseSdqZBDQtA165dmTRpUuC2U4+zGG7atInHH3+c3XfffbuP77XXXowbN+5/oXwNjiUS0kxYGM7Zl+HeegWs+hS74k3MkL95HUvaAfvTd7gzb4KiAujSA+eKmzHxSV7HknaowUNCjuOQmJgY+C8+Pn6Hy7uuy/33388pp5xCamrqdpfx+Xy11hkbG9vQWCIhz6R3wxx/OgB28VxsdpbHiSTU2W+/wr3nhupmpWdfnKtuV7MinmnwrozMzEzGjh2L3++nb9++jBo1ipSUlDqXz8jIID4+nqFDh7JmzZrtLrN69WrOO+88YmJi2HPPPRk5ciRxcXF1rrOiooKKiorAbWMMUVFRgZ+bU836QnX3e6jXB6FVo3PE8VR9thJ+/BY7fxbm8ptDqr7tCfX6IDhrdP/7Ce6/7oCKcky/ATiXTMRERjdqXcFYX3ML9RqDoT5jG3Cc5Oeff05paSnp6enk5OSQkZFBdnY299xzT6Bh2No333zDjBkzmDZtGvHx8cyePZuioqJac1hWrFhBREQEqampZGZmsmDBAiIjI5kyZUqdw01/nkvTs2dPpk6d2pC6Rdqsit9+ZuP407HlZSSNn0jsUToNujSv4nffYMtdN0BVFZH7HUzKdXdiwiO8jiXtXIP2sAwaNCjwc/fu3enTpw/jxo1j5cqVDB06tNayJSUl3H///YwdO3aHw0aDBw8O/NytWze6d+/O+PHj+frrr+nfv/92n3PCCScwfPjwwO2aji8rK4vKysqGlLRTxhjS0tLIzMwMyXNghHp9EII1hkVgjj8Du3guOQ9Np6DLrnTec0Do1PcnIbf9tiOYanTffR13/mywLma/Q6g45woyt2Q3aZ3BVF9LCfUaW6o+n89Hx471m8DdpNmtMTExpKenk5mZuc1jGzduJCsrq9aej5oiR44cyYwZM0hLS9vmeZ06dSIuLo7MzMw6Gxa/34/f79/uYy31RrHWhuSbsEao1wchVuOw4fDZ+/D9GqrmzcTe9XBo1bcdoV4feF+j++bz2EVzATCHHIk5/UJwwpotk9f1tYZQr9HL+prUsJSWlpKZmcnBBx+8zWPp6encfffdte5buHAhpaWljBkzps55L1u2bKGwsJCkJE3sEqmLccJwxlyGe8ul2DVfUvTKf2DQ4J0/UWQ7rLXYFxZiX1gAgDniBMzJY0J2Poa0TQ1qWObPn88+++xDSkoKOTk5LF68GMdxGDJkCACzZs0iOTmZUaNGER4eTrdu3Wo9PyYmBiBwf2lpKU8//TT7778/iYmJbNy4kSeeeIK0tDQGDhzYHPWJhCzTKR1zwlnYRQ+TO3cmzo27Qkonr2NJG2OtxT79CPaN5wEwx52O+fspalYk6DSoYcnOzmbmzJkUFBQQHx9Pv379mDJlSmCOyubNmxv0Jncch3Xr1rF8+XKKiopITk5mwIABnHrqqXUO+YjI/5ihw7GfrcR+9zXuvPswV96Kqce5kUQArFuFfeJf2HdfB8CMPB9n2LEepxLZvgYdJRTssrKyah3u3ByMMXTu3JkNGzaE5LhkqNcH7aDGrEzcmy/FlpViTrsAZ+jwnT+nDQn57Yc3NdrKSuwj92I/fheMgxl9Cc7gv7bIa2kbtn0tVZ/f76/3pFv9KSbSxpnUziScPR4A+5/HsJs2eJxIgp0tL8N94PbqZiXMh3PBVS3WrIg0FzUsIiEg9u8jMLv1h/Iy3Hkzsa7rdSQJUra0GPe+W+CrT8AfjnPxRMw+Q7yOJbJTalhEQoBxHJwxl0JEJHy3Grv0Ra8jSRCyRQW40yfDt19BZBTO5Tdh+v/F61gi9aKGRSREmI5pmJPPBsA+Ox+7cb3HiSSY2Lwc3Luuh5/WQmwczj9vw/Td0+tYIvWmhkUkhJhDj4LdB0J5+R9DQ1VeR5IgYLdswp12Lfz+CyQk41x1B6ZHH69jiTSIGhaREGKMwRk9HiKj4Ps12Ddf8DqSeMxm/oY79VrYtAE6pOJcfQdml247f6JIkFHDIhJiTIdUzIhzALDPPYHd8JvHicQr9tefcKddBzmbIa0LzjVTMamdvY4l0ihqWERCkDn4CNhjEFSU4z46Q0ND7ZD94Rvcu6+Hgjzo1qt6z0pSB69jiTSaGhaREFQ9NHQJREXDT2uxrz/ndSRpRXbNl7j3TobiIui9O84/p2DiEryOJdIkalhEQpRJ7og55VwA7PNPYdev8ziRtAb7xQe4990MZaWwxyCcy2/GRMd4HUukydSwiIQwM/ivsOdfoLIC99GZ2CoNDYUy94O3cf91J1RWwqADcC65ARMR6XUskWahhkUkhBljcM66BKJi4OfvsK8943UkaSHu8lexj9wLros58HCcsddgdBFZCSFqWERCnEnqgBl5PgB2yQLs7794nEiam/vqf7BPPADWYg4/BjPmMkxYmNexRJqVGhaRdsAceDgM3A+qKquHhiorvY4kzcBai/vsE9j/PAaAOfpkzGljMY7+aZfQo3e1SDtgjME5YxxEx8Iv32Nf/Y/XkaSJrOtiF/4b+/JiAMyJo3FOPAtjjMfJRFqGGhaRdsIkJmNOuwAA++Ii7K8/eZxIGstWVWHn3Vd9kUtjMKdfiHP0SV7HEmlRalhE2hGz/6Gw1wF/DA3NwFZWeB1JGshWVOA+dBd25VJwHMw5l+McdozXsURanBoWkXbEGINz5kUQGwe//oR9+WmvI0kD2LIy3Nm3wWfvg8+Hc+G1OAcc7nUskVahhkWknTHxSZjTxgJgX34au+4HjxNJfdjiItwZN8LXn0N4BM74SZhBB3gdS6TVqGERaYfMvgfD3gdBVRXuIxoaCna2IB/3nhvg+9UQFYNzxS2YPQZ5HUukValhEWmHjDE4p18IsfHw+y/YFxd5HUnqYHO24N51Haz7AeIScK66DdN7d69jibQ6NSwi7ZSJT6xuWgD7Sgb25+88TiR/ZrMycaddCxt+haQUnAl3YLrt6nUsEU+oYRFpx8w+QzD7DAHXrT6hXIWGhoKFXb+uulnZvBE6puFcfQemcxevY4l4Rg2LSDtnRl0IcQmwfh32hQVexxHA/vJ99TBQbjakd8O5+k5MSievY4l4Sg2LSDtn4uKrz4IL2Fefwf601uNE7Ztd+3X1BNvCAujRB2fC7ZjEZK9jiXhODYuIYPY+ELPfoWDd6qOGKsq9jtQuuas+w515I5QUQ9//w7nyVkxsvNexRIKCGhYRAcCcdj4kJEHmb9jnn/Q6TrtTvOIt3PtvhfJy6L8PzmU3YaKivY4lEjTUsIgIACZ2q6Gh15/H/vCNx4naD3fFW2y58zqoqsT8ZTDOuOsw4RFexxIJKmpYRCTA7LU/5oDDq4eGHp2JLS/zOlLIc996EffRGeC6mCF/w1xwFcbn9zqWSNBRwyIitZiR50NCMmz8HfvcE17HCVnWWtyXFmMXPgRA7HGn4Ywej3HCPE4mEpzUsIhILSYmFuesiwGwby7Bfrfa40Shx1qL/c9jgYbQHHsaiedfiTHG42QiwUsNi4hswwzYF3PQMLAWd95MbJmGhpqLdV3sk//CvvYMAGbEOYQdN0rNishOqGERke0yp54LiR1g0wbss/O9jhMSbGUl9pF7sctfBWMwZ16Mc8TxXscSaRPUsIjIdpnoWJzRlwBg33oB++0qjxO1bbaiHHfOVOyHyyEsDHPeP3EOOdLrWCJthhoWEamT2fMvmIOPAMB97D5saYnHidomW1pSfY6VLz4Enx9n3PU4+x3idSyRNkUNi4jskBlxDiSnQFYm9pnHvI7T5tiiQtwZN8KaLyEiCueyGzED9vU6lkibo4ZFRHbIREXjjB4PgF32Mvab/3qcqO2w+bm4d0+EH76B6FicK2/B9BvgdSyRNkkNi4jslNljEOaQowBw592HLS32OFHws9lZuNOug99+gvjE6osY9trN61gibZYaFhGpFzNiDHRIhS2bsBnzvI4T1OzG9bhTr4WNv0NyR5yr78R06eF1LJE2TQ2LiNSLidxqaGj5q9jVX3gbKEjZ337GnXYtZGdBp12qm5VO6V7HEmnz1LCISL2Z3QdiDjsGAPex+7ElGhramv1pLe5d10N+LnTpiXP17ZgOHb2OJRIS1LCISIOYk0ZDSifIzsI+/YjXcYKG/fYr3HsmQXEh9NoN56opmPgkr2OJhAw1LCLSICYyCmfMZQDYd1/HrvrM40Tes//9GHfmzVBWArsPxLniFkxMrNexREKKGhYRaTCz256YYccCfwwNFRd6nMg77sfv4j5wO1SUw8D9cMZPwkRGeR1LJOSoYRGRRjEnnAkd0yB3C3bxXK/jeMJ993Xsv++GqirMfofiXHgtxh/udSyRkKSGRUQaxUREVg8NGYNd8Rb2q0+8jtSq3Deex86fBdZiDjkKc+4VGJ/P61giIUsNi4g0mun7f5hh/wDAnT8LWxT6Q0PWWtwlTwX2KpkjT8SccRHG0T+nIi1JnzARaRJz/BnQaRfIzcYu+rfXcVqUtRa7+BHsCwuB6trNSaMxxnicTCT0qWERkSYxERE4Z18GxsGuXIb98iOvI7UI61Zh58/Cvvk8AGbkBTh/P0XNikgrUcMiIk1mdu2H+dtxALiPz8YWFXicqHnZygrsv+/BvvcGGAcz5jKcYcO9jiXSrqhhEZFmYY4bBWldIC8Hu+Ahr+M0G1tehvvAHdhP3oMwH87Yq3EGD/M6lki7o4ZFRJqFCd9qaOjD5djPVnodqclsSXH1CeG++gTCw3EumYj5y0FexxJplxp0DN7ixYvJyMiodV96ejozZszY6XNXrFjBzJkz2Weffbj66qsD91trWbx4MW+99RZFRUX069eP8847j86dOzckmogEAdNrN8xRJ2Bf+Q/uEw/g9Pk/TFy817EaxRbmVzcrP38HkVE44ydj+v6f17FE2q0GnzSga9euTJo0KXDbqcehfJs2beLxxx9n99133+ax559/nldeeYWLL76Y1NRUFi1axJQpU5g+fTrh4ToBk0hbY44dhf3iI9jwK3bBHMwFE7yO1GA2Nxt3xo3w+y8QG4dz+c2Y7r29jiXSrjW4YXEch8TExHov77ou999/P6eccgpr1qyhqKgo8Ji1lpdffpkTTzyRfffdF4BLLrmE888/n48//pjBgwdvd50VFRVUVFQEbhtjiIqKCvzcnGrWF6pHAoR6fRD6NQZbfSY8HHPO5VTdMQH78bvYvwzG2Wf7n+V6ra+V67ObN1ZfxDBrAyQkE/bPWzHp3Vr0NYNtGza3UK8PQr/GYKivwQ1LZmYmY8eOxe/307dvX0aNGkVKSkqdy2dkZBAfH8/QoUNZs2ZNrcc2bdpEbm4uAwYMCNwXHR1N7969Wbt2bZ0Ny7PPPltraKpnz55MnTqVjh1b7jLuaWlpLbbuYBDq9UHo1xhU9XXuTN6IMeQvegSeepDUg4cSlpjcpFW2Rn0Vv/1M1t0TYfNGwjrtQuqU2fg6d2nx160RVNuwBYR6fRD6NXpZX4Malj59+jBu3DjS09PJyckhIyODyZMnc8899wT2cGztm2++YenSpUybNm2768vNzQUgISGh1v0JCQmBx7bnhBNOYPjw/x1SWNPxZWVlUVlZ2ZCSdsoYQ1paGpmZmVhrm3XdwSDU64PQrzFY67OHDYf3luL+/jMbpt9UfZ2dRvx11lr12XU/UnXvZCjIg85d4cpbySIMNmxosdesEazbsLmEen0Q+jW2VH0+n6/eOxsa1LAMGjQo8HP37t0DDczKlSsZOnRorWVLSkq4//77GTt2LPHxzTvpzu/34/f7t/tYS71RrLUh+SasEer1QejXGHT1+Xw4Z1+Ge/s/sZ++j/vxuzj7Htzo1bVkffb7Nbj33QIlRdBtV5zLb4K4hFb/fQbdNmxmoV4fhH6NXtbXpCt1xcTEkJ6eTmZm5jaPbdy4kaysLKZOnRq4r6bIkSNHMmPGjMBcmLy8PJKSkgLL5eXl0aNHj6ZEE5EgYLrvijnmFOyLC7FPPYjdbU9MfNLOn9iK7OovcGdPgfIy6L0HzvhJmOgYr2OJyJ80qWEpLS0lMzOTgw/e9q+m9PR07r777lr3LVy4kNLSUsaMGUNKSgphYWEkJiby1VdfBRqU4uJivv/+e4444oimRBORIGH+PgL7xYfw20+4T/wL56LrgmZiov3iA9w506CyEv5vEM5F12MiIryOJSLb0aCGZf78+eyzzz6kpKSQk5PD4sWLcRyHIUOGADBr1iySk5MZNWoU4eHhdOtWe2Z9TEz1Xy1b33/MMcfwzDPP0LlzZ1JTU1m4cCFJSUmBo4ZEpG0zPj/OOZfjTrkSPv8A+9E7mP0P9ToW7gfLsI/OBNeFvQ/COe+fmDqGmkXEew1qWLKzs5k5cyYFBQXEx8fTr18/pkyZEpijsnnz5gb/5XTcccdRVlbGnDlzKC4upl+/flx//fU6B4tICDFde2KGn4p9/insU3Owu/XHNPGooaZw334Z+9QcsBZz4FDM6PGYsDDP8ojIzhkbQrODsrKyap2fpTkYY+jcuTMbNmwIyYlUoV4fhH6NbaU+W1mJe8cEWPcDDNwP5+KJ9foDp7nrc1/5D/aZx6rXffjfMSPPx9TjBJgtqa1sw8YK9fog9Gtsqfr8fn+9jxLStYREpFWYP44aIswHX36E/eDtVn19ay3us4//r1k55hTMaRd43qyISP3okyoircZ06YE5diQAduFD2JwtrfK61nWxCx7Cvvx0dY6TRuOccEbQTP4VkZ1TwyIircocdRJ07w3FRbiPz27x3ee2qgo7byZ22UtgDOb0C3GOOqlFX1NEmp8aFhFpVSYsDOecy8Hng68+wb7/Vou9lq2owH1oGnblMnAczDlX4Bx2TIu9noi0HDUsItLqTHo3zD9OB8AuehibvbnZX8OWleLOug0+W1l91t2LrsU54LBmfx0RaR1qWETEE+aI46FnXygpxp1/f7MODdniItwZN8LqzyE8Amf8ZMxeBzTb+kWk9alhERFPmLAwnLMvB58fvv4c+94bzbJeW5CHe88N8P0aiIrBueIWzB57Ncu6RcQ7alhExDOmcxfM8WcAYBfPxW7JatL6bM4W3GnXVZ/rJS4B56opmN67N0dUEfGYGhYR8ZT52z9g135QWoL72H2NHhqyWZm4066FzN8gKQXn6jsw3Xo1c1oR8YoaFhHxlHHCcMZcBv5wWPMl9p3XGrwO+/s63KnXwuaNkNoZ55o7MWldWiCtiHhFDYuIeM6k7YI58UwA7NOPYLMy6/1c+8v3uHdfB3nZsEt3nKvvxHRIbamoIuIRNSwiEhTM0GOhzx5QVor72P1Y193pc+zaVbh3T4TCAujRB2fC7ZiEpFZIKyKtTQ2LiAQF4zg4Yy6F8HD49ivs8ld2uLxd9SnujJugtAT67onzz1sxMXGtE1ZEWp0aFhEJGiY1HXPiGABsxrw6h4bspytwZ02BinLovw/OZTdiIqNbMamItDY1LCISVMzhx0DfPaG8DHfezG2GhtwVb+HOuQuqKjH7Howz7jpMeIRHaUWktahhEZGgEhgaioiEtV9jl74YeMx96wXsvJlgXczBR2DOuxLj83uYVkRaixoWEQk6pmMa5qQxALjPPEbF7+twX1yEXfjv6sf/ehzmzIsxTpiHKUWkNfm8DiAisj3m0KOwn70P3/yXTRPOxc3Lqb7/2NMwx47EGONxQhFpTdrDIiJByTgOzujxEBH1v2bllHNx/nGamhWRdkgNi4gELZPSCefsS/Gld8MZcxnO347zOpKIeERDQiIS1Jx9htD52BFs2LCh0dcZEpG2T3tYREREJOipYREREZGgp4ZFREREgp4aFhEREQl6alhEREQk6KlhERERkaCnhkVERESCnhoWERERCXpqWERERCToqWERERGRoKeGRURERIKeGhYREREJempYREREJOipYREREZGg5/M6QHPy+VqunJZcdzAI9fog9GtUfW1fqNcY6vVB6NfY3PU1ZH3GWmub9dVFREREmpmGhHaipKSEa665hpKSEq+jtIhQrw9Cv0bV1/aFeo2hXh+Efo3BUJ8alp2w1vLTTz8RqjuiQr0+CP0aVV/bF+o1hnp9EPo1BkN9alhEREQk6KlhERERkaCnhmUn/H4/J598Mn6/3+soLSLU64PQr1H1tX2hXmOo1wehX2Mw1KejhERERCToaQ+LiIiIBD01LCIiIhL01LCIiIhI0FPDIiIiIkEvtC968CerV69myZIl/PTTT+Tk5HDVVVex33777fA5X3/9NfPnz+fXX3+lQ4cOnHTSSRx22GG1lnn11Vd54YUXyM3NpXv37pxzzjn07t27BSupW0Nr/PDDD3n99df5+eefqayspEuXLowYMYK99torsMzixYvJyMio9bz09HRmzJjRQlXUraH1ff3119x8883b3P/QQw+RmJgYuB0s27Ch9c2ePZvly5dvc3+XLl2YPn06EFzb79lnn+Wjjz7i999/Jzw8nL59+3LGGWeQnp6+w+etXLmSRYsWkZWVRVpaGqeffjp777134HFrLYsXL+att96iqKiIfv36cd5559G5c+eWLmkbjanxzTff5J133uHXX38FoFevXpx22mm13oPb29YDBw5k4sSJLVNIHRpT39tvv80DDzxQ6z6/38+TTz4ZuB0s27Ax9d10002sXr16m/sHDRrEddddBwTP9gN4/fXXef3118nKygKq/704+eSTGTRoUJ3PCYbPYLtqWMrKyujRowdDhw7l7rvv3unymzZt4s477+Rvf/sb48ePZ9WqVTz44IMkJiYGvtDff/995s+fz/nnn0+fPn146aWXmDJlCjNmzCAhIaGFK9pWQ2tcs2YNAwYM4LTTTiMmJoZly5YxdepUbr/9dnr27BlYrmvXrkyaNClw23G82TnX0PpqzJgxg+jo6MDt+Pj4wM/BtA0bWt/ZZ5/N6aefHrhdVVXFhAkTOOCAA2otFyzbb/Xq1Rx55JHsuuuuVFVVsWDBAm677TamT59OZGTkdp/z7bffMnPmTEaNGsXee+/Ne++9x1133cXUqVPp1q0bAM8//zyvvPIKF198MampqSxatIgpU6Ywffp0wsPDW7PERtW4evVqBg8ezG677Ybf7+f5558PPCc5OTmw3F577cW4ceMCt7240F5j6gOIiopi5syZdT4eLNuwMfVdddVVVFZWBm4XFBQwYcIEDjzwwFrLBcP2A0hOTmbUqFF07twZay3Lly9n2rRpTJs2ja5du26zfNB8Bm07NWLECPvhhx/ucJnHH3/cXnnllbXuu/fee+1tt90WuH3dddfZhx9+OHC7qqrKXnDBBfbZZ59t1ryNUZ8at+eKK66wTz/9dOD2okWL7FVXXdWc0ZpFfepbtWqVHTFihC0sLKxzmWDdho3Zfh9++KE95ZRT7KZNmwL3Bev2s9bavLw8O2LECPv111/Xucz06dPtHXfcUeu+66+/3s6ZM8daa63ruvb888+3zz//fODxoqIiO2rUKPvee++1TPAGqE+Nf1ZVVWXPOuss+/bbbwfumzVrlp06dWpLRGyS+tS3bNkyO3r06DofD+Zt2Jjt9+KLL9qzzjrLlpSUBO4L1u1XY8yYMfatt97a7mPB8hlsV3tYGuq7776jf//+te4bOHAg8+bNA6CyspIff/yR448/PvC44zj079+ftWvXtmLS5uO6LiUlJcTGxta6PzMzk7Fjx+L3++nbty+jRo0iJSXFo5QNd/XVV1NRUUHXrl0ZMWIE/fr1A0JvGy5dupT+/fvTsWPHWvcH6/YrLi4G2Ob9trW1a9cyfPjwWvcNHDiQjz/+GKjeE5qbm8uAAQMCj0dHR9O7d2/Wrl3L4MGDWyB5/dWnxj8rKyujsrJym+esXr2a8847j5iYGPbcc09GjhxJXFxcs+ZtqPrWV1payrhx47DW0rNnT0477bTAX/PBvA0bs/2WLl3KQQcdtM0emWDcfq7rsnLlSsrKyujbt+92lwmWz6Aalh3Izc3dZkggISGBkpISysvLKSwsxHXdWnMhABITE1m/fn0rJm0+L7zwAqWlpbV2Zfbp04dx48aRnp5OTk4OGRkZTJ48mXvuuYeoqCgP0+5cUlIS559/PrvuuisVFRW89dZb3HzzzUyZMoVevXqRn58fMtswOzubL774gksvvbTW/cG6/VzXZd68eey2226B3crbU9fnMDc3N/B4zX11LeOV+tb4Z08++STJycm1/mDaa6+92H///UlNTSUzM5MFCxZw++23M2XKFM+G+OpbX3p6OhdddBHdu3enuLiYJUuWcMMNNzB9+nQ6dOgQtNuwMdvv+++/59dff+Wiiy6qdX+wbb9169YxceJEKioqiIyM5KqrrqJLly7bXTZYPoNqWCTgvffeIyMjgwkTJtR64209Eat79+6BL8CVK1cydOhQL6LWW3p6eq3JcrvtthsbN27kpZdeYvz48R4ma37Lly8nJiZmm0m6wbr95s6dy6+//sott9ziWYaW1pgan3vuOVasWMFNN91Ua+x/679Su3XrRvfu3Rk/fjxff/31NnuCW0t96+vbt2+tv9779u3LFVdcwRtvvMHIkSNbOmajNWb7LV26lG7dum0zaT/Ytl96ejp33XUXxcXFfPDBB8yePZubb765zqYlGOiw5h1ITEwkLy+v1n15eXlERUURHh5OfHw8juNs00Hm5uZu8xd7sFuxYgUPPvggV1xxRa3detsTExNDeno6mZmZrZSuefXu3TuQPVS2obWWZcuWcfDBB+90Il8wbL+5c+fy2WefceONN9KhQ4cdLlvX57Bm+9T8f0fLeKEhNdZYsmQJzz33HDfccAPdu3ff4bKdOnUiLi7Os+3YmPpq+Hw+evbsGcgejNuwMfWVlpayYsWKev0h4PX28/l8pKWl0atXL0aNGkWPHj14+eWXt7tssHwG1bDsQJ8+ffjqq69q3fff//438JeCz+ejV69erFq1KvC467qsWrWqzrHAYPTee+/xwAMPcNlll9U6TK0upaWlZGZmtqkv9K39/PPPJCUlAaGzDVevXk1mZma9/qH0cvtZa5k7dy4fffQRkydPJjU1dafP6du373Y/h3369AEgNTWVxMTEWssUFxfz/fffe7ING1MjVB9l8Z///Ifrr7+eXXfddafLb9myhcLCwsB7ubU0tr6tua7LunXrAtmDaRs2pb4PPviAyspKDj744J0u69X2q4vrulRUVGz3sWD5DLarIaGaf6hrbNq0iZ9//pnY2FhSUlJ46qmnyM7O5pJLLgHgiCOO4LXXXuOJJ57g8MMPZ9WqVaxcuZJrr702sI7hw4cze/ZsevXqRe/evXn55ZcpKyvb5lwtraWhNb733nvMnj2bMWPG0KdPn8CehvDw8MBhwPPnz2efffYhJSWFnJwcFi9ejOM4DBkyJOjre+mll0hNTaVr166Ul5ezdOlSVq1axQ033BBYRzBtw4bWV2Pp0qX06dNnu+PswbT95s6dy3vvvcfVV19NVFRU4P0WHR0dGP6YNWtW4LBLgGOOOYabbrqJF154gb333psVK1bwww8/cMEFFwBgjOGYY47hmWeeoXPnzqSmprJw4UKSkpLYd99920SNzz33HIsXL+bSSy8lNTU18JzIyEgiIyMpLS3l6aefZv/99ycxMZGNGzfyxBNPkJaWxsCBA4O+voyMDPr06UNaWhpFRUUsWbKErKwshg0bBgTXNmxMfTWWLl3Kvvvuu81E2mDafgBPPfUUe+21FykpKZSWlvLee++xevXqwDlhgvUz2K4alh9++KHWScTmz58PwKGHHsrFF19MTk4OmzdvDjyemprKtddey2OPPcbLL79Mhw4duPDCC2udVO2ggw4iPz+fxYsXk5ubS48ePbj++us92/vQ0BrffPNNqqqqmDt3LnPnzg3cX7M8VE/mnDlzJgUFBcTHx9OvXz+mTJlS61wmraWh9VVWVjJ//nyys7OJiIige/fuTJo0iT333DOwTDBtw4bWB9V/yXz44YeMGTNmu+sMpu33+uuvA9Un2trauHHjAg3i5s2bMcYEHtttt9249NJLWbhwIQsWLKBz585MmDChVnN23HHHUVZWxpw5cyguLqZfv35cf/31rX4OFmhcjW+88QaVlZWBk/3VOPnkkznllFNwHId169axfPlyioqKSE5OZsCAAZx66qn4/f4WrefPGlNfYWEhc+bMITc3l5iYGHr16sVtt91Wa75EsGzDxtQHsH79er755ptafwzVCKbtB9VDNbNnzyYnJ4fo6Gi6d+/OxIkTA9MBgvUzaKy1ttnWJiIiItICNIdFREREgp4aFhEREQl6alhEREQk6KlhERERkaCnhkVERESCnhoWERERCXpqWERERCToqWERERGRoKeGRURC3uLFiznllFPIz8/3OoqINJIaFhEREQl6alhEREQk6KlhERERkaDXrq7WLCItKzs7m4ULF/L5559TVFREWloaw4cPZ+jQoQB8/fXX3HzzzVx++eX8/PPPLFu2jNLSUvbcc0/OPfdcUlJSaq1v5cqVPPfcc/z2229ERkYycOBAzjjjDJKTk2st9/vvv7No0SK+/vprSktLSUlJ4YADDuC0006rtVxxcTGPP/44H3/8MdZa9t9/f84991wiIiJa9hcjIk2mhkVEmkVubi4TJ04E4MgjjyQ+Pp4vvviCBx98kJKSEv7+978Hln3mmWcwxnDccceRn5/PSy+9xK233spdd90VuBz922+/zQMPPMCuu+7KqFGjyMvL4+WXX+bbb79l2rRpxMTEAPDLL78wefJkfD4fw4YNIzU1lczMTD799NNtGpZ7772Xjh07MmrUKH788UeWLl1KfHw8Z5xxRiv9lkSksdSwiEizWLhwIa7rcvfddxMXFwfAEUccwYwZM3j66af529/+Fli2sLCQe++9l6ioKAB69uzJvffey5tvvskxxxxDZWUlTz75JF27duXmm28ONDH9+vXjzjvv5KWXXuKUU04B4JFHHgFg6tSptfbQnH766dtk7NGjBxdddFGtHMuWLVPDItIGaA6LiDSZtZYPP/yQv/zlL1hryc/PD/y31157UVxczI8//hhY/pBDDgk0KwAHHHAASUlJfP755wD8+OOP5OXlceSRRwaaFYC9996bXXbZhc8++wyA/Px81qxZw+GHH77NcJIxZpucWzdNUN0AFRQUUFxc3PRfgoi0KO1hEZEmy8/Pp6ioiDfffJM333yzzmVqhnE6d+5c6zFjDGlpaWRlZQEE/p+enr7NetLT0/nmm28A2LhxIwBdu3atV84/NzWxsbEAFBUVER0dXa91iIg31LCISJNZawE4+OCDOfTQQ7e7TPfu3fntt99aM9Y2HGf7O5Vr8otI8FLDIiJNFh8fT1RUFK7rMmDAgDqXq2lYNmzYUOt+ay2ZmZl069YNgI4dOwKwfv169txzz1rLrl+/PvB4p06dAPj111+bpxARCVqawyIiTeY4Dvvvvz8ffvgh69at2+bxP58S/5133qGkpCRw+4MPPiAnJ4dBgwYB0KtXLxISEnjjjTeoqKgILPf555/z+++/s/feewPVjdLuu+/OsmXL2Lx5c63X0F4TkdCiPSwi0ixGjRrF119/zcSJExk2bBhdunShsLCQH3/8ka+++opHH300sGxsbCyTJ0/msMMOIy8vj5deeom0tDSGDRsGgM/n4/TTT+eBBx7gpptuYvDgweTm5vLKK6/QsWPHWodIn3322UyePJlrrrkmcFhzVlYWn332GXfddVer/x5EpGWoYRGRZpGYmMjtt99ORkYGH374Ia+99hpxcXF07dp1m0OMTzjhBH755Reee+45SkpK6N+/P+edd16tE7gddthhhIeH8/zzz/Pkk08SERHBvvvuyxlnnBGYvAvVhypPmTKFRYsW8cYbb1BeXk7Hjh058MADW612EWl5xmq/qYi0kpoz3V555ZUccMABXscRkTZEc1hEREQk6KlhERERkaCnhkVERESCnuawiIiISNDTHhYREREJempYREREJOipYREREZGgp4ZFREREgp4aFhEREQl6alhEREQk6KlhERERkaCnhkVERESC3v8DjgqP9oeyXpQAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAG0CAYAAADKEdZ4AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABZKUlEQVR4nO3deXgUZfb28e9T6axACEsghCUhAqLIIgo4KMjiMjLgNq7gOwqCO6IILgEVlDhCBFGBEQccjeKCKDgsMo6CiKKMIzgSEBERFUIgLE2AkJBO1ftHfrTGBCEhSXdX7s91cUlXqqvPSQW5qXq6j3Ecx0FEREQkxFmBLkBERESkMijUiIiIiCso1IiIiIgrKNSIiIiIKyjUiIiIiCso1IiIiIgrKNSIiIiIKyjUiIiIiCso1IiIiIgreAJdQHXbt28fPp+v0o8bHx9PTk5OpR83WKi/0Of2Ht3eH7i/R/UX+qqiR4/HQ7169U5s30p95RDg8/koLCys1GMaY/zHduPUCfUX+tzeo9v7A/f3qP5CXzD0qNtPIiIi4goKNSIiIuIKCjUiIiLiCgo1IiIi4go1bqGwiIhIdTl06BA+nw9jDIcPH+bIkSOBLqlKVbTHmJgYPJ6TjyQKNSIiIlWgoKAAYwx169YFIDw8vNLffRtsKtKjbdscOHCAWrVqnXSw0e0nERGRKlBQUEB0dHSgywh6lmVRp04d8vLyTv5YlVCPiIiIlOHoZ7fI77OsyokjCjUiIiLiCgo1IiIi4goKNSIiIuIKCjUiIiICQIMGDYiNjQ10GRWmUFMJ7Mw1OIXu/uwBERGRYKdQc5Kc7zdiPzOenffeiPPzD4EuR0REpMaq0KfcLF26lIULF+L1eklKSmLIkCG0atXquM/79NNPeeaZZzj77LO5//77/dsdx2Hu3Ll8+OGHHDp0iLZt2zJ06FCaNGni3+fgwYO8+OKLfPnllxhj6NatG4MHDyYqKqoiLVSew3lQqzaFP3wHE0ZiLhuEufhyjBUW2LpERCRoOI6DU5CPE4gP34uIrNBby49+cODRv2ePHDnC/v37KSoqAiAsLIy6desSEREBQFFREXl5eRQWFvqfGxkZiWVZFBUVceDAAQ4fPlx5fZWh3KFm1apVZGRkMGzYMFq3bs3ixYtJS0tj6tSp/k9NLMuuXbt45ZVXOO2000p97d133+W9997jzjvvpFGjRrz55pukpaUxZcoU/zfr2WefZd++fYwdO5aioiJmzJjBzJkzGTFiRHlbqFTmjM6EjZ9G+NxZ5K/+GOedl3H+txpryL2YRk2OfwAREXG/IwUU3HVNQF7amjYXIst/ASAuLg6Px8PevXuxbZvY2FgaNGjArl27APx/5+/evRvHcfB4PISFFf+DPjY2lvDwcP9zw8LCquUze8p9+2nRokX07duX3r1706xZM4YNG0ZERATLly8/5nNs2+a5557jmmuuoVGjRiW+5jgOS5Ys4corr6RLly4kJSVx1113sW/fPr744gsAtm3bxldffcVtt91G69atadu2LUOGDGHVqlXs3bu3zNcsLCwkLy/P/+vX6dAYU6m/rLj6NHx4MmGDR0BUNHy/EfuxETgfL62S1wvEL7f0UVP7qwk9ur2/mtCj2/oLZWFhYURHR+P1ejly5Ag+n499+/ZhWZb/yk1YWJj/a0VFRRQUFPhHJISFhVFYWEhhYSFFRUUcOXKEgoKC477uyX4fy3WlxufzsWXLFi6//HL/NsuyaN++PZs2bTrm8+bNm0dsbCx9+vThm2++KfG1Xbt24fV66dChg39bTEwMrVq1YtOmTZx77rls2rSJWrVqccopp/j3ad++PcYYNm/eTNeuXUu95vz585k3b57/ccuWLZk4cSLx8fHlablcEq/6f/h69GXv0+MoWLcG+5UZRG34ivojHiasQdW9bnVJSEgIdAlVyu39gft7dHt/4P4e3dTf4cOHCQ8PB8DxeGDm/MAUUo7bT8YYf3BxHAfA3wMU32KKjIykqKiI/Px86tSpQ3R0tD+0FBUVER4eTkFBAbGxsURERPi/5vP5fr/MiIgSy04qolyhJjc3F9u2iYuLK7E9Li6OrKysMp+zceNGli1bxqRJk8r8utfrBSh166pu3br+r3m93lJvMQsLC6N27dr+fX7riiuuoH///v7HR09oTk7Ocb+x5WWMISEhgezsbBzH4Ax/FOvDhdhvv0z+l6vIuu1qrBvuwOrao1Jft7qU7M8JdDmVzu39gft7dHt/4P4e3djfkSNHSgx3DI+MCsxAy3L8nec4DrZt+/+eLKveoqIi/1WYQ4cOERUVRWRkJPXq1ePgwYMcOHCAwsJCDh8+TGRkJJGRkcTFxXHo0CFyc3OP+dpHjhxhx44dpbZ7PJ4TviBRpVO6Dx8+zHPPPcett95a7e97Dw8PL5Euf62q/sA4jlN8bGMwF1yKdXon7Benwo+bsV+YhLP2M8yg2zC16lTJ61c1f38u5fb+wP09ur0/cH+Pbu8vVPh8PowxJaZuG2MICwsrcWHAtm3/Mo+jV20OHDjg/9rhw4c5fPgwR44cITY29ndDDZz838/lCjWxsbFYllXq6ojX6y119QZg586d5OTkMHHiRP+2owVfd911TJ061f+8/fv3U69ePf9++/fvJzk5GSi+EvTbb0RRUREHDx4s83WDhUlsgfXgJJwlc3EWz8X5YiXOpvVYNw3HnHFWoMsTEREpU1FREYcPHyYuLo79+/f7Fwrbtk1+fj5QnAmO3layLIvIyEh/4KlTp47/ao4xhqioqEq/S1KWcoUaj8dDSkoKmZmZ/nUstm2TmZnJH//4x1L7JyYm8tRTT5XY9sYbb5Cfn89NN91Ew4YNCQsLIy4ujnXr1vlDTF5eHps3b+aiiy4CoE2bNhw6dIgtW7aQkpICQGZmJo7jnNBbyQPJeDyYSwfitO+C/eIUyN6O/cx4zPl/xFw1GBOlsfQiIhJ8vF4vdevWpX79+kDx7aE9e/aU2Kdu3bqEhYVh2zYFBQXk5eUBxRcw6tSp4383VEFBAfv27avymst9+6l///5Mnz6dlJQUWrVqxZIlSygoKKBXr14ATJs2jfr16zNw4EAiIiJo0aJFiefXqlULoMT2fv368c4779CkSRMaNWrEG2+8Qb169ejSpQsAzZo1o1OnTsycOZNhw4bh8/l48cUX6d69u/+bHexMy9ZYY6fizM/A+XAhzoqlOBu+whpyD6bV6YEuT0REpERocRznmOtWoXid7W/vohxd9nHw4EEOHjxYJTX+nnKHmu7du5Obm8vcuXPxer0kJyeTmprqvw20e/fucr8F67LLLqOgoICZM2eSl5dH27ZtSU1N9X9GDcDdd9/N7NmzeeyxxzCm+MP3hgwZUt7yA8pERmKuG4bTsSv2S89ATjb2pFTMH6/ADBiIOcYaIBERETk+49SwFVk5OTmVvvrcGEOTJk3YsWPHCS9ycvIO4bzxAs5n//f5Ps2SsW6+F9OsZaXWVhkq0l8ocXt/4P4e3d4fuL9HN/aXm5tb4k0yv15061Yn0+Nvv1+/PuaJvvtJs58CxMTUwhpyL9btD0HtWNi2FXvCfdjvzcOxiwJdnoiISMhRqAkw0/kPWOOfg45dociH804G9qSHcHaVfq++iIiIHJtCTRAwsfWw7hyDuankmAX7o/dccxlWRKQm0v/DT4xt25VyHIWaIGGMwTq3L9a45+DU9lCQjzPnb9jPjsfx7jnu80VEJLhERkZW+VRqN7BtmwMHDhATE3PSx6rSTxSW8jMNGmGNfBxn2UKctzMgcw32o8MxN9yO1SU0xyyIiNREkZGRHDp0iP3792OM8c9BcrOK9lirVi08npOPJAo1QchYFuaCy3BOP9M/ZsF5IR177echPWZBRKSmOfrZbG58d9dvBUOPuv0UxI6OWTADrgPLwvliJfajw3Eyvwx0aSIiIkFHoSbIGY8H69KBWA+mQ0JT2L8X+5nx2K/MwMnXvVoREZGjFGpChGnZGuvhqZi+AwBwPl6K/dgInM0bAlyZiIhIcFCoCSEmIhLrumFYIx+H+g39Yxbsd17GcfmnVIqIiByPQk0IMqd1xHr0Ocwf+oBj47z3NvYT9+Fs+yHQpYmIiASMQk2IKh6zcI/GLIiIiPwfhZoQ5x+z0Knbb8YsZAW6NBERkWqlUOMCJrYe1h2pJccsjNeYBRERqVkUalyi1JiFIwUasyAiIjWKQo3LHB2zYK69GTzh/jEL9n8+DnRpIiIiVUqhxoWMZWFdcBnWw09DUivIO4jz96ewX0jHOXQg0OWJiIhUCYUaF9OYBRERqUkUalxOYxZERKSmUKipITRmQURE3E6hpgY55piFtzVmQUREQp9CTQ1UaszC0rex00bi/KwxCyIiEroUamqoUmMWtv+InaYxCyIiEroUamo4jVkQERG3UKgRjVkQERFXUKgR4DhjFvZpzIKIiAQ/hRopoawxC0WP3kXein8FujQREZHfpVAjpZQ1ZmHPpDEUzZykMQsiIhK0FGrkmH4Zs3A9WGG/jFlYpzELIiISfBRq5HcZj4ewywbSaPKLv4xZeFZjFkREJPgo1MgJiWzTjrBHntGYBRERCVoKNXLCyh6z8JDGLIiISFBQqJFyKzlmwdGYBRERCQoKNVIhJcYs1KmrMQsiIhJwCjVyUkznP2CN05gFEREJPIUaOWkmNk5jFkREJOAUaqRSaMyCiIgEmkKNVKqyxizY44Zj/+fjQJcmIiIup1Ajla6sMQvO35/CfiEd52BuoMsTERGXUqiRKvPLmIXrwLKKxyyMu1tjFkREpEoo1EiVMh4P1qUDsR5M15gFERGpUgo1Ui1My9ZYD0/VmAUREakyCjVSbTRmQUREqpJCjVQ7jVkQEZGqoFAjAeEfs3BHqsYsiIhIpfBU5ElLly5l4cKFeL1ekpKSGDJkCK1atSpz39WrVzN//nyys7MpKioiISGBAQMG0LNnT/8+Xq+XOXPm8PXXX3Po0CFOO+00hgwZQpMmTfz7jBs3jg0bSq6/uOCCC7jlllsq0oIECXPmOVintMV+ZTp8tRrnnQyc//0Ha8g9mEaJgS5PRERCSLlDzapVq8jIyGDYsGG0bt2axYsXk5aWxtSpU6lbt26p/WvXrs2VV15JYmIiHo+HNWvWMGPGDGJjY+nUqROO45Ceno7H42H06NHExMSwaNEiHn/8caZMmUJUVJT/WH379uXaa6/1P46IiKhg2xJMjo5ZcFYtw3njBf+YBXP1EMz5f8QYE+gSRUQkBJT79tOiRYvo27cvvXv3plmzZgwbNoyIiAiWL19e5v7t2rWja9euNGvWjISEBPr160dSUhIbN24EYMeOHXz33XcMHTqUVq1akZiYyNChQzly5AiffvppiWNFRkYSFxfn/xUTE1OBliUYHXPMwjPjNGZBREROSLmu1Ph8PrZs2cLll1/u32ZZFu3bt2fTpk3Hfb7jOGRmZpKVlcWgQYP8xwQIDw8vcczw8HA2btxI3759/dtXrlzJypUriYuL46yzzuLPf/4zkZGRZb5WYWEhhb96R40xhujoaP/vK9PR47n1ikJ19mcaNsbcNwHnw4XYb78M69dijxuOdcPtWF17Hv8AFXlNl58/cH+Pbu8P3N+j+gt9wdBjuUJNbm4utm0TFxdXYntcXBxZWVnHfF5eXh633norPp8Py7K4+eab6dChAwCJiYk0bNiQ1157jVtuuYWoqCgWLVrEnj178Hq9/mOcd955NGzYkPr16/Pjjz8yZ84csrKyGDVqVJmvOX/+fObNm+d/3LJlSyZOnEh8fHx5Wi6XhISEKjt2MKjW/v5yG4W9LmLP5Ecp3PwN9gvpRG78inq3P0BYbFyVvKTbzx+4v0e39wfu71H9hb5A9lihhcLlFRUVRXp6Ovn5+axbt46MjAwaN25Mu3bt8Hg8jBo1ir/97W8MGTLEf+XnzDPPxHEc/zEuuOAC/+9btGhBvXr1eOyxx8jOzi7zG3jFFVfQv39//+OjyTEnJ8d/daiyGGNISEggOzu7RM1uEbD+wqNxRj2BWTwXZ/GbHP743xz+35dYNw3Han92pb2M288fuL9Ht/cH7u9R/YW+qurR4/Gc8AWJcoWa2NhYLMsqcQUFit+99NurN79mWZY/eCQnJ7N9+3YWLFhAu3btAEhJSSE9PZ28vDx8Ph+xsbGkpqaSkpJyzGMefbfVsUJNeHh4iVtav1ZVP1CO47j2hxUC1F9YGNal1+O0Pxv7xachexv2M+Nxev4Rc/VgTFR0pb2U288fuL9Ht/cH7u9R/YW+QPZYroXCHo+HlJQUMjMz/dts2yYzM5M2bdqc8HFs2y6x3uWomJgYYmNj2bFjB99//z1dunQ55jG2bt0KQL169U68AQlZxWMWnsZccCmgMQsiIlJauW8/9e/fn+nTp5OSkkKrVq1YsmQJBQUF9OrVC4Bp06ZRv359Bg4cCBSvbTnllFNo3LgxhYWFrF27lpUrVzJ06FD/MT/77DNiY2Np2LAhP/30Ey+99BJdunShY8eOQPHVmE8++YTOnTtTu3ZtfvrpJ15++WVOO+00kpKSKuHbIKHARERirh2K06EL9kvP+McsmIuvxFw6EHOMK3MiIlIzlDvUdO/endzcXObOnYvX6yU5OZnU1FT/7afdu3eXWPlcUFDArFmz2LNnDxERETRt2pThw4fTvXt3/z779u0jIyMDr9dLvXr16NmzJ1ddddUvRXo8rFu3zh+gGjRoQLdu3bjyyitPonUJVUfHLDhv/B3ns2U4S9/GWfdfrJtHYpq3DHR5IiISIMZx+82938jJySnz1tfJMMbQpEkTduzY4cp7pcHcn7P28+JPIz6wH8I8mMsGYi6+AmOFnfAxgrm/yuL2Ht3eH7i/R/UX+qqqx/Dw8BNeKKzZTxLSzJnnYI17Djp1gyIfzjsZ2JMewtl17I8YEBERd1KokZB3dMyCGTwCoqL9Yxbsj95z7b+IRESkNIUacQVjDFZ3jVkQEanJFGrEVUyDRlgjH8dcezOER/jHLNj/+TjQpYmISBVTqBHXMZaFdcFlWA8/DUmtIO8gzt+fwn4hHedgbqDLExGRKqJQI65lmjTHenASZsB1YFk4X6zEHnc3zrovA12aiIhUAYUacTXj8WBdOhDrwXRIaAb792I/Ox77lek4+YcDXZ6IiFQihRqpEUqPWfiXxiyIiLiMQo3UGCYiEuvaoVgjH4f68f4xC0XzXsIpPBLo8kRE5CQp1EiNUzxm4VlM977gODhL32bnPX/B+fmHQJcmIiInQaFGaiQTUwtr8AisO1KhTl0Kt26maMJI7Pfm4dhFgS5PREQqQKFGajRz5jmEjZ9G9Dnna8yCiEiIU6iRGs/ExtFg7FNYg+/RmAURkRCmUCPC/41ZOFdjFkREQplCjciv/DJmYeivxizchb16RaBLExGR41CoEfmN4jELl/5qzMIhnFmTNWZBRCTIKdSIHMMvYxau15gFEZEQoFAj8juKxyxcj/WQxiyIiAQ7hRqRE2CSjzFm4TuNWRARCRYKNSInyD9m4b4Jv4xZSH8Ie95LOIWFgS5PRKTGU6gRKSfTtkPJMQv/egc7baTGLIiIBJhCjUgF/HbMAtt/xE67D3vJWzhFGrMgIhIICjUiJ8GceQ7WuOegU7fiMQvzX8FO15gFEZFAUKgROUkmNg7rjlTM4BEasyAiEkAKNSKVwBiD1V1jFkREAkmhRqQSacyCiEjgKNSIVLJjjlmYOUljFkREqpBCjUgVKTVm4b+fYI8bjrPuv4EuTUTElRRqRKpQ6TEL+7CffUxjFkREqoBCjUg10JgFEZGqp1AjUk00ZkFEpGop1IhUs2OOWfhpS6BLExEJaQo1IgFQ5piFJ0ZpzIKIyElQqBEJII1ZEBGpPAo1IgFWYsxCdMyvxiws0ZgFEZFyUKgRCQL+MQuPPvurMQvPa8yCiEg5KNSIBJHfG7OgqzYiIr9PoUYkyBxrzILzQrrGLIiI/A6FGpEgpTELIiLlo1AjEsQ0ZkFE5MQp1IiEAI1ZEBE5PoUakRChMQsiIr9PoUYkxGjMgohI2RRqREKQxiyIiJSmUCMSwn4Zs3BOyTELOzVmQURqHoUakRBXPGbhoZJjFh7TmAURqXk8FXnS0qVLWbhwIV6vl6SkJIYMGUKrVq3K3Hf16tXMnz+f7OxsioqKSEhIYMCAAfTs2dO/j9frZc6cOXz99dccOnSI0047jSFDhtCkSRP/PkeOHCEjI4NVq1ZRWFhIx44dGTp0KHFxcRVpQcRVjDGY7n1xTm2P/Y9n4Nt1OHOex/lqNdaNd2PqNwx0iSIiVa7cV2pWrVpFRkYGV111FRMnTiQpKYm0tDT2799f5v61a9fmyiuvZMKECaSnp9O7d29mzJjBV199BYDjOKSnp7Nr1y5Gjx7NpEmTiI+P5/HHHyc/P99/nJdffpkvv/ySkSNHMn78ePbt28fkyZMr1rWIS2nMgojUZOW+UrNo0SL69u1L7969ARg2bBhr1qxh+fLlXH755aX2b9euXYnH/fr1Y8WKFWzcuJFOnTqxY8cOvvvuOyZPnkzz5s0BGDp0KLfccguffvopffv2JS8vj2XLljFixAjOOOMMAO644w7uvfdeNm3aRJs2bUq9bmFhIYW/epurMYbo6Gj/7yvT0eNV9nGDhfoLLSYsDC68DKddZ4penAJbN2P//Sn2bPwfXDUYU6tOoEusdG47h2Vxe4/qL/QFQ4/lCjU+n48tW7aUCC+WZdG+fXs2bdp03Oc7jkNmZiZZWVkMGjTIf0yA8PDwEscMDw9n48aN9O3bly1btlBUVET79u39+zRt2pSGDRseM9TMnz+fefPm+R+3bNmSiRMnEh8fX56WyyUhIaHKjh0M1F+IadIEp+Or5M59kdzXZ3N45b+xMtdQf8TDRHc5L9DVVQnXncMyuL1H9Rf6AtljuUJNbm4utm2XWscSFxdHVtax322Rl5fHrbfeis/nw7Isbr75Zjp06ABAYmIiDRs25LXXXuOWW24hKiqKRYsWsWfPHrxeL1C85sbj8VCrVq0Sx61bt65/n9+64oor6N+/v//x0eSYk5PjD1KVxRhDQkIC2dnZrrzEr/5CXO8BhKWchvnHM/i2bWX3uHswPS/GuuZmTFR0oKurFK4/h7i/R/UX+qqqR4/Hc8IXJCq0ULi8oqKiSE9PJz8/n3Xr1pGRkUHjxo1p164dHo+HUaNG8be//Y0hQ4b4r/yceeaZJ/VNCQ8PL3H159eq6gfKcRzX/rCC+gtlJqkVjZ99lawZk3A++CfOx/+i6Jv/YQ2+B9P69ECXV2ncfA6PcnuP6i/0BbLHcoWa2NhYLMsqdXXE6/X+7ruQLMvyX45KTk5m+/btLFiwwL/eJiUlhfT0dPLy8vD5fMTGxpKamkpKSgpQfCXI5/Nx6NChEldr9u/fr3c/iZwgKzKKsOuGYXfsWvwOqf8bs2AuugJz2SDMMf4RICISKsr17iePx0NKSgqZmZn+bbZtk5mZWea6lmOxbbvEIt6jYmJiiI2NZceOHXz//fd06dIFKA49YWFhrFu3zr9vVlYWu3fvLtfriojGLIiIe5X79lP//v2ZPn06KSkptGrViiVLllBQUECvXr0AmDZtGvXr12fgwIFA8YLdU045hcaNG1NYWMjatWtZuXIlQ4cO9R/zs88+IzY2loYNG/LTTz/x0ksv0aVLFzp27AgUh50+ffqQkZFB7dq1iYmJ4cUXX6RNmzYKNSIVYGJqYQaPwOnUDfuV6f4xC+bS6zEXX1n8DioRkRBT7lDTvXt3cnNzmTt3Ll6vl+TkZFJTU/23gXbv3l3i7VwFBQXMmjWLPXv2EBERQdOmTRk+fDjdu3f377Nv3z4yMjLwer3Uq1ePnj17ctVVV5V43RtvvBFjDJMnT8bn8/k/fE9EKs6ceQ7WKW2xX5kBX32OM/8VnK+/KF5r0zgx0OWJiJSLcdy+Yuk3cnJyyrz1dTKMMTRp0oQdO3a4cgGY+gt9x+vRcRycz5bhvPF3OJwHEZGYqwdjzr8kJD5XQ+cw9Km/0FdVPYaHh5/wu580+0lEMMZgde+L9ehz0LYDHCnAmfM89jPjcPbtCXR5IiInRKFGRPxMg3isex/DXDdMYxZEJOQo1IhICcaysPoOwHr4aUhqBXmHcGZNxnkhHedgbqDLExE5JoUaESmTadIc68FJmAHXg2Xh/PcT7HHDcdb9N9CliYiUSaFGRI7JeDxYl16P9VA6JDSD/fuwn30M+5XpOPmHA12eiEgJCjUiclwmuTXWw09jLrgMAOfjf2E/NgLnuw0BrkxE5BcKNSJyQkxEJNa1N2PdNwHqx/vHLNjz/oFTyR+TICJSEQo1IlIupccszNeYBREJCgo1IlJuJqYW1uARWHemQp26/jEL9pK3cIqKAl2eiNRQCjUiUmGm0zlY456DTudAkQ9n/ivY6Q/h7MwKdGkiUgMp1IjISTGxcVh3PIQZPAKiY+D7jdiPjcBevkQf2Cci1UqhRkROWpljFl57HnuqxiyISPVRqBGRSlNqzMIGjVkQkeqjUCMileqXMQtTNWZBRKqVQo2IVAnTpFnxmIVLB5Ycs/D1F4EuTURcSqFGRKqM8XiwBlxXcszCc49rzIKIVAmFGhGpchqzICLVQaFGRKqFxiyISFVTqBGRauUfs3CuxiyISOVSqBGRamdiamHdVMaYhcVzNWZBRCpMoUZEAqbUmIUFr2rMgohUmEKNiATUL2MW7tGYBRE5KQo1IhJwxWMW+mjMgoicFIUaEQkaGrMgIidDoUZEgsoxxyzMnKQxCyLyuxRqRCQolRqz8OWnGrMgIr9LoUZEglaJMQtNmv8yZiFjGk5+XqDLE5Ego1AjIkHPJLfGGjvllzELK9/HHj8CZ9P6AFcmIsFEoUZEQkKpMQu7d2I/laoxCyLip1AjIiGlrDELRRPu5cj33wa6NBEJMIUaEQk5ZY1Z2DnyRuwV7wW6NBEJIIUaEQlZR8csmE7dwOfDfmUG9ivTdTtKpIZSqBGRkGZi47DuHEPdG+8EY3A+/hf25DE43r2BLk1EqplCjYiEPGMMsdcMxrr7EYiuVTw/Km0kzvcbA12aiFQjhRoRcQ2r/dlYYyYXf6aNd2/xu6NWvh/oskSkmijUiIirmMaJWKnpcOY54PPhZEzDnvM8jk/rbETcTqFGRFzHRMVg3fYg5rJBADgfLcGe/DBO7r4AVyYiVUmhRkRcyVgWVv9rse4aC9ExsHkD9uMjcX74LtCliUgVUagREVczHbtipT4FCU3Buwd70oPYn34Y6LJEpAoo1IiI65mEZlgPPQUdu4KvEOelZ7Df+DuOzxfo0kSkEinUiEiNYGJqYd2RihlwHQDOhwuxn34E58D+AFcmIpVFoUZEagxjWViXDsS6IxUio2FTJvaEkTg/fh/o0kSkEijUiEiNY848p/ht340SYW8O9sQHsD9fHuiyROQkKdSISI1kEltgjXkK2p8NhUdwZj+N/eZsnKKiQJcmIhWkUCMiNZaJqY111xhMv2sAcD54F3vqozgHcgNcmYhUhKciT1q6dCkLFy7E6/WSlJTEkCFDaNWqVZn7rl69mvnz55OdnU1RUREJCQkMGDCAnj17+vfJz89nzpw5fPHFFxw4cIBGjRpxySWXcNFFF/n3GTduHBs2bChx7AsuuIBbbrmlIi2IiABgrDDMFTfgtEjB/sdU2Pg1dtrI4kXFLVICXZ6IlEO5Q82qVavIyMhg2LBhtG7dmsWLF5OWlsbUqVOpW7duqf1r167NlVdeSWJiIh6PhzVr1jBjxgxiY2Pp1KkTAC+//DKZmZkMHz6c+Ph4vv76a2bNmkX9+vU5++yz/cfq27cv1157rf9xREREBVoWESnNnNUdK6Ep9vQ0yMnGnng/5sa7sbr2PP6TRSQolPv206JFi+jbty+9e/emWbNmDBs2jIiICJYvL3uRXbt27ejatSvNmjUjISGBfv36kZSUxMaNv0zP3bRpE+effz7t2rWjUaNGXHDBBSQlJbF58+YSx4qMjCQuLs7/KyYmprzli4gck2mahDVmCrQ7E44cwfn7U9jz/oFja52NSCgo15Uan8/Hli1buPzyy/3bLMuiffv2bNq06bjPdxyHzMxMsrKyGDRokH97mzZt+PLLL+nTpw/16tVj/fr17NixgxtvvLHE81euXMnKlSuJi4vjrLPO4s9//jORkZFlvlZhYSGFhb8MsDPGEB0d7f99ZTp6vMo+brBQf6HP7T1WZn+mdh3MiEex57+K8948nH/Nh59/wNxyP6Z2nZM+foXr0jkMaW7vD4Kjx3KFmtzcXGzbJi4ursT2uLg4srKyjvm8vLw8br31Vnw+H5ZlcfPNN9OhQwf/14cMGcLMmTO57bbbCAsLwxjDrbfeyumnn+7f57zzzqNhw4bUr1+fH3/8kTlz5pCVlcWoUaPKfM358+czb948/+OWLVsyceJE4uPjy9NyuSQkJFTZsYOB+gt9bu+xUvu760HyOp7F3qfH42z4Cp4cTYOHJxORXPb6weqicxja3N4fBLbHCi0ULq+oqCjS09PJz89n3bp1ZGRk0LhxY9q1awfAe++9x3fffcf9999PfHw833zzDbNnz6ZevXr+8HPBBRf4j9eiRQvq1avHY489RnZ2dpnfwCuuuIL+/fv7Hx9Njjk5Ofgq+aPRjTEkJCSQnZ2N4ziVeuxgoP5Cn9t7rLL+Wp2B9eAkiqanUZS9nZ333og15B6ss8+rvNc4QTqHoc3t/UHV9ejxeE74gkS5Qk1sbCyWZeH1ekts93q9pa7e/JplWf7gkZyczPbt21mwYAHt2rXjyJEjvP7664wePZrOnTsDkJSUxNatW1m4cGGJKzq/dvTdVscKNeHh4YSHh5f53Kr6gXIcx7U/rKD+3MDtPVZJf82SscZMxn4hHb75H/bzE3Eu2Yy5/AaMFVa5r3UCdA5Dm9v7g8D2WK6Fwh6Ph5SUFDIzM/3bbNsmMzOTNm3anPBxbNv2r3fx+XwUFRWVugdnWdbvflO2bt0KQL169crRgYhI+ZnasVgjxmEuugIA5723sZ97HOfQwQBXJiK/Vu53P/Xv358PP/yQjz76iG3btjFr1iwKCgro1asXANOmTeO1117z7z9//ny+/vprdu7cybZt21i4cCErV66kR48eAMTExHD66afz6quvsn79enbt2sVHH33EihUr6Nq1K1B8NWbevHls2bKFXbt28d///pfp06dz2mmnkZSUVAnfBhGR32fCwrCuHowZeh9EREDmGuy0kTjbfwp0aSLyf8q9pqZ79+7k5uYyd+5cvF4vycnJpKam+m8/7d69u8RVl4KCAmbNmsWePXuIiIigadOmDB8+nO7du/v3ueeee3jttdd49tlnOXjwIPHx8Vx//fVceOGFxUV6PKxbt44lS5ZQUFBAgwYN6NatG1deeeVJti8iUj5Wt/NxmjTDnvHX4s+z+etorCEjMJ27H//JIlKljOP2m3u/kZOTU+Kt3pXBGEOTJk3YsWOHK++Vqr/Q5/YeA9GfcyAXe+ZE+HZdcQ1/ugZz6UCMVTXTZ3QOQ5vb+4Oq6zE8PPyEFwpr9pOISAWYOrFY9z6GueBSAJzFc7Gnp+HkHQpwZSI1l0KNiEgFmbAwrGuHYobcC55w+PoL7CdG4ez4OdClidRICjUiIifJ+kNvrAeehHoNYef24mDz1epAlyVS4yjUiIhUApPcGmvsFGjTDvIPY09Pw/7n6zi2HejSRGoMhRoRkUpiYuOw7n0c0/tPADgLX8f+219xDucFuDKRmkGhRkSkEhmPB2vgrZib7gaPB75aXXw7Knt7oEsTcT2FGhGRKmCdewHW/U9CXAPI3ob9xH04X38R6LJEXE2hRkSkipiWbYrX2bQ6HQ7nYU+bgL3oTa2zEakiCjUiIlXI1K2Hdd/jmF6XgOPgvDsHe+ZEnHytsxGpbAo1IiJVzHjCsQbdjvl/d0KYB9Z8hv3EaJxdWYEuTcRVFGpERKqJ1fNirNFPQN36sONn7LT7cDK/DHRZIq6hUCMiUo3MKW2xxk6GU9pC3iHsZx/Dfm+ea+cBiVQnhRoRkWpm4hpg3ZeG6XFR8TqbdzJwXkjHKcgPdGkiIU2hRkQkAEx4ONZf7sLccAeEeXD++wn2X0fj5GQHujSRkKVQIyISQNb5f8QaNQFi42D7j9gTRuJsWBvoskRCkkKNiEiAmVanY419Glq2gbyD2FPHY/9rvtbZiJSTQo2ISBAw9RpgjX4Cc25fcGycef/AmTUZp6Ag0KWJhAyFGhGRIGHCIzA33o0ZeCuEheH852Psiffj7N4Z6NJEQoJCjYhIEDHGYPX+E9bIx6FOXfj5B+y0kdjf/C/QpYkEPYUaEZEgZNqcUTw3KqkVHDyA/fQjHFjwmtbZiPwOhRoRkSBl6sdj3f9XzB96g23j/fsU7NlTcI5onY1IWRRqRESCmImIxAy+B+u6YWCF4Xz+EfbEB3H25AS6NJGgo1AjIhLkjDFYF1xK/ITpULsO/PQ9dtpInG8zA12aSFBRqBERCRFRHc8mbOzT0LwlHNiPPWUs9oeLtM5G5P8o1IiIhBDTsDHWA5MwXc8H28Z54wWcl57FKTwS6NJEAk6hRkQkxJjISMzQkZirB4OxcFZ9iD3pIZy9uwNdmkhAKdSIiIQgYwzWRVdg3TMOatWBrd9hT7gX57sNgS5NJGAUakREQpg5vRPWmMnQLLl4nc3kMdgfLdE6G6mRFGpEREKciU/AenASpksPKCrCmfM8TsY0nMLCQJcmUq0UakREXMBERmGGjcL8+UYwBueTf2M/lYrj3RPo0kSqjUKNiIhLGGOw/vhnrLsfhZhasOVb7AkjcTZ/E+jSRKqFQo2IiMuYMzoXr7NJbAH792E/NQb7438FuiyRKqdQIyLiQqZRItZD6dC5OxT5cF6Zjv3KDByf1tmIeynUiIi4lImKxrrtAczlNxSvs/l4KfbksTj79wW6NJEqoVAjIuJixhisP12DNfxhiK4Fm78p/jybLd8GujSRSqdQIyJSA5j2Zxevs2nSHLx7sdMfwv7k34EuS6RSKdSIiNQQpnEiVmo6dDoHfD6cl5/Dfu15HJ8v0KWJVAqFGhGRGsRExWDd/iDm0oEAOMuXYE8Zi5OrdTYS+hRqRERqGGNZWAOuw7pzDERFw3cbsCfch7P1u0CXJnJSFGpERGoo06kbVupkSGgK+3ZjT3wQe9WyQJclUmEKNSIiNZhp0gzroaegQxfwFeL8Yyr2G3/XOhsJSQo1IiI1nImphXXnGEz/6wBwPlyIPfVRnAP7A1yZSPko1IiISPE6m8sGYt2RCpHR8O264rlRP34f6NJETphCjYiI+Jkzzyl+23ejJrA3B3viA9iffxToskROiEKNiIiUYBJbFH9Q3xlnQeERnNlTsOfOxikqCnRpIr9LoUZEREoxMbWxho/F9LsaAOff72I/Mw7nYG6AKxM5Nk9FnrR06VIWLlyI1+slKSmJIUOG0KpVqzL3Xb16NfPnzyc7O5uioiISEhIYMGAAPXv29O+Tn5/PnDlz+OKLLzhw4ACNGjXikksu4aKLLvLvc+TIETIyMli1ahWFhYV07NiRoUOHEhcXV5EWRETkOIwVhrni/+G0SMH+xzPwzf+wJ4wsXlTcvGWgyxMppdyhZtWqVWRkZDBs2DBat27N4sWLSUtLY+rUqdStW7fU/rVr1+bKK68kMTERj8fDmjVrmDFjBrGxsXTq1AmAl19+mczMTIYPH058fDxff/01s2bNon79+px99tn+fdasWcPIkSOJiYlh9uzZTJ48mccff/zkvgMiIvK7zFnnYiU0w56eBjnZ2E+Oxtw0AqtLj0CXJlJCuW8/LVq0iL59+9K7d2+aNWvGsGHDiIiIYPny5WXu365dO7p27UqzZs1ISEigX79+JCUlsXHjRv8+mzZt4vzzz6ddu3Y0atSICy64gKSkJDZv3gxAXl4ey5Yt48Ybb+SMM84gJSWFO+64g2+//ZZNmzZVsHURETlRpmlS8Tqb08+EI0dwXkjHnvcSjq11NhI8ynWlxufzsWXLFi6//HL/NsuyaN++/QmFC8dxyMzMJCsri0GDBvm3t2nThi+//JI+ffpQr1491q9fz44dO7jxxhsB2LJlC0VFRbRv397/nKZNm9KwYUM2bdpEmzZtSr1WYWEhhYWF/sfGGKKjo/2/r0xHj1fZxw0W6i/0ub1Ht/cHwdGjqR2LuedR7HdewVn6Ns6/3oFtP2CGjcbUrnNyxw6C/qqS2/uD4OixXKEmNzcX27ZLrWOJi4sjKyvrmM/Ly8vj1ltvxefzYVkWN998Mx06dPB/fciQIcycOZPbbruNsLAwjDHceuutnH766QB4vV48Hg+1atUqcdy6devi9XrLfM358+czb948/+OWLVsyceJE4uPjy9NyuSQkJFTZsYOB+gt9bu/R7f1BkPQ4/CHyOp7F3qnjcdavhSdH0+DhyUQkl722sjyCor8q5Pb+ILA9VmihcHlFRUWRnp5Ofn4+69atIyMjg8aNG9OuXTsA3nvvPb777jvuv/9+4uPj+eabb5g9ezb16tUrEX7K44orrqB///7+x0eTY05ODr5K/vhvYwwJCQlkZ2fjOE6lHjsYqL/Q5/Ye3d4fBGGPrdtjPZhO0fQJFGVvZ+fIm7AG34N19rkVOlzQ9VfJ3N4fVF2PHo/nhC9IlCvUxMbGYllWqasjXq/3d9+FZFmWP7klJyezfft2FixYQLt27Thy5Aivv/46o0ePpnPnzgAkJSWxdetWFi5cSIcOHYiLi8Pn83Ho0KESV2v2799/zNcNDw8nPDy8zK9V1Q+U4ziu/WEF9ecGbu/R7f1BkPXYLBlrzBTsF9KL3xn1/JM4/a7GXDYQY4VV6JBB1V8VcHt/ENgey7VQ2OPxkJKSQmZmpn+bbdtkZmaWua7lWGzb9q938fl8FBUVlboHZ1mW/5uSkpJCWFgY69at8389KyuL3bt3l+t1RUSkcpnasVgjxmEuuhwAZ8lb2M9NwMk7GNjCpEYq9+2n/v37M336dFJSUmjVqhVLliyhoKCAXr16ATBt2jTq16/PwIEDgeK1LaeccgqNGzemsLCQtWvXsnLlSoYOHQpATEwMp59+Oq+++ioRERHEx8ezYcMGVqxY4V8oHBMTQ58+fcjIyKB27drExMTw4osv0qZNG4UaEZEAM2FhmKuHYLc4Befl5yDzS+y0UVh3pmISWwS6PKlByh1qunfvTm5uLnPnzsXr9ZKcnExqaqr/NtDu3btLXHUpKChg1qxZ7Nmzh4iICJo2bcrw4cPp3r27f5977rmH1157jWeffZaDBw8SHx/P9ddfz4UXXujf58Ybb8QYw+TJk/H5fP4P3xMRkeBgdTsfJ6EZ9ownYFcW9hOjsYbcg+n8h0CXJjWEcdx+c+83cnJySrzVuzIYY2jSpAk7duxw5b1S9Rf63N6j2/uD0OrRObAfe+Yk+LZ4yYDpfy1mwPUY69grHkKpv4pwe39QdT2Gh4ef8EJhzX4SEZFKZerUxbpnPKbvAACcRW9iT0/DyTsU4MrE7RRqRESk0hmPB+u6YZjB94AnHL7+Avuvo3B2bAt0aeJiCjUiIlJlrO59sB54Euo1hOzt2E/ch/O//wS6LHEphRoREalSJrk11tjJ0Pp0yD+MPW0C9sI3cGw70KWJyyjUiIhIlTOx9bBGTsD0/hMAzj9fw/7bkziH8wJcmbiJQo2IiFQL4/FgDbwVc9Pd4PHAV59j/3U0Tvb2QJcmLqFQIyIi1co69wKs0X+FuPqw42fsJ0Zhf/1FoMsSF1CoERGRamdSTsUa+zSc0hYOH8J+7nFy35jt2s9wkeqhUCMiIgFh6tbDGpWGOf+P4Djsf+VvxUMx8w8HujQJUQo1IiISMMYTjnXDHVh/uQs8HpwvVxWvs9m1I9ClSQhSqBERkYCzel5Mo7/OhLr1IOsn7LSROJlrAl2WhBiFGhERCQqRp3ck7OGnIeVUyDuE/exj2O+9rXU2csIUakREJGiYuAZYo57A9LgIHBvnnZdxXkjHKcgPdGkSAhRqREQkqJjwcMz/uxMz6HYIC8P57yfYT96Pk5Md6NIkyCnUiIhI0DHGYPW6BOu+NIiNg21bsdPuw9nwVaBLkyCmUCMiIkHLtD4da8wUSG4Nhw5gTx2H/f58rbORMinUiIhIUDP1G2Ld/1dM977F62ze+gfOrCk4BQWBLk2CjEKNiIgEPRMegbnpbsz1t4Bl4fxnBfbE+3H27Ap0aRJEFGpERCQkGGOw+vTHGjkB6tSFn3/AnjASZ+PXgS5NgoRCjYiIhBRz6hnF62ySWsHBXOynH8H+4F2tsxGFGhERCT2mQXzxOptzeoNt47w5G+fFqThHtM6mJlOoERGRkGQiIjFD7sFcO7R4nc3ny7EnPYSzJyfQpUmAKNSIiEjIMsZgXXAp1j3joXYd+HFz8dyoTZmBLk0CQKFGRERCnjmtY/E6m+Yt4cB+7CkPYy9bpHU2NYxCjYiIuIJp2BjrgUmYrj2hqAjn9RdwXn4Wp/BIoEuTaqJQIyIirmEiIzFD78NcPRiMhfPph9jpqTh7dwe6NKkGCjUiIuIqxhisi67AuudRqFUHfthUvM7muw2BLk2qmEKNiIi4kjn9TKwxk6FpEuR6sSePwf7oPa2zcTGFGhERcS0Tn4D1UDrm7POK19nM+RvOK9NxCgsDXZpUAYUaERFxNRMZhbllNObKG8EYnJXvYz+ViuPdE+jSpJIp1IiIiOsZY7Au+TPW3Y9ATC3Y8i32hPtwvt8Y6NKkEinUiIhIjWHOOKt4nU1iC9i/Fzs9FXvl+4EuSyqJQo2IiNQoplEi1kOToPMfoMiHkzEN+9UZOD6tswl1CjUiIlLjmKgYrNsexFx+Q/E6mxVLsSePxdm/L9ClyUlQqBERkRrJGIP1p2uw7hoL0bVg8zfYE0bi/LAp0KVJBSnUiIhIjWY6dMFKfQqaNAfvHuxJD2J/+kGgy5IKUKgREZEazyQ0xXooHTp1A58P56VnsV+biePzBbo0KQeFGhEREcBEx2Dd/hBmwPUAOMsXYz/9ME6uN7CFyQlTqBEREfk/xrKwLr0e684xEBUNm9YXz436cXOgS5MToFAjIiLyG6ZTN6zUydC4Kezdjf3kA9irlgW6LDkOhRoREZEymCbNihcQd+gCvkKcf0zFfuPvWmcTxBRqREREjsHE1MK6cwym/7UAOB8uxJ76KM6B/QGuTMqiUCMiIvI7jGVhXTYI6/aHIDIavl1X/Hk2P30f6NLkNxRqREREToDp/Ifit303agJ7c7AnPoC9ekWgy5JfUagRERE5QaZpi+IFxGecBUeO4MyajP3WizhFRYEuTVCoERERKRdTqzbW8LGYS64CwHl/AfYz43AO5ga4MvFU5ElLly5l4cKFeL1ekpKSGDJkCK1atSpz39WrVzN//nyys7MpKioiISGBAQMG0LNnT/8+11xzTZnPveGGG7j00ksBuPPOO8nJySnx9YEDB3L55ZdXpAUREZEKM1YY5sq/4LRIwf7HM/DN/7DT7sO6IxXTvGWgy6uxyh1qVq1aRUZGBsOGDaN169YsXryYtLQ0pk6dSt26dUvtX7t2ba688koSExPxeDysWbOGGTNmEBsbS6dOnQB44YUXSjxn7dq1PP/883Tr1q3E9muuuYYLLrjA/zgqKqq85YuIiFQac/Z5WAnNsGc8ATnZ2E/ej7lpBFaX8wJdWo1U7lCzaNEi+vbtS+/evQEYNmwYa9asYfny5WVeNWnXrl2Jx/369WPFihVs3LjRH2ri4uJK7PPFF1/Qrl07GjduXGJ7dHR0qX2PpbCwkMLCQv9jYwzR0dH+31emo8er7OMGC/UX+tzeo9v7A/f3GMr9meYtMWOmYP89HWf9WpwXJmH/9D3Wlf8PY4UV7xPC/Z2oYOixXKHG5/OxZcuWEuHFsizat2/Ppk3HH9XuOA6ZmZlkZWUxaNCgMvfxer2sXbuWO++8s9TXFixYwNtvv03Dhg0577zz+NOf/kRYWFiZx5k/fz7z5s3zP27ZsiUTJ04kPj7+uHVWVEJCQpUdOxiov9Dn9h7d3h+4v8fQ7a8Jzl+fZ//L0znwdgbO0rcJ35VF/fsnEFbnl7sYodvfiQtkj+UKNbm5udi2XepqSVxcHFlZWcd8Xl5eHrfeeis+nw/Lsrj55pvp0KFDmfuuWLGCqKgounbtWmL7JZdcQsuWLalduzbffvstr7/+Ovv27ePGG28s8zhXXHEF/fv39z8+mhxzcnLwVfKnQRpjSEhIIDs7G8dxKvXYwUD9hT639+j2/sD9Pbqmv0uuxmrQGPulZ8hf8xlZw28g7K4xWM2S3dHf76iqc+jxeE74gkSFFgqXV1RUFOnp6eTn57Nu3ToyMjJo3LhxqVtTAMuXL6dHjx5ERESU2P7rgJKUlITH4+Hvf/87AwcOJDw8vNRxwsPDy9wOVNkPlOM4rv1hBfXnBm7v0e39gft7dEN/pksPrMZN/2+dzQ6KnhiFM+Qe6H+VK/o7nkD2WK63dMfGxmJZFl6vt8R2r9f7u2tdLMsiISGB5ORkBgwYwDnnnMOCBQtK7ffNN9+QlZVFnz59jltL69atKSoqKvWOKBERkUAzLVKwxkyBth2gIB/7b0+yP2MGjq3Ps6lK5Qo1Ho+HlJQUMjMz/dts2yYzM5M2bdqc8HFs2y6xiPeoZcuWkZKSQnJy8nGPsXXrVowxxMbGnvDrioiIVBdTJxbrnvGYCy8DIPfNF7Gfm4CTdzDAlblXuT98r3///nz44Yd89NFHbNu2jVmzZlFQUECvXr0AmDZtGq+99pp///nz5/P111+zc+dOtm3bxsKFC1m5ciU9evQocdy8vDw+//zzMq/SbNq0icWLF7N161Z27tzJypUrefnll+nRowe1a9cubwsiIiLVwoSFYV1zM9bQ+zARkTjr/oudNgon66dAl+ZK5V5T0717d3Jzc5k7dy5er5fk5GRSU1P9t592795d4u1cBQUFzJo1iz179hAREUHTpk0ZPnw43bt3L3HcVatW4TgO551X+r39Ho+HVatW8dZbb1FYWEijRo3405/+VGKdjYiISLCyzulFg/ZnsnP8vbArC/uJ0Vg334s585xAl+YqxnH7iqXfyMnJKfPW18kwxtCkSRN27NjhygVg6i/0ub1Ht/cH7u+xpvSXtWkjRc9PhG/XFW/vfx1mwHUYK/SnFlXVOQwPDz/hdz+F/ndRREQkRJg6dYvX2fQdAICz6A3sGU/gHM4LcGXuoFAjIiJSjYzHg3XdMMzgEeAJh//9B/uJUTjZ2wJdWshTqBEREQkAq3tfrPufhHoNIXtbcbD5338CXVZIU6gREREJENOyNdbYydD6dDichz1tAvaiN3BsO9ClhSSFGhERkQAysfWwRj6O6d0PAOfd17D/9iROvtbZlJdCjYiISIAZTzjWwNswNw4Hjwe++hz7idE4O489V1FKU6gREREJEtZ5F2KN/ivE1YcdP2On3Yez7r+BLitkKNSIiIgEEZNyavHcqFPawuFD2M89jr3kLVd+fk9lU6gREREJMiauPtaoNEzPP4Lj4Mx/BXvmRJz8w4EuLagp1IiIiAQh4wnH+n93YP7fHRDmgS9XYT95P86uHYEuLWgp1IiIiAQxq+cfsUalQd16sP3H4nU2mWsCXVZQUqgREREJcqbVaVhjp0DLNpB3EPvZx7CXvq11Nr+hUCMiIhICTFwDrNF/xZx3ITg2ztsv4/z9KZyC/ECXFjQUakREREKECQ/H/OUuzKDbICwM54uVxetscrIDXVpQUKgREREJIcYYrF79sEZOgDp1YdvW4nU23/wv0KUFnEKNiIhICDJt2hWvs0lqBYcOYD/9KPb7C2r0OhuFGhERkRBl6sdjPfAk5g99itfZvPUizuwpOAUFgS4tIBRqREREQpgJj8AMHoG57hawLJzVK7AnPYCzZ1egS6t2CjUiIiIhzhiD1bc/1sjHoXYs/LQFe8JInI1fB7q0aqVQIyIi4hLm1PZYY5+GFilwMBf76UewP/hnjVlno1AjIiLiIqZBPNYDEzHn9ALbxnlzFs4/puIccf86G4UaERERlzERkZgh92Kuubl4nc1ny7EnPYSzNyfQpVUphRoREREXMsZgXXgZ1j3joXYd+HFz8TqbTZmBLq3KKNSIiIi4mDmtI9aYKdCsJRzYjz3lYezli125zkahRkRExOVMw8ZYD07CdOkBRUU4r83Eefk5nMIjgS6tUinUiIiI1AAmMhIzbBTmqsFgLJxPP8BOT8XZtyfQpVUahRoREZEawhiDdfEVWCMehZja8MMm7An34mzeEOjSKoVCjYiISA1j2p2JNWYyNE2CXC/2U2OxVywNdFknTaFGRESkBjKNmmA9OAnO6g5FPpxXZ2C/Mh2nsDDQpVWYQo2IiEgNZaKisW59AHPlX8AYnI//hT15DI53b6BLqxCFGhERkRrMGIN1yVVYwx+BmFrw/cbiz7P5fmOgSys3hRoRERHBtD+reJ1NYgvYvxf7qVTsle8HuqxyUagRERERAEyjRKyHJkHnP4DPh5MxDXvO33B8obHORqFGRERE/ExUTPE6m8sGFa+z+eg97MkP4+zfF+jSjkuhRkREREowloXV/1qsO8dCdAxs3lC8zuaH7wJd2u9SqBEREZEymY5dsFKfgoRm4N2DPelB7E8/DHRZx6RQIyIiIsdkEpoVB5uOXcFXiPPSM9ivv4Dj8wW6tFIUakREROR3megYrDtSMQOuB8BZtgj76Udwcr2BLew3FGpERETkuIxlYV16PdadqRAVDZsysdNG4vy4OdCl+SnUiIiIyAkznc4pvh3VuCns3Y098UHsz5YHuixAoUZERETKyTRpXhxs2p8NhUdwXnyaojf+jlMU2HU2CjUiIiJSbiamFtZdYzF/ugYA54N/kvPw8IB+UJ9CjYiIiFSIsSysy2/Auv1BiIwiIuVUjCc8YPV4AvbKIiIi4gqmc3fCmrWkbvuOHN6VE7A6dKVGRERETpppnIgJC+y1kgq9+tKlS1m4cCFer5ekpCSGDBlCq1atytx39erVzJ8/n+zsbIqKikhISGDAgAH07NnTv88111xT5nNvuOEGLr30UgAOHjzIiy++yJdffokxhm7dujF48GCioqIq0oKIiIi4TLlDzapVq8jIyGDYsGG0bt2axYsXk5aWxtSpU6lbt26p/WvXrs2VV15JYmIiHo+HNWvWMGPGDGJjY+nUqRMAL7zwQonnrF27lueff55u3br5tz377LPs27ePsWPHUlRUxIwZM5g5cyYjRowobwsiIiLiQuW+/bRo0SL69u1L7969adasGcOGDSMiIoLly8t+j3q7du3o2rUrzZo1IyEhgX79+pGUlMTGjRv9+8TFxZX49cUXX9CuXTsaN24MwLZt2/jqq6+47bbbaN26NW3btmXIkCGsWrWKvXv3VrB1ERERcZNyXanx+Xxs2bKFyy+/3L/Nsizat2/Ppk2bjvt8x3HIzMwkKyuLQYMGlbmP1+tl7dq13Hnnnf5tmzZtolatWpxyyin+be3bt8cYw+bNm+natWup4xQWFlJY+MvbyowxREdH+39fmY4er7KPGyzUX+hze49u7w/c36P6C33B0GO5Qk1ubi62bRMXF1die1xcHFlZWcd8Xl5eHrfeeis+nw/Lsrj55pvp0KFDmfuuWLGCqKioEkHF6/USGxtbYr+wsDBq166N1+st8zjz589n3rx5/sctW7Zk4sSJxMfHH6fLiktISKiyYwcD9Rf63N6j2/sD9/eo/kJfIHuslmXKUVFRpKenk5+fz7p168jIyKBx48a0a9eu1L7Lly+nR48eREREnNRrXnHFFfTv39//+GhyzMnJwVfJk0WNMSQkJJCdnY3jOJV67GCg/kKf23t0e3/g/h7VX+irqh49Hs8JX5AoV6iJjY3FsqxSV0e8Xm+pqze/ZlmWP7klJyezfft2FixYUCrUfPPNN2RlZXHPPfeU2B4XF0dubm6JbUVFRRw8ePCYrxseHk54eNkfAFRVP1CO47j2hxXUnxu4vUe39wfu71H9hb5A9liuhcIej4eUlBQyMzP922zbJjMzkzZt2pzwcWzbLrHe5ahly5aRkpJCcnJyie1t2rTh0KFDbNmyxb8tMzMTx3GO+VZyERERqVnK/e6n/v378+GHH/LRRx+xbds2Zs2aRUFBAb169QJg2rRpvPbaa/7958+fz9dff83OnTvZtm0bCxcuZOXKlfTo0aPEcfPy8vj888/p06dPqdds1qwZnTp1YubMmWzevJmNGzfy4osv0r17d+rXr1/eFkRERMSFyr2mpnv37uTm5jJ37ly8Xi/Jycmkpqb6bwPt3r27xMrngoICZs2axZ49e4iIiKBp06YMHz6c7t27lzjuqlWrcByH8847r8zXvfvuu5k9ezaPPfaY/8P3hgwZUt7yRURExKWM4/abe7+Rk5NT5q2vk2GMoUmTJuzYscOV90rVX+hze49u7w/c36P6C31V1WN4ePgJLxTW7CcRERFxBYUaERERcYXAjtMMAI+n6lquymMHA/UX+tzeo9v7A/f3qP5CX2X3WJ7j1bg1NSIiIuJOuv1UCQ4fPswDDzzA4cOHA11KlVB/oc/tPbq9P3B/j+ov9AVDjwo1lcBxHH744QfXrmhXf6HP7T26vT9wf4/qL/QFQ48KNSIiIuIKCjUiIiLiCgo1lSA8PJyrrrrqmAM0Q536C31u79Ht/YH7e1R/oS8YetS7n0RERMQVdKVGREREXEGhRkRERFxBoUZERERcQaFGREREXMH9QyjKacOGDfzzn//khx9+YN++fYwaNYquXbv+7nPWr19PRkYGP//8Mw0aNODPf/4zvXr1KrHP0qVLWbhwIV6vl6SkJIYMGUKrVq2qsJOylbe/1atX8/7777N161Z8Ph/NmjXj6quvplOnTv595s6dy7x580o8LzExkalTp1ZRF7+vvD2uX7+e8ePHl9r+wgsvEBcX538cqudw+vTprFixotT2Zs2aMWXKFCC4zuH8+fP5z3/+w/bt24mIiKBNmzbccMMNJCYm/u7zPvvsM958801ycnJISEhg0KBBdO7c2f91x3GYO3cuH374IYcOHaJt27YMHTqUJk2aVHVLJVSkvw8++ICPP/6Yn3/+GYCUlBSuv/76Ej9/ZZ3njh07MmbMmKpp5HdUpMePPvqIGTNmlNgWHh7OnDlz/I9D+RyOGzeODRs2lNp+5pln8tBDDwHBcw7ff/993n//fXJycoDi/1dcddVVnHnmmcd8TrD8+VOo+Y2CggKSk5Pp06cPTz311HH337VrF08++SQXXnghw4cPJzMzk+eff564uDj/X/yrVq0iIyODYcOG0bp1axYvXkxaWhpTp06lbt26VdxRSeXt75tvvqFDhw5cf/311KpVi+XLlzNx4kSeeOIJWrZs6d+vefPmPPzww/7HlhW4i4Dl7fGoqVOnEhMT438cGxvr/30on8PBgwczaNAg/+OioiJGjx7NOeecU2K/YDmHGzZs4OKLL+aUU06hqKiI119/nQkTJjBlyhSioqLKfM63337LM888w8CBA+ncuTOffPIJ6enpTJw4kRYtWgDw7rvv8t5773HnnXfSqFEj3nzzTdLS0pgyZQoRERFB3d+GDRs499xzOfXUUwkPD+fdd9/1P6d+/fr+/Tp16sQdd9zhfxyo4YkV6REgOjqaZ5555phfD+VzOGrUKHw+n//xgQMHGD16NH/4wx9K7BcM57B+/foMHDiQJk2a4DgOK1asYNKkSUyaNInmzZuX2j+o/vw5ckxXX321s3r16t/d55VXXnFGjhxZYtvTTz/tTJgwwf/4oYcecmbNmuV/XFRU5Nxyyy3O/PnzK7Xe8jqR/spy7733Om+99Zb/8ZtvvumMGjWqMkurNCfSY2ZmpnP11Vc7Bw8ePOY+bjqHq1evdq655hpn165d/m3BfA7379/vXH311c769euPuc+UKVOcv/71ryW2paamOjNnznQcx3Fs23aGDRvmvPvuu/6vHzp0yBk4cKDzySefVE3hJ+hE+vutoqIi5y9/+Yvz0Ucf+bdNmzbNmThxYlWUeNJOpMfly5c7N9544zG/7rZzuGjRIucvf/mLc/jwYf+2YD6HN910k/Phhx+W+bVg+vOnKzUn6bvvvqN9+/YltnXs2JGXXnoJAJ/Px5YtW7j88sv9X7csi/bt27Np06ZqrLRy2LbN4cOHqV27dont2dnZ3HrrrYSHh9OmTRsGDhxIw4YNA1Rlxdx///0UFhbSvHlzrr76atq2bQu47xwuW7aM9u3bEx8fX2J7sJ7DvLw8gFI/c7+2adMm+vfvX2Jbx44d+eKLL4DiK6per5cOHTr4vx4TE0OrVq3YtGkT5557bhVUfmJOpL/fKigowOfzlXrOhg0bGDp0KLVq1eKMM87guuuuo06dOpVab0WcaI/5+fnccccdOI5Dy5Ytuf766/1XBtx2DpctW0b37t1LXdkJtnNo2zafffYZBQUFtGnTpsx9gunPn0LNSfJ6vaVuP9StW5fDhw9z5MgRDh48iG3bJdZmAMTFxZGVlVWNlVaOhQsXkp+fX+KSaevWrbnjjjtITExk3759zJs3j0ceeYTJkycTHR0dwGpPTL169Rg2bBinnHIKhYWFfPjhh4wfP560tDRSUlLIzc11zTncu3cvX331FXfffXeJ7cF6Dm3b5qWXXuLUU0/1X8Yuy7H+HHq9Xv/Xj2471j6BcKL9/dacOXOoX79+iX9QderUiW7dutGoUSOys7N5/fXXeeKJJ0hLSwvo7eAT7TExMZHbb7+dpKQk8vLy+Oc//8nYsWOZMmUKDRo0cNU53Lx5Mz///DO33357ie3BdA5/+uknxowZQ2FhIVFRUYwaNYpmzZqVuW8w/flTqJET9sknnzBv3jxGjx5d4ofz14vHkpKS/H9BfvbZZ/Tp0ycQpZZLYmJiiQV+p556Kjt37mTx4sUMHz48gJVVvhUrVlCrVq1SC4uD9RzOnj2bn3/+mcceeyxgNVSlivS3YMECPv30U8aNG1diLcKv/7XbokULkpKSGD58OOvXry91Nbk6nWiPbdq0KXEloE2bNtx77738+9//5rrrrqvqMiusIudw2bJltGjRotQbDYLpHCYmJpKenk5eXh6ff/4506dPZ/z48ccMNsFCb+k+SXFxcezfv7/Etv379xMdHU1ERASxsbFYllUqjXq93lL/8g9mn376Kc8//zz33ntviUuIZalVqxaJiYlkZ2dXU3WVr1WrVv763XIOHcdh+fLl9OjR47iLD4PhHM6ePZs1a9bw6KOP0qBBg9/d91h/Do+en6P//b19qlt5+jvqn//8JwsWLGDs2LEkJSX97r6NGzemTp06IXMOf8vj8dCyZUt//W45h/n5+Xz66acn9I+FQJ5Dj8dDQkICKSkpDBw4kOTkZJYsWVLmvsH050+h5iS1bt2adevWldj29ddf+//F4fF4SElJITMz0/9127bJzMw85v3JYPPJJ58wY8YMRowYUeIteseSn59PdnZ2SP2F/1tbt26lXr16gDvOIRTfq8/Ozj6h/5kG8hw6jsPs2bP5z3/+wyOPPEKjRo2O+5w2bdqU+eewdevWADRq1Ii4uLgS++Tl5bF58+ZqP4cV6Q+K3z3y9ttvk5qayimnnHLc/ffs2cPBgwf9P8fVqaI9/ppt2/z000/++t1wDgE+//xzfD4fPXr0OO6+gTyHv2XbNoWFhWV+LZj+/On2028c/Z/5Ubt27WLr1q3Url2bhg0b8tprr7F3717uuusuAC666CL+9a9/8eqrr9K7d28yMzP57LPPePDBB/3H6N+/P9OnTyclJYVWrVqxZMkSCgoKSn2WTXUob3+ffPIJ06dP56abbqJ169b+qxURERH+tz9nZGRw9tln07BhQ/bt28fcuXOxLIvzzjuv2vuD8ve4ePFiGjVqRPPmzTly5AjLli0jMzOTsWPH+o8RyufwqGXLltG6desy7/sH0zmcPXs2n3zyCffffz/R0dH+n7mYmBj/7ZZp06b533YK0K9fP8aNG8fChQvp3Lkzn376Kd9//z233HILAMYY+vXrxzvvvEOTJk1o1KgRb7zxBvXq1aNLly5B39+CBQuYO3cud999N40aNfI/JyoqiqioKPLz83nrrbfo1q0bcXFx7Ny5k1dffZWEhAQ6duxYrf1VtMd58+bRunVrEhISOHToEP/85z/Jycmhb9++QOifw6OWLVtGly5dSi3+DaZz+Nprr9GpUycaNmxIfn4+n3zyCRs2bPB/Xk4w//lTqPmN77//vsQHsWVkZABw/vnnc+edd7Jv3z52797t/3qjRo148MEHefnll1myZAkNGjTgtttuK/HhdN27dyc3N5e5c+fi9XpJTk4mNTU1IP8KLm9/H3zwAUVFRcyePZvZs2f7tx/dH4oXnz7zzDMcOHCA2NhY2rZtS1paWonPealO5e3R5/ORkZHB3r17iYyMJCkpiYcffpgzzjjDv08on0Mo/lfR6tWruemmm8o8ZjCdw/fffx8o/rCyX7vjjjv8IXL37t0YY/xfO/XUU7n77rt54403eP3112nSpAmjR48uEeAuu+wyCgoKmDlzJnl5ebRt25bU1NRq/XwTqFh///73v/H5fP4PSzzqqquu4pprrsGyLH766SdWrFjBoUOHqF+/Ph06dODaa68lPDy8SvspS0V6PHjwIDNnzsTr9VKrVi1SUlKYMGFCiTUcoXwOAbKysti4cWOJfzAdFUzncP/+/UyfPp19+/YRExNDUlISY8aM8S89COY/f8ZxHKdSjygiIiISAFpTIyIiIq6gUCMiIiKuoFAjIiIirqBQIyIiIq6gUCMiIiKuoFAjIiIirqBQIyIiIq6gUCMiIiKuoFAjIgLMnTuXa665htzc3ECXIiIVpFAjIiIirqBQIyIiIq6gUCMiIiKuoCndIlKt9u7dyxtvvMHatWs5dOgQCQkJ9O/fnz59+gCwfv16xo8fzz333MPWrVtZvnw5+fn5nHHGGdx88800bNiwxPE+++wzFixYwLZt24iKiqJjx47ccMMN1K9fv8R+27dv580332T9+vXk5+fTsGFDzjnnHK6//voS++Xl5fHKK6/wxRdf4DgO3bp14+abbyYyMrJqvzEictIUakSk2ni9XsaMGQPAxRdfTGxsLF999RXPP/88hw8f5k9/+pN/33feeQdjDJdddhm5ubksXryYxx9/nPT0dCIiIgD46KOPmDFjBqeccgoDBw5k//79LFmyhG+//ZZJkyZRq1YtAH788UceeeQRPB4Pffv2pVGjRmRnZ/Pll1+WCjVPP/008fHxDBw4kC1btrBs2TJiY2O54YYbqum7JCIVpVAjItXmjTfewLZtnnrqKerUqQPARRddxNSpU3nrrbe48MIL/fsePHiQp59+mujoaABatmzJ008/zQcffEC/fv3w+XzMmTOH5s2bM378eH/Qadu2LU8++SSLFy/mmmuuAeDFF18EYOLEiSWu9AwaNKhUjcnJydx+++0l6li+fLlCjUgI0JoaEakWjuOwevVqzjrrLBzHITc31/+rU6dO5OXlsWXLFv/+PXv29AcagHPOOYd69eqxdu1aALZs2cL+/fu5+OKL/YEGoHPnzjRt2pQ1a9YAkJubyzfffEPv3r1L3boyxpSq89fBCopD0oEDB8jLyzv5b4KIVCldqRGRapGbm8uhQ4f44IMP+OCDD465z9FbRk2aNCnxNWMMCQkJ5OTkAPj/m5iYWOo4iYmJbNy4EYCdO3cC0Lx58xOq87fBp3bt2gAcOnSImJiYEzqGiASGQo2IVAvHcQDo0aMH559/fpn7JCUlsW3btuosqxTLKvsC9tH6RSR4KdSISLWIjY0lOjoa27bp0KHDMfc7Gmp27NhRYrvjOGRnZ9OiRQsA4uPjAcjKyuKMM84osW9WVpb/640bNwbg559/rpxGRCRoaU2NiFQLy7Lo1q0bq1ev5qeffir19d+OJ/j44485fPiw//Hnn3/Ovn37OPPMMwFISUmhbt26/Pvf/6awsNC/39q1a9m+fTudO3cGisPUaaedxvLly9m9e3eJ19DVFxF30ZUaEak2AwcOZP369YwZM4a+ffvSrFkzDh48yJYtW1i3bh3/+Mc//PvWrl2bRx55hF69erF//34WL15MQkICffv2BcDj8TBo0CBmzJjBuHHjOPfcc/F6vbz33nvEx8eXeHv44MGDeeSRR3jggQf8b+nOyclhzZo1pKenV/v3QUSqhkKNiFSbuLg4nnjiCebNm8fq1av517/+RZ06dWjevHmpt1dfccUV/PjjjyxYsIDDhw/Tvn17hg4dWuJD8Hr16kVERATvvvsuc+bMITIyki5dunDDDTf4FxxD8du009LSePPNN/n3v//NkSNHiI+P5w9/+EO19S4iVc84uv4qIkHk6CcKjxw5knPOOSfQ5YhICNGaGhEREXEFhRoRERFxBYUaERERcQWtqRERERFX0JUaERERcQWFGhEREXEFhRoRERFxBYUaERERcQWFGhEREXEFhRoRERFxBYUaERERcQWFGhEREXGF/w+WP5qzgX/4DgAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "data = []\n", + "for sample in samples:\n", + " print(sample['name'])\n", + " r = learn_sample(sample)\n", + " print(dict(before=r['before'], after=r['after']))\n", + " data.append(dict(**r, **sample))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
eval_lossloss
epoch
1.02.6388360.3704
2.02.6423680.3592
3.02.6508710.3644
\n", + "
" + ], + "text/plain": [ + " eval_loss loss\n", + "epoch \n", + "1.0 2.638836 0.3704\n", + "2.0 2.642368 0.3592\n", + "3.0 2.650871 0.3644" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiMAAAG0CAYAAADgoSfXAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAzmUlEQVR4nO3dfXRU9Z3H8c+dTB4mzxASkiwYEiCw9YGHXZ/XFeVUPcpZ66laQY5L68NWqHbtQWtFKVhwBV3Uc4Cj3c2upT4R2aJYqKKCtlhEz6KrgEorUigQCZLJ40wyk7n7R5hLJpmETEj4zQzv1znK3Pv73d/8vnMnk0/u3Llj2bZtCwAAwBCX6QkAAIDTG2EEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYJTb9ARiUVdXp2AwOKBjFhYWqra2dkDHjDfJXiP1Jb5kr5H6El+y1zhY9bndbg0ZMuTE/Qb8ngdRMBhUIBAYsPEsy3LGTdar4id7jdSX+JK9RupLfMleYzzUx9s0AADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAoxLqi/IAADid2bYt2bYkWwod+9fu8l/UNkl2KLIt/K+koMuWHQhKbjOxgDACIKl1vHiHjr8Yd/5XsbZ1frEPHbuDaG2dfhFIamtpkF17uGMuPf0CsXtZ31NblF86dq99wvPtrU3Hf2lFe1zC2x+r3ZJUn5Wl9sbGjvXOeFEez5h+efbtsbF7e9zUpd5Y2rrs3xq3W8G2tl72fajLdtFq7KWtr3UPkkOSUh54XCqvHLT76M1pHUZCO7ar+TNLIa/3+NcmOzv72A9i+Ha4reuTIfxk6dTtxGNEWTcgYyhyfrYty7JUn52tUGPDsbs5wbjOYi+PR7/HiDbPkxzDsnTUk6H2Fl+X/dPLGD2NG14+ts4egDEi5xxtjGM3ehjDsiwdTk1Ve1vb8RfdGMfo29y6jNGfcZ3+vYzbtf+xfw+6XGpvD/bxl5XU7Zdmj23x4WvTExhEtqQG05M4BQKmJzBQLEuSJbmO/WtJslyywsuGnN5hZN0LOrrnC9PTGFSnwwtFs+kJDCJbUqvpSZwC7aYn0BvLdewF24ryQt7lvx7aUtxutYdCx/tE267ruoi28Dw6r5fkcnWZo6uXNqvjdo9tlixZndr6VpsslzKzstTia+m5jhgeq8j5d/+l6fzba1unentpszq3RYzXfbuCYQX65mhd98emtzr6vH9jbIv5Oahj9VrRn+KWpZKSEh06dOj4H+an2GkdRqzySqXl5autra3jj6/wfnJ2WKcfDHVqi7YuvHHUMcK3rONt/RxDEWNEWRexXcftzMxMtfh8Xe6rl3GjjNGtf5/GiLKupzF66h91jOO3LctSTk6uGpsaj+/Dfo/bqe1k5hZe7vMYx25EGcOyXBoyJF91Xm/4QFAP43YZI+q4J6qvL2OcqL4Yx5BkWS4VFA7TN98c7Tio0uUFNPLF9dg6p03Hf2l1bQs/3tF+IfXU1uWFvKcX71jEwwv9YLIsS0NLStSapPVJHTVmlJTIlcQ1mnZah5GU6XeoKIlfJKTkf6GwLEu5JSVqTuL6MktKVJ+k9UkdNaaXlMg6dKj72zkATgt8tBcAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEa5Y+m8du1affDBBzpw4IDS0tJUWVmpmTNnqrS0tMdt3nnnHa1cuTJiXWpqqp5//vn+zRgAACSVmMLIrl27dOWVV2r06NFqb2/Xiy++qEWLFmnZsmXKyMjocTuPx6OnnnrqpCcLAACST0xhZN68eRHLc+bM0W233aY9e/boW9/6Vo/bWZal/Pz8fk0QAAAkt5jCSFctLS2SpOzs7F77+f1+zZ49W7Ztq7y8XNOnT9fIkSN77B8IBBQIBJxly7Lk8Xic2wMlPNZAjhlvkr1G6kt8yV4j9SW+ZK8xHuqzbNu2+7NhKBTS0qVL1dzcrF/84hc99tu9e7cOHTqksrIytbS0aN26dfrss8+0bNkyFRQURN2murpaa9ascZbLy8u1ZMmS/kwTAADEuX6Hkf/4j//Qxx9/rIcffrjHUBFNMBjUPffco4svvlg33XRT1D49HRmpra1VMBjsz3SjsixLxcXFqqmpUT8fhriX7DVSX+JL9hqpL/Ele42DWZ/b7VZhYeGJ+/Vn8KqqKm3fvl0LFy6MKYiEJ1ZeXq6ampoe+6Smpio1NTVq22A8EWzbTsonWGfJXiP1Jb5kr5H6El+y12iyvpiuM2LbtqqqqvTBBx9o/vz5KioqivkOQ6GQ9u3bpyFDhsS8LQAASD4xHRmpqqrSli1bdN9998nj8cjr9UqSMjMzlZaWJklavny5hg4dqhkzZkiS1qxZo7Fjx6q4uFjNzc1at26damtrNXXq1IGtBAAAJKSYwsjGjRslSQsWLIhYP3v2bE2ZMkWSdOTIkYgzcpuamvTMM8/I6/UqKytLFRUVWrRokUaMGHFyMwcAAEkhpjBSXV19wj5dg8qsWbM0a9asWO4GAACcRvhuGgAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARrlj6bx27Vp98MEHOnDggNLS0lRZWamZM2eqtLS01+22bt2q1atXq7a2VsXFxbr55ps1efLkk5o4AABIDjEdGdm1a5euvPJKLV68WA8++KDa29u1aNEi+f3+Hrf54osv9NRTT+nyyy/XkiVLdO655+qxxx7Tvn37TnryAAAg8cV0ZGTevHkRy3PmzNFtt92mPXv26Fvf+lbUbTZs2KCJEyfqn/7pnyRJN910kz799FO9/vrruuOOO6JuEwgEFAgEnGXLsuTxeJzbAyU81kCOGW+SvUbqS3zJXiP1Jb5krzEe6ospjHTV0tIiScrOzu6xz+7duzVt2rSIdRMmTNCHH37Y4zZr167VmjVrnOXy8nItWbJEhYWFJzPdHhUXFw/KuPEk2WukvsSX7DVSX+JL9hpN1tfvMBIKhfTss89q3LhxOuOMM3rs5/V6lZeXF7EuLy9PXq+3x22uu+66iAATTmu1tbUKBoP9nXI3lmWpuLhYNTU1sm17wMaNJ8leI/UlvmSvkfoSX7LXOJj1ud3uPh1I6HcYqaqq0v79+/Xwww/3d4gepaamKjU1NWrbYDwRbNtOyidYZ8leI/UlvmSvkfoSX7LXaLK+fn20t6qqStu3b9fPf/5zFRQU9No3Pz9f9fX1Eevq6+uVn5/fn7sGAABJJqYwYtu2qqqq9MEHH2j+/PkqKio64TaVlZX69NNPI9Z98sknGjt2bGwzBQAASSmmMFJVVaU//OEP+vGPfyyPxyOv1yuv16u2tjanz/Lly/XCCy84y1dffbX+7//+T6+99poOHDig6upqffnll7rqqqsGrgoAAJCwYjpnZOPGjZKkBQsWRKyfPXu2pkyZIkk6cuRIxMeDxo0bp7vvvlsvvfSSXnzxRZWUlOjee+/t9aRXAABw+ogpjFRXV5+wT9egIkkXXnihLrzwwljuCgAAnCb4bhoAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGOU2PQEAAILBoFpaWkxPo0c+n09tbW2mpzFoTqa+zMxMud0nFycIIwAAo4LBoJqbm5WTkyOXKz4P2KempioQCJiexqDpb32hUEiNjY3Kyso6qUASn3sdAHDaaGlpiesggp65XC7l5OSc9FEt9jwAwDiCSOIaiH3H3gcAAEYRRgAAgFGEEQAA4pDH41FxcXGf+ubk5KiwsHCQZzR4CCMAAMAowggAADCK64wAANBP2dnZyszMVEpKioLBoBobG+X3+zV8+HA1NjZGfOTV7XarsLBQhw8fVnt7u7KyspxtbduW3+9XQ0ODbNsesLllZWXJ5XIpGAyqoaFBra2tTnteXp4yMjLkcrkUCoXU3NyspqYmSR1v+3g8HqWkpCgUCsnn86mhoWFA5hUNYQQAEDds25baWk/ccTCkpcuyrD53z87OlsfjUX19vYLBoNLS0jRkyBB988038vl88ng8EWEkMzNTbW1tam9vd9bV19ervb1dKSkpysvLU25ururr60+6lKysLGVnZ8vr9SoQCCgzM1NDhw6NCELp6emqq6tTe3u70tLSnG0zMjKUlZWluro6BYNBuVwupaamnvScekMYAQDEj7ZWhX50o5G7di2vltIz+tw/Oztb33zzjXPlUp/Pp7S0NGVmZqqpqUmFhYVKSUlxwofH41FjY6OzfXNzs3O7vb1djY2NysvLG5Awkp2draamJvn9fklSY2Oj0tPTlZ2drfr6emde4UvAB4NBp47w0ZDwUZT29vZBv/osYQQAgBi53W65XC4VFBRErLcsS4FAQMFgUMFgUB6PR01NTUpLS5PL5ZLP53P6pqWlKScnR263W5ZlRfx3Mm/VWJallJSUbt8109bW5hzh8Pl8yszMVFFRkfx+f0QY8fl8ysrK0vDhw+X3+9Xa2uqEmsFCGAEAxI+09I4jFIbuu6/Cb+ccPXo04m0XSU6QCL9V09TUJI/Ho9bWVqctJSVFBQUFam5uVkNDg0KhkPM2z6kQCAT09ddfKz09Xenp6crNzXXetgmFQjp8+LDTlpeXp+zsbB05cmTQ5kMYAQDEDcuyYnqrxJRgMCjbtqMegQjz+XzKyclRamqqPB6PvF6v0xY+QtH5pNCUlJQBmZtt2855IJ3nlpaWFvF2S/ikWb/fr0AgoPz8fHm9Xicwtba2qrW1Vc3NzRo+fPigflkgYQQAgBjZtq2mpibl5uZK6ngLxOVyKS0tzfn0SficjPz8fEmKeKsjGAzKsixlZWXJ7/crLS1NWVlZAza/pqYm5eTkOG+/ZGZmKjU1VXV1dZI6TnANhUIKBAKybVvp6elqb2+XbdvyeDyyLEttbW2ybVuZmZkKhUIKBoMDNr+uCCMAAPRDY2OjQqGQsrOz5Xa7nV/u4Y/HSh1HR/Lz87t9q20wGFR9fb2ys7OVk5OjtrY2NTQ0DNjbNM3NzbIsS3l5ec5Hezu/pWTbtrKzs52jMcFgUN98843TlpWV5QSt8LYD9ZHjaAgjAAD0U3Nzc8SnYrpqaWnpFkR627bzCa4+ny9iuTeNjY0Rn9SROo6OdA5Gvc0rNTXVOfIRfuvmVOIKrAAAwCiOjAAAEOfC1yyJpr6+vs9HUOJVzGFk165dWrdunb766ivV1dVp7ty5Ou+883rsv3PnTi1cuLDb+l/+8pfOST0AAKBnR48e7bEtFAqdwpkMjpjDSGtrq0aNGqXLL79cjz/+eJ+3e/LJJ5WZmeksh0+MAQAAvet6LZNkE3MYmTRpkiZNmhTzHeXl5Q3ox5YAAEByOGXnjNx3330KBAIaOXKkbrjhBo0fP77HvoFAIOLCKpZlyePxOLcHSnisgRwz3iR7jdSX+JK9RurD6eJkngOWfRIfHL7xxhtPeM7IwYMHtXPnTo0ePVqBQEBvv/22/vCHP2jx4sWqqKiIuk11dbXWrFnjLJeXl2vJkiX9nSYAII7t2bNHOTk5pqeBk9DY2Njj7/S+GPQjI6WlpSotLXWWx40bp6+//lrr16/XXXfdFXWb6667TtOmTXOWw2mrtrZ2QK8AZ1mWiouLVVNTM6gXczEp2WukvsSX7DVS34m1tbUN+rfCnqzBvBR6PDjZ+tra2nTo0KFu691utwoLC0+4vZGP9o4ZM0aff/55j+2pqanOdfu7GowfZtu2k/JForNkr5H6El+y10h9SHYns/+NXPRs7969p+ybCQEAGAwFBQV8MnSAxHxkxO/3q6amxlk+fPiw9u7dq+zsbA0bNkwvvPCCjh49qh/96EeSpPXr16uoqEgjR45UW1ubNm3apB07dujBBx8cuCoAAEDCijmMfPnllxEXMVu1apUk6dJLL9WcOXNUV1enI0eOOO3BYFCrVq3S0aNHlZ6errKyMj300EM666yzBmD6AAAg0cUcRs4880xVV1f32D5nzpyI5WuvvVbXXntt7DMDACBBhL8hNyMjQ1LHCZ319fXOxcpSUlKUl5entLQ0SR0XMWtoaFBra6uzbXp6ulwul9rb29XY2Jjwl3iPBd9NAwCIG7Ztq7XdzImw6SlWv6+VkZ+fL7fbraNHjyoUCik3N1cFBQU6fPiwpI4Lf0rSkSNHZNu23G63c8Jnbm6uUlNTnW1TUlJOu+u2EEYAAHGjtd3W91bvNnLfq79XqQx37CEgJSVFHo9HtbW1zsdj6+rqNHz4cGVkZMjv9yslJUU+n8+5PEXny7unpKREXOwz2S/9Ho2RT9MAAJAswkc5Ol+nw7Zttbe3y+3u+Ju/ublZOTk5GjZsmHJycpz14baMjAwVFhY6R0lONxwZAQDEjfQUS6u/V2nsvgdLS0uL/H6/MjIylJ6ersLCQjU0NKi5uVmtra06fPiw0tPTlZ6ermHDhqm5uVkNDQ2DNp94QxgBAMQNy7L69VaJScFgUJZlRVzF1LIspaSkRFw1PBQKqaWlRS0tLcrJyVFmZqaam5udNp/PJ5/Pp7a2NuXm5hJGAABA37S3t8vn8yk/P1/19fXOCayhUEh+v19Sx0mqra2tCgaDcrlcSk9Pd4JKTk6Oc86IZVnKyMgY0K8+SQSEEQAATpLX61VeXp6GDh0qqeOjvd98801En7y8PKWkpCgUCqm1tVX19fWSOs4vycnJUUpKiiSptbVVdXV1p7YAwwgjAAD0Q+ewYdu2vF5vj30bGhp6fNulqalJTU1NAz29hMKnaQAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAIBxoVDI9BTQTwOx7wgjAACjMjMz1djYSCBJQKFQSI2NjcrMzDypcbjOCADAKLfbraysrLi+1kZaWpra2tpMT2PQnEx9WVlZEV/81x+EEQCAcW63W7m5uaanEZVlWSopKdGhQ4dk27bp6Qy4eKiPt2kAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUe5YN9i1a5fWrVunr776SnV1dZo7d67OO++8XrfZuXOnVq1apf3796ugoEDf/e53NWXKlP7OGQAAJJGYj4y0trZq1KhRuvXWW/vU//Dhw3r00Ud15plnaunSpbrmmmv09NNP6+OPP471rgEAQBKK+cjIpEmTNGnSpD7337hxo4qKinTLLbdIkkaMGKHPP/9c69ev18SJE2O9ewAAkGRiDiOx+tOf/qSzzz47Yt2ECRP07LPP9rhNIBBQIBBwli3LksfjcW4PlPBYAzlmvEn2Gqkv8SV7jdSX+JK9xniob9DDiNfrVV5eXsS6vLw8+Xw+tbW1KS0trds2a9eu1Zo1a5zl8vJyLVmyRIWFhYMyx+Li4kEZN54ke43Ul/iSvUbqS3zJXqPJ+gY9jPTHddddp2nTpjnL4bRWW1urYDA4YPdjWZaKi4tVU1Mj27YHbNx4kuw1Ul/iS/YaqS/xJXuNg1mf2+3u04GEQQ8j+fn5qq+vj1hXX18vj8cT9aiIJKWmpio1NTVq22A8EWzbTsonWGfJXiP1Jb5kr5H6El+y12iyvkG/zsjYsWP16aefRqz75JNPVFlZOdh3DQAAEkDMYcTv92vv3r3au3evpI6P7u7du1dHjhyRJL3wwgtavny50/+KK67Q4cOH9dxzz+nAgQN64403tHXrVl1zzTUDUwEAAEhoMb9N8+WXX2rhwoXO8qpVqyRJl156qebMmaO6ujonmEhSUVGR7r//fv3qV7/Shg0bVFBQoB/+8Id8rBcAAEjqRxg588wzVV1d3WP7nDlzom6zdOnSWO8KAACcBvhuGgAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARrn7s9Hrr7+u1157TV6vV2VlZfrBD36gMWPGRO37zjvvaOXKlRHrUlNT9fzzz/fnrgEAQJKJOYz88Y9/1KpVq3T77bdr7NixWr9+vRYvXqwnn3xSeXl5UbfxeDx66qmnTnqyAAAg+cQcRn77299q6tSpuuyyyyRJt99+u7Zv367NmzfrO9/5TtRtLMtSfn5+n+8jEAgoEAhEbO/xeJzbAyU81kCOGW+SvUbqS3zJXiP1Jb5krzEe6ospjASDQe3ZsycidLhcLp199tnavXt3j9v5/X7Nnj1btm2rvLxc06dP18iRI3vsv3btWq1Zs8ZZLi8v15IlS1RYWBjLdPusuLh4UMaNJ8leI/UlvmSvkfoSX7LXaLK+mMJIQ0ODQqFQt6Mc+fn5OnjwYNRtSktLdeedd6qsrEwtLS1at26dHnzwQS1btkwFBQVRt7nuuus0bdo0Zzmc1mpraxUMBmOZcq8sy1JxcbFqampk2/aAjRtPkr1G6kt8yV4j9SW+ZK9xMOtzu919OpDQrxNYY1FZWanKysqI5XvuuUdvvvmmbrrppqjbpKamKjU1NWrbYDwRbNtOyidYZ8leI/UlvmSvkfoSX7LXaLK+mD7am5ubK5fLJa/XG7He6/X2+ZwQt9ut8vJy1dTUxHLXAAAgScUURtxutyoqKrRjxw5nXSgU0o4dOyKOfvQmFApp3759GjJkSGwzBQAASSnmt2mmTZumFStWqKKiQmPGjNGGDRvU2tqqKVOmSJKWL1+uoUOHasaMGZKkNWvWaOzYsSouLlZzc7PWrVun2tpaTZ06dUALAQAAiSnmMHLRRRepoaFB1dXV8nq9GjVqlB544AHnbZojR45EfDyoqalJzzzzjLxer7KyslRRUaFFixZpxIgRA1YEAABIXP06gfWqq67SVVddFbVtwYIFEcuzZs3SrFmz+nM3AADgNMB30wAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMCofl0OPlms3HZINS0HFQgEZFmSJcmyOhKaZVlyOessp91lHVvuctuyji3LirjtOvY1PU7fLuN3tHUZw7I6UqIluY6N13VMq9N9WeExnD6d5uiyNNRrqd7bIEt25Hadxu9aS8SYXR6Djv5dHoOIx8/q9nj0NmbXxyHaYwwASF6ndRj5qq5VXxzxmZ7GKXDQ9AROWq+Bz7Vbkh0ZcBQZrnoNkVEC3/FwdTyUdg9e1rH7iRbmjodGV5dAFjlmZNBVxJgdbTnZzWppbpacOXSZs6xjwTVyu/D4EdtFPCaR4dOZV+fxo/TtPH73xy/6YxBRa+c2dQTmkNenw01tskO27GP73LYlW5KtYzcUXu74ny3JtsO9w8uRt4+Pdnw8dW7raVzZ6jR0lLF7H9fuvKFlKb/RraN1DbJt27mfyHmGt+8841jaTjTnE7d1nnPk42H32iZZyvrSp6ampo45xlhP9LHtiDn2Vk/X54tiqKfr8yVcUdf7lS2lZRyW398add9HzDnGejrPuU/1dG7rZz1OW6dxXSl79LNLSlUxJF0mnNZh5J8nFSolM1dHj9YpZNsKHdsroU4/UD3dtu1jy1Fu27YUCu/oLrd7H7NjDl3HDB174oTs7uNHtHUew5ZCx8ZJS0uTv7U1YvyOPp3m3MP43efVqV942an7+O1uc1bkdrE6/piElzq3JLujpidwCnxpegKD7K+mJzDIjpiewCnQZHoCgyyoQLu519PTOoycNTxLJSVFOnSoPSLtJhPLslRSUqJDhw7FTY2RIUhdQlJk4IsMOJGBr+MvAkvDCgv19deHewx2XcOfOgW1roFSUqcw159A2UtI7SnwnWD8zMwsNTU3H1sXPbD2N1CGOnZIZKDsFFh7DJR9GT/KPoy8fXxMy7KcP986DuZEHrVR+F+Fl4+197HNaQ+PbXVdF17uuc06NpjVbZvuc45ss5SWltrxdnC3bWKrp8f7Pdl6ut5vr/WEW+Qc6crKzFJLS4sk+4T1hN927emx6tZ2gjn3tZ6IOeu4ntqO32/HY5ifn6/6+npZnf4AirWevsy5c1tE7Z0mHT4K21s93Z7/XeqJmJdladiwYcpoa5Qpp3UYgRnOD5LzE2T13LkPY5UMyVSqPz1uwtZAiscwOdCSvUbqS3zHa7SSskbLslRSnKtDh5qN1cenaQAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYJTb9ARi4XYPznQHa9x4kuw1Ul/iS/YaqS/xJXuNg1FfX8e0bNu2B/zeAQAA+ui0fpvG5/Pppz/9qXw+n+mpDJpkr5H6El+y10h9iS/Za4yH+k7rMGLbtr766isl88GhZK+R+hJfstdIfYkv2WuMh/pO6zACAADMI4wAAACjTuswkpqaquuvv16pqammpzJokr1G6kt8yV4j9SW+ZK8xHurj0zQAAMCo0/rICAAAMI8wAgAAjCKMAAAAowgjAADAqKS50P6uXbu0bt06ffXVV6qrq9PcuXN13nnn9brNzp07tWrVKu3fv18FBQX67ne/qylTpkT0ef311/Xaa6/J6/WqrKxMP/jBDzRmzJhBrKRnsda4bds2bdy4UXv37lUwGNSIESN0ww03aOLEiU6f6upqrVmzJmK70tJSPfnkk4NURc9irW/nzp1auHBht/W//OUvlZ+f7ywn8j5csWKF3n333W7rR4wYoWXLlkmKn324du1affDBBzpw4IDS0tJUWVmpmTNnqrS0tNfttm7dqtWrV6u2tlbFxcW6+eabNXnyZKfdtm1VV1fr7bffVnNzs8aPH6/bbrtNJSUlg11SN/2p8a233tLvf/977d+/X5JUUVGh6dOnRzwHo+3nCRMmaN68eYNTSA/6U98777yjlStXRqxLTU3V888/7ywn+j5csGCBdu3a1W39pEmT9LOf/UxS/OzDjRs3auPGjaqtrZXU8Vpx/fXXa9KkST1uEw8/g0kTRlpbWzVq1Chdfvnlevzxx0/Y//Dhw3r00Uf17W9/W3fddZd27Nihp59+Wvn5+c4v6z/+8Y9atWqVbr/9do0dO1br16/X4sWL9eSTTyovL2+QK+ou1ho/++wznXPOOZo+fbqysrK0efNmLVmyRI888ojKy8udfiNHjtRDDz3kLLtcZg6YxVpf2JNPPqnMzExnOTc317md6Pvw+9//vm6++WZnub29Xffee68uuOCCiH7xsA937dqlK6+8UqNHj1Z7e7tefPFFLVq0SMuWLVNGRkbUbb744gs99dRTmjFjhiZPnqwtW7boscce05IlS3TGGWdIkl599VX97ne/05w5c1RUVKTVq1dr8eLFWrZsmdLS0k5lif2qcdeuXbr44os1btw4paam6tVXX3W2GTp0qNNv4sSJmj17trNs4kvZ+lOfJHk8Hj311FM9tif6Ppw7d66CwaCz3NjYqHvvvVcXXnhhRL942IdDhw7VjBkzVFJSItu29e6772rp0qVaunSpRo4c2a1/3PwM2knohhtusLdt29Zrn1//+tf2T37yk4h1TzzxhL1o0SJn+Wc/+5n9n//5n85ye3u7fccdd9hr164d0Pn2R19qjOaee+6xX375ZWd59erV9ty5cwdyagOiL/Xt2LHDvuGGG+ympqYe+yTbPty2bZt944032ocPH3bWxes+rK+vt2+44QZ7586dPfZZtmyZ/W//9m8R6x544AH7mWeesW3btkOhkH377bfbr776qtPe3Nxsz5gxw96yZcvgTDwGfamxq/b2dvuWW26x33nnHWfd8uXL7SVLlgzGFE9KX+rbvHmz/c///M89tifjPvztb39r33LLLbbP53PWxes+tG3bnjVrlv32229HbYuXn8GkOTISqz/96U86++yzI9ZNmDBBzz77rCQpGAxqz549+s53vuO0u1wunX322dq9e/cpnOnACYVC8vl8ys7OjlhfU1Ojf/mXf1FqaqoqKys1Y8YMDRs2zNAsY3ffffcpEAho5MiRuuGGGzR+/HhJybkPN23apLPPPluFhYUR6+NxH7a0tEhSt+dbZ7t379a0adMi1k2YMEEffvihpI4jmF6vV+ecc47TnpmZqTFjxmj37t26+OKLB2HmfdeXGrtqbW1VMBjsts2uXbt02223KSsrS2eddZZuuukm5eTkDOh8Y9XX+vx+v2bPni3btlVeXq7p06c7f4Un4z7ctGmTLrroom5HUuJtH4ZCIW3dulWtra2qrKyM2idefgZP2zDi9Xq7HabPy8uTz+dTW1ubmpqaFAqFIs49kKT8/HwdPHjwFM504Lz22mvy+/0RhxbHjh2r2bNnq7S0VHV1dVqzZo3mz5+vf//3f5fH4zE42xMbMmSIbr/9do0ePVqBQEBvv/22Fi5cqMWLF6uiokINDQ1JtQ+PHj2qjz/+WHfffXfE+njch6FQSM8++6zGjRvnHOqNpqefQ6/X67SH1/XUx5S+1tjV888/r6FDh0b8MTRx4kSdf/75KioqUk1NjV588UU98sgjWrx4sbG3TftaX2lpqe68806VlZWppaVF69at04MPPqhly5apoKAg6fbhn//8Z+3fv1933nlnxPp42of79u3TvHnzFAgElJGRoblz52rEiBFR+8bLz+BpG0ZON1u2bNGaNWt07733RjypOp/UVFZW5vxi27p1qy6//HITU+2z0tLSiJPOxo0bp6+//lrr16/XXXfdZXBmg+Pdd99VVlZWtxNe43EfVlVVaf/+/Xr44YeN3P+p0J8aX3nlFb333ntasGBBxHvtnf+6POOMM1RWVqa77rpLO3fu7HYE91Tpa32VlZURf3VXVlbqnnvu0ZtvvqmbbrppsKd5UvqzDzdt2qQzzjij20nw8bQPS0tL9dhjj6mlpUXvv/++VqxYoYULF/YYSOLBafvR3vz8fNXX10esq6+vl8fjUVpamnJzc+VyubolP6/X2+0v7Xj33nvv6emnn9Y999wTcagtmqysLJWWlqqmpuYUzW5gjRkzxpl7Mu1D27a1efNmXXLJJSc8Kc70PqyqqtL27dv185//XAUFBb327ennMLx/wv/21seEWGoMW7dunV555RU9+OCDKisr67Xv8OHDlZOTkxD7sCu3263y8nJn7sm0D/1+v957770+hXyT+9Dtdqu4uFgVFRWaMWOGRo0apQ0bNkTtGy8/g6dtGBk7dqw+/fTTiHWffPKJk/DdbrcqKiq0Y8cOpz0UCmnHjh09vvcWj7Zs2aKVK1fqxz/+ccRHtXri9/tVU1OTcL+sw/bu3ashQ4ZISp59KHW8F11TU9OnF0FT+9C2bVVVVemDDz7Q/PnzVVRUdMJtKisro/4cjh07VpJUVFSk/Pz8iD4tLS3685//bGQf9qdGqePTCP/zP/+jBx54QKNHjz5h/2+++UZNTU3Oc/lU6W99nYVCIe3bt8+Ze7LsQ0l6//33FQwGdckll5ywr6l9GE0oFFIgEIjaFi8/g0nzNk34BTjs8OHD2rt3r7KzszVs2DC98MILOnr0qH70ox9Jkq644gq98cYbeu6553TZZZdpx44d2rp1q+6//35njGnTpmnFihWqqKjQmDFjtGHDBrW2tna7FsmpEmuNW7Zs0YoVKzRr1iyNHTvWOUKQlpbmfBR21apV+vu//3sNGzZMdXV1qq6ulsvl0j/8wz/EfX3r169XUVGRRo4cqba2Nm3atEk7duzQgw8+6IyR6PswbNOmTRo7dmzU97XjZR9WVVVpy5Ytuu++++TxeJznW2ZmpvOWxPLly52PHkrS1VdfrQULFui1117T5MmT9d577+nLL7/UHXfcIUmyLEtXX321fvOb36ikpERFRUV66aWXNGTIEJ177rmntL7+1vjKK6+ourpad999t4qKipxtMjIylJGRIb/fr5dfflnnn3++8vPz9fXXX+u5555TcXGxJkyYEPf1rVmzRmPHjlVxcbGam5u1bt061dbWaurUqZKSYx+Gbdq0Seeee263k1LjaR++8MILmjhxooYNGya/368tW7Zo165dzvVO4vVnMGnCyJdffhlxAaxVq1ZJki699FLNmTNHdXV1OnLkiNNeVFSk+++/X7/61a+0YcMGFRQU6Ic//GHEBcEuuugiNTQ0qLq6Wl6vV6NGjdIDDzxg7KhBrDW+9dZbam9vV1VVlaqqqpz14f5Sx0mRTz31lBobG5Wbm6vx48dr8eLFEdfqOFVirS8YDGrVqlU6evSo0tPTVVZWpoceekhnnXWW0yfR96HU8VfItm3bNGvWrKhjxss+3Lhxo6SOC0R1Nnv2bCf8HTlyRJZlOW3jxo3T3XffrZdeekkvvviiSkpKdO+990aErmuvvVatra165pln1NLSovHjx+uBBx445denkPpX45tvvqlgMOhcpC7s+uuv14033iiXy6V9+/bp3XffVXNzs4YOHapzzjlH3/ve9075V7r3p76mpiY988wz8nq9ysrKUkVFhRYtWhRxfkKi70NJOnjwoD7//POIP3bC4mkf1tfXa8WKFaqrq1NmZqbKyso0b9485y36eP0ZtGzbtgdsNAAAgBidtueMAACA+EAYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQRAQquurtaNN96ohoYG01MB0E+EEQAAYBRhBAAAGEUYAQAARiXNt/YCGFxHjx7VSy+9pI8++kjNzc0qLi7WtGnTdPnll0uSdu7cqYULF+pf//VftXfvXm3evFl+v19nnXWWbr31Vg0bNixivK1bt+qVV17RX//6V2VkZGjChAmaOXOmhg4dGtHvwIEDWr16tXbu3Cm/369hw4bpggsu0PTp0yP6tbS06Ne//rU+/PBD2bat888/X7feeqvS09MH94EBcNIIIwBOyOv1at68eZKkK6+8Urm5ufr444/19NNPy+fz6ZprrnH6/uY3v5FlWbr22mvV0NCg9evX6xe/+IUee+wx5yvH33nnHa1cuVKjR4/WjBkzVF9frw0bNuiLL77Q0qVLlZWVJUn6y1/+ovnz58vtdmvq1KkqKipSTU2N/vd//7dbGHniiSdUWFioGTNmaM+ePdq0aZNyc3M1c+bMU/QoAegvwgiAE3rppZcUCoX0+OOPKycnR5J0xRVX6Mknn9TLL7+sb3/7207fpqYmPfHEE/J4PJKk8vJyPfHEE3rrrbd09dVXKxgM6vnnn9fIkSO1cOFCJ6CMHz9ejz76qNavX68bb7xRkvRf//VfkqQlS5ZEHFm5+eabu81x1KhRuvPOOyPmsXnzZsIIkAA4ZwRAr2zb1rZt2/R3f/d3sm1bDQ0Nzn8TJ05US0uL9uzZ4/T/x3/8RyeISNIFF1ygIUOG6KOPPpIk7dmzR/X19bryyiudICJJkydP1t/8zd9o+/btkqSGhgZ99tlnuuyyy7q9xWNZVrd5dg5EUke4aWxsVEtLy8k/CAAGFUdGAPSqoaFBzc3Neuutt/TWW2/12Cf81kpJSUlEm2VZKi4uVm1trSQ5/5aWlnYbp7S0VJ9//rkk6euvv5YkjRw5sk/z7BpYsrOzJUnNzc3KzMzs0xgAzCCMAOiVbduSpEsuuUSXXnpp1D5lZWX661//eiqn1Y3LFf1Ab3j+AOIXYQRAr3Jzc+XxeBQKhXTOOef02C8cRg4dOhSx3rZt1dTU6IwzzpAkFRYWSpIOHjyos846K6LvwYMHnfbhw4dLkvbv3z8whQCIW5wzAqBXLpdL559/vrZt26Z9+/Z1a+96Gfbf//738vl8zvL777+vuro6TZo0SZJUUVGhvLw8vfnmmwoEAk6/jz76SAcOHNDkyZMldYSgv/3bv9XmzZt15MiRiPvgaAeQXDgyAuCEZsyYoZ07d2revHmaOnWqRowYoaamJu3Zs0effvqp/vu//9vpm52drfnz52vKlCmqr6/X+vXrVVxcrKlTp0qS3G63br75Zq1cuVILFizQxRdfLK/Xq9/97ncqLCyM+Jjw97//fc2fP18//elPnY/21tbWavv27XrsscdO+eMAYHAQRgCcUH5+vh555BGtWbNG27Zt0xtvvKGcnByNHDmy28dsr7vuOv3lL3/RK6+8Ip/Pp7PPPlu33XZbxMXHpkyZorS0NL366qt6/vnnlZ6ernPPPVczZ850ToSVOj6uu3jxYq1evVpvvvmm2traVFhYqAsvvPCU1Q5g8Fk2xzsBDIDwFVh/8pOf6IILLjA9HQAJhHNGAACAUYQRAABgFGEEAAAYxTkjAADAKI6MAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIz6f3mFJl+QhEYbAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df_hist = data[0]['hist']#.groupby('epoch').last().dropna(axis=1).drop(columns=['step'])\n", + "df_hist[['eval_loss', 'loss']].plot()\n", + "df_hist[['eval_loss', 'loss']]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "### Perplexity\n", + "\n", + "Perplexity measures how well a language model predicts a text sample. Lower is better\n", + "\n", + "It’s calculated as the average number of bits per word a model needs to represent the same\n", + "\n", + "https://huggingface.co/docs/transformers/perplexity\n", + "https://thegradient.pub/understanding-evaluation-metrics-for-language-models/\n" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
beforeafterin_trainingimprovement
name
wikipedia on LK-9933.34950331.391512False1.957991
Theory o. general relativity27.83138826.375334True1.456055
good_ml28.01332527.246099False0.767225
sokal hoax17.25156016.814535True0.437025
lorem ipsum1.7382311.706331True0.031900
bad_ml14.04796514.164684False-0.116719
\n", + "
" + ], + "text/plain": [ + " before after in_training improvement\n", + "name \n", + "wikipedia on LK-99 33.349503 31.391512 False 1.957991\n", + "Theory o. general relativity 27.831388 26.375334 True 1.456055\n", + "good_ml 28.013325 27.246099 False 0.767225\n", + "sokal hoax 17.251560 16.814535 True 0.437025\n", + "lorem ipsum 1.738231 1.706331 True 0.031900\n", + "bad_ml 14.047965 14.164684 False -0.116719" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "df_res = pd.DataFrame(data)\n", + "df_res = df_res[['before', 'after', 'name', 'in_training']].set_index('name')\n", + "df_res['improvement'] = df_res['before'] - df_res['after']\n", + "df_res.sort_values('improvement', ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# DEBUG" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from IPython.display import display, HTML, Markdown\n", + "import torch\n", + "\n", + "@torch.no_grad()\n", + "def gen(model, inputs, tokenizer, clean=True):\n", + " s = model.generate(\n", + " input_ids=inputs[\"input_ids\"][None, :].to(model.device),\n", + " attention_mask=inputs[\"attention_mask\"][None, :].to(model.device),\n", + " use_cache=False,\n", + " max_new_tokens=100,\n", + " min_new_tokens=100,\n", + " do_sample=False,\n", + " early_stopping=False,\n", + " )\n", + " input_l = inputs[\"input_ids\"].shape[0]\n", + " tokenizer_kwargs=dict(clean_up_tokenization_spaces=clean, skip_special_tokens=clean)\n", + " old = tokenizer.decode(\n", + " s[0, :input_l], **tokenizer_kwargs\n", + " )\n", + " new = tokenizer.decode(\n", + " s[0, input_l:], **tokenizer_kwargs\n", + " )\n", + " s_old = \"\"+old.replace('\\n', '
')\n", + " s_new = '' + new.replace('\\n', '
')+ '

'\n", + " display(HTML(f\"{s_old}{s_new}\"))\n", + " # print([old, new])\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "samples = samples[1]\n", + "\n", + "s = sample['text']\n", + "first_half = s[:len(s)//2]\n", + "second_half = s[len(s)//2:]\n", + "ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + "ds_val = Dataset.from_dict(tokenizer([second_half]))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "with model.disable_adapter():\n", + " gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": ".venv", + "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": "3.11.0rc1" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/nbs/02_use_lora_transformertrain_collate.ipynb b/nbs/02_use_lora_transformertrain_collate.ipynb deleted file mode 100644 index f4a741a..0000000 --- a/nbs/02_use_lora_transformertrain_collate.ipynb +++ /dev/null @@ -1,597 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "https://github.com/huggingface/peft/blob/main/examples/fp4_finetuning/finetune_fp4_opt_bnb_peft.py" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-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": [ - "from torch import optim\n", - "import lightning as pl\n", - "from matplotlib import pyplot as plt" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "import os\n", - "\n", - "import torch\n", - "import torch.nn as nn\n", - "import transformers\n", - "from datasets import load_dataset\n", - "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig\n", - "import numpy as np\n", - "from tqdm.auto import tqdm\n", - "import pandas as pd\n", - "import warnings\n", - "from peft import LoraConfig, get_peft_model, IA3Config" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [], - "source": [ - "plt.style.use('ggplot')\n", - "torch.set_float32_matmul_precision('medium')\n", - "warnings.filterwarnings(\"ignore\", \".*does not have many workers.*\")" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [], - "source": [ - "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n", - "\n", - "model_name = \"microsoft/phi-2\"\n", - "\n", - "# model = AutoModelForCausalLM.from_pretrained(\n", - "# model_name,\n", - "# # max_memory=max_memory,\n", - "# quantization_config=BitsAndBytesConfig(\n", - "# load_in_4bit=True,\n", - "# llm_int8_threshold=6.0,\n", - "# llm_int8_has_fp16_weight=False,\n", - "# bnb_4bit_compute_dtype=torch.float16,\n", - "# bnb_4bit_use_double_quant=True,\n", - "# bnb_4bit_quant_type=\"nf4\",\n", - "# ),\n", - "# torch_dtype=torch.float16,\n", - "# trust_remote_code=True,\n", - "# )\n", - "\n", - "\n", - "\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "model_name = \"TheBloke/phi-2-GPTQ\"\n", - "# model_name = \"microsoft/phi-2\"\n", - "\n", - "def load_model():\n", - "\n", - " # model = AutoModelForCausalLM.from_pretrained(\n", - " # model_name,\n", - " # # quantization_config=BitsAndBytesConfig(\n", - " # # load_in_4bit=True,\n", - " # # llm_int8_threshold=6.0,\n", - " # # llm_int8_has_fp16_weight=False,\n", - " # # bnb_4bit_compute_dtype=torch.float16,\n", - " # # bnb_4bit_use_double_quant=True,\n", - " # # bnb_4bit_quant_type=\"nf4\",\n", - " # # ),\n", - " # torch_dtype=torch.float16,\n", - " # trust_remote_code=True,\n", - " # )\n", - "\n", - "\n", - " config = AutoConfig.from_pretrained(model_name, trust_remote_code=True,)\n", - " config.quantization_config['use_exllama'] = False\n", - " config.quantization_config['disable_exllama'] = True\n", - " model = AutoModelForCausalLM.from_pretrained(\n", - " model_name,\n", - " torch_dtype=torch.bfloat16,\n", - " trust_remote_code=True,\n", - " config=config,\n", - " )\n", - " return model\n" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "CUDA extension not installed.\n", - "CUDA extension not installed.\n" - ] - } - ], - "source": [ - "base_model = load_model()\n", - "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True,)\n", - "tokenizer.pad_token = tokenizer.eos_token" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "def reset_model(base_model):\n", - " peft_config = LoraConfig(\n", - " # task_type=TaskType.TOKEN_CLS, \n", - " target_modules=[ \"fc2\", \"Wqkv\",],\n", - " inference_mode=False, r=8, lora_alpha=8, \n", - " # lora_dropout=0.1, \n", - " # bias=\"all\"\n", - " )\n", - " model = get_peft_model(base_model, peft_config)\n", - " model.config.use_cache = False\n", - " return model\n", - "\n", - "model = reset_model(base_model)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import json\n", - "MAX_LEN = 2000\n", - "samples = json.load(open(\"../samples.json\"))\n" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Helpers" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# modified from https://github.dev/huggingface/evaluate/blob/8dfe05784099fb9af55b8e77793205a3b7c86465/measurements/perplexity/perplexity.py#L154\n", - "\n", - "# from evaluate.measurements.perplexity import Perplexity\n", - "import evaluate\n", - "from evaluate import logging\n", - "from torch.nn import CrossEntropyLoss\n", - "\n", - "# @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)\n", - "def perplexity_compute(\n", - " data, model, tokenizer, batch_size: int = 16, add_start_token: bool = True, device=None, max_length=None\n", - "):\n", - "\n", - " if device is not None:\n", - " assert device in [\"gpu\", \"cpu\", \"cuda\"], \"device should be either gpu or cpu.\"\n", - " if device == \"gpu\":\n", - " device = \"cuda\"\n", - " else:\n", - " device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", - "\n", - " # model = AutoModelForCausalLM.from_pretrained(model_id)\n", - " model = model.to(device)\n", - "\n", - " # tokenizer = AutoTokenizer.from_pretrained(model_id)\n", - "\n", - " # # if batch_size > 1 (which generally leads to padding being required), and\n", - " # # if there is not an already assigned pad_token, assign an existing\n", - " # # special token to also be the padding token\n", - " # if tokenizer.pad_token is None and batch_size > 1:\n", - " # existing_special_tokens = list(tokenizer.special_tokens_map_extended.values())\n", - " # # check that the model already has at least one special token defined\n", - " # assert (\n", - " # len(existing_special_tokens) > 0\n", - " # ), \"If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1.\"\n", - " # # assign one of the special tokens to also be the pad token\n", - " # tokenizer.add_special_tokens({\"pad_token\": existing_special_tokens[0]})\n", - "\n", - " # if add_start_token and max_length:\n", - " # # leave room for token to be added:\n", - " # assert (\n", - " # tokenizer.bos_token is not None\n", - " # ), \"Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False\"\n", - " # max_tokenized_len = max_length - 1\n", - " # else:\n", - " max_tokenized_len = max_length\n", - "\n", - " encodings = tokenizer(\n", - " data,\n", - " add_special_tokens=False,\n", - " padding=True,\n", - " truncation=True if max_tokenized_len else False,\n", - " max_length=max_tokenized_len,\n", - " return_tensors=\"pt\",\n", - " return_attention_mask=True,\n", - " ).to(device)\n", - "\n", - " encoded_texts = encodings[\"input_ids\"]\n", - " attn_masks = encodings[\"attention_mask\"]\n", - "\n", - " # check that each input is long enough:\n", - " if add_start_token:\n", - " assert torch.all(torch.ge(attn_masks.sum(1), 1)), \"Each input text must be at least one token long.\"\n", - " else:\n", - " assert torch.all(\n", - " torch.ge(attn_masks.sum(1), 2)\n", - " ), \"When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings.\"\n", - "\n", - " ppls = []\n", - " loss_fct = CrossEntropyLoss(reduction=\"none\")\n", - "\n", - " for start_index in logging.tqdm(range(0, len(encoded_texts), batch_size)):\n", - " end_index = min(start_index + batch_size, len(encoded_texts))\n", - " encoded_batch = encoded_texts[start_index:end_index]\n", - " attn_mask = attn_masks[start_index:end_index]\n", - "\n", - " # if add_start_token:\n", - " # bos_tokens_tensor = torch.tensor([[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)).to(device)\n", - " # encoded_batch = torch.cat([bos_tokens_tensor, encoded_batch], dim=1)\n", - " # attn_mask = torch.cat(\n", - " # [torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(device), attn_mask], dim=1\n", - " # )\n", - "\n", - " labels = encoded_batch\n", - "\n", - " with torch.no_grad():\n", - " out_logits = model(encoded_batch, attention_mask=attn_mask).logits\n", - " # print(out_logits.shape)\n", - "\n", - " shift_logits = out_logits[..., :-1, :].contiguous()\n", - " shift_labels = labels[..., 1:].contiguous()\n", - " shift_attention_mask_batch = attn_mask[..., 1:].contiguous()\n", - "\n", - " perplexity_batch = torch.exp(\n", - " (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch).sum(1)\n", - " / shift_attention_mask_batch.sum(1)\n", - " )\n", - " # perplexity_batch = torch.exp(\n", - " # (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch)\n", - " # / shift_attention_mask_batch.sum(1)\n", - " # )\n", - " # print(perplexity_batch.shape)\n", - "\n", - " ppls += perplexity_batch.tolist()\n", - "\n", - " return {\"perplexities\": ppls, \"mean_perplexity\": torch.tensor(ppls).mean()}" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# perplexity_compute(\n", - "# second_half, model, tokenizer\n", - "# )" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Training" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from torch.nn import functional as F\n", - "from torch.utils.data import DataLoader, TensorDataset" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Lightning helpers" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "\n", - "\n", - "\n", - "\n", - "def str2xya(s, tokenizer):\n", - " max_len = min(MAX_LEN, len(s))\n", - " input_ids = tokenizer(s, return_tensors=\"pt\")[\"input_ids\"][0]\n", - "\n", - " pad = tokenizer.bos_token_id\n", - " data = []\n", - " for i in range(1, len(input_ids)):\n", - " x = input_ids[:i][-max_len:]\n", - " padding = max_len - len(x)\n", - " x = torch.tensor([pad]*padding + x.tolist())\n", - "\n", - " label_ids = input_ids[i:i+1]\n", - " attention_mask = (x==pad)*1\n", - " data.append(dict(input_ids=x, label_ids=label_ids, attention_mask=attention_mask))\n", - " \n", - " return data\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "def eval(model, tokenizer, second_half):\n", - " model.eval();\n", - " with torch.no_grad():\n", - " with model.disable_adapter():\n", - " results = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", - " results2 = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", - " return dict(before=results['mean_perplexity'].item(), after=results2['mean_perplexity'].item())\n" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Train" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from datasets import Dataset" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "def learn_sample(sample):\n", - " device = 'cuda'\n", - " lr = 4e-3\n", - " epochs = 3\n", - " accum_steps = 16\n", - " batch_size = 1\n", - "\n", - " s = sample['text']\n", - " first_half = s[:len(s)//2]\n", - " second_half = s[len(s)//2:]\n", - " ds_train = Dataset.from_dict(tokenizer([first_half]))\n", - " ds_val = Dataset.from_dict(tokenizer([second_half]))\n", - "\n", - " os.environ['CUDA_VISIBLE_DEVICES']=\"1\"\n", - " verbose = False\n", - " model = reset_model(base_model)\n", - " eval(model, tokenizer, second_half)\n", - " trainer = transformers.Trainer(\n", - " model=model,\n", - " train_dataset=ds_train,\n", - " eval_dataset=ds_val,\n", - " args=transformers.TrainingArguments(\n", - " per_device_train_batch_size=batch_size,\n", - " gradient_accumulation_steps=8,\n", - " warmup_steps=0,\n", - " max_steps=40,\n", - " learning_rate=3e-4,\n", - " fp16=True,\n", - " logging_steps=1,\n", - " output_dir=\"outputs\",\n", - " log_level='error',\n", - " disable_tqdm=not verbose,\n", - " ),\n", - " data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),\n", - " )\n", - " trainer._signature_columns = ['input_ids', 'attention_mask', 'label_ids']\n", - " model.config.use_cache = False # silence the warnings. Please re-enable for inference!\n", - " train_output = trainer.train()\n", - "\n", - " if verbose:\n", - " df_hist = pd.DataFrame(trainer.state.log_history)\n", - " df_hist_epoch = df_hist.groupby('epoch').last().dropna(axis=1).drop(columns=['step'])\n", - " df_hist_step = df_hist.set_index('step').dropna(thresh=2, axis=1)\n", - " for c in df_hist_epoch.columns:\n", - " df_hist_epoch[[c]].plot()\n", - "\n", - "\n", - " result = eval(model, tokenizer, second_half)\n", - " return result\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "data = []\n", - "for sample in samples:\n", - " print(sample['name'])\n", - " r = learn_sample(sample)\n", - " print(r)\n", - " data.append(dict(**r, **sample))" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "df_res = pd.DataFrame(data)\n", - "df_res = df_res[['before', 'after', 'name', 'in_training']]\n", - "df_res['improvement'] = df_res['before'] - df_res['after']\n", - "df_res" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# DEBUG" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from IPython.display import display, HTML, Markdown\n", - "import torch\n", - "\n", - "@torch.no_grad()\n", - "def gen(model, inputs, tokenizer, clean=True):\n", - " s = model.generate(\n", - " input_ids=inputs[\"input_ids\"][None, :].to(model.device),\n", - " attention_mask=inputs[\"attention_mask\"][None, :].to(model.device),\n", - " use_cache=False,\n", - " max_new_tokens=100,\n", - " min_new_tokens=100,\n", - " do_sample=False,\n", - " early_stopping=False,\n", - " )\n", - " input_l = inputs[\"input_ids\"].shape[0]\n", - " tokenizer_kwargs=dict(clean_up_tokenization_spaces=clean, skip_special_tokens=clean)\n", - " old = tokenizer.decode(\n", - " s[0, :input_l], **tokenizer_kwargs\n", - " )\n", - " new = tokenizer.decode(\n", - " s[0, input_l:], **tokenizer_kwargs\n", - " )\n", - " s_old = \"\"+old.replace('\\n', '
')\n", - " s_new = '' + new.replace('\\n', '
')+ '

'\n", - " display(HTML(f\"{s_old}{s_new}\"))\n", - " # print([old, new])\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "samples = samples[1]\n", - "\n", - "s = sample['text']\n", - "first_half = s[:len(s)//2]\n", - "second_half = s[len(s)//2:]\n", - "ds_train = Dataset.from_dict(tokenizer([first_half]))\n", - "ds_val = Dataset.from_dict(tokenizer([second_half]))" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "with model.disable_adapter():\n", - " gen(model, ds_train.with_format('pt')[0], tokenizer)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "gen(model, ds_train.with_format('pt')[0], tokenizer)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": ".venv", - "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": "3.11.0rc1" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/nbs/03_use_ia3_hftrain .ipynb b/nbs/03_use_ia3_hftrain .ipynb new file mode 100644 index 0000000..a49eede --- /dev/null +++ b/nbs/03_use_ia3_hftrain .ipynb @@ -0,0 +1,6106 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "https://github.com/huggingface/peft/blob/main/examples/fp4_finetuning/finetune_fp4_opt_bnb_peft.py" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-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": [ + "from torch import optim\n", + "import lightning as pl\n", + "from matplotlib import pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import transformers\n", + "from datasets import load_dataset\n", + "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig\n", + "import numpy as np\n", + "from tqdm.auto import tqdm\n", + "import pandas as pd\n", + "import warnings\n", + "from peft import LoraConfig, get_peft_model, IA3Config" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "plt.style.use('ggplot')\n", + "torch.set_float32_matmul_precision('medium')\n", + "warnings.filterwarnings(\"ignore\", \".*does not have many workers.*\")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n", + "\n", + "model_name = \"microsoft/phi-2\"\n", + "\n", + "# model = AutoModelForCausalLM.from_pretrained(\n", + "# model_name,\n", + "# # max_memory=max_memory,\n", + "# quantization_config=BitsAndBytesConfig(\n", + "# load_in_4bit=True,\n", + "# llm_int8_threshold=6.0,\n", + "# llm_int8_has_fp16_weight=False,\n", + "# bnb_4bit_compute_dtype=torch.float16,\n", + "# bnb_4bit_use_double_quant=True,\n", + "# bnb_4bit_quant_type=\"nf4\",\n", + "# ),\n", + "# torch_dtype=torch.float16,\n", + "# trust_remote_code=True,\n", + "# )\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "# model_name = \"TheBloke/phi-2-GPTQ\"\n", + "model_name = \"microsoft/phi-2\"\n", + "\n", + "def load_model():\n", + "\n", + " model = AutoModelForCausalLM.from_pretrained(\n", + " model_name,\n", + " # quantization_config=BitsAndBytesConfig(\n", + " # load_in_4bit=True,\n", + " # llm_int8_threshold=6.0,\n", + " # llm_int8_has_fp16_weight=False,\n", + " # bnb_4bit_compute_dtype=torch.float16,\n", + " # bnb_4bit_use_double_quant=True,\n", + " # bnb_4bit_quant_type=\"nf4\",\n", + " # ),\n", + " torch_dtype=torch.float16,\n", + " trust_remote_code=True,\n", + " )\n", + "\n", + "\n", + " # config = AutoConfig.from_pretrained(model_name, trust_remote_code=True,)\n", + " # config.quantization_config['use_exllama'] = False\n", + " # config.quantization_config['disable_exllama'] = True\n", + " # model = AutoModelForCausalLM.from_pretrained(\n", + " # model_name,\n", + " # torch_dtype=torch.bfloat16,\n", + " # trust_remote_code=True,\n", + " # config=config,\n", + " # )\n", + " return model\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.85it/s]\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n" + ] + } + ], + "source": [ + "base_model = load_model()\n", + "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True,)\n", + "tokenizer.pad_token = tokenizer.eos_token" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "def reset_model(base_model):\n", + " # peft_config = LoraConfig(\n", + " # # task_type=TaskType.TOKEN_CLS, \n", + " # target_modules=[ \"fc2\", \"Wqkv\",],\n", + " # inference_mode=False, r=4, lora_alpha=4, \n", + " # # lora_dropout=0.1, \n", + " # # bias=\"all\"\n", + " # )\n", + " peft_config = IA3Config(\n", + " target_modules=[ \"fc2\", \"Wqkv\",], \n", + " feedforward_modules=[\"fc2\"],\n", + " inference_mode=False,\n", + " )\n", + " model = get_peft_model(base_model, peft_config)\n", + " model.config.use_cache = False\n", + " return model\n", + "\n", + "model = reset_model(base_model)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "MAX_LEN = 2000\n", + "samples = json.load(open(\"../samples.json\"))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "# modified from https://github.dev/huggingface/evaluate/blob/8dfe05784099fb9af55b8e77793205a3b7c86465/measurements/perplexity/perplexity.py#L154\n", + "\n", + "# from evaluate.measurements.perplexity import Perplexity\n", + "import evaluate\n", + "from evaluate import logging\n", + "from torch.nn import CrossEntropyLoss\n", + "\n", + "# @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)\n", + "def perplexity_compute(\n", + " data, model, tokenizer, batch_size: int = 16, add_start_token: bool = True, device=None, max_length=None\n", + "):\n", + "\n", + " if device is not None:\n", + " assert device in [\"gpu\", \"cpu\", \"cuda\"], \"device should be either gpu or cpu.\"\n", + " if device == \"gpu\":\n", + " device = \"cuda\"\n", + " else:\n", + " device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "\n", + " # model = AutoModelForCausalLM.from_pretrained(model_id)\n", + " model = model.to(device)\n", + "\n", + " # tokenizer = AutoTokenizer.from_pretrained(model_id)\n", + "\n", + " # # if batch_size > 1 (which generally leads to padding being required), and\n", + " # # if there is not an already assigned pad_token, assign an existing\n", + " # # special token to also be the padding token\n", + " # if tokenizer.pad_token is None and batch_size > 1:\n", + " # existing_special_tokens = list(tokenizer.special_tokens_map_extended.values())\n", + " # # check that the model already has at least one special token defined\n", + " # assert (\n", + " # len(existing_special_tokens) > 0\n", + " # ), \"If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1.\"\n", + " # # assign one of the special tokens to also be the pad token\n", + " # tokenizer.add_special_tokens({\"pad_token\": existing_special_tokens[0]})\n", + "\n", + " # if add_start_token and max_length:\n", + " # # leave room for token to be added:\n", + " # assert (\n", + " # tokenizer.bos_token is not None\n", + " # ), \"Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False\"\n", + " # max_tokenized_len = max_length - 1\n", + " # else:\n", + " max_tokenized_len = max_length\n", + "\n", + " encodings = tokenizer(\n", + " data,\n", + " add_special_tokens=False,\n", + " padding=True,\n", + " truncation=True if max_tokenized_len else False,\n", + " max_length=max_tokenized_len,\n", + " return_tensors=\"pt\",\n", + " return_attention_mask=True,\n", + " ).to(device)\n", + "\n", + " encoded_texts = encodings[\"input_ids\"]\n", + " attn_masks = encodings[\"attention_mask\"]\n", + "\n", + " # check that each input is long enough:\n", + " if add_start_token:\n", + " assert torch.all(torch.ge(attn_masks.sum(1), 1)), \"Each input text must be at least one token long.\"\n", + " else:\n", + " assert torch.all(\n", + " torch.ge(attn_masks.sum(1), 2)\n", + " ), \"When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings.\"\n", + "\n", + " ppls = []\n", + " loss_fct = CrossEntropyLoss(reduction=\"none\")\n", + "\n", + " for start_index in logging.tqdm(range(0, len(encoded_texts), batch_size)):\n", + " end_index = min(start_index + batch_size, len(encoded_texts))\n", + " encoded_batch = encoded_texts[start_index:end_index]\n", + " attn_mask = attn_masks[start_index:end_index]\n", + "\n", + " # if add_start_token:\n", + " # bos_tokens_tensor = torch.tensor([[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)).to(device)\n", + " # encoded_batch = torch.cat([bos_tokens_tensor, encoded_batch], dim=1)\n", + " # attn_mask = torch.cat(\n", + " # [torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(device), attn_mask], dim=1\n", + " # )\n", + "\n", + " labels = encoded_batch\n", + "\n", + " with torch.no_grad():\n", + " out_logits = model(encoded_batch, attention_mask=attn_mask).logits\n", + " # print(out_logits.shape)\n", + "\n", + " shift_logits = out_logits[..., :-1, :].contiguous()\n", + " shift_labels = labels[..., 1:].contiguous()\n", + " shift_attention_mask_batch = attn_mask[..., 1:].contiguous()\n", + "\n", + " perplexity_batch = torch.exp(\n", + " (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch).sum(1)\n", + " / shift_attention_mask_batch.sum(1)\n", + " )\n", + " # perplexity_batch = torch.exp(\n", + " # (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch)\n", + " # / shift_attention_mask_batch.sum(1)\n", + " # )\n", + " # print(perplexity_batch.shape)\n", + "\n", + " ppls += perplexity_batch.tolist()\n", + "\n", + " return {\"perplexities\": ppls, \"mean_perplexity\": torch.tensor(ppls).mean()}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [], + "source": [ + "# perplexity_compute(\n", + "# second_half, model, tokenizer\n", + "# )" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Training" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "from torch.nn import functional as F\n", + "from torch.utils.data import DataLoader, TensorDataset" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Lightning helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "\n", + "\n", + "# def str2xya(s, tokenizer):\n", + "# max_len = min(MAX_LEN, len(s))\n", + "# input_ids = tokenizer(s, return_tensors=\"pt\")[\"input_ids\"][0]\n", + "\n", + "# pad = tokenizer.bos_token_id\n", + "# data = []\n", + "# for i in range(1, len(input_ids)):\n", + "# x = input_ids[:i][-max_len:]\n", + "# padding = max_len - len(x)\n", + "# x = torch.tensor([pad]*padding + x.tolist())\n", + "\n", + "# labels = input_ids[i:i+1]\n", + "# attention_mask = (x==pad)*1\n", + "# data.append(dict(input_ids=x, labels=labels, attention_mask=attention_mask, return_loss=True))\n", + " \n", + "# return data\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "def eval(model, tokenizer, second_half):\n", + " model.eval();\n", + " with torch.no_grad():\n", + " with model.disable_adapter():\n", + " results = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " results2 = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " return dict(before=results['mean_perplexity'].item(), after=results2['mean_perplexity'].item())\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Train" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "from datasets import Dataset\n", + "\n", + "\n", + "def compute_metrics(eval_prediction):\n", + " return {}" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trainer docs\n", + "\n", + "- https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "def learn_sample(sample):\n", + " # device = 'cuda'\n", + " # lr = 4e-3\n", + " # epochs = 3\n", + " # accum_steps = 1\n", + " batch_size = 6\n", + " verbose = True\n", + "\n", + " s = sample['text']\n", + " first_half = s[:len(s)//2]\n", + " second_half = s[len(s)//2:]\n", + " ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + " ds_val = Dataset.from_dict(tokenizer([second_half]))\n", + "\n", + " os.environ['CUDA_VISIBLE_DEVICES']=\"1\"\n", + " model = reset_model(base_model)\n", + " eval(model, tokenizer, second_half)\n", + "\n", + " # https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer\n", + " trainer = transformers.Trainer(\n", + " model=model,\n", + " train_dataset=ds_train,\n", + " eval_dataset=ds_val,\n", + " compute_metrics=compute_metrics, # without this it wont even give val loss\n", + " args=transformers.TrainingArguments(\n", + " # checkpoint='epoch',\n", + " save_strategy='epoch',\n", + " label_names=['labels',],\n", + " per_device_train_batch_size=batch_size,\n", + " gradient_accumulation_steps=3,\n", + " warmup_steps=6,\n", + " max_steps=20,\n", + " learning_rate=2e-3,\n", + " fp16=True,\n", + " logging_steps=1,\n", + " output_dir=\"outputs\",\n", + " log_level='error',\n", + " # do_eval=True,\n", + " evaluation_strategy=\"epoch\",\n", + " eval_steps=1,\n", + " load_best_model_at_end=True,\n", + " \n", + " # disable_tqdm=not verbose,\n", + " ),\n", + " data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),\n", + " )\n", + " trainer._signature_columns = ['input_ids', 'attention_mask', 'labels',]\n", + " model.config.use_cache = False # silence the warnings. Please re-enable for inference!\n", + " train_output = trainer.train()\n", + "\n", + " df_hist = pd.DataFrame(trainer.state.log_history)\n", + " df_hist_epoch = df_hist.groupby('epoch').last().drop(columns=['step'])\n", + " df_hist_step = df_hist.set_index('step').dropna(thresh=2, axis=1)\n", + " if verbose:\n", + " df_hist_epoch['loss'].plot()\n", + " plt.twinx()\n", + " df_hist_epoch['eval_loss'].plot(c='b', label='eval')\n", + " plt.legend()\n", + " plt.show()\n", + "\n", + "\n", + " result_train = {f'train/{k}':v for k,v in eval(model, tokenizer, first_half).items()}\n", + " result = eval(model, tokenizer, second_half)\n", + " result['hist'] = df_hist_epoch\n", + " result.update(result_train)\n", + " return result\n" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 5.37it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.16it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + " 0%| | 0/20 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.87it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.29it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.77it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.18it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "bad_ml\n", + "{'before': 13.906105995178223, 'after': 13.862305641174316}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.47it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.95it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1471, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.3446907997131348, 'eval_runtime': 0.0514, 'eval_samples_per_second': 19.443, 'eval_steps_per_second': 19.443, 'epoch': 1.0}\n", + "{'loss': 1.1413, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.3427512645721436, 'eval_runtime': 0.0519, 'eval_samples_per_second': 19.286, 'eval_steps_per_second': 19.286, 'epoch': 2.0}\n", + "{'loss': 1.1074, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.3391706943511963, 'eval_runtime': 0.0457, 'eval_samples_per_second': 21.87, 'eval_steps_per_second': 21.87, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0979, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 3.3322410583496094, 'eval_runtime': 0.0462, 'eval_samples_per_second': 21.661, 'eval_steps_per_second': 21.661, 'epoch': 4.0}\n", + "{'loss': 1.0826, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.3301784992218018, 'eval_runtime': 0.0469, 'eval_samples_per_second': 21.311, 'eval_steps_per_second': 21.311, 'epoch': 5.0}\n", + "{'loss': 1.056, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 3.3214917182922363, 'eval_runtime': 0.0464, 'eval_samples_per_second': 21.559, 'eval_steps_per_second': 21.559, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0074, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 3.3130364418029785, 'eval_runtime': 0.0458, 'eval_samples_per_second': 21.835, 'eval_steps_per_second': 21.835, 'epoch': 7.0}\n", + "{'loss': 0.9524, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.3035030364990234, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.991, 'eval_steps_per_second': 21.991, 'epoch': 8.0}\n", + "{'loss': 0.9138, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.298600196838379, 'eval_runtime': 0.0463, 'eval_samples_per_second': 21.59, 'eval_steps_per_second': 21.59, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8819, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 3.294665813446045, 'eval_runtime': 0.0459, 'eval_samples_per_second': 21.806, 'eval_steps_per_second': 21.806, 'epoch': 10.0}\n", + "{'loss': 0.8619, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 3.2902116775512695, 'eval_runtime': 0.0459, 'eval_samples_per_second': 21.783, 'eval_steps_per_second': 21.783, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8455, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 3.2865536212921143, 'eval_runtime': 0.0475, 'eval_samples_per_second': 21.07, 'eval_steps_per_second': 21.07, 'epoch': 12.0}\n", + "{'loss': 0.8071, 'learning_rate': 0.001, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.283342123031616, 'eval_runtime': 0.0473, 'eval_samples_per_second': 21.123, 'eval_steps_per_second': 21.123, 'epoch': 13.0}\n", + "{'loss': 0.7878, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 3.2826781272888184, 'eval_runtime': 0.0457, 'eval_samples_per_second': 21.86, 'eval_steps_per_second': 21.86, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7665, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.27935791015625, 'eval_runtime': 0.047, 'eval_samples_per_second': 21.273, 'eval_steps_per_second': 21.273, 'epoch': 15.0}\n", + "{'loss': 0.7461, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.277428150177002, 'eval_runtime': 0.0471, 'eval_samples_per_second': 21.212, 'eval_steps_per_second': 21.212, 'epoch': 16.0}\n", + "{'loss': 0.7316, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 3.2803244590759277, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.961, 'eval_steps_per_second': 21.961, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7258, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.2791643142700195, 'eval_runtime': 0.0477, 'eval_samples_per_second': 20.96, 'eval_steps_per_second': 20.96, 'epoch': 18.0}\n", + "{'loss': 0.7076, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2756590843200684, 'eval_runtime': 0.0447, 'eval_samples_per_second': 22.354, 'eval_steps_per_second': 22.354, 'epoch': 19.0}\n", + "{'loss': 0.7127, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 3.278388738632202, 'eval_runtime': 0.0471, 'eval_samples_per_second': 21.234, 'eval_steps_per_second': 21.234, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'train_runtime': 3.4493, 'train_samples_per_second': 208.739, 'train_steps_per_second': 5.798, 'train_loss': 0.9040146082639694, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.73it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.09it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.51it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.06it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "good_ml\n", + "{'before': 28.347332000732422, 'after': 26.456573486328125}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.51it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.03it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8976, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 2.770636796951294, 'eval_runtime': 0.082, 'eval_samples_per_second': 12.201, 'eval_steps_per_second': 12.201, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8932, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 2.7694220542907715, 'eval_runtime': 0.0811, 'eval_samples_per_second': 12.334, 'eval_steps_per_second': 12.334, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8782, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 2.7660436630249023, 'eval_runtime': 0.0817, 'eval_samples_per_second': 12.233, 'eval_steps_per_second': 12.233, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.877, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 2.7656893730163574, 'eval_runtime': 0.084, 'eval_samples_per_second': 11.902, 'eval_steps_per_second': 11.902, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8601, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 2.762709140777588, 'eval_runtime': 0.0833, 'eval_samples_per_second': 12.011, 'eval_steps_per_second': 12.011, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8495, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 2.7619409561157227, 'eval_runtime': 0.0819, 'eval_samples_per_second': 12.212, 'eval_steps_per_second': 12.212, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8031, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 2.756824016571045, 'eval_runtime': 0.0836, 'eval_samples_per_second': 11.955, 'eval_steps_per_second': 11.955, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7805, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 2.7579498291015625, 'eval_runtime': 0.0821, 'eval_samples_per_second': 12.181, 'eval_steps_per_second': 12.181, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7545, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 2.756481409072876, 'eval_runtime': 0.0849, 'eval_samples_per_second': 11.776, 'eval_steps_per_second': 11.776, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7221, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 2.754746675491333, 'eval_runtime': 0.0812, 'eval_samples_per_second': 12.323, 'eval_steps_per_second': 12.323, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.697, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 2.7567291259765625, 'eval_runtime': 0.0826, 'eval_samples_per_second': 12.101, 'eval_steps_per_second': 12.101, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6809, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 2.7562639713287354, 'eval_runtime': 0.0844, 'eval_samples_per_second': 11.849, 'eval_steps_per_second': 11.849, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6618, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 2.7598867416381836, 'eval_runtime': 0.0821, 'eval_samples_per_second': 12.174, 'eval_steps_per_second': 12.174, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6502, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 2.7595736980438232, 'eval_runtime': 0.0846, 'eval_samples_per_second': 11.819, 'eval_steps_per_second': 11.819, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6368, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 2.7620177268981934, 'eval_runtime': 0.0844, 'eval_samples_per_second': 11.849, 'eval_steps_per_second': 11.849, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6319, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 2.764033555984497, 'eval_runtime': 0.0814, 'eval_samples_per_second': 12.291, 'eval_steps_per_second': 12.291, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6105, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 2.7691619396209717, 'eval_runtime': 0.0831, 'eval_samples_per_second': 12.031, 'eval_steps_per_second': 12.031, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6122, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 2.768242835998535, 'eval_runtime': 0.0841, 'eval_samples_per_second': 11.892, 'eval_steps_per_second': 11.892, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6035, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 2.7695817947387695, 'eval_runtime': 0.0831, 'eval_samples_per_second': 12.039, 'eval_steps_per_second': 12.039, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5964, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 2.7675888538360596, 'eval_runtime': 0.0824, 'eval_samples_per_second': 12.129, 'eval_steps_per_second': 12.129, 'epoch': 20.0}\n", + "{'train_runtime': 5.2175, 'train_samples_per_second': 137.998, 'train_steps_per_second': 3.833, 'train_loss': 0.7348627179861069, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.17it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.97it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.28it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.49it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "sokal hoax\n", + "{'before': 15.966412544250488, 'after': 15.714754104614258}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.07it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.99it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0657, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.294236421585083, 'eval_runtime': 0.0664, 'eval_samples_per_second': 15.051, 'eval_steps_per_second': 15.051, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0643, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 3.2933406829833984, 'eval_runtime': 0.0645, 'eval_samples_per_second': 15.501, 'eval_steps_per_second': 15.501, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.049, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.2884457111358643, 'eval_runtime': 0.0594, 'eval_samples_per_second': 16.841, 'eval_steps_per_second': 16.841, 'epoch': 3.0}\n", + "{'loss': 1.031, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2826619148254395, 'eval_runtime': 0.0603, 'eval_samples_per_second': 16.594, 'eval_steps_per_second': 16.594, 'epoch': 4.0}\n", + "{'loss': 1.0147, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2724156379699707, 'eval_runtime': 0.0612, 'eval_samples_per_second': 16.333, 'eval_steps_per_second': 16.333, 'epoch': 5.0}\n", + "{'loss': 0.9806, 'learning_rate': 0.002, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2572481632232666, 'eval_runtime': 0.0596, 'eval_samples_per_second': 16.77, 'eval_steps_per_second': 16.77, 'epoch': 6.0}\n", + "{'loss': 0.9593, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.245199203491211, 'eval_runtime': 0.0611, 'eval_samples_per_second': 16.371, 'eval_steps_per_second': 16.371, 'epoch': 7.0}\n", + "{'loss': 0.906, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 3.2294065952301025, 'eval_runtime': 0.06, 'eval_samples_per_second': 16.654, 'eval_steps_per_second': 16.654, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8816, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.225297212600708, 'eval_runtime': 0.0611, 'eval_samples_per_second': 16.379, 'eval_steps_per_second': 16.379, 'epoch': 9.0}\n", + "{'loss': 0.8374, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.222148895263672, 'eval_runtime': 0.0601, 'eval_samples_per_second': 16.636, 'eval_steps_per_second': 16.636, 'epoch': 10.0}\n", + "{'loss': 0.8355, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2083401679992676, 'eval_runtime': 0.061, 'eval_samples_per_second': 16.405, 'eval_steps_per_second': 16.405, 'epoch': 11.0}\n", + "{'loss': 0.8047, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2118797302246094, 'eval_runtime': 0.061, 'eval_samples_per_second': 16.4, 'eval_steps_per_second': 16.4, 'epoch': 12.0}\n", + "{'loss': 0.7823, 'learning_rate': 0.001, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2061452865600586, 'eval_runtime': 0.0601, 'eval_samples_per_second': 16.637, 'eval_steps_per_second': 16.637, 'epoch': 13.0}\n", + "{'loss': 0.7662, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 3.206078052520752, 'eval_runtime': 0.0584, 'eval_samples_per_second': 17.135, 'eval_steps_per_second': 17.135, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7484, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.201680898666382, 'eval_runtime': 0.0601, 'eval_samples_per_second': 16.626, 'eval_steps_per_second': 16.626, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7341, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 3.200582265853882, 'eval_runtime': 0.0595, 'eval_samples_per_second': 16.818, 'eval_steps_per_second': 16.818, 'epoch': 16.0}\n", + "{'loss': 0.7348, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.206627130508423, 'eval_runtime': 0.0591, 'eval_samples_per_second': 16.92, 'eval_steps_per_second': 16.92, 'epoch': 17.0}\n", + "{'loss': 0.7258, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.2030231952667236, 'eval_runtime': 0.059, 'eval_samples_per_second': 16.947, 'eval_steps_per_second': 16.947, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7164, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 3.202587842941284, 'eval_runtime': 0.058, 'eval_samples_per_second': 17.244, 'eval_steps_per_second': 17.244, 'epoch': 19.0}\n", + "{'loss': 0.7088, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 3.201478958129883, 'eval_runtime': 0.0595, 'eval_samples_per_second': 16.805, 'eval_steps_per_second': 16.805, 'epoch': 20.0}\n", + "{'train_runtime': 4.087, 'train_samples_per_second': 176.17, 'train_steps_per_second': 4.894, 'train_loss': 0.8673275351524353, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.26it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.93it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.43it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.99it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Theory o. general relativity\n", + "{'before': 26.952022552490234, 'after': 24.542512893676758}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.53it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.94it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.1165, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 0.4710708558559418, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.966, 'eval_steps_per_second': 21.966, 'epoch': 1.0}\n", + "{'loss': 0.1141, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.47040221095085144, 'eval_runtime': 0.0429, 'eval_samples_per_second': 23.295, 'eval_steps_per_second': 23.295, 'epoch': 2.0}\n", + "{'loss': 0.1209, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 0.46998435258865356, 'eval_runtime': 0.0434, 'eval_samples_per_second': 23.017, 'eval_steps_per_second': 23.017, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.1018, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 0.47150325775146484, 'eval_runtime': 0.0437, 'eval_samples_per_second': 22.874, 'eval_steps_per_second': 22.874, 'epoch': 4.0}\n", + "{'loss': 0.0845, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 0.4715323746204376, 'eval_runtime': 0.043, 'eval_samples_per_second': 23.254, 'eval_steps_per_second': 23.254, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0616, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 0.4763885736465454, 'eval_runtime': 0.0427, 'eval_samples_per_second': 23.398, 'eval_steps_per_second': 23.398, 'epoch': 6.0}\n", + "{'loss': 0.0433, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 0.47699809074401855, 'eval_runtime': 0.0439, 'eval_samples_per_second': 22.771, 'eval_steps_per_second': 22.771, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0455, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 0.47627171874046326, 'eval_runtime': 0.0417, 'eval_samples_per_second': 23.97, 'eval_steps_per_second': 23.97, 'epoch': 8.0}\n", + "{'loss': 0.0349, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 0.47513699531555176, 'eval_runtime': 0.0444, 'eval_samples_per_second': 22.529, 'eval_steps_per_second': 22.529, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0251, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 0.4725719392299652, 'eval_runtime': 0.043, 'eval_samples_per_second': 23.233, 'eval_steps_per_second': 23.233, 'epoch': 10.0}\n", + "{'loss': 0.0265, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 0.47139081358909607, 'eval_runtime': 0.0441, 'eval_samples_per_second': 22.653, 'eval_steps_per_second': 22.653, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0244, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 0.47071537375450134, 'eval_runtime': 0.0429, 'eval_samples_per_second': 23.33, 'eval_steps_per_second': 23.33, 'epoch': 12.0}\n", + "{'loss': 0.024, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 0.46806150674819946, 'eval_runtime': 0.0441, 'eval_samples_per_second': 22.656, 'eval_steps_per_second': 22.656, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.022, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 0.467593252658844, 'eval_runtime': 0.0445, 'eval_samples_per_second': 22.488, 'eval_steps_per_second': 22.488, 'epoch': 14.0}\n", + "{'loss': 0.0096, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.4675810933113098, 'eval_runtime': 0.0417, 'eval_samples_per_second': 23.995, 'eval_steps_per_second': 23.995, 'epoch': 15.0}\n", + "{'loss': 0.0123, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 0.4671429693698883, 'eval_runtime': 0.0438, 'eval_samples_per_second': 22.851, 'eval_steps_per_second': 22.851, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0093, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 0.4678424596786499, 'eval_runtime': 0.0425, 'eval_samples_per_second': 23.51, 'eval_steps_per_second': 23.51, 'epoch': 17.0}\n", + "{'loss': 0.0082, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 0.4684832692146301, 'eval_runtime': 0.046, 'eval_samples_per_second': 21.741, 'eval_steps_per_second': 21.741, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.0115, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 0.46846842765808105, 'eval_runtime': 0.0434, 'eval_samples_per_second': 23.033, 'eval_steps_per_second': 23.033, 'epoch': 19.0}\n", + "{'loss': 0.007, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 0.46743687987327576, 'eval_runtime': 0.0426, 'eval_samples_per_second': 23.455, 'eval_steps_per_second': 23.455, 'epoch': 20.0}\n", + "{'train_runtime': 3.1449, 'train_samples_per_second': 228.939, 'train_steps_per_second': 6.359, 'train_loss': 0.045142221334390345, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.36it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.86it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.42it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.94it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "lorem ipsum \n", + "{'before': 1.6016581058502197, 'after': 1.5953787565231323}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.35it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.89it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9544, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.472707509994507, 'eval_runtime': 0.0454, 'eval_samples_per_second': 22.024, 'eval_steps_per_second': 22.024, 'epoch': 1.0}\n", + "{'loss': 0.9445, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.469721794128418, 'eval_runtime': 0.0483, 'eval_samples_per_second': 20.686, 'eval_steps_per_second': 20.686, 'epoch': 2.0}\n", + "{'loss': 0.946, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.4643774032592773, 'eval_runtime': 0.0463, 'eval_samples_per_second': 21.589, 'eval_steps_per_second': 21.589, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9389, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 3.4600937366485596, 'eval_runtime': 0.0468, 'eval_samples_per_second': 21.362, 'eval_steps_per_second': 21.362, 'epoch': 4.0}\n", + "{'loss': 0.9084, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.451901912689209, 'eval_runtime': 0.0482, 'eval_samples_per_second': 20.748, 'eval_steps_per_second': 20.748, 'epoch': 5.0}\n", + "{'loss': 0.8894, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 3.4409453868865967, 'eval_runtime': 0.0469, 'eval_samples_per_second': 21.313, 'eval_steps_per_second': 21.313, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8561, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 3.4258673191070557, 'eval_runtime': 0.0492, 'eval_samples_per_second': 20.329, 'eval_steps_per_second': 20.329, 'epoch': 7.0}\n", + "{'loss': 0.8003, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.4128029346466064, 'eval_runtime': 0.047, 'eval_samples_per_second': 21.28, 'eval_steps_per_second': 21.28, 'epoch': 8.0}\n", + "{'loss': 0.7699, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.402852773666382, 'eval_runtime': 0.0461, 'eval_samples_per_second': 21.708, 'eval_steps_per_second': 21.708, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7424, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 3.3996169567108154, 'eval_runtime': 0.0474, 'eval_samples_per_second': 21.116, 'eval_steps_per_second': 21.116, 'epoch': 10.0}\n", + "{'loss': 0.7199, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.3883135318756104, 'eval_runtime': 0.0461, 'eval_samples_per_second': 21.686, 'eval_steps_per_second': 21.686, 'epoch': 11.0}\n", + "{'loss': 0.7013, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 3.3812174797058105, 'eval_runtime': 0.0474, 'eval_samples_per_second': 21.091, 'eval_steps_per_second': 21.091, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6796, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 3.3781800270080566, 'eval_runtime': 0.0476, 'eval_samples_per_second': 20.998, 'eval_steps_per_second': 20.998, 'epoch': 13.0}\n", + "{'loss': 0.6666, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.371669054031372, 'eval_runtime': 0.0476, 'eval_samples_per_second': 21.029, 'eval_steps_per_second': 21.029, 'epoch': 14.0}\n", + "{'loss': 0.6623, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.369558811187744, 'eval_runtime': 0.0467, 'eval_samples_per_second': 21.408, 'eval_steps_per_second': 21.408, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6331, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 3.3651580810546875, 'eval_runtime': 0.0469, 'eval_samples_per_second': 21.336, 'eval_steps_per_second': 21.336, 'epoch': 16.0}\n", + "{'loss': 0.6301, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.36873459815979, 'eval_runtime': 0.0467, 'eval_samples_per_second': 21.409, 'eval_steps_per_second': 21.409, 'epoch': 17.0}\n", + "{'loss': 0.6198, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.362344264984131, 'eval_runtime': 0.047, 'eval_samples_per_second': 21.266, 'eval_steps_per_second': 21.266, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6147, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 3.365997552871704, 'eval_runtime': 0.0475, 'eval_samples_per_second': 21.067, 'eval_steps_per_second': 21.067, 'epoch': 19.0}\n", + "{'loss': 0.5957, 'learning_rate': 0.0, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.3667006492614746, 'eval_runtime': 0.0476, 'eval_samples_per_second': 21.003, 'eval_steps_per_second': 21.003, 'epoch': 20.0}\n", + "{'train_runtime': 3.2509, 'train_samples_per_second': 221.479, 'train_steps_per_second': 6.152, 'train_loss': 0.7636661320924759, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.31it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.10it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.74it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.20it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "wikipedia on LK-99\n", + "{'before': 32.219017028808594, 'after': 28.852493286132812}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.45it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.86it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5053, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 0.7548888921737671, 'eval_runtime': 0.0432, 'eval_samples_per_second': 23.134, 'eval_steps_per_second': 23.134, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4909, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 0.7530910968780518, 'eval_runtime': 0.0452, 'eval_samples_per_second': 22.101, 'eval_steps_per_second': 22.101, 'epoch': 2.0}\n", + "{'loss': 0.505, 'learning_rate': 0.001, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.7560164332389832, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.979, 'eval_steps_per_second': 21.979, 'epoch': 3.0}\n", + "{'loss': 0.4813, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 0.7553694248199463, 'eval_runtime': 0.0462, 'eval_samples_per_second': 21.651, 'eval_steps_per_second': 21.651, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4292, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 0.7545289397239685, 'eval_runtime': 0.0438, 'eval_samples_per_second': 22.822, 'eval_steps_per_second': 22.822, 'epoch': 5.0}\n", + "{'loss': 0.4078, 'learning_rate': 0.002, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.7601871490478516, 'eval_runtime': 0.0454, 'eval_samples_per_second': 22.049, 'eval_steps_per_second': 22.049, 'epoch': 6.0}\n", + "{'loss': 0.3897, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 0.7599422335624695, 'eval_runtime': 0.0453, 'eval_samples_per_second': 22.06, 'eval_steps_per_second': 22.06, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3686, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 0.770047128200531, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.956, 'eval_steps_per_second': 21.956, 'epoch': 8.0}\n", + "{'loss': 0.3446, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.7731327414512634, 'eval_runtime': 0.0478, 'eval_samples_per_second': 20.914, 'eval_steps_per_second': 20.914, 'epoch': 9.0}\n", + "{'loss': 0.3145, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 0.7693179249763489, 'eval_runtime': 0.0451, 'eval_samples_per_second': 22.166, 'eval_steps_per_second': 22.166, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3055, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 0.7710816264152527, 'eval_runtime': 0.0465, 'eval_samples_per_second': 21.489, 'eval_steps_per_second': 21.489, 'epoch': 11.0}\n", + "{'loss': 0.2886, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 0.775175154209137, 'eval_runtime': 0.0451, 'eval_samples_per_second': 22.171, 'eval_steps_per_second': 22.171, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.2834, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 0.7782232165336609, 'eval_runtime': 0.0461, 'eval_samples_per_second': 21.704, 'eval_steps_per_second': 21.704, 'epoch': 13.0}\n", + "{'loss': 0.2713, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.781578004360199, 'eval_runtime': 0.0452, 'eval_samples_per_second': 22.101, 'eval_steps_per_second': 22.101, 'epoch': 14.0}\n", + "{'loss': 0.2506, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 0.780716598033905, 'eval_runtime': 0.0468, 'eval_samples_per_second': 21.367, 'eval_steps_per_second': 21.367, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.248, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 0.7813991904258728, 'eval_runtime': 0.0446, 'eval_samples_per_second': 22.42, 'eval_steps_per_second': 22.42, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.2436, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 0.7857518792152405, 'eval_runtime': 0.0498, 'eval_samples_per_second': 20.086, 'eval_steps_per_second': 20.086, 'epoch': 17.0}\n", + "{'loss': 0.2305, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 0.7873539328575134, 'eval_runtime': 0.0466, 'eval_samples_per_second': 21.473, 'eval_steps_per_second': 21.473, 'epoch': 18.0}\n", + "{'loss': 0.229, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 0.7843477725982666, 'eval_runtime': 0.0523, 'eval_samples_per_second': 19.127, 'eval_steps_per_second': 19.127, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.2195, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 0.7839252948760986, 'eval_runtime': 0.0532, 'eval_samples_per_second': 18.81, 'eval_steps_per_second': 18.81, 'epoch': 20.0}\n", + "{'train_runtime': 3.6325, 'train_samples_per_second': 198.211, 'train_steps_per_second': 5.506, 'train_loss': 0.3403413608670235, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.45it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.02it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.14it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.73it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "I have a dream\n", + "{'before': 2.127256393432617, 'after': 2.123436212539673}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.77it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.18it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8084, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 2.0325565338134766, 'eval_runtime': 0.0752, 'eval_samples_per_second': 13.293, 'eval_steps_per_second': 13.293, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7944, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 2.031243085861206, 'eval_runtime': 0.0765, 'eval_samples_per_second': 13.072, 'eval_steps_per_second': 13.072, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7712, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 2.0322251319885254, 'eval_runtime': 0.0756, 'eval_samples_per_second': 13.22, 'eval_steps_per_second': 13.22, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.781, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 2.0296175479888916, 'eval_runtime': 0.081, 'eval_samples_per_second': 12.35, 'eval_steps_per_second': 12.35, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7462, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 2.029218912124634, 'eval_runtime': 0.0763, 'eval_samples_per_second': 13.106, 'eval_steps_per_second': 13.106, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7054, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 2.029827117919922, 'eval_runtime': 0.0758, 'eval_samples_per_second': 13.192, 'eval_steps_per_second': 13.192, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6704, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 2.0316803455352783, 'eval_runtime': 0.0777, 'eval_samples_per_second': 12.869, 'eval_steps_per_second': 12.869, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6434, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 2.034038782119751, 'eval_runtime': 0.076, 'eval_samples_per_second': 13.156, 'eval_steps_per_second': 13.156, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6142, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 2.032022714614868, 'eval_runtime': 0.0799, 'eval_samples_per_second': 12.509, 'eval_steps_per_second': 12.509, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5884, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 2.0296545028686523, 'eval_runtime': 0.0763, 'eval_samples_per_second': 13.113, 'eval_steps_per_second': 13.113, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.557, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 2.0316550731658936, 'eval_runtime': 0.076, 'eval_samples_per_second': 13.151, 'eval_steps_per_second': 13.151, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5349, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 2.029772996902466, 'eval_runtime': 0.0757, 'eval_samples_per_second': 13.208, 'eval_steps_per_second': 13.208, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5141, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 2.031522750854492, 'eval_runtime': 0.0775, 'eval_samples_per_second': 12.908, 'eval_steps_per_second': 12.908, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4971, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 2.026484251022339, 'eval_runtime': 0.0767, 'eval_samples_per_second': 13.042, 'eval_steps_per_second': 13.042, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4837, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 2.0277669429779053, 'eval_runtime': 0.0749, 'eval_samples_per_second': 13.344, 'eval_steps_per_second': 13.344, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4651, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 2.02577543258667, 'eval_runtime': 0.0776, 'eval_samples_per_second': 12.879, 'eval_steps_per_second': 12.879, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4688, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 2.025529623031616, 'eval_runtime': 0.0776, 'eval_samples_per_second': 12.888, 'eval_steps_per_second': 12.888, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4465, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 2.0272207260131836, 'eval_runtime': 0.0803, 'eval_samples_per_second': 12.458, 'eval_steps_per_second': 12.458, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4396, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 2.025996446609497, 'eval_runtime': 0.077, 'eval_samples_per_second': 12.985, 'eval_steps_per_second': 12.985, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4348, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 2.0273077487945557, 'eval_runtime': 0.0767, 'eval_samples_per_second': 13.032, 'eval_steps_per_second': 13.032, 'epoch': 20.0}\n", + "{'train_runtime': 4.7556, 'train_samples_per_second': 151.4, 'train_steps_per_second': 4.206, 'train_loss': 0.59822296500206, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.84it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.40it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.39it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.84it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "AI gen fake paper\n", + "{'before': 7.6328349113464355, 'after': 7.5795063972473145}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.54it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.87it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1582, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.388429641723633, 'eval_runtime': 0.0802, 'eval_samples_per_second': 12.475, 'eval_steps_per_second': 12.475, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1689, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 3.3883776664733887, 'eval_runtime': 0.083, 'eval_samples_per_second': 12.054, 'eval_steps_per_second': 12.054, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1657, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.383607864379883, 'eval_runtime': 0.081, 'eval_samples_per_second': 12.342, 'eval_steps_per_second': 12.342, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1466, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 3.3813862800598145, 'eval_runtime': 0.0802, 'eval_samples_per_second': 12.474, 'eval_steps_per_second': 12.474, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.1253, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 3.3783440589904785, 'eval_runtime': 0.0805, 'eval_samples_per_second': 12.416, 'eval_steps_per_second': 12.416, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0923, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 3.369931221008301, 'eval_runtime': 0.0812, 'eval_samples_per_second': 12.315, 'eval_steps_per_second': 12.315, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0774, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 3.365234136581421, 'eval_runtime': 0.0817, 'eval_samples_per_second': 12.241, 'eval_steps_per_second': 12.241, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.035, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 3.3629069328308105, 'eval_runtime': 0.0793, 'eval_samples_per_second': 12.603, 'eval_steps_per_second': 12.603, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0034, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.3572800159454346, 'eval_runtime': 0.0809, 'eval_samples_per_second': 12.358, 'eval_steps_per_second': 12.358, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9772, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 3.3547165393829346, 'eval_runtime': 0.083, 'eval_samples_per_second': 12.053, 'eval_steps_per_second': 12.053, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9588, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 3.351543426513672, 'eval_runtime': 0.0802, 'eval_samples_per_second': 12.47, 'eval_steps_per_second': 12.47, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.941, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 3.3515827655792236, 'eval_runtime': 0.0806, 'eval_samples_per_second': 12.41, 'eval_steps_per_second': 12.41, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9232, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 3.351295232772827, 'eval_runtime': 0.0825, 'eval_samples_per_second': 12.124, 'eval_steps_per_second': 12.124, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9052, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 3.34902286529541, 'eval_runtime': 0.0869, 'eval_samples_per_second': 11.505, 'eval_steps_per_second': 11.505, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8889, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.3556995391845703, 'eval_runtime': 0.0852, 'eval_samples_per_second': 11.736, 'eval_steps_per_second': 11.736, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8808, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 3.3538990020751953, 'eval_runtime': 0.0835, 'eval_samples_per_second': 11.97, 'eval_steps_per_second': 11.97, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8652, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 3.3535618782043457, 'eval_runtime': 0.0798, 'eval_samples_per_second': 12.533, 'eval_steps_per_second': 12.533, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.868, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.3534038066864014, 'eval_runtime': 0.083, 'eval_samples_per_second': 12.046, 'eval_steps_per_second': 12.046, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8547, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 3.3547372817993164, 'eval_runtime': 0.0825, 'eval_samples_per_second': 12.119, 'eval_steps_per_second': 12.119, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8467, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 3.352417469024658, 'eval_runtime': 0.0797, 'eval_samples_per_second': 12.54, 'eval_steps_per_second': 12.54, 'epoch': 20.0}\n", + "{'train_runtime': 5.4487, 'train_samples_per_second': 132.142, 'train_steps_per_second': 3.671, 'train_loss': 0.9941257268190384, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 10.75it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.74it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.56it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.97it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Schmidhuber 2023 Subjective Novelty, Surprise\n", + "{'before': 29.614953994750977, 'after': 28.47076988220215}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.94it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.54it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0744, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.2226405143737793, 'eval_runtime': 0.0742, 'eval_samples_per_second': 13.486, 'eval_steps_per_second': 13.486, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0721, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n", + "{'eval_loss': 3.223418712615967, 'eval_runtime': 0.0778, 'eval_samples_per_second': 12.847, 'eval_steps_per_second': 12.847, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0759, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.2250990867614746, 'eval_runtime': 0.0742, 'eval_samples_per_second': 13.481, 'eval_steps_per_second': 13.481, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0788, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 3.2234678268432617, 'eval_runtime': 0.0744, 'eval_samples_per_second': 13.435, 'eval_steps_per_second': 13.435, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0265, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 3.221116065979004, 'eval_runtime': 0.0767, 'eval_samples_per_second': 13.033, 'eval_steps_per_second': 13.033, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9834, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 3.2161364555358887, 'eval_runtime': 0.0802, 'eval_samples_per_second': 12.469, 'eval_steps_per_second': 12.469, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.958, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 3.210041046142578, 'eval_runtime': 0.0824, 'eval_samples_per_second': 12.139, 'eval_steps_per_second': 12.139, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.9219, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 3.2037718296051025, 'eval_runtime': 0.0774, 'eval_samples_per_second': 12.922, 'eval_steps_per_second': 12.922, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8684, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.2055044174194336, 'eval_runtime': 0.0745, 'eval_samples_per_second': 13.426, 'eval_steps_per_second': 13.426, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8611, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 3.202153205871582, 'eval_runtime': 0.0792, 'eval_samples_per_second': 12.627, 'eval_steps_per_second': 12.627, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8311, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 3.2075014114379883, 'eval_runtime': 0.0777, 'eval_samples_per_second': 12.875, 'eval_steps_per_second': 12.875, 'epoch': 11.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.813, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n", + "{'eval_loss': 3.206439971923828, 'eval_runtime': 0.0742, 'eval_samples_per_second': 13.477, 'eval_steps_per_second': 13.477, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7881, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 3.2009530067443848, 'eval_runtime': 0.0741, 'eval_samples_per_second': 13.503, 'eval_steps_per_second': 13.503, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.765, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 3.19985294342041, 'eval_runtime': 0.0762, 'eval_samples_per_second': 13.123, 'eval_steps_per_second': 13.123, 'epoch': 14.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7592, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.2009499073028564, 'eval_runtime': 0.0739, 'eval_samples_per_second': 13.54, 'eval_steps_per_second': 13.54, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7307, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 3.1999948024749756, 'eval_runtime': 0.0755, 'eval_samples_per_second': 13.25, 'eval_steps_per_second': 13.25, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7533, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 3.1982595920562744, 'eval_runtime': 0.0784, 'eval_samples_per_second': 12.754, 'eval_steps_per_second': 12.754, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7196, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.193620204925537, 'eval_runtime': 0.0756, 'eval_samples_per_second': 13.23, 'eval_steps_per_second': 13.23, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7177, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 3.19625186920166, 'eval_runtime': 0.0746, 'eval_samples_per_second': 13.411, 'eval_steps_per_second': 13.411, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7134, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 3.198460340499878, 'eval_runtime': 0.08, 'eval_samples_per_second': 12.496, 'eval_steps_per_second': 12.496, 'epoch': 20.0}\n", + "{'train_runtime': 4.7749, 'train_samples_per_second': 150.788, 'train_steps_per_second': 4.189, 'train_loss': 0.8755794435739517, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.79it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.56it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.32it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.29it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "email_to_fauci\n", + "{'before': 25.08931541442871, 'after': 24.371374130249023}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 34.95it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 31.78it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.177, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 3.249210834503174, 'eval_runtime': 0.0412, 'eval_samples_per_second': 24.276, 'eval_steps_per_second': 24.276, 'epoch': 1.0}\n", + "{'loss': 1.205, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.2476515769958496, 'eval_runtime': 0.0403, 'eval_samples_per_second': 24.843, 'eval_steps_per_second': 24.843, 'epoch': 2.0}\n", + "{'loss': 1.1889, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 3.2459347248077393, 'eval_runtime': 0.04, 'eval_samples_per_second': 25.026, 'eval_steps_per_second': 25.026, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.161, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 3.2447614669799805, 'eval_runtime': 0.0412, 'eval_samples_per_second': 24.249, 'eval_steps_per_second': 24.249, 'epoch': 4.0}\n", + "{'loss': 1.125, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.239017963409424, 'eval_runtime': 0.0434, 'eval_samples_per_second': 23.036, 'eval_steps_per_second': 23.036, 'epoch': 5.0}\n", + "{'loss': 1.0341, 'learning_rate': 0.002, 'epoch': 6.0}\n", + "{'eval_loss': 3.234159469604492, 'eval_runtime': 0.0488, 'eval_samples_per_second': 20.484, 'eval_steps_per_second': 20.484, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.0079, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 3.222565174102783, 'eval_runtime': 0.0427, 'eval_samples_per_second': 23.438, 'eval_steps_per_second': 23.438, 'epoch': 7.0}\n", + "{'loss': 0.9675, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 3.223250389099121, 'eval_runtime': 0.0393, 'eval_samples_per_second': 25.471, 'eval_steps_per_second': 25.471, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.921, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n", + "{'eval_loss': 3.2214527130126953, 'eval_runtime': 0.0405, 'eval_samples_per_second': 24.712, 'eval_steps_per_second': 24.712, 'epoch': 9.0}\n", + "{'loss': 0.8556, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 3.219179391860962, 'eval_runtime': 0.0384, 'eval_samples_per_second': 26.025, 'eval_steps_per_second': 26.025, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.8345, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 3.2118680477142334, 'eval_runtime': 0.0403, 'eval_samples_per_second': 24.838, 'eval_steps_per_second': 24.838, 'epoch': 11.0}\n", + "{'loss': 0.795, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.20888614654541, 'eval_runtime': 0.0454, 'eval_samples_per_second': 22.039, 'eval_steps_per_second': 22.039, 'epoch': 12.0}\n", + "{'loss': 0.7881, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 3.2091894149780273, 'eval_runtime': 0.0435, 'eval_samples_per_second': 23.005, 'eval_steps_per_second': 23.005, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7197, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 3.1942005157470703, 'eval_runtime': 0.0398, 'eval_samples_per_second': 25.137, 'eval_steps_per_second': 25.137, 'epoch': 14.0}\n", + "{'loss': 0.7144, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 3.198335886001587, 'eval_runtime': 0.041, 'eval_samples_per_second': 24.385, 'eval_steps_per_second': 24.385, 'epoch': 15.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6973, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n", + "{'eval_loss': 3.198418617248535, 'eval_runtime': 0.0385, 'eval_samples_per_second': 25.96, 'eval_steps_per_second': 25.96, 'epoch': 16.0}\n", + "{'loss': 0.6987, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.204080581665039, 'eval_runtime': 0.04, 'eval_samples_per_second': 24.997, 'eval_steps_per_second': 24.997, 'epoch': 17.0}\n", + "{'loss': 0.6781, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 3.195650577545166, 'eval_runtime': 0.0385, 'eval_samples_per_second': 25.956, 'eval_steps_per_second': 25.956, 'epoch': 18.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6583, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n", + "{'eval_loss': 3.199404239654541, 'eval_runtime': 0.0393, 'eval_samples_per_second': 25.472, 'eval_steps_per_second': 25.472, 'epoch': 19.0}\n", + "{'loss': 0.6624, 'learning_rate': 0.0, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 3.1974809169769287, 'eval_runtime': 0.0423, 'eval_samples_per_second': 23.636, 'eval_steps_per_second': 23.636, 'epoch': 20.0}\n", + "{'train_runtime': 3.3623, 'train_samples_per_second': 214.142, 'train_steps_per_second': 5.948, 'train_loss': 0.8944688588380814, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 37.19it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 32.88it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 37.05it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 34.12it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "enron_email1\n", + "{'before': 25.76974868774414, 'after': 24.39041519165039}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.62it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.88it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.737, 'learning_rate': 0.0003333333333333333, 'epoch': 1.0}\n", + "{'eval_loss': 2.766712188720703, 'eval_runtime': 0.0481, 'eval_samples_per_second': 20.776, 'eval_steps_per_second': 20.776, 'epoch': 1.0}\n", + "{'loss': 0.7504, 'learning_rate': 0.0006666666666666666, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.7666499614715576, 'eval_runtime': 0.0482, 'eval_samples_per_second': 20.744, 'eval_steps_per_second': 20.744, 'epoch': 2.0}\n", + "{'loss': 0.7246, 'learning_rate': 0.001, 'epoch': 3.0}\n", + "{'eval_loss': 2.7607975006103516, 'eval_runtime': 0.0483, 'eval_samples_per_second': 20.697, 'eval_steps_per_second': 20.697, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.7138, 'learning_rate': 0.0013333333333333333, 'epoch': 4.0}\n", + "{'eval_loss': 2.76033353805542, 'eval_runtime': 0.0503, 'eval_samples_per_second': 19.864, 'eval_steps_per_second': 19.864, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.696, 'learning_rate': 0.0016666666666666668, 'epoch': 5.0}\n", + "{'eval_loss': 2.7581703662872314, 'eval_runtime': 0.0496, 'eval_samples_per_second': 20.178, 'eval_steps_per_second': 20.178, 'epoch': 5.0}\n", + "{'loss': 0.6755, 'learning_rate': 0.002, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.7516887187957764, 'eval_runtime': 0.0501, 'eval_samples_per_second': 19.97, 'eval_steps_per_second': 19.97, 'epoch': 6.0}\n", + "{'loss': 0.6444, 'learning_rate': 0.0018571428571428573, 'epoch': 7.0}\n", + "{'eval_loss': 2.7450146675109863, 'eval_runtime': 0.0468, 'eval_samples_per_second': 21.369, 'eval_steps_per_second': 21.369, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.6127, 'learning_rate': 0.0017142857142857142, 'epoch': 8.0}\n", + "{'eval_loss': 2.7416346073150635, 'eval_runtime': 0.0463, 'eval_samples_per_second': 21.602, 'eval_steps_per_second': 21.602, 'epoch': 8.0}\n", + "{'loss': 0.5637, 'learning_rate': 0.0015714285714285715, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.738495349884033, 'eval_runtime': 0.049, 'eval_samples_per_second': 20.393, 'eval_steps_per_second': 20.393, 'epoch': 9.0}\n", + "{'loss': 0.5521, 'learning_rate': 0.0014285714285714286, 'epoch': 10.0}\n", + "{'eval_loss': 2.736967086791992, 'eval_runtime': 0.0457, 'eval_samples_per_second': 21.859, 'eval_steps_per_second': 21.859, 'epoch': 10.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.5376, 'learning_rate': 0.0012857142857142859, 'epoch': 11.0}\n", + "{'eval_loss': 2.737375259399414, 'eval_runtime': 0.0455, 'eval_samples_per_second': 21.963, 'eval_steps_per_second': 21.963, 'epoch': 11.0}\n", + "{'loss': 0.5116, 'learning_rate': 0.0011428571428571427, 'epoch': 12.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.734422445297241, 'eval_runtime': 0.0499, 'eval_samples_per_second': 20.029, 'eval_steps_per_second': 20.029, 'epoch': 12.0}\n", + "{'loss': 0.4978, 'learning_rate': 0.001, 'epoch': 13.0}\n", + "{'eval_loss': 2.729034185409546, 'eval_runtime': 0.0465, 'eval_samples_per_second': 21.528, 'eval_steps_per_second': 21.528, 'epoch': 13.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4787, 'learning_rate': 0.0008571428571428571, 'epoch': 14.0}\n", + "{'eval_loss': 2.728099822998047, 'eval_runtime': 0.0462, 'eval_samples_per_second': 21.638, 'eval_steps_per_second': 21.638, 'epoch': 14.0}\n", + "{'loss': 0.4696, 'learning_rate': 0.0007142857142857143, 'epoch': 15.0}\n", + "{'eval_loss': 2.7260758876800537, 'eval_runtime': 0.0551, 'eval_samples_per_second': 18.163, 'eval_steps_per_second': 18.163, 'epoch': 15.0}\n", + "{'loss': 0.4445, 'learning_rate': 0.0005714285714285714, 'epoch': 16.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.724435329437256, 'eval_runtime': 0.0461, 'eval_samples_per_second': 21.688, 'eval_steps_per_second': 21.688, 'epoch': 16.0}\n", + "{'loss': 0.4471, 'learning_rate': 0.00042857142857142855, 'epoch': 17.0}\n", + "{'eval_loss': 2.7250912189483643, 'eval_runtime': 0.0451, 'eval_samples_per_second': 22.169, 'eval_steps_per_second': 22.169, 'epoch': 17.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.4351, 'learning_rate': 0.0002857142857142857, 'epoch': 18.0}\n", + "{'eval_loss': 2.7233238220214844, 'eval_runtime': 0.0483, 'eval_samples_per_second': 20.725, 'eval_steps_per_second': 20.725, 'epoch': 18.0}\n", + "{'loss': 0.4332, 'learning_rate': 0.00014285714285714284, 'epoch': 19.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'eval_loss': 2.719698667526245, 'eval_runtime': 0.0466, 'eval_samples_per_second': 21.461, 'eval_steps_per_second': 21.461, 'epoch': 19.0}\n", + "{'loss': 0.4262, 'learning_rate': 0.0, 'epoch': 20.0}\n", + "{'eval_loss': 2.7211437225341797, 'eval_runtime': 0.0453, 'eval_samples_per_second': 22.099, 'eval_steps_per_second': 22.099, 'epoch': 20.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'train_runtime': 3.815, 'train_samples_per_second': 188.728, 'train_steps_per_second': 5.242, 'train_loss': 0.5675859734416008, 'epoch': 20.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 13.04it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.41it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.85it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 13.44it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "openai_board_ann\n", + "{'before': 15.90396499633789, 'after': 15.173632621765137}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "data = []\n", + "for sample in samples:\n", + " r = learn_sample(sample)\n", + " print(sample['name'])\n", + " print(dict(before=r['before'], after=r['after']))\n", + " data.append(dict(**r, **sample))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'df_hist' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf_hist\u001b[49m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlearning_rate\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mplot(logy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n", + "\u001b[0;31mNameError\u001b[0m: name 'df_hist' is not defined" + ] + } + ], + "source": [ + "df_hist['learning_rate'].plot(logy=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df_hist = data[0]['hist']#.groupby('epoch').last().dropna(axis=1).drop(columns=['step'])\n", + "df_hist['loss'].plot(label='train')\n", + "plt.twinx()\n", + "df_hist['eval_loss'].plot(c='b', label='eval')\n", + "plt.legend()\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "### Perplexity\n", + "\n", + "Perplexity measures how well a language model predicts a text sample. Lower is better\n", + "\n", + "It’s calculated as the average number of bits per word a model needs to represent the same\n", + "\n", + "https://huggingface.co/docs/transformers/perplexity\n", + "https://thegradient.pub/understanding-evaluation-metrics-for-language-models/\n", + "\n", + "The **improvement** column, is perplexity decrease" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df_res = pd.DataFrame(data)\n", + "df_res['len'] = df_res.text.str.len()\n", + "df_res = df_res[['before', 'after', 'name', 'in_training', 'len']].set_index('name')\n", + "df_res['improvement%'] = (df_res['before'] - df_res['after'])/ df_res['before']\n", + "df_res['improvement'] = (df_res['before'] - df_res['after'])\n", + "df_res.sort_values('improvement%', ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df_res.to_markdown()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# DEBUG" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from IPython.display import display, HTML, Markdown\n", + "import torch\n", + "\n", + "@torch.no_grad()\n", + "def gen(model, inputs, tokenizer, clean=True):\n", + " s = model.generate(\n", + " input_ids=inputs[\"input_ids\"][None, :].to(model.device),\n", + " attention_mask=inputs[\"attention_mask\"][None, :].to(model.device),\n", + " use_cache=False,\n", + " max_new_tokens=100,\n", + " min_new_tokens=100,\n", + " do_sample=False,\n", + " early_stopping=False,\n", + " )\n", + " input_l = inputs[\"input_ids\"].shape[0]\n", + " tokenizer_kwargs=dict(clean_up_tokenization_spaces=clean, skip_special_tokens=clean)\n", + " old = tokenizer.decode(\n", + " s[0, :input_l], **tokenizer_kwargs\n", + " )\n", + " new = tokenizer.decode(\n", + " s[0, input_l:], **tokenizer_kwargs\n", + " )\n", + " s_old = \"\"+old.replace('\\n', '
')\n", + " s_new = '' + new.replace('\\n', '
')+ '

'\n", + " display(HTML(f\"{s_old}{s_new}\"))\n", + " # print([old, new])\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "sample = samples[1]\n", + "s = sample['text']\n", + "first_half = s[:len(s)//2]\n", + "second_half = s[len(s)//2:]\n", + "ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + "ds_val = Dataset.from_dict(tokenizer([second_half]))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "with model.disable_adapter():\n", + " gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": ".venv", + "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": "3.11.0rc1" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/nbs/03_use_lora_hftrain.ipynb b/nbs/03_use_lora_hftrain.ipynb new file mode 100644 index 0000000..bc9f6a5 --- /dev/null +++ b/nbs/03_use_lora_hftrain.ipynb @@ -0,0 +1,4094 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "https://github.com/huggingface/peft/blob/main/examples/fp4_finetuning/finetune_fp4_opt_bnb_peft.py" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-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": [ + "from torch import optim\n", + "import lightning as pl\n", + "from matplotlib import pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import transformers\n", + "from datasets import load_dataset\n", + "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig\n", + "import numpy as np\n", + "from tqdm.auto import tqdm\n", + "import pandas as pd\n", + "import warnings\n", + "from peft import LoraConfig, get_peft_model, IA3Config" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "plt.style.use('ggplot')\n", + "torch.set_float32_matmul_precision('medium')\n", + "warnings.filterwarnings(\"ignore\", \".*does not have many workers.*\")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n", + "\n", + "model_name = \"microsoft/phi-2\"\n", + "\n", + "# model = AutoModelForCausalLM.from_pretrained(\n", + "# model_name,\n", + "# # max_memory=max_memory,\n", + "# quantization_config=BitsAndBytesConfig(\n", + "# load_in_4bit=True,\n", + "# llm_int8_threshold=6.0,\n", + "# llm_int8_has_fp16_weight=False,\n", + "# bnb_4bit_compute_dtype=torch.float16,\n", + "# bnb_4bit_use_double_quant=True,\n", + "# bnb_4bit_quant_type=\"nf4\",\n", + "# ),\n", + "# torch_dtype=torch.float16,\n", + "# trust_remote_code=True,\n", + "# )\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "# model_name = \"TheBloke/phi-2-GPTQ\"\n", + "model_name = \"microsoft/phi-2\"\n", + "\n", + "def load_model():\n", + "\n", + " model = AutoModelForCausalLM.from_pretrained(\n", + " model_name,\n", + " # quantization_config=BitsAndBytesConfig(\n", + " # load_in_4bit=True,\n", + " # llm_int8_threshold=6.0,\n", + " # llm_int8_has_fp16_weight=False,\n", + " # bnb_4bit_compute_dtype=torch.float16,\n", + " # bnb_4bit_use_double_quant=True,\n", + " # bnb_4bit_quant_type=\"nf4\",\n", + " # ),\n", + " # torch_dtype=torch.float16,\n", + " trust_remote_code=True,\n", + " )\n", + "\n", + "\n", + " # config = AutoConfig.from_pretrained(model_name, trust_remote_code=True,)\n", + " # config.quantization_config['use_exllama'] = False\n", + " # config.quantization_config['disable_exllama'] = True\n", + " # model = AutoModelForCausalLM.from_pretrained(\n", + " # model_name,\n", + " # torch_dtype=torch.bfloat16,\n", + " # trust_remote_code=True,\n", + " # config=config,\n", + " # )\n", + " return model\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.34it/s]\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n" + ] + } + ], + "source": [ + "base_model = load_model()\n", + "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True,)\n", + "tokenizer.pad_token = tokenizer.eos_token" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "from peft import TaskType\n", + "\n", + "def reset_model(base_model):\n", + " peft_config = LoraConfig(\n", + " # task_type=TaskType.CAUSAL_LM, \n", + " target_modules=[\n", + " # \"fc1\", \n", + " \"fc2\",\n", + " \"out_proj\",\n", + " \"Wqkv\",],\n", + " inference_mode=False, r=16, lora_alpha=8, \n", + " lora_dropout=0.1, \n", + " # bias=\"all\"\n", + " )\n", + " # peft_config = IA3Config(\n", + " # target_modules=[ \"fc2\", \"Wqkv\",], \n", + " # feedforward_modules=[\"fc2\"],\n", + " # inference_mode=False,\n", + " # )\n", + " model = get_peft_model(base_model, peft_config)\n", + " model.config.use_cache = False\n", + " return model\n", + "\n", + "model = reset_model(base_model)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "MAX_LEN = 2000\n", + "samples = json.load(open(\"../samples.json\"))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "# modified from https://github.dev/huggingface/evaluate/blob/8dfe05784099fb9af55b8e77793205a3b7c86465/measurements/perplexity/perplexity.py#L154\n", + "\n", + "# from evaluate.measurements.perplexity import Perplexity\n", + "import evaluate\n", + "from evaluate import logging\n", + "from torch.nn import CrossEntropyLoss\n", + "\n", + "# @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)\n", + "def perplexity_compute(\n", + " data, model, tokenizer, batch_size: int = 16, add_start_token: bool = True, device=None, max_length=None\n", + "):\n", + "\n", + " if device is not None:\n", + " assert device in [\"gpu\", \"cpu\", \"cuda\"], \"device should be either gpu or cpu.\"\n", + " if device == \"gpu\":\n", + " device = \"cuda\"\n", + " else:\n", + " device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "\n", + " # model = AutoModelForCausalLM.from_pretrained(model_id)\n", + " model = model.to(device)\n", + "\n", + " # tokenizer = AutoTokenizer.from_pretrained(model_id)\n", + "\n", + " # # if batch_size > 1 (which generally leads to padding being required), and\n", + " # # if there is not an already assigned pad_token, assign an existing\n", + " # # special token to also be the padding token\n", + " # if tokenizer.pad_token is None and batch_size > 1:\n", + " # existing_special_tokens = list(tokenizer.special_tokens_map_extended.values())\n", + " # # check that the model already has at least one special token defined\n", + " # assert (\n", + " # len(existing_special_tokens) > 0\n", + " # ), \"If batch_size > 1, model must have at least one special token to use for padding. Please use a different model or set batch_size=1.\"\n", + " # # assign one of the special tokens to also be the pad token\n", + " # tokenizer.add_special_tokens({\"pad_token\": existing_special_tokens[0]})\n", + "\n", + " # if add_start_token and max_length:\n", + " # # leave room for token to be added:\n", + " # assert (\n", + " # tokenizer.bos_token is not None\n", + " # ), \"Input model must already have a BOS token if using add_start_token=True. Please use a different model, or set add_start_token=False\"\n", + " # max_tokenized_len = max_length - 1\n", + " # else:\n", + " max_tokenized_len = max_length\n", + "\n", + " encodings = tokenizer(\n", + " data,\n", + " add_special_tokens=False,\n", + " padding=True,\n", + " truncation=True if max_tokenized_len else False,\n", + " max_length=max_tokenized_len,\n", + " return_tensors=\"pt\",\n", + " return_attention_mask=True,\n", + " ).to(device)\n", + "\n", + " encoded_texts = encodings[\"input_ids\"]\n", + " attn_masks = encodings[\"attention_mask\"]\n", + "\n", + " # check that each input is long enough:\n", + " if add_start_token:\n", + " assert torch.all(torch.ge(attn_masks.sum(1), 1)), \"Each input text must be at least one token long.\"\n", + " else:\n", + " assert torch.all(\n", + " torch.ge(attn_masks.sum(1), 2)\n", + " ), \"When add_start_token=False, each input text must be at least two tokens long. Run with add_start_token=True if inputting strings of only one token, and remove all empty input strings.\"\n", + "\n", + " ppls = []\n", + " loss_fct = CrossEntropyLoss(reduction=\"none\")\n", + "\n", + " for start_index in logging.tqdm(range(0, len(encoded_texts), batch_size)):\n", + " end_index = min(start_index + batch_size, len(encoded_texts))\n", + " encoded_batch = encoded_texts[start_index:end_index]\n", + " attn_mask = attn_masks[start_index:end_index]\n", + "\n", + " # if add_start_token:\n", + " # bos_tokens_tensor = torch.tensor([[tokenizer.bos_token_id]] * encoded_batch.size(dim=0)).to(device)\n", + " # encoded_batch = torch.cat([bos_tokens_tensor, encoded_batch], dim=1)\n", + " # attn_mask = torch.cat(\n", + " # [torch.ones(bos_tokens_tensor.size(), dtype=torch.int64).to(device), attn_mask], dim=1\n", + " # )\n", + "\n", + " labels = encoded_batch\n", + "\n", + " with torch.no_grad():\n", + " out_logits = model(encoded_batch, attention_mask=attn_mask).logits\n", + " # print(out_logits.shape)\n", + "\n", + " shift_logits = out_logits[..., :-1, :].contiguous()\n", + " shift_labels = labels[..., 1:].contiguous()\n", + " shift_attention_mask_batch = attn_mask[..., 1:].contiguous()\n", + "\n", + " perplexity_batch = torch.exp(\n", + " (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch).sum(1)\n", + " / shift_attention_mask_batch.sum(1)\n", + " )\n", + " # perplexity_batch = torch.exp(\n", + " # (loss_fct(shift_logits.transpose(1, 2), shift_labels) * shift_attention_mask_batch)\n", + " # / shift_attention_mask_batch.sum(1)\n", + " # )\n", + " # print(perplexity_batch.shape)\n", + "\n", + " ppls += perplexity_batch.tolist()\n", + "\n", + " return {\"perplexities\": ppls, \"mean_perplexity\": torch.tensor(ppls).mean()}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [], + "source": [ + "# perplexity_compute(\n", + "# second_half, model, tokenizer\n", + "# )" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Training" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "from torch.nn import functional as F\n", + "from torch.utils.data import DataLoader, TensorDataset" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Lightning helpers" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "def eval(model, tokenizer, second_half):\n", + " model.eval();\n", + " with torch.no_grad():\n", + " with model.disable_adapter():\n", + " results = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " results2 = perplexity_compute(data=second_half, model=model, tokenizer=tokenizer, device='cuda')\n", + " return dict(before=results['mean_perplexity'].item(), after=results2['mean_perplexity'].item())\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Train" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "from datasets import Dataset\n", + "\n", + "\n", + "def compute_metrics(eval_prediction):\n", + " return {}" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trainer docs\n", + "\n", + "- https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "def learn_sample(sample):\n", + " # device = 'cuda'\n", + " # lr = 4e-3\n", + " # epochs = 3\n", + " # accum_steps = 1\n", + " batch_size = 1\n", + " verbose = True\n", + "\n", + " s = sample['text']\n", + " first_half = s[:len(s)//2]\n", + " second_half = s[len(s)//2:]\n", + " ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + " ds_val = Dataset.from_dict(tokenizer([second_half]))\n", + "\n", + " os.environ['CUDA_VISIBLE_DEVICES']=\"1\"\n", + " model = reset_model(base_model)\n", + " eval(model, tokenizer, second_half)\n", + "\n", + " # https://huggingface.co/docs/transformers/v4.36.1/en/main_classes/trainer#transformers.Trainer\n", + " trainer = transformers.Trainer(\n", + " model=model,\n", + " train_dataset=ds_train,\n", + " eval_dataset=ds_val,\n", + " compute_metrics=compute_metrics, # without this it wont even give val loss\n", + " args=transformers.TrainingArguments(\n", + " # checkpoint='epoch',\n", + " save_strategy='epoch',\n", + " label_names=['labels',],\n", + " per_device_train_batch_size=batch_size,\n", + " # gradient_accumulation_steps=1,\n", + " warmup_steps=4,\n", + " max_steps=10,\n", + " learning_rate=1e-5,\n", + " fp16=True,\n", + " logging_steps=1,\n", + " output_dir=\"outputs\",\n", + " log_level='error',\n", + " # do_eval=True,\n", + " evaluation_strategy=\"epoch\",\n", + " eval_steps=1,\n", + " load_best_model_at_end=True,\n", + " \n", + " # disable_tqdm=not verbose,\n", + " ),\n", + " data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),\n", + " )\n", + " trainer._signature_columns = ['input_ids', 'attention_mask', 'labels',]\n", + " model.config.use_cache = False # silence the warnings. Please re-enable for inference!\n", + " train_output = trainer.train()\n", + "\n", + " df_hist = pd.DataFrame(trainer.state.log_history)\n", + " df_hist_epoch = df_hist.groupby('epoch').last().drop(columns=['step'])\n", + " df_hist_step = df_hist.set_index('step').dropna(thresh=2, axis=1)\n", + " if verbose:\n", + " df_hist_epoch['loss'].plot()\n", + " plt.twinx()\n", + " df_hist_epoch['eval_loss'].plot(c='b', label='eval')\n", + " plt.legend()\n", + " plt.show()\n", + "\n", + "\n", + " result_train = {f'train/{k}':v for k,v in eval(model, tokenizer, first_half).items()}\n", + " result = eval(model, tokenizer, second_half)\n", + " result['hist'] = df_hist_epoch\n", + " result.update(result_train)\n", + " return result\n" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 5.51it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.53it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + " 0%| | 0/10 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.95it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.66it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.99it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.46it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "bad_ml\n", + "{'before': 13.885271072387695, 'after': 13.874102592468262}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.30it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.90it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.375, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.3444020748138428, 'eval_runtime': 0.0748, 'eval_samples_per_second': 13.369, 'eval_steps_per_second': 13.369, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.3792, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.3444230556488037, 'eval_runtime': 0.0721, 'eval_samples_per_second': 13.861, 'eval_steps_per_second': 13.861, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4435, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.3442118167877197, 'eval_runtime': 0.0704, 'eval_samples_per_second': 14.202, 'eval_steps_per_second': 14.202, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.3473, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.3446550369262695, 'eval_runtime': 0.0716, 'eval_samples_per_second': 13.959, 'eval_steps_per_second': 13.959, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.3052, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.3441321849823, 'eval_runtime': 0.0711, 'eval_samples_per_second': 14.068, 'eval_steps_per_second': 14.068, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4044, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.3439669609069824, 'eval_runtime': 0.0705, 'eval_samples_per_second': 14.176, 'eval_steps_per_second': 14.176, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.3996, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.344259262084961, 'eval_runtime': 0.0786, 'eval_samples_per_second': 12.715, 'eval_steps_per_second': 12.715, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4594, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.343461751937866, 'eval_runtime': 0.0714, 'eval_samples_per_second': 14.002, 'eval_steps_per_second': 14.002, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.3788, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.344158172607422, 'eval_runtime': 0.0711, 'eval_samples_per_second': 14.073, 'eval_steps_per_second': 14.073, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4302, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.343691825866699, 'eval_runtime': 0.0722, 'eval_samples_per_second': 13.859, 'eval_steps_per_second': 13.859, 'epoch': 10.0}\n", + "{'train_runtime': 15.52, 'train_samples_per_second': 1.289, 'train_steps_per_second': 0.644, 'train_loss': 3.3922712326049806, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.65it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.36it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.70it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.06it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "good_ml\n", + "{'before': 28.339096069335938, 'after': 28.31243324279785}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.57it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.24it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6742, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 2.772010564804077, 'eval_runtime': 0.1278, 'eval_samples_per_second': 7.822, 'eval_steps_per_second': 7.822, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6839, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 2.7720797061920166, 'eval_runtime': 0.1266, 'eval_samples_per_second': 7.898, 'eval_steps_per_second': 7.898, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.667, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 2.771838426589966, 'eval_runtime': 0.1273, 'eval_samples_per_second': 7.854, 'eval_steps_per_second': 7.854, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6788, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 2.771756410598755, 'eval_runtime': 0.1333, 'eval_samples_per_second': 7.503, 'eval_steps_per_second': 7.503, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6894, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 2.7716634273529053, 'eval_runtime': 0.1304, 'eval_samples_per_second': 7.666, 'eval_steps_per_second': 7.666, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6981, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 2.7719693183898926, 'eval_runtime': 0.1269, 'eval_samples_per_second': 7.88, 'eval_steps_per_second': 7.88, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6772, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 2.772239923477173, 'eval_runtime': 0.1286, 'eval_samples_per_second': 7.776, 'eval_steps_per_second': 7.776, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6648, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 2.771648645401001, 'eval_runtime': 0.1289, 'eval_samples_per_second': 7.755, 'eval_steps_per_second': 7.755, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.689, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 2.7726099491119385, 'eval_runtime': 0.1288, 'eval_samples_per_second': 7.764, 'eval_steps_per_second': 7.764, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.6739, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 2.7720842361450195, 'eval_runtime': 0.1292, 'eval_samples_per_second': 7.743, 'eval_steps_per_second': 7.743, 'epoch': 10.0}\n", + "{'train_runtime': 12.8731, 'train_samples_per_second': 1.554, 'train_steps_per_second': 0.777, 'train_loss': 2.679630756378174, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.73it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.36it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.48it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 7.77it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "sokal hoax\n", + "{'before': 15.988316535949707, 'after': 15.98253059387207}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 9.52it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.35it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.124, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.2923994064331055, 'eval_runtime': 0.1057, 'eval_samples_per_second': 9.456, 'eval_steps_per_second': 9.456, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.158, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.293436288833618, 'eval_runtime': 0.1029, 'eval_samples_per_second': 9.722, 'eval_steps_per_second': 9.722, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1423, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.292522668838501, 'eval_runtime': 0.0968, 'eval_samples_per_second': 10.336, 'eval_steps_per_second': 10.336, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1551, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.292370319366455, 'eval_runtime': 0.0978, 'eval_samples_per_second': 10.221, 'eval_steps_per_second': 10.221, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1887, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.2926437854766846, 'eval_runtime': 0.1006, 'eval_samples_per_second': 9.942, 'eval_steps_per_second': 9.942, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1303, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.2924861907958984, 'eval_runtime': 0.097, 'eval_samples_per_second': 10.309, 'eval_steps_per_second': 10.309, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1553, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.2921712398529053, 'eval_runtime': 0.098, 'eval_samples_per_second': 10.204, 'eval_steps_per_second': 10.204, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1617, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.2929515838623047, 'eval_runtime': 0.1014, 'eval_samples_per_second': 9.86, 'eval_steps_per_second': 9.86, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.177, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.2918519973754883, 'eval_runtime': 0.0963, 'eval_samples_per_second': 10.381, 'eval_steps_per_second': 10.381, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1702, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.292269229888916, 'eval_runtime': 0.097, 'eval_samples_per_second': 10.31, 'eval_steps_per_second': 10.31, 'epoch': 10.0}\n", + "{'train_runtime': 16.7488, 'train_samples_per_second': 1.194, 'train_steps_per_second': 0.597, 'train_loss': 3.1562697649002076, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 9.64it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.38it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.57it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.37it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Theory o. general relativity\n", + "{'before': 26.90251922607422, 'after': 26.887775421142578}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.89it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.37it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3854, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 0.4702971577644348, 'eval_runtime': 0.0685, 'eval_samples_per_second': 14.604, 'eval_steps_per_second': 14.604, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3339, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 0.4702734649181366, 'eval_runtime': 0.0704, 'eval_samples_per_second': 14.199, 'eval_steps_per_second': 14.199, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3039, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 0.47032833099365234, 'eval_runtime': 0.0711, 'eval_samples_per_second': 14.067, 'eval_steps_per_second': 14.067, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3085, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 0.4703848958015442, 'eval_runtime': 0.0708, 'eval_samples_per_second': 14.123, 'eval_steps_per_second': 14.123, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3198, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 0.47002241015434265, 'eval_runtime': 0.0714, 'eval_samples_per_second': 14.013, 'eval_steps_per_second': 14.013, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3547, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 0.4700290858745575, 'eval_runtime': 0.0693, 'eval_samples_per_second': 14.44, 'eval_steps_per_second': 14.44, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3611, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 0.47006598114967346, 'eval_runtime': 0.0705, 'eval_samples_per_second': 14.178, 'eval_steps_per_second': 14.178, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.328, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 0.47035178542137146, 'eval_runtime': 0.0721, 'eval_samples_per_second': 13.879, 'eval_steps_per_second': 13.879, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3103, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 0.47035568952560425, 'eval_runtime': 0.0711, 'eval_samples_per_second': 14.057, 'eval_steps_per_second': 14.057, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 0.3373, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 0.4699896275997162, 'eval_runtime': 0.0703, 'eval_samples_per_second': 14.228, 'eval_steps_per_second': 14.228, 'epoch': 10.0}\n", + "{'train_runtime': 12.8473, 'train_samples_per_second': 1.557, 'train_steps_per_second': 0.778, 'train_loss': 0.3342802584171295, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.56it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.53it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.31it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.74it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "lorem ipsum \n", + "{'before': 1.600419521331787, 'after': 1.5999276638031006}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.10it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.48it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8088, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.472930669784546, 'eval_runtime': 0.0774, 'eval_samples_per_second': 12.92, 'eval_steps_per_second': 12.92, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8934, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.4726057052612305, 'eval_runtime': 0.0752, 'eval_samples_per_second': 13.289, 'eval_steps_per_second': 13.289, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8154, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.4735727310180664, 'eval_runtime': 0.0725, 'eval_samples_per_second': 13.796, 'eval_steps_per_second': 13.796, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8602, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.4736719131469727, 'eval_runtime': 0.0733, 'eval_samples_per_second': 13.636, 'eval_steps_per_second': 13.636, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8472, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.4726154804229736, 'eval_runtime': 0.0722, 'eval_samples_per_second': 13.86, 'eval_steps_per_second': 13.86, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8786, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.473383903503418, 'eval_runtime': 0.0734, 'eval_samples_per_second': 13.632, 'eval_steps_per_second': 13.632, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8225, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.472898244857788, 'eval_runtime': 0.0725, 'eval_samples_per_second': 13.797, 'eval_steps_per_second': 13.797, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.83, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.4716172218322754, 'eval_runtime': 0.0731, 'eval_samples_per_second': 13.686, 'eval_steps_per_second': 13.686, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8249, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.4717400074005127, 'eval_runtime': 0.0736, 'eval_samples_per_second': 13.586, 'eval_steps_per_second': 13.586, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.8463, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.4718592166900635, 'eval_runtime': 0.0736, 'eval_samples_per_second': 13.585, 'eval_steps_per_second': 13.585, 'epoch': 10.0}\n", + "{'train_runtime': 14.973, 'train_samples_per_second': 1.336, 'train_steps_per_second': 0.668, 'train_loss': 2.842736101150513, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 10.78it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 10.70it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.09it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.64it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "wikipedia on LK-99\n", + "{'before': 32.226192474365234, 'after': 32.18389892578125}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 12.01it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.95it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.4629, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 0.7537348866462708, 'eval_runtime': 0.0738, 'eval_samples_per_second': 13.551, 'eval_steps_per_second': 13.551, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.5278, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 0.7536290884017944, 'eval_runtime': 0.0735, 'eval_samples_per_second': 13.603, 'eval_steps_per_second': 13.603, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.5075, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 0.7543337941169739, 'eval_runtime': 0.0709, 'eval_samples_per_second': 14.104, 'eval_steps_per_second': 14.104, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.432, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 0.7537673711776733, 'eval_runtime': 0.0738, 'eval_samples_per_second': 13.55, 'eval_steps_per_second': 13.55, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.4949, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 0.7528185248374939, 'eval_runtime': 0.0731, 'eval_samples_per_second': 13.679, 'eval_steps_per_second': 13.679, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.5574, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 0.7516946792602539, 'eval_runtime': 0.0717, 'eval_samples_per_second': 13.952, 'eval_steps_per_second': 13.952, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.5096, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 0.7530063986778259, 'eval_runtime': 0.073, 'eval_samples_per_second': 13.702, 'eval_steps_per_second': 13.702, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.4305, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 0.75247722864151, 'eval_runtime': 0.0714, 'eval_samples_per_second': 14.0, 'eval_steps_per_second': 14.0, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.4682, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 0.7539510726928711, 'eval_runtime': 0.0726, 'eval_samples_per_second': 13.777, 'eval_steps_per_second': 13.777, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 1.4889, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 0.752701461315155, 'eval_runtime': 0.0737, 'eval_samples_per_second': 13.57, 'eval_steps_per_second': 13.57, 'epoch': 10.0}\n", + "{'train_runtime': 12.2685, 'train_samples_per_second': 1.63, 'train_steps_per_second': 0.815, 'train_loss': 1.4879708528518676, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 10.88it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.81it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 12.30it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.50it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "I have a dream\n", + "{'before': 2.124803304672241, 'after': 2.120471954345703}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.88it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.50it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3804, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 2.0329105854034424, 'eval_runtime': 0.1215, 'eval_samples_per_second': 8.234, 'eval_steps_per_second': 8.234, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3772, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 2.03286075592041, 'eval_runtime': 0.1219, 'eval_samples_per_second': 8.202, 'eval_steps_per_second': 8.202, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3615, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 2.0326783657073975, 'eval_runtime': 0.1217, 'eval_samples_per_second': 8.215, 'eval_steps_per_second': 8.215, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.369, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 2.0326778888702393, 'eval_runtime': 0.1212, 'eval_samples_per_second': 8.254, 'eval_steps_per_second': 8.254, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3635, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 2.0327913761138916, 'eval_runtime': 0.1215, 'eval_samples_per_second': 8.232, 'eval_steps_per_second': 8.232, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.341, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 2.032545328140259, 'eval_runtime': 0.1205, 'eval_samples_per_second': 8.301, 'eval_steps_per_second': 8.301, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.384, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 2.0328757762908936, 'eval_runtime': 0.1194, 'eval_samples_per_second': 8.376, 'eval_steps_per_second': 8.376, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3573, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 2.0324862003326416, 'eval_runtime': 0.1222, 'eval_samples_per_second': 8.185, 'eval_steps_per_second': 8.185, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.3939, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 2.032426595687866, 'eval_runtime': 0.12, 'eval_samples_per_second': 8.334, 'eval_steps_per_second': 8.334, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.365, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 2.0326268672943115, 'eval_runtime': 0.1265, 'eval_samples_per_second': 7.902, 'eval_steps_per_second': 7.902, 'epoch': 10.0}\n", + "{'train_runtime': 13.9125, 'train_samples_per_second': 1.438, 'train_steps_per_second': 0.719, 'train_loss': 2.3692641973495485, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 9.01it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.76it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.93it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.13it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "AI gen fake paper\n", + "{'before': 7.635533809661865, 'after': 7.631838798522949}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.66it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.06it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4767, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.388134241104126, 'eval_runtime': 0.1253, 'eval_samples_per_second': 7.981, 'eval_steps_per_second': 7.981, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4838, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.3873133659362793, 'eval_runtime': 0.1259, 'eval_samples_per_second': 7.945, 'eval_steps_per_second': 7.945, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4723, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.387073278427124, 'eval_runtime': 0.1267, 'eval_samples_per_second': 7.893, 'eval_steps_per_second': 7.893, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.5019, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.387176513671875, 'eval_runtime': 0.125, 'eval_samples_per_second': 8.003, 'eval_steps_per_second': 8.003, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4934, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.387197256088257, 'eval_runtime': 0.1234, 'eval_samples_per_second': 8.102, 'eval_steps_per_second': 8.102, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.5131, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.3876898288726807, 'eval_runtime': 0.126, 'eval_samples_per_second': 7.938, 'eval_steps_per_second': 7.938, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4993, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.3870561122894287, 'eval_runtime': 0.1262, 'eval_samples_per_second': 7.927, 'eval_steps_per_second': 7.927, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4632, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.3876845836639404, 'eval_runtime': 0.1357, 'eval_samples_per_second': 7.372, 'eval_steps_per_second': 7.372, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.5131, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.3870444297790527, 'eval_runtime': 0.1251, 'eval_samples_per_second': 7.992, 'eval_steps_per_second': 7.992, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.4708, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.387460708618164, 'eval_runtime': 0.125, 'eval_samples_per_second': 7.998, 'eval_steps_per_second': 7.998, 'epoch': 10.0}\n", + "{'train_runtime': 15.2221, 'train_samples_per_second': 1.314, 'train_steps_per_second': 0.657, 'train_loss': 3.488762640953064, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.29it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 7.86it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.60it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.40it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Schmidhuber 2023 Subjective Novelty, Surprise\n", + "{'before': 29.606185913085938, 'after': 29.573911666870117}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 9.03it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.98it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2565, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.2224748134613037, 'eval_runtime': 0.1146, 'eval_samples_per_second': 8.723, 'eval_steps_per_second': 8.723, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2123, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.2232015132904053, 'eval_runtime': 0.1158, 'eval_samples_per_second': 8.633, 'eval_steps_per_second': 8.633, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1825, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.223541736602783, 'eval_runtime': 0.1154, 'eval_samples_per_second': 8.666, 'eval_steps_per_second': 8.666, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2017, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.2232275009155273, 'eval_runtime': 0.1157, 'eval_samples_per_second': 8.641, 'eval_steps_per_second': 8.641, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2476, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.2222542762756348, 'eval_runtime': 0.1131, 'eval_samples_per_second': 8.84, 'eval_steps_per_second': 8.84, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2973, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.2214126586914062, 'eval_runtime': 0.1191, 'eval_samples_per_second': 8.395, 'eval_steps_per_second': 8.395, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.1922, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.22304630279541, 'eval_runtime': 0.1168, 'eval_samples_per_second': 8.56, 'eval_steps_per_second': 8.56, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2295, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.2223405838012695, 'eval_runtime': 0.1154, 'eval_samples_per_second': 8.668, 'eval_steps_per_second': 8.668, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2669, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.22277569770813, 'eval_runtime': 0.1219, 'eval_samples_per_second': 8.205, 'eval_steps_per_second': 8.205, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.2785, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.22255539894104, 'eval_runtime': 0.1181, 'eval_samples_per_second': 8.466, 'eval_steps_per_second': 8.466, 'epoch': 10.0}\n", + "{'train_runtime': 13.6454, 'train_samples_per_second': 1.466, 'train_steps_per_second': 0.733, 'train_loss': 3.2364880084991454, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 8.54it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.38it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.03it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 8.95it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "email_to_fauci\n", + "{'before': 25.085100173950195, 'after': 25.0584774017334}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 33.61it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 26.31it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.6233, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 3.24851131439209, 'eval_runtime': 0.0612, 'eval_samples_per_second': 16.329, 'eval_steps_per_second': 16.329, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.8175, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 3.24828839302063, 'eval_runtime': 0.0618, 'eval_samples_per_second': 16.173, 'eval_steps_per_second': 16.173, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.6368, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 3.247272491455078, 'eval_runtime': 0.0625, 'eval_samples_per_second': 16.012, 'eval_steps_per_second': 16.012, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.7074, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 3.2483201026916504, 'eval_runtime': 0.0634, 'eval_samples_per_second': 15.772, 'eval_steps_per_second': 15.772, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.5788, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 3.247889280319214, 'eval_runtime': 0.0619, 'eval_samples_per_second': 16.157, 'eval_steps_per_second': 16.157, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.7083, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 3.2475459575653076, 'eval_runtime': 0.0633, 'eval_samples_per_second': 15.8, 'eval_steps_per_second': 15.8, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.6332, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 3.247795820236206, 'eval_runtime': 0.0629, 'eval_samples_per_second': 15.892, 'eval_steps_per_second': 15.892, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.6081, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 3.2480216026306152, 'eval_runtime': 0.1059, 'eval_samples_per_second': 9.444, 'eval_steps_per_second': 9.444, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.691, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 3.2482614517211914, 'eval_runtime': 0.0617, 'eval_samples_per_second': 16.214, 'eval_steps_per_second': 16.214, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 3.667, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 3.247227191925049, 'eval_runtime': 0.0614, 'eval_samples_per_second': 16.286, 'eval_steps_per_second': 16.286, 'epoch': 10.0}\n", + "{'train_runtime': 12.2797, 'train_samples_per_second': 1.629, 'train_steps_per_second': 0.814, 'train_loss': 3.6671237468719484, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmYAAAG0CAYAAACYMuszAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC6mElEQVR4nOydd3hUZdqH7/fMTHoHQhJCEkJvIthFsXdx1cWC+um6Nmywu2JFFFxRyqqrgq7YdWUtrIKuuCKisCLYUSChlwRICJDeM3Pe74+TMymkzCQzmZL3vq5cMJNTnpl35uQ5T/k9QkopUSgUCoVCoVD4HM3XBigUCoVCoVAoDJRjplAoFAqFQuEnKMdMoVAoFAqFwk9QjplCoVAoFAqFn6AcM4VCoVAoFAo/QTlmCoVCoVAoFH6CcswUCoVCoVAo/ATlmCkUCoVCoVD4CcoxUygUCoVCofATrL42wJOUl5dTV1fnazP8lvj4eIqKinxthqIetR7+h1oT/0Kth3/hjfWw2WxERUV59JiBTlA5ZnV1dVRVVfnaDL9ECAFAdXU1agqX71Hr4X+oNfEv1Hr4F2o9ug6VylQoFAqFQqHwE5RjplAoFAqFQuEnKMdMoVAoFAqFwk9QjplCoVAoFAqFnxBUxf8KhUKhUHgTu91OZWWlr83wCVVVVdTW1nZo34iICKxW5XK4gnqXFAqFQqFwAbvdTkVFBdHR0Wha90s42Wy2DklS6bpOWVkZkZGRyjlzge73yVIoFAqFogNUVlZ2W6esM2iaRnR0dLeNNLqL+nQpFAqFQuEiyinrGOp9cx31TikUCoVCoVD4CcoxUygUCoVCofATlGOmUCgUCoVC4Scox0yhUCgUCkWHCQ8PJykpyddmBA3KMWuHffs0Nmyw+dqMTiOlRDocvjZDoVAoFApFGyjHrA22bbMyfnwvrrsugdxci6/N6RT6szPIu3E8srLc16YoFAqFQqFoBaX01gbJyQ4SEnSys21cf30CS5YcIjZW+tost5FVlciNP+MAtO3ZiJHH+tokhUKhCHikhKoq4ZNzh4dLhBunjoqKIiIiAovFgt1up6ysjOrqanr37k1ZWVkTjTGr1UqvXr0oKCjA4XAQGRnpVO7XdZ3q6mpKS0uRMvD+HgYCyjFrg6goyVtvHWb8+F5s3WrjttsSePvtw9gCLbO5d3fD//fsAOWYKRQKRaepqhIMHJjsk3Nv25ZHRIRrjlFUVBTh4eGUlJRgt9sJCQkhPj6ew4cPU1VVRXh4eBPHLCIigtraWhyNyl9KSkoQQiClJDY2lpiYGEpKSjz+uhQqldkuKSk6b7xRSHi4zv/+F8pDD8USaDcJcu+uhv/v2e5DSxQKhULR1URFRVFcXExNTQ0Oh4OqqioqKyuJiIigsrKSkJAQLJaGcp3w8HCqqqqcjysqKqitrUXXdWpraykrKyMsLMwXL6VboCJmLjByZB0vvFDEH/+YwKJFkfTr5+COOwKoViu3kWOWs8OHhigUCkXwEB4u2bYtz2fndgWr1YqmafTo0aPJ80II6urqsNvt2O12wsPDKS8vJyQkBE3TmjhmISEhREdHY7VaEUI0+VHpTM+jHDMXOffcGmbOLOWRR2KZNSuGtDQ7F19c7WuzXEI2TmUWHkKWlSCiY31mj0KhUAQDQuByOtFXiPpCtMLCwiapScDpVJnpzPLycsLDw6mpqXH+zmKx0KNHDyoqKqisrKS2ttaZClV4B5XKdIObbqrgj380ImVTpsTz00/+X2wmdQfs2wOACAs3ntyjomYKhULRHbDb7UgpsVgsOByOJj+6rgOGY2a1WrHZbEfUm9nqi6pLS0ux2+04HI4maU+F51GOmZvMmFHK2WdXU10tuPHGBHJy/PwDWpAPtTUQEkLYcacAKp2pUCgU3QUpJeXl5cTExBAeHo7FYsFmsxEZGUl4uHGz7nA4qK2tJS4uDoDq6oZskN1uRwhBZGQkmqYRHh5OZGSkL15Kt0E5Zm5iscALLxQxYkQthw9b+L//S6C42Dft0i5hFv6npBMycBgAUkXMFAqFottQVlZGeXk5UVFRJCYmkpCQQGhoaJPUZlVVFTabrYlTBoZjVlJSQlRUFAkJCYSHh1NaWtrVL6FboWrMOkBkpOSNNwq5+OJebN9u49ZbE/jnPw8TEuJry45E5u4GQPTtR8iAocaTKmKmUCgU3YqKigoqKipa/X1lZWWTFGZL+9psNurq6gCaNAdUVVU1eazoHCpi1kGSk3XeeuswkZE6a9aE8sADcX4po2FKZYi+/QjpP9h48tABZEWZD61SKBQKhULREsox6wTDh9t58cUiNE3y3nsRPP98lK9NOhLTMUvthxYVDb3qB83m7PShUQqFQqFQKFpCOWad5KyzavjrXw314zlzYli61H9E92RFGRQeMh6kZgAg0vsbv1NCswqFQqFQ+B3KMfMAf/hDJbfcYsho/PnP8fzwg5/IaJj6ZT0SERFGF41IMxwzFTFTKBQKhcL/UI6Zh5g+vZRzz62ipkbwxz8msHu372U0pKn4Xx8tAyB9gPE71ZmpUCgUbmNqfyncQ71vrqMcMw9hscCCBcWMHFlLYaGF669PoKjIxzIajQr/TcxUJgX7kZWtd+goFAqFoikRERGUlZUpJ8NNdF2nrKyMiIgIX5sSECi5DA8SEWHIaIwf35MdO2zccksCixb5TkbDKZWR2sgxi4qBHolwuMCYoTl4hG+MUygUigDDarUSGRlJeXkAzUr2ICEhIdTW1nZo38jISKxW5XK4gnqXPExSks6bbxZy2WU9Wbs2lHvvjePvfy9GdHHwTDocsD/HeNA3o+kv0zLhcAFyz3aEcswUCoXCZaxWKzExMb42o8sRQpCcnExeXp4aXO5lVCrTCwwbZuell4qwWCSLF0fw97/7QEYjfx/Y6yA0HHomNflVQwOAqjNTKBQKhcKfUI6Zlzj99BpmzTJkNP72txg+/DC8S89vCsuSmo7Qmi6zUA0ACoVCoVD4Jcox8yL/93+VTJpk1CLcc08c333XhcVm9VIZonFHpkl6pvHvgX3IajVGQ6FQKBQKf0E5Zl5m2rRSLrywitpawU03xbNzZ9fIaDREzPod8TsREw9xPUDKhiHnCoVCoVAofI5bxf/Lly9n+fLlHDx4EIDU1FQmTJjA6NGjW93n008/Zfny5Rw6dIiYmBhOOOEErrnmGkIatSr+97//5ZNPPqG4uJj09HT++Mc/MmDAgA6+JP9C0+C554rZv9/C+vUhXH99Dz7++CAJCV4unmw0vLxF0vtD8WHknh2IAcO8a4tCoVAoFAqXcCtilpCQwDXXXMPs2bN58sknGTFiBHPnziU3N7fF7b/55hsWLVrEFVdcwTPPPMOkSZNYu3Yt//rXv5zbfPvtt7z11ltMmDCBOXPmkJ6ezqxZsygpKencK/MjwsMlr79eSGqqnV27rNx8cwI1Nd47nywrgZJCEAL6pLe4jbMBQNWZKRQKhULhN7jlmB177LGMGTOG5ORkUlJSmDhxImFhYWzbtq3F7bds2cLgwYM55ZRTSExMZNSoUYwdO5bt2xvmNP7nP//hrLPO4owzziA1NZVbbrmFkJAQvvrqq869Mj8jMVHnrbcKiY7W+e67UKZOjcNrHcem4n+vJERYy00HzpmZqjNToVAoFAq/ocM6Zrqus3btWmpqahg0aFCL2wwePJj//e9/bN++nQEDBnDgwAF++eUXTj31VADsdjs7d+7k0ksvde6jaRojR45k69atrZ67rq6Ourq6JvuEhRnDw0VXC4a5wZAhDhYuLOK66xL48MMIMjIcTJ3qeaFC2ajw33w/mv9rjmZify7U1iBC/Wf4enfgiPVQ+By1Jv6FWg//Qq1H1+G2Y5aTk8O0adOoq6sjLCyMqVOnkpqa2uK2p5xyCqWlpUyfPh0Ah8PBOeecw+WXXw5AaWkpuq4TFxfXZL+4uDj279/fqg0fffQRixcvdj4eO3YsU6ZMIT4+3t2X0+VcfTWUlcGtt8LTT0czalQ011/v2XMcPpxPJRA99Chik5Ob/C4pydA0k0lJ7I/rgV58mB7V5YRmtFKLpvAq5noo/Ae1Jv6FWg//wtfr4W6t+4oVK1i9erWz5CozM5OJEye2Wse+cOFCVqxYwQ033MBFF13kfH7//v3885//ZMuWLdjtdtLS0rjqqqsYMeJIkfaysjLuvfdeCgsLef3114mMjHTrNbrtmKWkpDBv3jwqKytZt24dCxYsYObMmS06Z5s2beKjjz7i5ptvZuDAgeTn5/P666+zePFiJkyY4O6pnVx22WVcfPHFzsdavU5XUVER1dXVHT5uV3HxxXDnndEsWBDFzTdLoqIKOemkjo25aAn71iwAyuN6UpmXBxh3OUlJSeTn5ztVm2VqBhQf5tDP36HF9vTY+RXt09J6KHyLWhP/Qq2Hf+Gt9QgLC3MrqGLWuicnJyOlZNWqVcydO5e5c+fSt2/fI7bPyspi7NixDB48GJvNxtKlS3n88cd5+umnSUhIaLLt999/z7Zt21q0Z86cOSQlJfHII48QEhLCp59+ypw5c3j++eePCC69+OKLpKenU1hY6PLraozbjpnVanV6zJmZmezYsYNly5Zx6623HrHte++9x7hx4zjrrLMASEtLo7q6moULF3L55ZcTExODpmkUFxc32a+4uPiIF9oYm82GzWZr8XeB8gV+4IFSdu+28Omn4dx0UzxLlx5kwABHp48r7XWQt9d4kJpxxPshpWx4Lr0/bPwJuWdHwLxvwUaT9VD4BWpN/Au1Hv6Fr9fj2GOPbfJ44sSJLF++nG3btrXomE2ePLnJ40mTJvHdd9+xYcMGTjvtNOfzhYWFvPbaa0ybNo3Zs2c32ae0tJS8vDwmTZpEerrRUHfttdeyfPlycnJymvgry5cvp7KykgkTJvDLL7906DV2elamrutN6r0aU1NTc0Q+WmukQm+1WsnMzGTjxo0cf/zxzuNt3LiR888/v0P2BEr+22IxZDTy8iz8/HMIN9zQg08+OUSPHp38wBfkIUJCITwe0bN36zVmgJY5GD08Eg7sC5j3LVhQ9Rr+h1oT/0Kth3/h7fWoqqpq4vC1FYAxcaXWvTk1NTXY7XaiohpGJeq6zvPPP88ll1zSonMXHR1NSkoKq1atol+/fthsNr744gtiY2PJzMx0brd3714WL17ME088wYEDB1yypyXccswWLVrE0UcfTc+ePamuruabb74hKyuLadOmATB//nxnmBHgmGOO4dNPP6Vfv37OVOZ7773HMccc43TQLr74YhYsWEBmZiYDBgxg2bJl1NTUcPrpp7v9YgKhxqw5n30GJ5wAu3dbmTQpiRUrIKwzdfjJybB4Vau/blIfkPw7OP93nTiZorP4ul5DcSRqTfwLtR7+hbfWY8aMGeza1SB4PmHCBK688soWt3Wn1r0577zzDgkJCYwcOdL53NKlS7FYLFxwwQUt7iOEYPr06cybN48bbrgBIQSxsbE89NBDTgevrq6OZ599luuuu46ePXt2nWNWUlLCggULKCoqIiIigvT0dKZNm8ZRRx0FwKFDh5p407///e8RQvDuu+9SWFhITEwMxxxzDBMnTnRuc/LJJ1NaWsr7779PcXExGRkZPPTQQ22mMlsjUGrMmvPmm1bGj+/BmjUaV19dxYIFxWgdnMmgL3kb+eWniHHnoV1xo/P5FmvMpER/6BYoL0e7d1aDtpnC66j6Gf9DrYl/odbDv/B2jdmMGTOOiJi1hju17o1ZsmQJa9asYcaMGU6R+507d7Js2TLmzJnTajRQSsmrr75KbGwsM2fOJCQkhJUrVzJnzhyefPJJ4uPjWbRoEX369GHcuHEdeBeaImQQfeKLioqoqgrM2Y/ffBPCtdf2wG4XTJlSxn33lXXoOI6np0P2r4jr70I79Vzn80IIkpOTycvLa/LhdzzzCGStR/zfHWjjOpY+VrhPa+uh8B1qTfwLtR7+hbfWIzw8vNPZrr/+9a/07t27xVp3k48//pgPP/yQ6dOn079/QxDi008/5a233mrilOm6jhCCnj17smDBAjZs2MDjjz/O66+/TkREhHO7yZMnc+aZZ3LppZdy7733kpOT4zyOWYunaRqXX355q9G/luh0jZnCM5xySi1z5xbzl7/E8+yz0aSn27nqKvecTCllo+HlrslfiPT+yKz1agKAQqFQKAKStmrdwUhVfvjhh0ybNq2JUwYwbty4JmlNgFmzZjFu3DjOOOMMwKhLg6Y18mA4q7quA3DPPfdQW9ugrrBjxw5efPFFHnvsMXr37u3W61GOmR9x1VVV7N5t5bnnornvvjj69HFwyiluyGiUFEFZCQgN+qS5tItI648EpHLMFAqFQuHnuFvrvmTJEt5//30mT55MYmKiUwUiLCyMsLAwoqOjiY6ObnIOq9VKXFwcKSkpAAwaNIioqCjmz5/PhAkTCAkJ4csvv6SgoIAxY8YAR9belZUZWa8+ffp4X8dM4V3uvbeMPXssLF0awa23JrB06SEGDrS7tvPe+sLJ3ilGZ6YrmBMA9u1G2u0Iq/pIKBQKhcI/cbfW/YsvvsBut/P00083OU5bzQXNiYmJ4aGHHuLdd9/lsccew+FwkJqayn333UdGRobHXpuJqjHzQ6qr4aqrevLjjyGkpdn55JND9Oypt7uf/tm/kR++iTjuVLRb723yu9bqA6SU6FOugaoKtOl/R6RlNj+swguo+hn/Q62Jf6HWw7/w5xqzYKODvX8KbxIWBq+9Vkh6up2cHCs33piAS/6mGTFLzXD5XEIIqHfG1EBzhUKhUCh8i3LM/JQePXTeeuswcXE6P/8cwp//HI/eTtBM5hqOmXDDMQMQZjpT1ZkpFAqFQuFTlGPmxwwY4ODllwux2SSffBLOnDnRrW4r62rhwD7jgYsdmU5UxEyhUCgUCr9AOWZ+zskn1zJvXjEA8+dH869/RbS84f4c0HWIjIb4Hm6dwxkx27sL6ej8vE6FQqFQKBQdQzlmAcAVV1Tx5z8brbcPPBDL6tUhR2xjpjFJzXB/llliMoSFQ20t5O/trLkKhUKhUCg6iHLMAoR77injsssqsdsFt96awJYtzWQtTGHZvm6mMQGhaQ3pTFVnplAoFAqFz1COWYAgBDz1VDHHH19DWZnG9dcncPBgw/LJesfM7foy8/jmnExVZ6ZQKBQKhc9QjlkAERoKr75aSL9+dvbuNWU0hKEpY3Zk9s3o2MHrHTMVMVMoFAqFwncoxyzASEiQThmNX34JYfLkOPTDh6CyHCwWSHZtFFNzRHp9xCx3J1JXDQAKhUKhUPgC5ZgFIJmZDl57rZCQEMmyZeE88Vh9p2ZSKsJm69hBk/pASCjUVMOBPM8Zq1AoFAqFwmWUYxagnHBCLU89VQzAP/49kHdyLnNbWLYxQrNAfeOA3LPdAxYqFAqFQqFwF+WYBTCXX17F1KmlADy86X5WlYzr1PFUA4BCoVAoFL5FOWYBzp/+VM7l/b/CIa1M+seFbN5sbX+n1qgXmpU5Oz1knaIt2huxpVAoFIruh3LMAp3aauYMnMaJCT9RXmnj+usTOHCgY8sq0g0tM3J2IJXX4FX+9rcoYmPhl186WBOoUCgUiqBEOWaBzr49hGq1LBz3VzIz7ezbZ8hoVFa6qf4PkNQXrDaoqoRD+Z63VeHk44/DKS+HZ56J8rUpCoVCofAjlGMW4Mi9hn5Z3ICevP32YRISHPz6awh33RWHu2MvhdXaqAFA1Zl5i6oq2LnTAsCKFWFs396J9LNCoVAoggrlmAU6ubsBEKn9yMhw8NprRYSGSj7/PJzHH49x+3CifjQTyjHzGlu22ND1hojmK69E+tAahUKhUPgTyjELcMyIGfWK/8cdV8szzxQBsHBhFG+8EeHeAZ0NAMox8xZZWUZdWWKi8fiDD8IpLFRfRYVCoVAoxyygkbreMLy80YzM3/2umvvvN2Q0pk+PZeXKUJeP6ZTM2LPDGPWk8DjZ2Ubq8v/+D0aOrKO6WuPtt910oBUKhUIRlCjHLJA5XADVVWC1QlJqk1/dfXc5V11Via4LJk2KZ9MmF+uY+qSBxWqMeDpc4AWjFWbEbNQouPXWCgDeeCOSmhpfWqVQKBQKf0A5ZoFMfbSM5L5G4X4jhIDZs4sZO7aGigqN669PYP/+9g8prDbok248UHVmHkfKBsfsqKNg/PgqkpIcFBRYWLo03MfWKRQKhcLXKMcsgJG5Rn1Z4zRmY0JCYOHCQgYMqCMvz8L48WC3t39cc6C5qjPzPPv2WSgt1bDZJEOHGmt0441G1Ozll6NQ2WOFQqHo3ijHLIBpKPxv2TEDiIuTvPVWIdHROj//DOvXuyBoWl9npmZmep6sLCOyOXCgnZAQ47lrr60gPFwnK8vGmjUhPrROoVAoFL5GOWaBjLPwP6PNzdLTHRx/fC0Amza175iZETNydqoGAA9jpjGHDatzPhcfL7nyyirA6KRVKBQKRfdFOWYBiqyqhIP16vytpDIbM3y4kcN0qQkgNQM0DcpKoOhwJ6xUNMd0zIYObZpTvummcoSQfPmlEpxVKBSK7oxyzAKVfbuNf+MSENHtC8mOGGFEaDZudCFiZguBlDTjQY5KZ3qSliJmAP37OzjnnGpACc4qFApFd0Y5ZgGKrFf8dyVaBjB8uOEIbN5sc68BYM/OjpinaIHKSsHu3cYoJjOC2RhTOkMJzioUCkX3RV39A5X6wn9Rr/jfHunpDqKioLpasHOnC6ky1QDgcbKzrUgpSEx00LOnfsTvTzyxlpEja5XgrEKhUHRjlGMWoJhSGa5GzDTNEDQFFxsA0hoaABSeITu75TSmiRBwyy1KcFahCBYqKgQPPhjLhx8qjUKF6yjHLACRugP27QFAtCGV0ZzRo41/Xakzo28/EBqUFCKLCztipqIZrRX+N0YJzioUwYGU8Oc/x/HWW5E88kiM0ihUuIxyzAKRgnyorQFbCCSmuLzb0Ucb/7oUMQsNg6Q+xgMlNOsRTA2z1iJmoARnFYpg4YUXovj0U+PmqqjIQl6e+nOrcA31SQlEzI7MlDSExeLybg2OmdWlP/gifQCgJgB4Al1vP5VpogRnFYrA5uuvQ3nyyWgAQkONi60ZMVco2kM5ZgGIcxSTG2lMgOHDwWKRFBZayM93YenTM43zqZmZnWbvXgvl5RohIZL+/dtui1WCswpF4LJ7t4U77ohHSsG111ZwwQXGd1k5ZgpXUY5ZACLN4eUuFv6bhIXBoEGGU+CSnlmaETFTqczOY16UBw2qw+bC9VkJzioUgUdlpeDmmxMoKdEYM6aWv/61pJG4t3LMFK6hHLNAJNc9qYzGmHpmLl0k0uodv8JDyLISt8+laMCsL2ur8L8xSnBWoQgspIS//CWO7GwbiYkOXn65kNDQhtIFFTFTuIpyzAIMWVEOhQeNB+3MyGwJd+7eRFgE9K5vAFDpzE7RmuJ/WyjBWYUicPjHPyL55JNwrFbJwoVFJCUZWoXmzfCuXRYqK4UvTVQECOpqH2iYacweiYgI9+uPzIuEq3dvDRMAlNBsZ+iIY6YEZxWKwGD16lCeeMIYjffYYyUcd1yt83e9eun06uVASkF2tipLULSPcswCDLnXFJbN6ND+pmO2e7eV0lIX7t7MCQBKaLbDlJcL9uwxpTJcS2WCEpxVKAKBnBwLt98ej64LJk6s4PrrK4/YRqUzFe6gHLNAw6wv66BjFh8v6dPHcA5M+Ya2MCNmqgGg45h3yUlJDhISjhzF1BZKcFah8F8qKwV//GMCxcUao0fX8vjjJYgW7nfdqu1VdHuUYxZgmB2Z7kplNMa9BgBDMoNDB5AVZR0+Z3emI2lMEyU4q1D4J1LC1KmxZGfb6NnTwcKFhYSFtbytGSlXETOFKyjHLICQjoZRTO5KZTSmoQGg/XoHEREFvZKMByqd2SE645iBEpxVKPyRl16KZOnSCGexf0pK69Fw82Y4O9uK7l7QXNENUY5ZIHFgH9jrIDSswVnqACNGGBcJl2Zm0jDQXDUAdIzOOmZKcFah8C9Wrw5h1iyj2H/mzBJOOKG2ze0zM+2EhkoqKzV273Z9Wouie6JaRAIIU/GfPukIreM+tXn3tnWrjdpaI13WJun94ac1KmLWAXQdNm92v/C/OTfdVM5bb0U4BWcHDOj4sRQKRcfJzTWU/XVdcOWVldxww5HF/s2xWmHw4Dp++y2ErCwbmZmOLrA0OFm+fDnLly/n4EFDNio1NZUJEyYwevToFrdfsWIFq1evJjc3F4DMzEwmTpzIgAEDWtx+4cKFrFixghtuuIGLLrrI+fz+/fv55z//yZYtW7Db7aSlpXHVVVcxYsQIAHbv3s2SJUvYsmULpaWlJCYmcs4553DhhRe6/RpVxCyQqJ+RKTqRxgRITXUQE6NTWytcUpVXkhkdZ88eC5WVGqGhkn79Ou5MKcFZhcL3VFUJbropgaIiC6NG1fLkk8UtFvu3hGoA8AwJCQlcc801zJ49myeffJIRI0Ywd+5cp+PVnKysLMaOHcujjz7K448/To8ePXj88ccpLCw8Ytvvv/+ebdu2ER8ff8Tv5syZg8Ph4JFHHmH27Nmkp6czZ84ciouLAdi5cyexsbHcfffdPP3001x22WUsWrSI//73v26/xqCLmAlXvyWBSEE+IjwS0W+g26/T3F4IgaYZF4m1a0PJygph+PB27t4yBiLCI6GsFKqqEBFKU8tVsrONcOTgwXXYbA1r1ng9XOW22ypZvjycDz6I4L77yujRQ3UCeJKOrInCe/jbekgJ990Xx6ZNRrH/K68UER7uum2NGwD85TW5g7fXo6qqCtmou8lms2FrYX7dscce2+TxxIkTWb58Odu2baNv375HbD958uQmjydNmsR3333Hhg0bOO2005zPFxYW8tprrzFt2jRmz57dZJ/S0lLy8vKYNGkS6enpAFx77bUsX76cnJwc4uLiOPPMM5vs07t3b7Zu3cp3333H+eef7+K7YBBUjllLXm5Q8diznT5EUpJRm3bCCbB2LezaFUdyclw7eyXD4lWdPnd3JCfH+PfYY0NITk4+4vfmerjCZZfBmDHw88+CpUuTmDbNU1YqGuPOmii8j7+sxzPPwIcfGmnJf//bwrHH9nZrf9MH2Lw5rMVrQaDgrfWYMWMGu3btcj6eMGECV155ZZv76LrO2rVrqampYdCgQS6dp6amBrvdTlRUQ72urus8//zzXHLJJS06d9HR0aSkpLBq1Sr69euHzWbjiy++IDY2lszMzFbPVVlZ2eQ8rhJUjllRURHV1dW+NsMryPIy9AdvAUCb95oxLskNhBAkJSWRn5+PlJKMjHAgju+/ryEv78iQbnMcrzwFv/6AuOw6tDMv7shL6JZ89108EEZGRgl5eQ21KM3Xw1VuvDGcn3+O47nnHFx7bQGhoV4wupvS0TVReAd/Wo9vvgnh3nsTAMGjj5YwcGAleXnuHSMxUQBJ7N0LWVn5xMcH1mfMW+sRFhZGfHw8M2bMOCJi1ho5OTlMmzaNuro6wsLCmDp1KqmpqS6d75133iEhIYGRI0c6n1u6dCkWi4ULLrigxX2EEEyfPp158+Zxww03IIQgNjaWhx56qFXHa8uWLaxdu5YHHnjAJbsaE1SOGeDzL7C3kDk7kFUVRjdmaHiHX6eUEiklw4YZXUSbNtnQddl+nUTvPsiqr2HHZuQZF7WzscLEFJcdNqyuxTUz18NVLr64klmzosnPt7BkSZizW1PhOdxdE4V38fV67N1rYdKkOBwOwYQJldx4Y0WH9ASjoyV9+9rJzbWyaZOVsWPb7uT0V7y1HuHhrgtop6SkMG/ePCorK1m3bh0LFixg5syZ7TpnS5YsYc2aNcyYMYOQ+q63nTt3smzZMubMmdNqmlZKyauvvkpsbCwzZ84kJCSElStXMmfOHJ588skjsnU5OTnMnTuXCRMmMGrUKJdfl4kq/g8QnB2ZnRCWbczAgXZsNklJica+fe23b4t0o4NFqmHmLlNaKsjNNRyzoUM7JpXRHCU4q1B0HVVVcPPN8RQWWjjqqFpmz3a92L8lVAOAZ7BarSQlJZGZmck111xDRkYGy5Yta3Ofjz/+mCVLlvDwww8768QAsrOzKS0t5Y477uDqq6/m6quv5uDBg7z11lvceeedAGzcuJGffvqJKVOmMGTIEDIzM7n55psJCQlh1aqmZT579+7lr3/9K2effTa///3vO/b6OrSXouvZa45i8oxjFhJiFKRv3BjCxo02UlPbaQBIr8+jH9iHrK5ChKnxQO1hjrxKSbETF+c5D+raayv4+9+jnIKzp5wSmHfeCoU/Yxb7b9gQQkKCWezfuWMOG2bnv/9VEwA8ja7r1NW1fvO7dOlSPvzwQ6ZNm0b//v2b/G7cuHFN0poAs2bNYty4cZxxxhmAUZcGoDWTqRJCoDdSDM7NzeWxxx7jtNNOY+LEiR1+PSpiFiDI3N1Ax2dktkTDBAAXZmbGxENcD+Nqlbur3e0VkJXVef2yllCCswqF93n11Ug+/DACi0Xy0ktF9OnTee0xFTHrPIsWLSIrK4uCggJycnKcj0899VQA5s+fz6JFi5zbL1myhPfee4/bb7+dxMREiouLKS4udtajR0dHk5aW1uTHarUSFxdHSkoKAIMGDSIqKor58+eze/du9u/fz9tvv01BQQFjxowBjPTlzJkzOeqoo7j44oud5yktLXX7NaqIWQAg7XWQV6/R4lHHzLxIuPgxSO8PxYeROTsQA4d5zI5gpbOK/22hBGcVCu/x7bchPPaYoez/yCOlnHyyZ6LS5rVg2zara+LeiiMoKSlhwYIFFBUVERERQXp6OtOmTeOoo44C4NChQ01qxb744gvsdjtPP/10k+O40vVpEhMTw0MPPcS7777LY489hsPhIDU1lfvuu4+MjAwA1q1bR2lpKf/73//43//+59y3V69eLFiwwK3XqByzQCB/LzjsEB4BPd1r0W4Ld+/eRFp/5K/fg6ozcwkzlekNx8wUnF2+PJxXXolk9uwSj59DoeiO7NtnYdKkeBwOweWXV3LTTRUeO3bfvg6io3XKyjS2b7d6PJreHbj99tvb/P2MGTOaPHbXKWptn/79+zOtDY2iK6+80mVHrz1UKjMAMNOY9MnwqLif6TDs3WulqKj94zonAOQox6w9HI6GjkxPFf4359ZbjT8YH3wQTmGh+iorFJ3FLPY/fNjCiBG1zJ1b0qli/+YI0XDdVelMRWuoq3kgYBb+983w6GFjYiTp6Q1q1O1SP8yc/bnI+mJIRcvs2mWhulojLEynXz/vzMU78cRaRo6spbpa4+231TQGhaIzSAkPPBDHb7+FEB/v4NVXiwgP93zbs+mYqQYARWu4lcp0d3jojBkzyMrKOuL50aNH8+CDDwJGyLB5u+moUaPaDBl2N5xSGR7qyGzM8OF17NljZdMmW/u6OnEJEBMHpcWGs9h/iMftCRbMi+7QoXYs7auRdAgh4JZbKpg8OYQ33ohk0qRyJTirUHSQN96IYPFio9j/H/8oar9TvYO403Sl6J645ZiZw0OTk5ORUrJq1Srmzp3L3LlzWxxjMHXqVOz2hhx6WVkZ9957LyeddFKT7Y4++mjuuOOOBqOsqvStCXt3AyA8pGHWmGHD6li2LNy1zkwhjKjZxp+QOTsRyjFrFW/WlzVm/Pgqnngihvx8C0uXhivBWYWiA6xbF8KMGbEAPPxwqVclaBoiZlakxKOpUkVw4FYq89hjj2XMmDEkJyeTkpLCxIkTCQsLY9u2bS1uHxUVRVxcnPPnt99+IzQ0lBNPPLHJdmZrqvnTkdlSwYosKYKyEhAapKS3v4ObjBjhZgNAfZ0Ze7Z73JZgoiFi5l3HTAnOKhSdY98+jVtvjcduF1x2WSW33OK5Yv+WGDSoDk2TFBVZyM9X1USKI+lwaKojw0NXrlzJySefTFhYWJPns7KyuPnmm4mMjGTEiBFcffXVREdHt3qcurq6JmJymqY5j+nJ4nh/QNZHy+idjNbsfXMH831p/v6MGGFENLdts1JTI2jvFCJ9ABKMiFmQvdeexHTMhg+3t/g+tbYeHeG66yqdgrPffhuqBGc7iCfXRNF5umI9qqvh1lsTOHzYwvDhdcybV4KmeXf9IyJgwAA7W7fayMoKISUlMOp11fej63DbMevo8NDt27eTm5t7RKvr0UcfzQknnEBiYiL5+fn861//4oknnmDWrFlHqOyafPTRRyxevNj5eOzYsUyZMuWIeVXBQOmaQ5QA4QOH0TM5udPHS0pKavYYevSAw4cFRUXJ1GvltYr9uJPJA9i/h6SePRA2JcTTnMJC2L/f+P8ZZ/QkNrb1bZuvR0dIToYbb4QXXoA33+zBFVd0+pDdGk+sicJzeGs9pISbboL16yEhAf7zHxsZGZ2/xrrCMcfA1q2Qm5uABy7rXYr6fngftx2zjg4PXblyJWlpaQwYMKDJ82PHjnX+Py0tjfT0dO6++242bdp0xJgEk8suu4yLL77Y+dh04IqKipxqvsGCI+s3AGp6JpGXl9fh4wghSEpKIj8//4gBtEOHJvDNN6F8/XUxyclt1yhJKSEqGsrLyPtxHSJjYIdtCla+/TYE6EHfvnYqKw9SWXnkNm2tR0eYONHCiy/24tNPBatXFzBwoHcKl4MZT6+JonN4ez3eeCOC11+PRdMkL7xQSGhoLZ24xLpFZmYkEMO6dVXk5RV3zUk7ibfWIywsLCiDKp3BbcfMHB4KkJmZyY4dO1i2bBm33nprq/tUV1ezZs0arrrqqnaP37t3b6Kjo8nPz2/VMbPZbNhsLddEBdsFtaEjM8Mjr01KecRxRoyo45tvQtm40eraOdL6Q9Z69D3b0dIHtL99N6NhFFNdu+9nS+vRETIz7Upw1kN4ak0UnsEb6/HddyE88oih7D9tWimnnlrTpfWZjbXMAu2zpr4f3qfTlYftDQ8FY1SB3W53zrJqi8OHD1NeXq48aEDW1Rqq/+DRUUzNcXsCgLMBQAnNtoTpmA0d2rWq3kpwVqFon/37G4r9f/e7Sm67zbvF/i1hOma7dlmorFQ1W4qmuHX1dnd4qMnKlSs57rjjjijor66u5u2332br1q0UFBSwYcMG5s6dS1JSEqNGjerEywoS9ueCrkNEFMT39NppTMcsK8uGrre/vagXmpXKMWsRb87IbAslOKtQtE1NjVHsf+iQhaFD6/jb3zyr7O8qiYk6vXo5kFI4J4QoFCZufSLcHR4KsH//fjZv3szDDz98xPE0TSMnJ4dVq1ZRUVFBQkICRx11FFdddVWrqcruhKxX/KdvP692wvTvbyc0VFJerpGTYyEjo536JDN9uW830m5HKN05J3Y7bNniG8dMCc4qFK0jJUybFssvv4QQF6fz2muFRET4LiU3bFgdq1ZZyMqyccwxXXutUPg3bv1FdXd4KBjNAu+//36L24eEhCiF/7aory8TXkxjAlitMGRIHb/+GsLGjbb2HbOevSEiEiorYH8OpGV61b5AYudOQ3YkMlInPb3rC/CV4KxC0TJvvx3Bv/4ViaZJXnyxiLQ03zbIDB9ex6pVYWo0k+IIVCGKH+PUMPOC4n9z3BGadU4AQA00b46ZlhgyxE4rai9eRQnOKhRH8sMPITzyiKFb8+CDZYwb53vtsGHD1GgmRcsox8xPkVI2iph53zFr3CXkCmadmWoAaEpXKf63xbXXVhAerpOVZWPNGqUzp+je5Ocbxf51dYLx46u4/fZyX5sENFxzs7OtLtX2KroPyjHzV4oOQ2U5aBqkHDmH1NO425lppi9VxKwpvir8b0x8vHSmMBcuVOPNFN2Xmhq45ZYECgqMYv+nny72m9mUZm1vZaXG7t0WX5uj8COUY+avmIX/Saldoq4/bJgdIST5+RYOH27/YyHMBoC9u5AOJWZq4g+OGcBNN5UjhOTLL8PYvl01Zyi6J9Onx/Lzz0ax/yuv+LbYvzlWKwwe3NARr1CYKMfMT5FdmMYEiIyU9OtnOFguRc0SkyEsHGobaa11cwoLNfLzjTvfrtYwa07//g7OOceYgvHKK5E+tUWh8AX//GcE77wTiRCSBQuK2m9q8gGNpYoUChPlmPkrzsL/jC47ZUM6s/0Ii9C0hnSmqjMDGoRl09PtREX5/s5cCc4quis//mjj4YeNYv8HHijj9NN9X+zfEqoBQNES6mrtp5gaZl0VMYMOTAAwGwBUnRngP2lMEyU4q+iOGMX+CdTVCS66qIo77/SPYv+WMK8V5k2dQgHKMfNLZE0NHKifptsFUhkmpmO2caOLd2/pagJAY/zNMTMFZwHeeCOSGv8MGigUHqO21lD2P3DAwuDBdTzzjP8U+7eEea3Yv99KUZEfG6roUpRj5o/s3wNSh+hYRGzXzQw1tcx27LBSVdX+RcIZMcvdidT9r36jq2lwzHxbX9aY8eOrSEpyUFBgCM4qFMHMI4/E8tNPIcTG6rz6aiGRkb4vKWiLmBhJ377G9ULVmSlMlGPmh5iF/94cXN4S5vw2XRds3uxCaD2pD4SEQk11Q4Svm1JXB9u2Ge+Zv0TMQAnOKroPixZF8PbbRrH//PlFzmYmf0c1ACiaoxwzf8SsL+vCNKaJO3VmQrM4U61yz3av2uXv7NhhpbZWEBWlk5rqX38QlOCsItj56Scb06YZxf733VfGmWcGTt5eNQAomqMcMz9E5u42/tOFhf8m7taZqQYAg8aK/74YxdQWSnBWEcwUFBjF/rW1ggsvrOLuu/232L8lGhoAlGOmMPCzPyEKKSXs2w2A6EKpDBO3JwDUC83KnJ3eMikg8Mf6ssYowVlFMGIU+8eTn29h0CD/L/ZvCfOau3WrldpaHxuj8AuUY+ZvHDoAVZVgsUJSapef3rxIZGdbcUXQX6QbWmbk7EB244FvZru7P9WXNUYJziqCkRkzYvnhh1BiYoxif3/QD3SXvn0dREfr1NUJddOkAJRj5n+YwrLJfRHWrg9t9+vnIDxcp6pKY9cuF+a3JaeBLcRwJg/le99APyU727+kMlpCCc4qgol33w3nzTeNYv/nny8iM9O/ajtdRQiVzlQ0RV2d/QxZ75j5Io0JYLE0jBNyqQHAYnF2j3ZXPbNDhzQKCiwIIRkyxD9TmaAEZxXBwy+/2HjwwTgApk4t4+yzA6fYvyVMx0w1AChAOWZ+h6n474vCfxNTz8z1CQD16cxu6piZd7kZGQ6/GpLcHCU4qwgGDh7UuPlmo9j//POrmDw5sIr9W8KsTVURMwUox8z/yPWdVIZJxxsAuqtj5t/1ZY1RgrOKQKa2Fm67zSj2HziwjmefLfa7LuiO0KBlZlVagwrlmPkTsroSDtbXafkwYtbhmZl7dhhdpd0M830KBMdMCc4qApnHHovhu+9CiY7WeeWVwCz2b4lBg+rQNElhoYX8fPVnubujPgH+xN49xr9xCYjoGJ+ZMWSIHU2THDxo4cABFz4ifdKMLtLKcjhc4H0D/YxAKPxvjBKcVQQi770XzuuvGzp8zz1XxIABgVns3xLh4TBggEpnKgyUY+ZH+EN9GUB4uHReJFxqALDaoE+68aCb1ZnV1uJscfdXDbPmKMFZRaCxfn3jYv9Szj03+AokVQOAwkQ5Zv5EveK/6OIZmS3hdjoz3Uhndrc6s23brNTVCWJjdfr0CZw7eCU4qwgUDh0yiv1ragTnnlvFlCmBX+zfEqoBQGGiHDM/oiFiluFTO6ADDQD1dWbdbWZm41FMgaQ4rgRnFYFAXR3cdlsceXkW+vev47nngqPYvyUaNwAoujdB+hEPPKSuwz6jxsyXHZkmw4cbd28uz8xMN2dm7uxWDQANo5gCo76sMUpwVuHvTJ0Ka9eGEhWl89prRURHB++1xbyG7NxppbIygO7yFB5HXY39hYP5UFMNVhv07uNra5x3b7t3Wygvd+EikZoBmgZlJVB0yLvG+RFm4b8pyhtIKMFZhT/zwQfhPPec8f/nnit21r0GK4mJOr16OZBSsHmzipp1Z5Rj5i+Yacw+6Yaavo/p0UMnKcm4SGRnt3+RELYQSEkzHnSTOjMpA0vDrDlKcFbhr6xfb+P++2MB+POfyzjvvGofW9Q1qAYABSjHzG+QprCsH9SXmXS4AWDPTq/Z5E8UFGgcPmxB0ySDBweeYwZKcFbhf+zbZ+HGGxOorhaMHw/33BOcxf4toRoAFKAcM7/BnJGJH9SXmagGgLYxL56ZmXbCA9SnUYKzCn+ivFxwww0JFBRYGDasjnfeIWiL/VuioQFAOWbdGZXI9hfM4eU+1jBrjPszM/sjAXK6R8SsofA/sGtfrr22gr//PcopOHvKKbW+NknRDXE44I474snOttGrl4M33igkOro35d0nYOZMZWZlWdH17uWUusry5ctZvnw5Bw8eBCA1NZUJEyYwevToFrdfsWIFq1evJjc3F4DMzEwmTpzIgAEDWtx+4cKFrFixghtuuIGLLrrI+fz+/fv55z//yZYtW7Db7aSlpXHVVVcxYsQI5zaHDh3i5ZdfZtOmTYSFhXHaaadxzTXXYHGzPEktux8gGyvm+2Eqc/NmG3ZXfI++/UBoUFKILC70rnF+gFl7N3RoYKYxTZTgrMIfeOyxGL78MoywMMnrrxeSmqr72qQup39/O6GhkspKjT17fF9r7I8kJCRwzTXXMHv2bJ588klGjBjB3LlznY5Xc7Kyshg7diyPPvoojz/+OD169ODxxx+nsPDIv1Hff/8927ZtIz4+/ojfzZkzB4fDwSOPPMLs2bNJT09nzpw5FBcXA6DrOk8++SR2u53HH3+cO++8k6+//pr33nvP7deoHDN/wExjJvRCRPrPH8a0NAdRUTo1NcIlEVIRGgZJ9R2l3aABIJClMpqjBGcVvuTNNyN45RXj2vfss0WMHh3436mOYLXirFdVDQAtc+yxxzJmzBiSk5NJSUlh4sSJhIWFsW3btha3nzx5Mueddx4ZGRn06dOHSZMmIaVkw4YNTbYrLCzktddeY/LkyVitTa+BpaWl5OXlcemll5Kenk5ycjLXXnstNTU15OTkAPDrr7+yd+9e7r77bjIyMhg9ejRXXXUVn3/+OXaXIhsNBJ1jJoQIuB/y9yHCIxEDhnr3PG6+PxaLaFSMGuLSPtrA4YjwSNif6/P31Zs/jZ3V4cPtXbIe3vwZMEDnnHOMtsxXX430uT2++vGnNekuP6tWhTJ9utGB+cADpYwfX9Ot18O85mZn23xuS/Mfb6yHSVVVFZWVlc6furr2nXNd11mzZg01NTUMGjTIJR+hpqYGu91OVFRDEETXdZ5//nkuueQS+vbte8Q+0dHRpKSksGrVKqqrq3E4HHzxxRfExsaSmZkJwNatW0lLSyMuLs6539FHH01VVVWr0bzWCKpb45bCjwHB1TcaP11AUlKSW9ufcAJ8/z3s3h1HcnJc+zvc/3jHDAswfv7ZqIlJSIAxY3ojOqgH6e56eJOHHoLly+GDDyJ56qlIevb0tUW+wZ/WJNjZtAkmTTK+SzfcAE88EYMQMU226W7rcfLJ8O67sGNHNMnJ0b425wi8tR4zZsxg165dzscTJkzgyiuvbHHbnJwcpk2bRl1dHWFhYUydOpXU1FSXzvPOO++QkJDAyJEjnc8tXboUi8XCBRdc0OI+QgimT5/OvHnzuOGGGxBCEBsby0MPPeR08IqLi5s4ZQCxsbHO37lDUDlmRUVFVFcHnt6NY95DkLMT7Y9TEKNP8so5hBAkJSWRn5/vljJ/RkY4EMd339WQl9d+3Zjcno3+7EyI74HlsQWdsNi/WbXKeF+GDq0hP9/9erqOroc3GTgQRo7syYYNNv72t7KgnUnYGv64JsHMoUMaF13Ug9JSKyecUMOMGYXk5zf8vruuR2pqCNCDn35ykJdX4GtznHhrPcLCwoiPj2fGjBlNjmuztZ7KTUlJYd68eVRWVrJu3ToWLFjAzJkz23XOlixZwpo1a5gxYwYhISEA7Ny5k2XLljFnzpwmEbzGSCl59dVXiY2NZebMmYSEhLBy5UrmzJnDk08+6fGgUFA5ZkDAfYGlw4HcuQXqapFJffG2XoGU0q33yGwA2LjRhq7LdiNDsk8asqoCqirQS4sR0bGdMddvMYVlhwyp69Rnzt318Da33FLO5MnxvP56BLfdVkZoqK8t6nr8bU2CkepquPHGeHJzrWRk2HnllUJCQmSLl7/uth5Dhxpd0fv3WygsNJpz/AlvrUe4G5pDVqvVGbnLzMxkx44dLFu2jFtvvbXVfT7++GOWLFnC9OnTSU9Pdz6fnZ1NaWkpd9xxh/M5Xdd56623WLZsGQsWLGDjxo389NNPvP7660RERDjP+9tvv7Fq1SouvfRS4uLi2L69qVRUSUkJwBGRtHZfn1tbKzxPwX6oq4WQUEj0v5D9oEF1WK2S4mKN/fs1+vRpu1NKhEUYI6UO7IM9O2DEmC6ytGsxC/9NxzVYGD++iieeiCE/3xCcNbs1FQpPISXcc08cP/0UQmyszptvHiYhwb+cD18SEyPp29dObq6VrCwbY8cq+Zr20HW9zZq0pUuX8uGHHzJt2jT69+/f5Hfjxo1rktYEmDVrFuPGjeOMM84AjLo0AK2ZfokQAl03/iYOGjSIDz/8kJKSEmcK87fffiM8PNzlNKtJ0BX/Bxqm4j990hGa/7VHh4bCwIFGMar7EwCCU2jWGMUUHBpmzVGCswpv88wzUSxZEoHVKnn55UIGDHD42iS/o0HPTHVmNmfRokVkZWVRUFBATk6O8/Gpp54KwPz581m0aJFz+yVLlvDee+9x++23k5iYSHFxMcXFxc6yp+joaNLS0pr8WK1W4uLiSElJAQynKyoqivnz57N7927279/P22+/TUFBAWPGGMGHUaNGkZqa6txm/fr1vPvuu5x33nltpmVbQkXMfE39jEzhR4r/zRk+vI7sbBubNtk491wXBiqm9YfvVyODVGg2L0+juFjDYpEMHBhcETNQgrMK7/HRR+E89ZRR3D97domKBrXC8OF2Pv9cOWYtUVJSwoIFCygqKiIiIoL09HSmTZvGUUcdBRgir41rxb744gvsdjtPP/10k+O01VzQnJiYGB566CHeffddHnvsMRwOB6mpqdx3331kZGQARjTtgQce4JVXXuHhhx8mNDSU0047jauuusrt16gcMx8jc3cb//Ejxf/mDB9ex+LF7kXMJECQRsyys433oX9/O2FhPjbGC5iCs2++GcnChVGcckrwiwUrvM8PP9j4y1/iALj99nImTqz0rUF+jBpm3jq33357m7+fMWNGk8cLFrjfhNbSPv3792fatGlt7terVy8efPBBt8/XHJXK9DXmKKa+GT41oy3cn5lp6LpwuABZUeYlq3xHMAnLtoYSnFV4kpwcCzfdlEBtreD886t46KFSX5vk15jX3G3brNSqoGK3QzlmPkSWl0LxYeOBH41iao55kcjJsVJS0r5gl4iIgl71jQxBmM4M1vqyxvTv7+Ccc4wajFdeifSxNYpAprTUGEx++LCFkSNref75YjUDsh369nUQHa1TW+va1BVFcKG+Hr7ELPzvlWR0M/opcXGS1NQGNWpXEGnB2wBgSmUEc8QM4NZbjSaADz4Ip7BQXSoU7mO3w6RJ8WzdaiMpycHrrxcSEaE6StpDiIYZvKrOrPuhrrY+RJozMv04WmbSWM/MJeo7M4MtYlZVBTt3dg/H7MQTaxk5spbqao233/bfGweFfyIlTJ8ey6pVYYSH67zxRiHJyd1vMHlHMa+5yjHrfijHzJfUR8yEHxf+mwwfriQzALZutaHrgoQEB4mJwf1HRgi45RYjavbGG5HUuNCQq1CYvPpqJG+9FYkQkgULihk5MrhvZDyNWSqhGgC6H8ox8yEyAKQyTEaMcLcBoD5iVpCHrKzwklVdT+P6so7Oxwwkxo+vIinJQUGBITirULjCihWhzJxpyGI8/HAp550XeKPyfE2DlplV6Ql2M5Rj5iOk3Q559RPnAyiVuXWra11CIioGeiQaD3KDJ53ZXerLTJTgrMJdNm2ycscd8ei64NprK7jttuC5MetKBg+uQ9MkhYUWDhxQf6q7E2q1fUX+XqMyNiy8wYHxY/r0cRAbq1NXJ9i61cUuoXrZDLlnhxct61q6g1RGc669toLwcN0pOKtQtMaBAxo33NCDigqNU06pYdaskm4RWfYG4eGGViKodGZ3QzlmPsJMY5KagQiA3nEh3Bc9FOkDjP/kBIdj1nQUU/dxzEzBWYCFC6N8bI3CX6mqEtx4YwJ5eRb696/jpZcKcXMSjaIZqgGge+L/HkGwUq/4HwiF/ybu1pk1SGYEh2O2f7+F0lINq1UyYEDwapi1hBKcVbSFrsPkyXH8+msI8fEO3nqrkLg4lffuLKoBoHuiHDMf4YyY+bHif3PcvntLr58AcGAfsrrKS1Z1HZs2GQ7JwIF2QkN9bEwXowRnFW0xZ040y5aFY7NJXn21iIwMNZjcEzRuAFB0H5Rj5isCSCrDpPFoJleKwEVMPMT1MHKApphuAGM6pKbwY3cjmAVnZV0d+i9rkbVKE8Rd3nsvnPnzowGYN6+YE05QM4Q8hXnN3bnTSmWlKtbrLgTX1TVAkCVFUFZiFG71Sfe1OS4zcKCdkBBJaalGbq7FtZ1MPbMgqDMzHTPzYtkZpK6jVwXWEOdgFpyVn/8bfcETFP3jb742JaBYuzaE+++PA2DKlDKuuCLwI+P+RGKiTs+eDqQUbN6sombdBeWY+QJT8T8xBREa5lNT3MFmM1q4wf06M4KgzsyTMzL1f73EvivPQO7c2uljdRXBLDgr138PQMWXnyALD/nYmsBg504LN9+cQF2dYPz4KqZOLfO1SUGJagDofijHzAc4hWUDQL+sOY3Tma4ggiRiVlkp2L3biBJ2NpUp9+cgv/4MdAf6d197wLquIxgFZ2VZSUPnsN2Ovvwj3xoUABQVCW64oQfFxRqjR9fyzDNFajC5l1ANAN0P9VXyBWa9VQAo/jfHHM3k9szM/bnIAA6xbN5sRUpBr14OevXq3Cgm+Z/3MIv05KafPWFelxGMgrMya72xHqGGoylXf44sK/WtUX5MbS3ccksCO3da6dPHzuuvFxIeHD66X9LQAKAcs+6Ccsx8gDm8PJAK/00aImYu1jvEJkBMHEgd9gZuA4Cn9Mvkvhzkj98YDzQN8vchDxd01rwuJegEZ7PWAyBOPx9b/yFQW4Nc+YlPTfJXpIQHH4xl7dpQoqJ03nyzsNM3Koq2Ma+52dlWdPVWdwuUY9bFyLo6Q/UfAkoqw8R0TPbvt1JY2H6XkBDCOTdT5gTuaCZP1ZfJT/4FUiKOOZmQwSOM5zb90mn7upJgEpyVUiKzjPdfDB9DzFU3Gs+v/A+yOrCaM7qCF1+M4t13I9E0yYsvFjF0aPfS8/MF/fvbCQ2VVFRo7NnjYtOVIqBRjllXk5cDDgdEREF8T19b4zbR0ZKMDONi7Gpo3awzY892b5nldbKzjQhhZ+rL5N7dyJ/WAKCNn0jYmJOM5wPMMYMgEpzdnwPFhRASghg4jPCTzoCkPlBZgVz1X19b51d89lkYTzxhyGLMnFnKmWcGbmlCIGG1NjRdqXRm90A5Zl2MrFf8JzXDiCYFIGbUzNU6M+cEgABtAJASsrM7n8rUP3kXAHHMWERqhtMxI/tXpCOwBDmDRXDW6RQPGoGwhSA0De38CcbvvliKrFOaXAC//WbjrrvikFLwhz9U8Mc/qsHkXYm74/AUgY1yzLoasyMzAAv/TdztzMScmbk/x0jlBhi5uRbKyjRCQjo+iknm7oKfvwUhEOMnAhAycKgROa2qgF2BI5thEgyCs8405rDRzufEiadBQk8oKUJ+u9JXpvkN+/dr/OEPCVRXa5xxRjUzZ5b42qRuh1lCoSJm3QO3chDLly9n+fLlHDx4EIDU1FQmTJjA6NGjW9x+xowZZGVlHfH86NGjefDBBwGjxuP999/nyy+/pKKigiFDhnDzzTeTnJzs7msJCGRuw/DyQMWcmenyRSKhJ0RFQ3kZ7NsNGQO9Z5wXMF/nwIH2Dg9l1j/5FwDi2FMQfdKM/1ssiGGjkD+uQW76BTFgqEfs7SpMwdkNG0JYuDCSBx4ILB0rWVsDWzcBzRwzqw1x7mXId19G/vffyFPOQVi6Z21PRYXgD3/owYEDFoYMqePFF4uwBnDmOlBp0DJTb353wK3b3ISEBK655hpmz57Nk08+yYgRI5g7dy65ubktbj916lQWLlzo/HnqqafQNI2TTjrJuc3SpUv57LPPuOWWW3jiiScIDQ1l1qxZ1NYGXwpBSukUlw2GiNm2bVaqq9vf3mgAMKJmgZjONC+GHU1jypyd8Ms6I1p28VVNfieGjzG2CTDZDDAEZ6dMKQcM6Yz9+wMsarY9C+pqjbFhKX2b/Eqcci5ExcChAw1dtN0MhwPuuiuOTZts9Ozp4M03C4mODgJ9lADErG3dt89KUVFglsAoXMct9/vYY49t8njixIksX76cbdu20bdv3yO2j4pq2rG1Zs0aQkNDOfHEEwHDUVm2bBmXX345xx13HAB33XUXt9xyCz/88ANjx45t0Y66ujrqGqXENE0jLMxQ0Pfruq2iw1BRBpqG6JPepbaa5/LEOZOTJQkJDgoLLWzdGsKoUe07LCK9v5E22rPDv9eoBRrqy+wdst0ZLTvuVLT6EVzmcbQRx6AD7N4OFeWIqGiP2NxVXHBBDSecUMN334Uyd24Mzz4bOGkufZPZjTkaTdOafEe0sDA4+xL0Jf9EfrYYjh+H6GYKqrNmRbN8eTihoZLXXy+ib18dCMxrVqATFwd9+9rJzbWyeXMIJ5/c9YELtR5dR4fjorqus3btWmpqahg0aJBL+6xcuZKTTz7Z6UQVFBRQXFzMUUcd5dwmIiKCAQMGsHXr1lYds48++ojFixc7H48dO5YpU6YQHx/f0ZfTJVTl7uAQYE3NIDnNNzMyk5KSPHKcMWNgxQrYu7cn55/f/vaVo47l8GeLseblkhRgaeotW4x/Tz01huTkGLf2rd2+mQPrvwNNo/cfJ2Nr9tqTh40gLy0Te85O4vJziDj1bE+Z3WU8/zwcfzx88EEEDzwQwZgxvrbINfK3bqQOSBh7BhGN1sX8jugTb2L/5x8h9+0hfu8Owk8Y5yNLu56FC+Gll4z/v/mm4OKLfddB7qlrVqAzZgzk5kJubg98eQlV6+F93HbMcnJymDZtGnV1dYSFhTF16lRSU1Pb3W/79u3k5uZy++23O58rLi4GIDY2tsm2sbGxzt+1xGWXXcbFF1/sfKzV38kWFRVR7UpuzUfoG4x0lSMplby8vC49txCCpKQk8vPzjZRqJxk4MJoVK6JYs6aCiy5qXyVdxvYAoG7XVvbn5iCsgVHEWl4u2LHDuBD17p1PXp57753jtecAEMeN45A1FOrXvfF6OAaPhJydFH7zJSUDhnv2BXQBqalw2WVxfPRROHffXcMHHxTi7zfVsrgQx+7tIATFyemU5OW1/B057Xz477859M5CLH0HdItowerVIdxxRwIguPfeMsaNK6eLL1eA569ZgU5mZhQQzdq1lVx1VddHpr21HmFhYX4fVOlq3HbMUlJSmDdvHpWVlaxbt44FCxYwc+bMdp2zlStXkpaWxoABAzpsrInNZsPWShW2P3+BGwr/+/nMTimlR87deAKAK8eTPRIhItLQh9qXA2mZnbahKzDry5KSHCQk6G6NIJK7tyF//R6Ehrj4qhbfJyklYthoQ5ph0y/ouh6Qf/wfeKCUZcvC+PbbUJYvD+Hcc/1b40o3a/rS+kNUTJO1afwdEWdfglzxMezYjNyyEepFgYOVbdus3HprPA6H4PLLK5kypcznY7c8dc0KdBo3APjy/VDr4X3cLpqwWq0kJSWRmZnJNddcQ0ZGBsuWLWtzn+rqatasWcOZZ57Z5Pm4uDgASkqaev8lJSXO3wUTpmMmAlDxvzkNFwmbS2NCmk4ACJwGgM6MYtI/rq8tO+E0RFKf1jccNBysNig6BHktN9L4O6mpDm65xWgEePzxGPxeFWXTesCoL2sLERuPOMVIL+vLPvC2VT6lsFDjhhsSKC3VOO64Gv72t2K/j3x2J8xr0NatNv//fik6RaerWXVdb1KI3xLr1q3Dbrdz6qmnNnk+MTGRuLg4NmzY4HyusrKS7du3u1y3FijI2ho4sN94EIAzMpuTmWknLMwYE7J7t2tSAqbQLHsCxzEzC//dVfyXu7bChh+NRo9mnZjNESGhhnNGYE4BMLnzznISEhzs2GHjnXcifG1Oq0hdR2avB9p3zADEuZcZc02zfkEG8PSKtqipgZtuimfPHivp6XZefbWI0FBfW6VoTN++DqKjdWprRWBP21C0i1uO2aJFi8jKyqKgoICcnBznY9Phmj9/PosWLTpiv5UrV3LccccRHd2040wIwYUXXsiHH37Ijz/+SE5ODvPnzyc+Pt7ZpRk07MsxBnlHx0Js4OfTrdYGZ8V1odlAjpi5Jyyrf2x8D8SJZyB6p7S7vekgBKJshklMjOSeewwts6eeiqa01E/DLbm7oKwEQsMhc3C7m4teSYjjjcJ//bPF7WwdeEgJU6fG8f33ocTEGIPJe/RQ07L9DU1ruOYqodngxi3HrKSkhAULFvCnP/2Jxx57jB07djBt2jRnV+WhQ4coKipqss/+/fvZvHnzEWlMk9/97necf/75vPTSSzz44IPU1NTw0EMPERIS0sGX5J/IvQ3CsoFYQ9QS7o4JcUbM9u4KiBFEut4wI9OdVKbcsRk2/mxEyy660qV9TD0ztm4yoqsBynXXVTJgQB2FhRaef94/B5ybav8MGelyE4qoH9PEz2uReXu9ZJlvePbZKD78MAKLRfLSS4UMHKgGk/sr5g2iGs0U3LgVD23cUdkSM2bMOOK5lJQU3n///Vb3EUJw1VVXcdVVbad7Ah6zviyAFf+b4/ZopsRkCAuH6irI3wt9fCMZ4ip79liorNQIDZVkZrr+x8pZW3bSmYhEF/vaU9IModPiw4bw6bD2U2z+iNUKDz9cyh/+0INXX43i+usr6dvXv5xw2Ui/zFVEnzQYdTz8+j3y838j/jDFW+Z1KUuXhjFvniEB88QTJYwbF3zC3sFE49peRfDSvRQTfUhDxCzw68tM3HXMhKY5uzEDoVbHvPgNGlTn8hgauT0bsn4Bi8XlaBkYNyhi+NHGMQK4zgzg7LNrOPnkGmpqBLNn+5dgrqyugu3ZQNMxTK6gXVA/3Hzd18jDBz1uW1fz0082/vxno6zi1lvLue66Sh9bpGiPhiyF1efdsgrvoRyzLsAYxbQHCOxRTM0xlPAlBw5YOHjQtY+SM52Zs9OLlnmGxor/ruKsLTv5LEQvN4UYneOZAtsxEwIefbQEISRLlkTwyy9+dHe/dSM47NCztxHBdQPRfwgMHgkOB/KLJd6xr4vIzbXwxz8mUFMjOPfcKh5+uH0tQoXvGTy4Dk2TFBZaOHBA/fkOVtTKdgWHC6CqAixWSG5fjDdQiIhoSPG5HFo3GwACoDPT3RmZclsWZP9qRMsuvMLt84mhowyvZt8eZNFht/f3J0aMsDNhQhUAM2fG+M3dvTONOWx0h2o9tQvro2b/+xxZFjjjpxpTVib4wx8SOHTIwvDhdcyfX0w3ndEecISHQ//+bl5zFQGHcsy6AjONmZwaMIr3rjJ8uHGR2LjRzQaA3J1I3b9qj5rjroaZM1o29mxEz95un09ExUB6/bD3rMCOmgHcf38pYWE6P/wQymefhfnaHKDhfTXTxm4z9GhjjWprkV9+4jG7ugq7HW6/PZ7Nm2307u3gjTcOExnpJ15zkOJpMVZ3m64UgYdyzLoAmbsbABFE9WUmjScAuERSHwgJhZpqOOCDOS8uUloqyM01XpMrGmZy60bY/BtYrIgLXa8ta46zID3A05kAyck6kyZVADBrVgy1Pq4rl4cLIH+foTsw5Kj2d2gBIURD1Gzlp8iqwKrLmjEjhq++CiMsTOeNNwpJSVGyGN5EFh1Gf/AWHLPvMyaeeADzZlhFzIIX5Zh1AXLvbuM/QaD435wRI9xtALBAfZ2dPzcAmPVlyckO4uPbv+N1dmKecjaiR68On9eUzZBZ6/0+ougKt99eTq9eDnbvtvLmm5E+tcVZu9dvECKiE1IeR58ISalQVYFc9ZlnjOsCXn89gtdfN173888Xc9RRSj7e28iV/zFKWXZsRn/8T+if/bvT3+vGDQCK4EQ5Zl3BXlMqI3gjZjt2WKmsdK1mp6EBwH/rzNzRL5NbNsCWDWC1dqi2rAn9BkF4BFSUwR7/b5Boj6goyb33GqKzf/97NEVFvtPwc6YxOylFIjQNcf7vjWN+sRRZ5/8SEytXhvLII7EAPPRQKRdeWO1ji4IfWVOD/N9y40FqP7DbkR++iT7nAWR+x7XwzGvurl1WqqqCQxNT0RTlmHkZWV0FB/ONB0HUkWnSq5dOYqIDKYXTmWkXs47KjxsAXK0vk1I21Jadci4ioePRMgBhtTrTbIE8BaAxV19dyZAhdRQXazz7rG/kM6TuMBozcE+/rDXECadBQi8oLUauWdHp43mT7Gwrt98ej64Lrr66gjvuKPe1Sd0C+f0q4warRyLa9KcN7bvwCNi5Bf2xP6F/sbRD0bPERJ2ePR3oumDzZhU1C0aUY+Zt9u0xZp7EJiCiY31tjVdwW88s3dAyMxoA/LPGxeXC/82/wdZNRrSsXueqs4ggkc0wsVhg+nRDjuGNNyJdnq3qUXZtg8oKiIiEjIGdPpywWo0ZmoD8/CO/nWRRUGAMJi8v1zj55BqefLJEDSbvAqSUzuYQceZFCM2CNvYstBnPG+LRdbXI919FnzcNWeB+ra1qAAhulLvtZWS94n8w1peZDB9ex1dfhbl+kUhOA1sIVFXCoXxIbH+WZFficLiWyjSiZfW1Zaeeh0jo6ZHzi2FHIwF2bkZWViAifFub5QlOP72G006rZtWqMJ54IoaFC4va38mDyKz1xn+GjkJ4SBtCnHIO8tP34NAB5A//Q5x4ukeO6ymqquCPf0xg3z4rmZl2Fi4sJMgm3fkvWzcaN+UhoYix5zifFgm90P40A/m/5cj3X4PtWegzJyMm/AFx2gWGCLcLDB9uZ/Xq7tkAsHz5cpYvX87Bg4bIc2pqKhMmTGD06JYj4StWrGD16tXk5uYCkJmZycSJExkwYECL2y9cuJAVK1Zwww03cNFFFwGwadMmZs6c2eL2TzzxhPNY69ev54MPPiA3NxebzcbQoUO5/vrrSUxMdOs1qoiZtwni+jITtyNmFgvUj6byx3Tm7t0Wqqs1wsJ0+vVrIxKS/asxPslqQ1zomWgZGEOzSUwxhnVu/s1jx/U106eXommSTz8N54cfutZD8FR9WWNEaCjirPHG8T9b7FfRX12HP/85nl9+CSEuTufNNw+71MSi8Ay6GS076QxEZNNGEyEE2rjz0GY8ZwgW19YgF72E/swjyEMHXDp+d46YJSQkcM011zB79myefPJJRowYwdy5c52OV3OysrIYO3Ysjz76KI8//jg9evTg8ccfp7Cw8Ihtv//+e7Zt20Z8fHyT5wcPHszChQub/Jx55pkkJibSv79RM11QUMC8efMYPnw4c+fOZdq0aZSVlfHUU0+5/RqVY+ZlnB2ZQTQjszmmY5adbcXVjI6oH82EHzpm5l3okCH2VoU3m9SWnXY+Iq6HR20w66CCJZ0JMHSonauvNuQlulJ0VlZWwM4tgGfqyxojzrjQmP+6Pwd++8Gjx+4Mf/tbNJ98Eo7NJnnllUIyM/0z1RqMyEMHYP33AIgzL251O9GzN9pf/oqYeKshIbT5N/QZk9FX/7dd7bPG11w/uh/oEo499ljGjBlDcnIyKSkpTJw4kbCwMLZt29bi9pMnT+a8884jIyODPn36MGnSJKSUbNiwocl2hYWFvPbaa0yePBlrsxl8VquVuLg4509UVBQ//vgjp59+ulOoeufOnei6ztVXX01SUhKZmZmMHz+e3bt3Y7e7Pj0GgjCV2RE1b28hdR1xuADCI9HSBvjUNvPc3rAhM1MnIkKnslJj1y4bAwe2/yEU/YfC9/+DA/v8as2g6SimVm3bvAGxPxdi4tAuvMLt19Deemijjkdf9zXsyG5zu0Dj3nvLWbIknF9+CeGTT8L53e+6oDtwexYiNBx6J6O1Ifzbke+IiIyGcy5FrvgYufI/iKNP8PlaLV4c7myymDu3hJNPrgMC7/PjzWuWN5HfrkCEhcPgEWh90tvcVlgscNZ45FHHov/zH8YNxOI3kZt+QUy8DRHf8g3fgAEOQkMlFRUaublWMjK873h7ez2qqqqaOKQ2mw2bre2IoK7rrF27lpqaGgYNGuTSeWpqarDb7URFNUQydV3n+eef55JLLqFv377tHuPHH3+krKyMM844w/lcZmYmQgi+/vprTj/9dKqrq1m9ejUjR448wtFrDyE9LUus6JaMHQvffguLFsHEib62pnOMHw//+Q88/zzcdZevrQk+HnsMHn0UMjIgOxvC/GMoQFCwdi2cfjrU1sIDD8CTT/raIoW3OOYY+PlnWLwYfv97X1vTee6//3527drlfDxhwgSuvLJlse6cnBymTZtGXV0dYWFhTJ48mTFjxrh0nldeeYVff/2Vp556ipD6osuPPvqITZs2MW3aNIQQ3HnnnVx44YXOGrPmPFn/xXrwwQebPJ+VlcUzzzxDWVkZuq4zaNAgHnzwQSIj3asTDqqIWVFREdXV/qPPI9d/h/7qM9C3H5b7fHuFFEKQlJREfn6+x0eEAAwcGMO330byzTflnH56WbvbS3sd+tQ/gMOB9uizHRph5C1+/jkRsJCaeoi8vCOL/+Wm9ej/mA0hNrQZzyOi49w+hyvr4XjuMdiWhbjiD2jjznf7HP7KtdcKXnyxF7t3W5g1q5Q77qjw2rmklOgz7obCQ2i33YcY0frFuzPfEf391wzNqiEjsdw5rbNmd4hDhzR+//ue1NZauPDCKu66q5g8/x2u0S7evmZ5A33Nl8h3X4aeiWjTnzEEtd1E5u9Df+dF2F0vwD1iDNrVtyBim9Y9DRoUy88/R/DNN2WcfLL3JVC8tR5hYWHEx8czY8aMIyJmrZGSksK8efOorKxk3bp1LFiwgJkzZ5Ka2vYs6iVLlrBmzRpmzJjhdMp27tzJsmXLmDNnjkvRwMOHD7N+/Xr+/Oc/N3m+uLiYl156idNOO42xY8dSVVXF+++/z9NPP83DDz/sVqQxqBwz8Pxcss6g796GrKpA9OrtN3ZJKb1ii1nzsHGj1bXjW6zIhF6QswO5ezv0cK9rxVsUFwv27zcupoMH1x3xWqSU6B+9BVUViFMvhajYTr2fba7HgGHI335Arv8ecep5HT6HvxEeLrnvvlL+8pd4nnsuiquuqiQhwTuFMrJgP3LfHuPz1n8IrhS2deg7csaFyBVL4Zd16Lu2IjwgyeEODgfceWcceXkWBgyo45lnihFC+s3w+M7grWuWp5FSoi//yLg2nHQmCK1jdvdOQUyZgVy+BPnxO/DD/3Bs+gVxzW2I48c5/8A3bgDoyvfHW+sRHh7u8rZWq5WkpCTASCHu2LGDZcuWceutt7a6z8cff8ySJUuYPn066ekNKebs7GxKS0u54447nM/pus5bb73FsmXLWLBgQZPjfPXVV0RHR3Psscc2ef6///0vERERXHfddc7n7r77bm6//Xa2bdvmcqoVVPG/V3FKZQRxR6ZJ485MV7+zIt3oZpF+NAHArC9LTbUTG9vCC9nwI+zeZrTBn3e5V21xFqpv2YC0B9f4nCuuqGL48DpKSzWeeaYT45Hawdk8MWCoUffjJUTP3ojjTwNA/2yx187TGs88E83//hdKeLjOwoVFREX5vyMTdGzZYEhkhIYhxp7VqUMJiwXtgt+jPfwMpPWHynLkK0+h/2M2srQYaLjmZmUFXXzFbXRdp66u9Wvk0qVL+fe//81DDz3k7KI0GTduHPPmzWPu3LnOn/j4eC655BKmTWsa/ZZS8vXXXzNu3Lgj6sZqa2uPiIpp9fIn7jqyyjHzJvUdmSIIFf+bM3hwHRaL5PBhCwcOuPixqh/N5E8zM9sSlm2iW3bGhYiYOO8ak5oB0bHGwPft2d49VxejafDIIyUAvPVWJDt2eEd01nTMxLCjvXL8xphjmvhlHTKv4yN33OWrr0L5+98N53bu3BIGD3avA0zhGfQv/wPUS2R0ZhZrI0SfdLQH5yF+d42h1PzzWvRH70L+tIahQ41r1L59VoqLA6tBojMsWrSIrKwsCgoKyMnJcT4+9dRTAZg/fz6LFi1ybr9kyRLee+89br/9dhITEykuLqa4uNhZ9hQdHU1aWlqTH7MLMyWlqcbmxo0bKSgo4KyzjnS8x4wZw44dO1i8eDF5eXns3LmTF154gV69etGvn3s+gHK1vYSsrDCG10K3iJiFh8OAAXa2bLGxaZONpKSadvcR6f0NIdWcnUgp/aL7yrz7HDashT9uv/0Ae7Ybd8RejpZB/UzG4aOR6742urTqRzUFC6ecUstZZ1Xz5ZdhzJoVw2uveVZ0VtrtsNloiTenKXgT0ScNjj4B1n+H/O+/ETdO8fo59+2zcPfdcUgp+L//q+Dyy6u8fk7FkciD+fBrvUTGGS0XjHcUYbUiLr4aedTx6K//HfbuRv/HHKKP+5bUPnPZu89GVpaNk0/2/5mtnqCkpIQFCxZQVFREREQE6enpTJs2jaOOMq6Phw4davK35IsvvsBut/P00083OU5bzQWtsXLlSgYPHkyfPn2O+N2IESOYPHkyH3/8MUuXLiU0NJRBgwbx0EMPOevZXEU5Zt7C1C9L6HmEwGCwMnx4HVu22Ni40cZZZ7XvmJGaYYROykqg6JAxe9DHmBEz827UpGm07KKuG681fDSs+9qYm/n7G7rmnF3I9OmlfP11KJ9/Hs7atRWcdJIH/7js3Aw1VUbUsYui1toFE9DXf4f87mvkJdcgenjvM11bC7fdFk9RkYVRo2qZObPEa+dStI38+jOQOgw7GpGS5pVziLRMtGlPIf/zniFo/MP/GMb37GVst3LMbr/99jZ/P2PGjCaPm9eIuUJr+0yZ0vbN1tixYxk7dqzb52uOSmV6Cbm3+9SXmbg9AcAWAuZFzA/qzOx22Lq1lVTmr98ZNoaGO2ckdgVOpfrcXcjSrh1j1BUMHGjn2msbRGc9KZYpN60HQAw92uVRN51FZA42htA7HMjlH3n1XH/9a4xT2f+ll4oIDfXq6RStIGuqkd8sB0A7c7xXzyWsNrRLr0N7YB4k92Vo+CYANi7ZiqxQw+mDBeWYeQuzvkw5Zm3ibADwgwkAu3ZZqa4WREToTQQbm0TLzrwIER3TZTaJmDion5LgnPcYZNxzTxlRUTobNoTw0UeeK9A3xzAx/GiPHdMVtPph9vKb5c5CbU+zdGkYr71mROL//vci+vZVyv6+Qq77GioroFcSjDymS84p+g1Em/4Mw08zBGizd0Sjz7gLueGnLjm/wrsox8xLmB2ZIoiHlzdn+HCjLmv3bivl5S7Wi6X5j2Nm1pcNGWKnSYDll3WQuwvCwhHnXtrldjm7M4NoPFNjevbUuesu425/9uxoqjxQJiXLSo16QLqm8L8JQ0dBxkCorUXWz0z0JNu3W7n33jgA7rqrjHPOcaFsQOEVpJTONRZnXtRlkVkwMg4jbjoFgK3l/akrLEF/bib6m88jqyq7zA6F51GOmReQugP27zEedKOIWUKCTnKycedu1mq1h0gfYPwnZ6e3zHKZljoypa6jf2JGy8YjorouWmZiFq7LTb/41aBsT3LzzeX06WNn/34rL7/c+ZpMuflXQ7OsT7rH55i2hxCiIWr21TKP/pGsrBTcems8FRUaJ51Uw733ti/mrPAim3+DvFyjIejks7v89H37OoiK0qnVbewYcSMIgfzmCyN6FqQR9u6Acsy8wYE8ozI3JAQSk3xtTZfSkM50sa8kNQOEBiWFyOJC7xnmAi0W/v+yzkhLh0cgzv2dbwzrPwRCw4wmCbN2McgID4cHHjCcjPnzozh4sJOXpk0/A54fWu4yR58AyX2hqsIoDPcAUsL998eyZYuN3r0dvPBCEW6O4FN4GN2Mlp18JiLCvbE7nkDTGm4kN6ddhTZ1lpFSLTyE/swj6O+8iKxWnbqBhnLMvICz8L9PRodGcgQyI0a42QAQGgZJ9a3HPm4AMB0zMyXbJFp21nhjYLUPEFYbDB5p2BSk6UyASy+tYtSoWioqNJ56quPvtZSyofB/mG8cM6FpTl0z+cUSZG3n043//GcEH34YgcUieeGFIhITgzN6GijIg/mGhA4gzrjYZ3aY0j5ZWTbEoBFojzyLOP1CwOgW1WdORm7Z6DP7FO6jHDNvYNaXpWb41g4f0LEGACOd6cs6s8JCQX6+4UQ7I2Y/f2soeYdHIs72UbSsHjPyE8yOmSE6WwrAO+9EsHVrB8NBeblQfBhsITBwmActdA9x/Dhj1FhZCXLNl5061m+/2XjkEUOi5cEHSznxxO4hjeDPyK+XGWHM4aMRyW3PaPQmza+5Iiwc7dpJaH/5qyFBdOgA+t8eQn/3ZWSNqkcMBJRj5gWkqWHWDRT/m2NeJDZvttHGhIympNd3HfowYmZGy9LT7URFyfpo2bsAiLPH+1yLzimQuj07qFMTJ55Yy/nnV6Hrgr/+tWP1fE7ndeBwRIjvNCSE1epsFpGff2gI3naA4mKjrqy2VnDeeVVMmuS9oe8K15DVVcj/fQGAdqbvomXQkMrMyrI2GYcnho5Cm/E84tRzAZBffoL+2BRkkE0RCUaUY+YNnBGz7ueY9e3rIDpap7ZWsH27axEPkVbfAODDiFnzwn/50xrYn1MfLbvEZ3Y5SUyGnr3BYYcgT0s89FApVqtk5cowVq92TzEbGmQyRBfLZLSEOOUcQ+D2cAHyh/+5vb+uw5Qp8eTmWklLs9cPJ/eCoQq3kOu+hqp6iYwRXSOR0RqDB9ehaS2PwxPhEWjX34U25VGI6wEF+9HnPoi++HVknYq6+ivKMfMwsrzUSKOAUdjezdC0DqQz0/qBEFB0yGu6T+3RUPhvR+oOpBktO/d3Hpt71xmEEI3SmT/72Brv0r+/gxtuMKJCjz0Wi8MNiS5ZVwtbDce1K8YwtYcICXU69vKzxW531b74YhQrVoQRGip5+eVCYmPVcHJfI6VErqyfi3nmxV0qkdES4eHQv39DnVlLiBHHoM18HnHSmSB15Ocfof/1z8hd27rSVIWLKMfM05hpzJ69EeERPjXFV7g9ASAsAnrXD4v1kWxGdrY5I7MO+cM3Rp1SRBTiLD+IltXTWDYj2PnTn8qIidHJzraxeLEborPbsoyO6LiEhqkSPkacfiGERxifqd++d3m/b78NYfZsowni8cdLGDFCDSf3C7J/rZfICEecfOQwa1/QkM5s/ZorIqLQ/vgntDunQWw85OWiz74X/aO3kS7XnSi6AuWYeZjuOIqpOaZjtnGjGw0ATqHZ7V6xqS3q6hpGMQ0dUo38jxktu9S/nOvBI42QZMF+oyMsiElIkEyZYshnzJkTQ2Wla/k7Zxpz2Ogmg4x9iYiIxOyS05ctRsr2o14HDmjccUc8ui644opKJk5UgqH+gm5Gy3wkkdESZie5KzfD4ugT0GY8jzj+NNB15LIP0Gf9xac1voqmKMfM0+TuBrqX4n9zTMcsK8uGC3+DDEzHzAcRsx07rNTWCqKidFLzvoL8fRAZjfBxUW9zREQkZA4BukfU7MYbK0hLs3PggIV//MO1P4CmTAZdrfbfDuLsS4wu0V1bDVHSNrDb4Y474jl40MLQoXU8+WSJqivzE2RBXoNExpkX+diaBho3ALiCiIpBu+UetEkPGDWQ+/agPzEV/eN/dbhJReE5lGPmYcyIWXcs/DcZNMiOzSYpLtbYv981HTdzZiY+iJiZ4f8hg+sQn75n2ONv0bJ6nHVmWcHvmIWGGtIQAC+8EEV+ftuXK1lSZAjwCtH1Y5jaQcTEIU4xlOH1zxa3ue3cudGsWxdKVJTOSy8VEh6u6sr8BflVvUTGiDGIJN9JZDTHdMx27rRSVeW6Fy+OORltxvMw5mRwOJCf/Av9yXuR+/Z4yVKFKyjHzINIu93o5INuKZVhEhICAweaoXUXtajqB3VzuABZ0bVjZsz6sqE9dkPBfoiK9qu74cY4C9o3/9Yt7mzHj69mzJhaqqo0/va3tkVnnSNo0vojomO9b5ybiPMuB4sFsn9tteh6+fJQFiwwXuff/lZM//5qOLm/IKurkGtMiYzxPramKYmJOj17OtB1webN7un/iZg4tEn3I26ZCpHRkLMD/fE/oy/7AOlO543CYyjHzJMc2GfkIcLCDWHJboy7dWYiIspoPYcubwBwdmSWrTBsOfdyoyHBH0nPhKhoqKo00mJBjhDwyCMlALz7bkTbqRpzDJOfRctMRI9EQ3QW0D/74Ijf79lj4U9/igfgppvKGT++ukvtU7SNXPuV8b1LTAFfjfpqBSFcawBofX+Bdvw4tJnzYdTxYLcjP3obfc79yLxcT5uraAflmHkQmWuOYkr3eQu1r+nQBAAfNQA4Ncz4AaJiEGdc2KXndwehWRBDjwaCXzbD5Ljj6rj44iqkNERnW6pblLrujJj5bD6mC5hjmvhlHdKMrgPV1XDbbfGUlGgcc0wtDz9c6iMLFS3hbxIZLeFOA0BriNh4tDunIW78E4RHwq6t6I/9CX35R0hdRc+6Cv/7dAUyZn1ZN05jmrg7MxOA+tFMXRkxO3RIo6DAgkBncPQOxPmXI8LckGfwBd1INsPkoYdKCQmRrF4dxldftaDmv3e3MeQ9NMwY+u6niJQ0GH0iAPK//3Y+/8gjsWzYEEJCgoMXXywkxH1dXYU3yV4P+XshLBxx8pm+tqZF3G0AaA0hBNrJZ6LNeB5GjAF7HfKD13HMfZC6fTnt7q/oPMox8yCyviOzO0tlmJgXidxcKyUlrhWjCnM0UxdGzJyjmCL2Ehkfgilr4M84U3V7tiPLukdkJT3dwY03GqKzf/1rDM3L65xO6uCRxtB3P0a74AoA5PerkYcL+OCDcN55JxIhJPPnF9OnjxpO7m/oX5oSGWf5ZVMQNE1luqlj3CIioSfa5EcR199llOdsz+bA3ROR+fs6f3BFmyjHzJM4OzIzfGuHHxAbK+nb183Qen0qk4I8ZGXXzAPM2mh8BYbGbDOiZaFhXXLeziDie0CfdJASmb3e1+Z0GZMnlxEXp7N1q4133236x7Gxfpm/I/oNhKGjwOEg6401PPCA0ajwl7+Ucdppasi0vyEL9sOGHwEQZ/hnUxAY6v+hoZKKCo2cHNe64dtDCIF26rloM55HDDmKsNEnNoiBK7yGcsw8hCwtgtJiowpTOWZAByYARMU0NE3kdk06M2u1MT5rWM8cxGn+Hy0zcdZRdQPZDJO4OMmf/2x07M6bF015uRGJlTXVsD0L8O/6ssZoF0yg3B7BpJcuprpa47TTqpkypdzXZilaoEEi4xhEUh9fm9MqNhsMGtTxBoC2ED0S0f7yVxKm/tVvhJuDGeWYeQozjdkrOSCiLl1Bh+rM0sx0pvdVqKW9zhkxG3ZWEiK0hdolP6VhbuYvLinJBwvXX19BRoadQ4csLFhQP8N060ajG7pHYsDczcvBR3HfzjnsrEgnOa6U+fOLsXgmyKHwILK6ErnG6NbWzvIvwemW6EjTlasITUPz0zRusKEcMw/hHMXUjRX/m9OhzkxnA4D3HbOa1V+xvbgvAMMnjPD6+TzKwOGGYFxxYYN2XjcgJARnx+LChVHs26c568vEcP8Zw9Qer78exX+2n4RV2Hnx6PuID+ta7T6FazglMnr3gQBIkw8bZg4z71wDgMK3KMfMU9QPL+/Oiv/NMdu3t261UuNi6UyDZIZ3HTNpr2Pbu99TJ23ERNSQ2i+wwhXCFgKDDGeyu8hmmJx/fjUnnFBDdbVg7tyYBpmMAPjDCfDjjzYeeywGgIdPeIMxET8iv17mY6sUzZG63kgi4yK/lMhojtkA4I2ImaLr8P9PWoBgapgpqYwGUlIcxMXp2O2CbdtcvIOr78zkwD5kdZXXbJPfrCB7b08Ahg6XATmLsHE6szthiM4aUbPFiyPYsDkChAZDjvKxZe1TWKgxaVICdrvg4our+OM9hjSLXPExslYV/vsVWeuNubl+LJHRHNMx27fPSnFxAF7UFIByzDyCrKszNG5ASWU0QogONADExENcD6PY1hTs9TCyrg657AOySwcCMGxEYI42ckaItm5CuhqSDBKOPrqOyy6rBODx7D8j+w1CREb52Kq2cTjgrrviyMuzkJlp529/K0Y7/lSjNq6sxFnLpPAPdDNaNvZs/50E0ozYWElqqnE9y85WUbNARTlmniAv17jqRkRCQk9fW+NXdKgYtX6gufRSnZn85gsoOkRW1XCgoS4j4EjuC/E9wV4H2zb62pou54EHygi11LG28FhW2H/va3Pa5bnnoli1KoywMJ2FCwuJjpYIq9WYoQnIzz/qFvNPAwF5oF4iQwi/nZvbGt5sAFB0Dcox8wDOwv/UfgFTfNxVuDszExrqzPCC0Kysq0Uuex8pIbtyKNAQ/g80hBCN0pnrfWuMD+iTUstNA94H4Ill51Lnx8u4enUoTz1lDCefM6eEoUMbHDAx9iyIjoXDBcjvV/vKREUj5FefGv8ZcQwiMTA6fU0aGgCUYxaoKMfME9RLZaj6siNpfPfmqhq1cEbMPK9lJlcvh+JCCsIHcbg0HE2TDB4cuFGKBsesezUAALBnB3ekLSQhpJgdOZG8845/ppv27dO48844pBRce20FEyY0rZ0UIaGIc34HGGOapCdk2xUdpolExpn+L5HRHE+NZlL4DuWYeQBnxKxPum8N8UMGDDDUqMvLNXJzXex8rHfM2J/r0dopWVuD/GwxAJsHXg9Av352wsMDWAds6NFG4XteLrLwoK+t6VLkpp+JsVXwlzOXA/DUU9GUlvpXxLq2Fm6/PYHCQgsjRtTy2GMlLW4nTrvAGBqdlwu/ft/FVioaI79dCdVVkNQHzPFnAYR5M7xli82vo8iK1lGOWSeRUqrh5W1gs8HgwW7WPMQmQEwcSN353noCufpzKCmEhF5kaycAAVxfVo+IjIJ+RhNDd+vONNO3115bwYABdRQWWnj+ef9qAJg1K4affgohJkZn4cIiwlrRnhYRkYgzjMkT+rIPupVosD9hSGQYaUxx5sUBIZHRnL59HURF6dTWCnbsUFGzQCTwPnX+RnEhlJcZUYuUNF9b45e4W2cmhIB6oVlPpTNlbQ3yv/82jn/RFWRvNlT+A7W+rDHOMUTdyDGTVZWwczMAtpGjnKKzr7wS5Xpk1sv85z9hvPKK4Sg++2wR6emONrcXZ40HWwjs3gabf+sKExXNyfoFDuyD8AjESWf42poOoWkwdKhqAAhklGPWWcyITlIfREjgjPTpSjo0AaB+NJOnGgDkqv9CSRH0SEScfJazMNa8gAUypmyGzP4Vqbf9xz9o2Pwb6DokpiB6JXH22TWMHVtDba1g9uxoX1vHjh0W7rknDoA77ijj3HPbT8mLmDjEqecCoNen3BVdi/5l4ElktIQp7q0aAAIT5Zh1EqewrBpc3ioj6nXC3HPMPCeZIWsaR8uupMZuY/t2I8QfDBEz+g0y6pMqy2HXNl9b0yXIrIYxTGCKzpYghGTJkgh++cV3f5CqqgS33ZZAebnGiSfWcP/9ro9bEudeBhYLZP+K3LXVi1YqmiPz98HGnwyJjPq0cqCiGgACG+WYdZb6UUyo+rJWMaNSeXkWCgtd/MiZMzP35yDrajt1frlqGZQWQ8/eiJPOZPt2Kw6HIC5OJyUl8DvghMUCQ0cBOMcTBTuN52OajBhhd3Y8zpwZgy/KtKSEBx6IJTvbRq9eDl54oQirG38bRY9eiONPA0BfpqJmXYlTImPksQEnkdGcxlkKVa4YeCjHrJNINSOzXaKiJBkZRtRs40YX/0ol9ISoaEO4d9+eDp9b1lQj//shYETLhNXqjNwNHVoXkKOYWqI7yWbIgjw4mG9ElgY3HT5///2lhIXp/PBDKMuWtVJp70X+9a8IFi+OQNMkL7xQRO/e7jv+4oLfGyHA9euQ3WhAvS+RVZXINV8CoJ0VeBIZzRk8uA5Nkxw+bKGgQP2ZDzTUinUCWVtjzFID6JvhU1v8HfMOztWaByEEpJkNAB1PZ8qvl0FZCfRKQpx4RhMbgiKNWY8YPsb4z66tyMpy3xrjZcw0Jv2HHlEHlJysM2lSBQBPPBFDbeeCrW6xcaOVhx+OBeD++8s4+eSOnVwk94XRJwIgP/u3x+xTtI789kuoqTKmaQw92tfmdJrwcMjMdL+EROEfKMesM+zPMSQdomIMiQdFq4wY0YEGAHOg+Z6OOWayuqpRtOwqRH1OKSgdsx69ICnVKIjPDu6OPmcasxWNqdtvL6dXLwe7d1t5883ILrGppERw660J1NQIzj67mjvu6JxzrF0wAQD5/SrkoQOeMFHRCoZERn3R/5kXBc30FndvhhX+g3LMOoFZ+E9fNYqpPTrWmVnfANBRx+yrZVBeConJiBNPN56TkJ1tFv4HtoZZc7pDOlPa7U4picb1ZY2JipLce69RcP/3v0dTVOTd76aU8Oc/x7Fnj5W+fe08+2wRnZW/EhkDjbpBXUcu/8gzhipaZtPPUJAH4ZHOqHow0DCaSTUABBpurdjy5ctZvnw5Bw8aCuOpqalMmDCB0aNbvkACVFRU8K9//Yvvv/+e8vJyevXqxQ033MCYMUbq5f3332fx4qZFrikpKfz9739386X4AGd9WYZPzQgETMds+3YrVVVGqL1dzAaAfbuR9jqE1XWnTlZXIpc3ipZZDG2r/HyNoiILFotk0KDgiZiB4ajILz9BbvoFKWVw3izs2mqoskdFgzlTtQWuvrqS116LZPNmG88+G82MGaVeM+kf/4jk88/DCQmRLFxYRFycZ6qttQuvQM/+FfnNCuTFVyFi4j1yXEVT9JWNJTJcuTAFBmqYeeDilmOWkJDANddcQ3JyMlJKVq1axdy5c5k7dy59+/Y9Ynu73c7jjz9OTEwMf/nLX0hISODQoUNERDStC+nbty/Tp093PtYCRG258fByRdv07q3To4eDw4ctbNli4+ijXXCKevaGiEiorID9uWBqm7mAXPmpIfybmII44TTn82ZYv39/e6sq7AHLoBFgtULhQaP2MTnV1xZ5HDMaKIYe3aYqu8UC06eXcu21PXjjjUj+8IcKMjI8r/G2bl0ITz4ZA8Bjj5Vw1FEedPYHjzSkUHZtRa74GHH5DZ47tgIAmb8XNv4cFBIZzTFLNXbutFJVJQJ79Fw3wy0P6Nhjj2XMmDEkJyeTkpLCxIkTCQsLY9u2lrWTVq5cSXl5Offeey9DhgwhMTGRYcOGkZGR0dQITSMuLs75ExMT0+EX1FVIKRuGl6uIWbsI4X6dmdEAYKYzXRealVWVyOVLjGOMv9oZLYPgrC8zEaFhMHA40KhAPshwyoG0ksZszOmn13DaadXU1QmeeMLz15SCAo3bb4/H4RBcfnkl111X6dHjCyHQLqyvNfv6s6Bv6vAF5vgljjoOkZjsW2M8TGKicTOs64LNm1U6M5Do8Grpus7atWupqalh0KBBLW7z008/MXDgQF599VV+/PFHYmJiGDt2LJdeemmTqFh+fj633XYbNpuNQYMGcc0119CzZ89Wz11XV0ddo+msmqYRVh/+6LL0TeFBqKoAiwWRkub3aSPTPl/aOXy4nVWrDMfMVTtEen/k5t8gd6fL+8iV/4GKMkhKRTthXJP9GhT/7T59L7y1HtrwMejZv8KmXxBnX+LRY/saWV5mjCvCeJ2uvHePPFLGOeeE8umn4fzwQwXHH9+6Q+7OmtjtcNdd8RQUWBg8uI65c0vRNC98nkadYIx6258DX3+GuOhKz5/DT/H2NUtWVhgDywHtrPF+fw13FyGMa+7q1Rays22MGdO5mlp/+BsC7pdUrVixgtWrV5ObmwtAZmYmEydOZMCAAS1uv3DhQlasWMENN9zARRddBMCmTZuYOXNmi9s/8cQTzmNJKfnkk0/48ssvOXjwINHR0Zx33nlcfvnlbr1Gtx2znJwcpk2bRl1dHWFhYUydOpXU1JZTJgcOHODgwYOccsopPPjgg+Tn5/PKK6/gcDi44oorABg4cCB33HEHKSkpFBUVsXjxYh555BGeeuopwlspRProo4+a1KWNHTuWKVOmEB/fdTUYVXu2cgiw9e1HUlrgzMhMSkry2blPOQVeeAG2bo0kOdm1brnKUcdy+POPsOXl0ju5/TtavaKcvBUfA5Dwf5OI7NP0s2kGd089NYbkZN9HZj29HrWnn8uBxa/D1o0k9eyBsIV49Pi+pPJ/GzksJdb0TJKHjWh/ByA5Gf74R3jlFXjyyZ6sXUu72nWurMm0abBmDURFwZIlNvr39973qmLizRQ+9Qis/A+9r7sNLehy8G3jrWtW2dJ/UVxThbVvP5LOPN/nDoc3OP54WL0adu+OIzk5ziPH9OXfEHC/pCorK4uxY8cyePBgbDYbS5cu5fHHH+fpp58mIaGpmsL333/Ptm3bjvAlBg8ezMKFC5s89+6777Jx40b692+odX399df57bff+L//+z/S0tIoLy+nvNz9SLfbjllKSgrz5s2jsrKSdevWsWDBAmbOnNmicyalJCYmhttuuw1N08jMzKSwsJCPP/7Y6Zg19nLT09OdjtratWs588wzW7Thsssu4+KLG0QAzehbUVERNTXtz6TzBHr2RkR4JI60/uTn53fJOTuDEILevXtz4MABIw3rA/r0sQC9+PVXnX37CrC4MGtaxvVChEdSl5dL3r59TdKSLaF/thjpcCD6DaJ00EjKGq1NVRVs2dIbECQnF5Cf7zvVf2+thwyLQiT1gZJi8r5dhTZ4pMeO7Wsc369BhEeijzjWre/c3XdrLFrUk+++03jppWIuvbS6xe1cXZMvvgjliSeMC/ff/lZMXFw13rwEyMGjEKnpyMOHyF/6Ltpp53vvZH6EN69ZUtdxfPYRIjwSedYlHDgQnJIkGRlhQBzff19Lfn5hp47lrfUIDQ0lPj6eqqqqJse12WzYbEeWvRx77LFNHk+cOJHly5ezbdu2Fh2zyZMnN3k8adIkvvvuOzZs2MBppzXUHxcWFvLaa68xbdo0Zs+e3WQfq9VKXFyc87HdbufHH3/k/PMbHPq9e/fyxRdf8NRTT5GSYkyOSExMdPFdaIrbjpnVanV6zJmZmezYsYNly5Zx6623HrFtXFwcVqu1SdqyT58+FBcXY7fbsbYwqyQyMpKUlJQ2L7ytLVhXRsy48U7jJ8Do3bu3z87dq5fRjVlZqVFRkUQrGfCmJCXB4lWun+TGu4yfFvjxR0Pmq2dPGDUq0S9U/72yHq8u9fwx/YF7ZgAz3N4tKQkeeAAeeQRmz47jD3+gzcaPttZk1y4wr/N33w233Rbntj0d4qXuKzTrtWvWP973znH9CNPv2Lw5hMTEpE7LuID31mPGjBns2rXL+XjChAlceWXbqXtXSqqaU1NTg91uJyoqqslxnn/+eS655JIWnbvm/Pjjj5SVlXHGGQ3yKj/99BOJiYn89NNPzJo1C4CRI0dy3XXXNTmXK3S6IlDX9Sb1Xo0ZPHgwa9asQdd1p3OWl5dHfHx8i04ZQHV1Nfn5+Zx66qlu21JUVER1dct3w57G8dgUOHgA7c6HEEOO6pJzdgYhBElJSeTn5/ssYgYwdGgPfv45hK++KiI62rW1cjw7A7ZvRlx3O1qjDsvm6Ms+MJTSk1PRHph7RNfeqlXhQBxDhtR0+u6xs3hzPfQfv0G+OR/6pGF5YK5Hj+0rZP4+9Fn3gNWKNvtVRGioW/tfc43ghRd6sWePhVmzSrnjjoojtmlvTWpq4NJLe1BcHMKYMbXcc89h8vI6/JLcQtbVos+4G0pL2v0eBAve/I44FjwBm39DnHUR2qX/59Fj+xMxMRASkkRZmeC77wo61ZnsrfUICwsjPj6eGTNmHBExaw13Sqqa884775CQkMDIkQ3ZhKVLl2KxWLjgggtcOsZXX33F0UcfTY8ePZzPHThwgEOHDrFu3TruuusudF3nzTff5KmnnuLRRx916bgmbvnPixYtIisri4KCAnJycpyPTSdq/vz5LFq0yLn9ueeeS3l5OW+88Qb79+/n559/5qOPPuK8885zbvPWW285j7llyxbmzZuHpmmccsopbr0QEyml13/0qkpk7i5kVQUyuW+XnNMTP131/rT1Y3ZDbtxodd3u3n2M93rnltbXpLzMSGNWVSDO+R0IccQ2ptDi0KF1Pn8fvLkeDBph6Lhtz0YvOuzz1+mJH33Dj8ZnoG8/CAlxe//wcJ377jO0zJ57LorDh4/8fLS3Jo8+GsNvv4UQF6fzj38UYbN14WfFaoOx5yCrKtA/eRfd4fD5mnTJ6/bCd0Tfn4P8ZS2yuhJOPtvnr9GbP1arZPBgsxve9WtuV66HSXh4OBEREc6fthwzs6TqiSee4Nxzz2XBggXs3bu3Xf9gyZIlrFmzhqlTpxISYtTf7ty5k2XLlnHHHXe4VGd4+PBh1q9f3yRaZr4vdXV13HnnnQwdOpThw4czadIkNm3axP79+9s9bmPcipiVlJSwYMECioqKiIiIID09nWnTpnHUUUbE6NChQ01eWM+ePZk2bRpvvvkm9957LwkJCVxwwQVceumlzm0KCwt59tlnKSsrIyYmhiFDhjBr1iz/lszYt8eQ+46NR8TE+dqagKJDoofp7UtmyBVLoaoS+qTDmJNb3CY7O3ilMhojomMNmZE925FZ6xEnt1yrGUg0jGFqXyajNa64oopXX41i0yYbTz8dxeOPuy46++GH4bz1ViRCSObPL6JPH89rorWHOP0C5GeLIX8vrF/X6udc0TZOiYxRxyN6+baQvSsYNszOhg0hZGXZuPDCrskoeRt3SqpMPv74Y5YsWcL06dNJT093Pp+dnU1paSl33HGH8zld13nrrbdYtmwZCxYsaHKcr776iujo6CNq3eLj47FYLM76MsAZxTt06FCT59t9fS5vCdx+++1t/n7GjBlHPDdo0CBnvrUl/vSnP7ljgl8g6xX/UfplbtOhmZlp/ZEAubuQugOhNW0AkBVlyPpOTG38xBaFR6UMbg2z5ojhow1HdtMvEOCOmayrg60bABDDj+7wcTQNHnmkhKuu6snbbxuiswMGtO9gbd1q5b77jOHkU6aUc8YZXdNg1BwRHoE44yLksvfRly1GG31SUHYSehNZWY5cWy+RcebF7WwdHDTcDAevlllbJVVgpCo//PBDpk2b1qSLEmDcuHFN0poAs2bNYty4cS1Gxb7++mvGjRt3RDnW4MGDcTgc5OfnO51GM1LWlvxXSwSGxL6/Ua/4L5Tiv9sMHWpH0yQFBRYKClz8+CX1gZBQqKmGA0cW9cjlS40xPakZMPrEFg+xf7+FkhINq1UycGBwzchsCefczKxfkLrvuk89wvYsqK2F2Hjok9GpQ51ySi1nnVWN3e6a6Gx5ueCWW+KpqtI49dQa/vKXsk6dv7OIs8dDSAjs2Q7Zv/rUlkBErvnSuI6kpEEA1AZ7AvNGNFiGmbtbUrVkyRLee+89br/9dhITEykuLqa4uNhZjx4dHU1aWlqTH7MLs3mUa+PGjRQUFHDWWWcdYdfIkSPp168fL774Irt27WLnzp28/PLLHHXUUW5Fy8ADxf/dkcbDyxXuER4uycy0s327jU2bbCQmth99EJrFeK93bEbu2Y5oNGpIlpciv/wEaD1aBg13iwMG2HGzbjwwyRwCoeHGEPfcnQ1zRwOQhjTm0R6JEE2fXsrXX4fy+efhrF1bwUkn1bZ8Xgn33RfL9u02kpIcLFhQ5JLEizcR0bGIU89DfvkJ+rIPsAw72rcGBRBSdyC/MtKY4syLu020cehQwzHbu9dKcbHw2CxXX+FuSdUXX3yB3W7n6aefbnIcV7o+m7Ny5UoGDx5Mnz59jvidpmncf//9vPbaazz66KOEhoYyevRorr/+erdfo3LM3ETqOuzdA6iIWUcZPrzO6Zi5mhYSaf2ROzZDzg448XTn83L5EqipMhy3VqJl0L3SmADCaoUhI+HX75Ebf0YEsmNmjpfqRH1ZYwYOtHPttZW89VYkM2fGsGzZoRZlBN58M4KlSyOwWiX/+EcRPXr4R+RRnHMp8utlsGUDcucWROZgX5sUGGz4GQ7mQ0QkotE1JNiJi5OkptrZu9dKdrat1RuRQMHdkqrmNWKu0No+U6ZMaXO/hIQEpk6d6vb5mqNSme5y6IDhCFit0Nu98KTCYMQII5XoXgNA/ciLPTucT8myUmchr3bJxDbvgLtL4X9jxPAxQGDPzZSlRVAfoRYejA7dc08ZUVE6GzaE8OGHR04Y+eUXGzNmGHVl06aVctxx/vPHTPTohTjhdMAQVFa4hr7SiKyLU8415sp2I4ItnRnsKMfMXerry0hJM6ISCrfpSDGqSM80/pO701kzJZd/ZDjJaf2NmYJt0BAxC/76MhOzzowdmw1pgADEObQ8LdOjHdA9e+rcfbcxKmX27Biqqhp+V1gouO22eOrqBBdeWMUttxypeeZrxPm/N2ZLrf8OuW+Pr83xe+T+HMhaD0JDnHGhr83pcoYP78DNsMJnKMfMTWTubkClMTuDefe2c6eVigoX6zyS08AWYkhiHMxHlpU460Xai5ZVVgp27bI0OXd3QCQmQ68kcDhg8wZfm9MxNq0HGjmZHuSmm8rp08dOXp6Fl182lLl1HSZPjmPfPisZGXaeeqrYLyZENEckp8LokwCQ/+2+UwFcxbxWMOp4RE/fTT/xFQ0RMxVMCASUY+Ym0oyY9c3wqR2BTK9eOr17O5BSkJ3t2oVCWCxOeRKZswP5+YdGd1X6ADjquDb33bzZipSCnj0d9OrlH3VCXYUznbkp8NKZUkpnGrYz+mWtER4ODzxgdFnOnx/FwYMaTzwBK1eGERYmefnlQmJi/LdQWrtwAgDy+9XIg/4/r9dXyMpy5Lf1EhlndQ+JjOaYjtnWrTbaUJVQ+AnKMXOXXCWV4Qk6IjQr6oVm2fgz8qtlAGi/u6bd7qruWF9m4pTN2PSzjy3pAHt3Q2mxIZXSf6hXTnHppVWMGlVLRYXGrbfG8cgjxvNPPFHs92lvkT7AaIjQdSOtr2gR+c0KqK0xxKcHj2x/hyAkLc1BVJROTY1gxw4VNfN3lGPmBrKyAg4XGA+UVEan6NAEgLT6CQDffmlcaPsNghHHtLtbd6wvczJkJFgsRvq3oIsGO3oIZ9PC4JGINsazdAZDdNaYAPDdd6FICRMnVnLVVVXt7OkfOKNm36xAlhT52Br/o7tKZDRH0xpkM1QDgP+jHDN3MBX/43siIqN9akqg06GIWVpTxeb2astMzLqKbhkxC4uA/kOAwEtnOvXLvFBf1pgTT6zl/PMNR2zUKHj88RKvns+jDBoBmYPBXuecfqFoxG8/Gp30EVHOTtbuimoACByUY+YGct9u4z9qFFOnMR2zzZtt2F0NZPVJA0t9GD5zMNTXT7WFlN07lQkN9VmBlM6UNTWwbRPgnfqy5sybV8L995exbJlRexYoCCHQLrwCAPn1MmRluY8t8i/0lf8BQJx6DqJbKEu3jmoACByUY+YOZn2ZSmN2mowMB5GROtXVgp07XWwAsNpg0HAQAu3S61yKluXmWigr07DZJP37d8NUJiBG1DuwmzcgXfaCfcy2jWC3Q0IvYySXl0lI0JkypRw3J6f4ByOPNeqnqquctZcKkPtyjLFVQkOc3v0kMppjOmabNtmQ/tvTokA5Zm7RMLxcOWadRdOaXihc3u/We9EefQ4xdJRL25vRsoED7YSEuG9nUNA3E6JjDc23nZt9bY1LNE5jdte6IFcRmmbomgFyxcdGtFGB/MqIlnF095TIaM6QIcac4sOH3ZhTrPAJanVcROoOqE9lCiWV4RHMmoeNG92oM4uKQfRJd3n77lxfZiI0DTH0aCBw6swaz8dUtI847lTo2RvKS5HfLPe1OT5HVpQj134FgHbWeB9b4x+Yc4pBNQD4O8oxc5WCPKithZAQSEz2tTVBQYc6M92ku83IbBWnbIb/O2ay8BDk5YLQwMXIaHdHWCyI8y4HjIkY0t69P+9yzRcNEhmDRvjaHL+hK665is6jHDMXMRX/6ZOB0Cw+tSVYaDyayVs1D6ZjZraKd1eckaecHcgy/+46dMpkZAxQ3c9uIMaeBbHxUHgI+fVnvjbHZ0jd4ZyhK84ar1LhjTAlg1QDgH+jHDNX2WsKy2b41o4gYvDgOiwWSWGhhfx8z38Uy8sFu3cbFyAzbdpdEXEJRjexlA3zJ/2VevuEC123igaELQRx7qUAyPdeQX/zeWR1YOixeZTffjD0JiOjEcef5mtr/Ao1zDwwUI6Zi8j6jkwlleE5wsKMonxwr87MVTZvNpyy3r0d9OjRvUYxtYRTD8yPZTOk7nA6jmL40T61JRARZ11ipDSFQH7zBfpjU5A7t/jarC5F/9KUyDi320tkNMfMUuzYYaWqG/rsgYJyzFylviNTjWLyLB3pzHQVVV/WFOfczKz1SH/tl9+zEyrKIDwCMgb52pqAQ1gsaBP+gPaXv0J8TziYjz7nfvRP3kU6HL42z+vIfXtg829KIqMVEhN1evRwoOuCLVtU1MxfUY6ZC8iKMig6ZDxQETOP4s1iVOWYNWPAMGPuZEmRs8PY33DWlw05CmFVdTAdRQw5ypCVOe5UY5bmx4vQ5z0YcGO53EXWC8oy+kREj16+NcYPEUI1AAQCyjFzBTON2SMRERHpW1uCjBEjvFfz0FD4373ry0yEzeYc4uyv3ZnmdIKuUPsPdkRkFOKWqYib/mJEIHdsRn/sT+hrVvhvxLQTyIoy5DpTIuNiH1vjvzQ0ACjHzF9RjpkLyPrCfzW43POY0azdu62Ulnque0rXITtbaZg1R/ixbIasqoT6eihvz8fsLggh0E48He2RZ2HgMKipQr7xHPo/5iDLS31tnkeR33xhSBqlZsDA4b42x29Ro5n8H+WYuYKqL/MaCQmSlBTjDs5U6fcEOTkWKis1QkO77yimlnA6PNs2IWuqfWtMc7ZsAIcDEpMRvZJ8bU1QIXr2Rps6C3HZ/4HFAj9/iz5zckPqOMCRusM5jkqcebGSyGgDM5WZlWVDVz1RfolyzFzA1DBTiv/ewZSy8GTNgxmmHzSoDlWq1IjefYz5k3Y7bN3oa2ua0KD2r6Jl3kBoFrQLr0B7YK7xOSguRH/mUfT3XkHW1fravM7xayOJjBOUREZb9O9vJyREUl6ukZurNDn9EeWYtYN0OGB/jvFARcy8gllntmmT5zyohsJ/FS1rjBDCb9OZZvRGyWR4F5ExEG36M4jTzgeM+Zr6rHsaZgEHIPqXnwAgxp2LCFESGW1hsxkakqAaAPwV5Zi1R/4+sNdBaLgxi07hcczQuie1zMz6ie6u+N8STtkMP3LM5MF8Y+yZxQKDj/K1OUGPCA1Du+4OtLumGwPu9+1Bn/UX9C+WIgMsvyX37jbS4JqGOE1JZLiCagDwb5Rj1g7Owv/UdISm3i5vYDpmW7faqPVQRkVJZbTB0KNA0yB/L/LwQV9bAzRyEjMHI8IjfGtMN0KMOg5txnMw8liw25Hvv4r+90eRRYd9bZrLKIkM91ENAP6N8jTao14qQ6iOTK/Rt6+DmBid2lrB9u2dv1CUlgpyc1VHZmuIiCjoZ4i3Sj+ZAuBMY6r6si5HxMSj3T0dce0kCAmB7F+NxoCfvvW1ae0iy0uR330NgHbmeN8aE0AoLTP/Rjlm7eCMmPXJ8KkdwYynRQ83bzaOkZzsID4++PSaPIE/pTOlw2GotaPmY/oKIQTa6ReiPfx3SOsPFWXo/5iN/vqzyOpKX5vXKk6JjL79DDkQhUuYJR5791opKVEdrP6Gcszaw5TKUBEzr2JGtjxRZ6bqy9rHKZuR/avvR/Xs2gJVlRAZDemZvrWlmyOSU9EenIu4YIIxb/PbL9Ef+xNye7avTTsC6WgkkXHWeCWR4QZxcZLUVM/LFCk8g3LM2kCWFhvja4SAPum+Nieo8WTETNWXuUDGAIiIgqoK2LXVp6bITesBEMOORmiqfd/XCKsN7fLr0abOMqRVDuajz30QfekipN2Pupx//Q4KD0JUDOL4cb62JuDw5pxiRedQjllbhEeiTX0CccPdiLBwX1sT1DQWPezstBjlmLWP0CyIoaMA36cznXVuw472qR2KpohBI9AefdbQBZM68j/vos99AFmw39emAaB/aRT9i3HnIWwhPrYm8GjozFQNAP6GcszaQNhsiMEj0Mae7WtTgp5Bg+zYbJKSEo19+zoeNXE4YPNm40JjCtcqWsHUM/Oh+rusKIPd2wFV+O+PiIgotJvvQdx8D4RHwq6txrzN/y336bxNmbvLEEjWNMRpF/jMjkBGNQD4L8oxU/gFISGGcwadqzPbvdtCVZVGWJikXz/lmLWFs9B+1zZkRblvjNj8G0gdkvsiEnr6xgZFu2gnnIb26HMwaATUVCPfmo/+wpPIMt/M2zQlMsTok9TnpoOYGYWtW234U4ZaoRwzhR/hiTs4M405+P/bu/foqMp7/+PvPZmEJCQhCSEmISQxYBISoIBYLwiCtKLg8lbKr6BneVoVK57S2mN1tameUMEK+EP7U2zr8UKtUqQuTGzBFhDQolxFLLkYIAFBIIZILkAuZDL798cwA0MSSEgys5N8XmuxyOx5Zu9nz0OG7zyX75PeSICmK12QER0D8YNcgVHRLr/UwbMNkzYttzyj/wBs//0UxvfuhQA77NriSqvh46FwV4qMD111mqQUGZcqKamJsDAnDQ0GJSUazrQSBWZiGWcDs0v/kND8svbxZ9oM0zS1P2Y3Y9gCsN38PWy/XARxiVB9HOfz/4Nz+f9inm7wSR3Mf62FxtOQlApDhvrkmj2RzXZ25bqGM61FgZlYxtk9My/9Q8K99Ft7ZLbNuftm+nzO0NeHXavq7HbXEJl0G0byYGy/fg5jomsLJPODv7n22zyTkLurmE1NmBtXuepwo1JkdJS2ZrImBWZiGe5erq++slNZeWkfuO4VRuoxa6MrssAeCJUVcPSQTy/t6aW7Igujjzae7m6MPn2wzfwxtjlPQkQkHDmI8+n/xrnm3a7bb3PXVjhecSZFxriuuUYv0hmjFNL5FJiJZUREmCQlXfo3uKoqg8OHlVy2PYw+fSAtC/D9cObZYcyRPr2udC5j+BjXwoBvfdu13+ZfX8f53JOYxys6/VrO9X9zXXP8zUqR0QnO7pmpHjMrUWAmltKRBQDuYcyBAx3066etmNrK8EPaDLOxEYp3n7m+tmHq7oyISGwPZ2P8x2wI6gNf/Nu1MGDHpk67hnmwFPYUuFJkTFCKjM6QkeHAZjOpqAigvFzhgFWoJcRSOhKYnZ34r/ll7eEJjPbkYzae9s1FS4rgdINrCEy7avQIhmFgG38ztieeh5QroPYkzj8uxPnac5h1Hd9v05Mi48qxGFH9O3w+gZAQk9RU1+elFgBYhwIzsZSO9ZhpftklSUiCyP6uzaD3Fvjkku7eOSNzFIZNH0M9iRE3ENvjCzCmTgfDhrl5g6v3bF/hJZ/TPHFOiowbb+2sqgpaAGBF+kQUS3EHZnv32qmvb99rlSrj0hiGgZE1EvDdPDPPdc5cV3oWw27Hdsc92B57GvrHwjflOBf+Cmfum5e036b5r3+CoxGSBsPgjC6oce+lBQDWo8BMLCUhwUlkpBOHw2Dv3rZ/g3M4oLjYVV4T/y+BD/OZmTVVcLAU0MT/ns4Ykontf/4fxrUTXfttrlqBc8HjmGWH23wO0+HA3Pi+63yTblWKjE6mBQDWoxBZLMUwXPnMNm3qQ0GBneHD2xZk7d9vp77eICTESUpKUxfXsucxhn4L0zDg8JeYld906Rwes+hz1w+DLseIiOqy64g1GCGhGD96BOfwqzDffAkO7MX51M8w/s99GOMmXzTQMndtcaVzCe+HcZVSZHQ2d49ZSYmdujoICfFzhS5izZo1rFmzhmPHjgGQmJjItGnTGDWq5STV69at46OPPuLQIVc6oNTUVGbMmMGQIUNaLP/yyy+zbt067r33XqZOnQpAQUEBc+fObbH8008/3excZWVlPPbYY9hsNpYuXdrue1RgJpaTleUKzFx7Zta16TXu/GUZGQ5txXQJjLAISB4CB/ZiFn6GMfY7XXexgp2uayrbf69iu+p6zMEZOF9/Hr74N+afX8L89w5s9/4EI7xfq69zfnBm0v/4yUqR0QViY53079/EN98EUFwcyMiR1h5xiI6OZubMmcTHx2OaJh9++CELFy5k4cKFDBo0qFn5wsJCxo4dS3p6OoGBgeTl5TFv3jwWL15MdHS0V9lt27axd+9eoqK8vzCmp6fz8ssvex1bvnw5+fn5DB482Ou4w+Hgd7/7HUOHDqW4uPiS7lFDmWI5l7IAQPPLOs6zX2UXDmeapolZuMv7etJrGNEx2B75Dcb3f+ja8eHzbThzfoK5+9MWy58u+cK1ICUgAOMGpcjoCobRvRYAjBkzhtGjRxMfH09CQgIzZswgODiYvXv3tlh+zpw5TJ48mZSUFAYOHMiPf/xjTNNk9+7dXuWOHz/Oa6+9xpw5c7Dbvfus7HY7kZGRnj9hYWHs2LGDCRMmNOvxXb58OQkJCVx77bWXfI89rsdM8w9a5n5fusP7M2zY2Q8J0zRoy6I9dw6zrCxHt7hHK7aHbcRVONevggN7wHRi2Lqg6/HIIYzTp6FfJMYVWZa6fyu2SU9kBATA5Lswh12J808vwNGvMP/3WRg/GeP2mRhBrl0gDMPg5D/fxQjpi3HltdiiY/xc854rK6uRf/2rDwUFga3+++/q34+6ujqvbeECAwMJDLxwoOh0Otm8eTMNDQ2kpaW16ToNDQ04HA7CwsK8zvPCCy9w2223tdjrdr4dO3Zw4sQJJk6c6HU8Pz+fLVu2sHDhQrZt29am+rSkRwVm53c/SnNxcXH+rsJFDRgAffrAyZM26uvjOa+nuEVffOH6e9y4fsTHtz4sYjWWao/4eLh+4sXLdfQa73zYtdfoIEu1SU8WHw9jrrlwmdm/JHr2L31Tn15s7Fj4wx9g376+xMf3vWDZrvr9yMnJYf/+s3utTps2jenTp7dY9uDBg2RnZ9PY2EhwcDCPPvooiYmJbbrOW2+9RXR0NMOHD/ccy8vLIyAggFtuaVuv7IYNGxg5ciT9+5+di3vixAmWLFnCT37yE0JDQ9t0ntb0qMCssrKS+vbmWOglDMMgLi6OsrIy329WfQkyMvrz+edBrF9fSWjohdv0+HGDw4ddHxaxsWUcPWr9+7NqezS98n/h8+0YU6dju/muzj//kvnwxW6M7/0HtglTO/38HWHVNukNzMLPcS77PVRXuYYtb52O4WjCuWoFJKdi++/56snsQgMH2oEB7Nrl5PDhr1scpeiq34/g4GCioqLIyclp1mPWmoSEBBYtWkRtbS1btmxhyZIlzJ0796LBWW5uLh9//DE5OTkEBbnmK5aWlrJ69WoWLFjQpn9j33zzDbt27eKRRx7xOv7HP/6R66+/nszMzIue42J6VGAG6AP1IkzT7BbvUVZWI59/HkR+vp2pUy9cX/dctKQkB2FhTrrB7XlYrj2GZGJu2Yi5ayvG5Ds79dTm6QbXXCJHI0bacGvd9zks1ya9wdARGI8twPnnF+GzLZjLX/E8ZTuzEEVt0nVSUxsJCjI5edLGwYM2kpNbX9neVb8fIe1YDmq32z09d6mpqZSUlLB69WpmzZrV6mvee+89cnNzeeKJJ0hOPrvbSFFRETU1NcyePdtzzOl08sYbb7B69WqWLFnidZ4NGzYQHh7OmDFjvI7n5+ezY8cO/vY3136u7vfpBz/4AbNmzeLGG29s+/21uaSID7VnAYB7fpkm/neckTkSE6D0C8zaUxihFx7WaJc9Ba4koVExENe2YQfpPYzwCGwP/RJz01rMt1+BhnpskdEYY5Qio6sFBkJaWiP5+UEUFgZeMDCzIqfTSWNj65//eXl5rFy5kuzs7GarKMePH+81rAkwf/58xo8f32wOmWmabNy4kfHjxzdbIDBv3jycTqfn8Y4dO8jLy+Opp55qtvrzYhSYiSW1JzDTHpmdxxgQB7EJUH7Etcn4qIvMAWoHzzZMWaM0LCUtMgwDY9xNmOnDMNfk0f+7U6kMDFRvmQ9kZTnIzw+ioCCQW26x7pSgZcuWMXLkSGJiYqivr2fTpk0UFhaSnZ0NwIsvvuhJqQGu4csVK1YwZ84cYmNjqaqqAlxDqMHBwYSHhxMeHu51DfcqzISEBK/j+fn5lJeXM2nSpGb1On8YtbS0FMMwSEpKavc9KjATSxo61IFhmJSVBfDNNzb693e2Wtadw0wZ/zuHkTUKs/wIZsFOjM4MzNxpOJS/TC7CiE3A9h+zCY6Ph6NH/V2dXuHsDgDWDguqq6tZsmQJlZWVhIaGkpycTHZ2NiNGjACgoqLC64vf2rVrcTgcLF682Os8F1pc0Jr169eTnp7OwIEDO34jF2DtFpBeKyzMJCWlif377RQUBDJ+fEOL5RobYc8eDWV2JiNrNOaGVZgFn2GaZqf0bpmV38CRg2AYGENHdEItRaQzuUcprJ7L7KGHHrrg8zk5OV6Pz58j1hatveanP/1pm88xYcIEJkyY0O5rgxLMioW1ZXPd0lI7p08b9O3rJCmpe82LsKz0YRBgh4qvobxzeivcSWVJucK1y4CIWIp7xOHQITvV1Zpq4E8KzMSyhg27+Dwz97e7oUMdbUpEKxdnBIfAkKEAmGe2T+owzzZMIzvnfCLSqSIjTQYOdM3TdS+oEv/Qf2ViWe4eM9eemS1zz4fQMGbnMrJGA+fMC+sA0+nELNrlOq/ml4lYVncZzuzpFJiJZbk/JEpK7NTVtdy1frbHTIFZZzKyRrp+KN6N6ejge3uoFE6egOAQSE3vcN1EpGu4V7ZfaPqIdL12vftr1qxhzZo1HDt2DHAtD502bRqjRrX+LfjUqVP85S9/Ydu2bZw8eZIBAwZw7733Mnr0aE+Zf/zjH/ztb3+jqqqK5ORkfvSjHzFkyJBLvCXpKWJjncTENFFREcAXX9gZNap5gKDNy7tI4uUQ3g9OVEPJF5A+/OKvaYWZf2Y4NGMEhl0f+CJWpR4za2jXp6Q7N0h8fDymafLhhx+ycOFCFi5c2OLGnw6Hg3nz5hEREcHPf/5zoqOjqaio8NpH6pNPPuGNN97ggQce4IorrmDVqlXMnz+f559/nn79us+eh9L5DMM1z2zjxgAKCgKbBWYVFTbKywMwDJOhQ5XDrDMZNpsrbcaWja60GR0JzM5M/Ncwpoi1ub/gFhcH4nCAvkf5R7uGMseMGcPo0aOJj48nISGBGTNmEBwczN69e1ssv379ek6ePMkvfvELMjIyiI2NJTMzk5SUFE+Zv//970yaNImJEyeSmJjIAw88QFBQEBs2bOjQjUnPcKF5Zu75ZcnJTfTtqwSUnS7LFUh1ZJ6ZWV/r6nHDlR9NRKwrKamJvn2dNDQYlJQoKvOXS37nnU4nmzdvpqGhgbS0tBbLfPrpp1xxxRW8+uqr7Nixg4iICMaOHcsdd9yBzWbD4XBQWlrKHXfc4XmNzWZj+PDh7Nmzp9VrNzY2em2/YLPZCA4OBlBG8Va435fu9v5kZbl6wgoLA5vVvajItQltZmZjt7uv7tAetqzRNAEcLIWaKox+Ue0+h1lcAE0OGBCH7bKEi7/Aj7pDm/Qmag/fCwhwzTPbvt21NVNGxtkURGoP32l3YHbw4EGys7NpbGwkODiYRx99tNUd3b/++muOHTvG9ddfzy9/+UvKysp45ZVXaGpq4vvf/z41NTU4nU4iIyO9XhcZGcmRI0darcO7777LO++843k8duxYfvrTnxIV1f7/OHob98av3YV7q7KioiBiY+MJCDj73P79rr+vvjqE+Pi2b4BrJZZuj/h4ygan01hSTL8jB+ibkdnuU1TmFnMS6HvV9UTHx3d+HbuApdukF1J7+NZVV8H27fDll1G09Cur9uh67Q7MEhISWLRoEbW1tWzZsoUlS5Ywd+7cFoMz0zSJiIjgwQcfxGazkZqayvHjx3nvvff4/ve/f8mVvvPOO7n11ls9j21nElhVVlZSX2/dPb78yTAM4uLiKCsr61b7zoWFQUjIZdTW2vjkk3KGDDn7De7TT2OAQAYNOs7Roy3vDGBV3aU9mtKGQ0kxlR+vp2Zo+4ciHds3AVB3eRpHLb61Tndpk95C7eEfKSkhQCTbtjVw9Ohxz/Guao/g4GB1qpyn3YGZ3W73RMypqamUlJSwevVqZs2a1axsZGQkdrvdEzgBDBw4kKqqKhwOBxEREdhsNs+mom5VVVXNetHOFRgYSGBgy6tG9At8YaZpdqv3yGZzJY/duTOI/Hw7gwe7hjZPn4a9e8/mMOtO93Quq7eHkTkS8/13MAs+w9nUhNGOLL7msTL4+oirEdOGW/o+z2X1Nult1B6+5V4AUFBgb/F9V3t0vQ7nMXM6nV7zvc6Vnp5OWVkZTufZDaiPHj1KVFQUdrsdu91Oamoq+fn5XufLz89vdd6a9D5nt2Y6G4zv22ensdEgPNxJYqK2YuoyQ4ZCn2BX2oyvDrTrpe6ksqRmYIT27fSqiUjny8hwYLOZVFQEUF6uVKf+0K53fdmyZRQWFlJeXs7Bgwc9j8eNGwfAiy++yLJlyzzlb7rpJk6ePMnSpUs5cuQIO3fu5N1332Xy5MmeMrfeeisffPABGzdu5KuvvuKVV16hoaHhkjf/lJ6npcDs3MSymovadQx7oCeHWXtXZ7rLe5LViojlhYSYpKaeXXQlvteuoczq6mqWLFlCZWUloaGhJCcnk52dzYgRIwCoqKjwWrERExNDdnY2f/rTn/jFL35BdHQ0t9xyi9cqzOuuu46amhpWrFhBVVUVKSkp/OpXv7rgUKb0Li3tmXk2sazyl3U1I2sU5r+3u/bNvOV7bXqN2dQERf92vV75y0S6lcxMB/v2BVJQEMiECd1r/m5P0K7A7KGHHrrg8zk5Oc2OpaWlMX/+/Au+7uabb+bmm29uT1WkF3F3rR87FsDXX9u47DKnMv77kJE1GhNgXxFmfZ1rk/OLObAX6k5BaBikaBcPke4kM7OR994L8eSKFN/SALJYXkiI6Zn07+41KyrS5uU+ExsPMZe58pEV51+8PLh61wBj6LcwbAEXKS0iVtLS9BHxHQVm0i2c+0FRXm6josK1FVNGhoYyu5phGJ6s/e6A62Lc2zChbP8i3Y77C29JiZ26Oj9XphdSYCbdwrnzzNzDmJdf3kRIiJZt+4J7nlhbFgCYtSehdI/X60Sk+7jsMif9+zfhdBrs2aNeM19TYCbdgntrpvz8QM0v84eMEa58ZOVHXPnJLqTo32A6IS4Ro/8A39RPRDqNYZxdWKXhTN9TYCbdgjsIO3AggO3bFZj5mhHaF1IzgHOGKVthFrrTZKi3TKS7cn++agGA7ykwk24hJsZJXFwTpmmwYYNrw3oFZr7Vlnlmpmmek79MgZlId6UFAP6jwEy6DfcHRWOjK1eecpj5lpE12vXDF//GdLTy3n99BL4pB7sd0ob5rnIi0qncX3yLigLRDky+pcBMug13YAbQr5+ThARtxeRTyakQFg51tbB/T4tF3MOYDMnE6BPsw8qJSGcaMsRBUJDJiRM2Dh1SyhtfUmAm3ca5gVlmprZi8jXDFoAxdCTQ+nCmZxhTqzFFurXAQEhL03CmPygwk27j/MBM/CCr9bQZpqMRincD2h9TpCdwTxfRnpm+pcBMuo3k5CbCwpyAAjN/8fSEfbkP82SN95MlxdBQD+H9IPFy31dORDqV+8uwVmb6lgIz6TZsNrjttjoiIpyMG6eNdf3BiOoPA5PBNDGLPvd6zrMNU+ZIDJs+WkS6O/cXYA1l+pY+PaVbWbiwmqKiMgYOdPq7Kr2WJw3GefPMPPnNNL9MpEdwB2aHDtmprtakXl9RYCbdiib8+59xzjwz88w6evNENRwscT2fOdJfVRORThQZaTJwoGueWVGRes18RYGZiLTPFVkQFARVx+HIQeBMb5lpQmIKRmS0f+snIp3m7NZMmmfmKwrMRKRdjMAgT/JYT9qMM8OYyvYv0rOcXQCgHjNfUWAmIu3mXp3pHs707I+p+WUiPcrZBQDqMfMVBWYi0m6enrE9BXBgn2tYMygIrsj0b8VEpFO5e8yKiwNpbSc26VwKzESk/eIHQVQMOBpx5r7pOpY2zDXMKSI9RlJSE337OmloMCgu9ndtegcFZiLSboZhnO010zCmSI9ls8HQoa6uss8/v0hh6RQKzETkkpw/0V+BmUjP5B7OVGDmGwrMROTSDB0JxpmPkMj+kDDIr9URka7hXgCwa5d/69FbKDATkUti9A2Dy69w/Zw1EkPZf0V6JPWY+ZYCMxG5ZLab7oTYeIyJU/1dFRHpIhkZDmw2k+BgqKnRF7CupsQkInLJjCuvI+DK6/xdDRHpQiEhJkVFX5OWFsfRoyZndmKTLqIeMxEREbmg8HBFY76iHjMRERHpFtasWcOaNWs4duwYAImJiUybNo1Ro1peFb5u3To++ugjDh06BEBqaiozZsxgyJAhLZZ/+eWXWbduHffeey9Tp7qmaBQUFDB37twWyz/99NMMGTKEgoICVq1axb59+6irqyMuLo7bbruNcePGtfseFZiJiIhItxAdHc3MmTOJj4/HNE0+/PBDFi5cyMKFCxk0qPnK8MLCQsaOHUt6ejqBgYHk5eUxb948Fi9eTHR0tFfZbdu2sXfvXqKioryOp6en8/LLL3sdW758Ofn5+QwePBiA4uJikpKSuP322+nXrx87d+7kxRdfJDQ0lCuvvLJd96jATERERLqFMWPGeD2eMWMGa9asYe/evS0GZnPmzPF6/OMf/5itW7eye/dubrjhBs/x48eP89prr5Gdnc0zzzzj9Rq73U5kZKTnscPhYMeOHdx8882e1eh33XWX12umTJnC559/ztatWxWYacl+y9zvi94fa1B7WI/axFrUHtbS1e1RV1eHec6qgsDAQAIDAy/4GqfTyebNm2loaCAtLa1N12loaMDhcBAWFuZ1nhdeeIHbbrutxeDufDt27ODEiRNMnDjxguVqa2sZOHBgm+p1rh4VmJ3f/SjNxcXF+bsKcg61h/WoTaxF7WEtXdUeOTk57N+/3/N42rRpTJ8+vcWyBw8eJDs7m8bGRoKDg3n00UdJTExs03XeeustoqOjGT58uOdYXl4eAQEB3HLLLW06x4YNGxg5ciT9+/dvtcwnn3xCSUkJs2bNatM5z9WjArPKykrq6+v9XQ1LMgyDuLg4ysrKvL6ViH+oPaxHbWItag9r6ar2CA4OJioqipycnGY9Zq1JSEhg0aJF1NbWsmXLFpYsWcLcuXMvGpzl5uby8ccfk5OTQ1BQEAClpaWsXr2aBQsWtKk38JtvvmHXrl088sgjrZbJz8/n97//PQ8++GCbeuDO16MCM0C/wBdhmqbeIwtRe1iP2sRa1B7W0lXtERIS0uaydrvd03OXmppKSUkJq1evvmDv1HvvvUdubi5PPPEEycnJnuNFRUXU1NQwe/ZszzGn08kbb7zB6tWrWbJkidd5NmzYQHh4eLO5bm6FhYUsWLCAe++912sOW3v0uMBMREREeg+n00ljY2Orz+fl5bFy5Uqys7M9qyjdxo8f7zWsCTB//nzGjx/fbA6ZaZps3LiR8ePHY7c3D58KCgp45plnuPvuu/nOd75zyfejwExERES6hWXLljFy5EhiYmKor69n06ZNFBYWkp2dDcCLL77oSakBruHLFStWMGfOHGJjY6mqqgJcQ6jBwcGEh4cTHh7udQ33KsyEhASv4/n5+ZSXlzNp0qRm9crPz2fBggXccsstXHPNNZ7r2O12r4UGbaHATERERLqF6upqlixZQmVlJaGhoSQnJ5Odnc2IESMAqKio8JortnbtWhwOB4sXL/Y6z4UWF7Rm/fr1pKent7jS8sMPP6ShoYHc3Fxyc3M9xzMzM8nJyWnXdQyzBw3eV1ZWUldX5+9qWJJhGMTHx3P06FHN17AAtYf1qE2sRe1hLV3VHiEhIcqocB7tlSkiIiJiEQrMRERERCyiR80xu1iWYHFNeBTrUHtYj9rEWtQe1tLZ7aH/t5vrUXPMRERERLozDWX2EvX19fzud7/TzggWofawHrWJtag9rEXt4TsKzHoJp9PJxx9/jNPp9HdVBLWHFalNrEXtYS1qD99RYCYiIiJiEQrMRERERCxCgVkvERgYyLRp07QCxiLUHtajNrEWtYe1qD18R6syRURERCxCPWYiIiIiFqHATERERMQiFJiJiIiIWIQCMxERERGL6FF7ZUpz7777Ltu2bePw4cMEBQWRlpbGPffcQ0JCgr+rJkBubi7Lli1jypQp/Od//qe/q9MrHT9+nDfffJNdu3bR0NBAXFwcs2fPZvDgwf6uWq/jdDpZsWIF//rXv6iqqiI6OpobbriB733vexiG4e/q9QqFhYW899577N+/n8rKSh599FG+/e1ve543TZMVK1bwwQcfcOrUKTIyMrj//vuJj4/3Y617FgVmPVxhYSGTJ09m8ODBNDU18Ze//IV58+axePFibQ7sZ/v27WPt2rUkJyf7uyq91smTJ3niiSfIysriV7/6FRERERw9epS+ffv6u2q9Um5uLmvXruXhhx8mMTGR0tJSXnrpJUJDQ5kyZYq/q9crNDQ0kJKSwo033sizzz7b7Pm8vDzef/99Hn74YWJjY3n77beZP38+ixcvJigoyA817nkUmPVw2dnZXo8ffvhh7r//fkpLS8nMzPRTraS+vp4XXniBBx98kJUrV/q7Or1WXl4e/fv3Z/bs2Z5jsbGxfqxR77Znzx7GjBnD6NGjAVdbbNq0iX379vm5Zr3HqFGjGDVqVIvPmabJ6tWrueuuu7jqqqsA+K//+i8eeOABtm/fztixY31Z1R5Lc8x6mdraWgDCwsL8XJPe7ZVXXmHUqFGMGDHC31Xp1Xbs2EFqaiqLFy/m/vvv57HHHmPdunX+rlavlZaWRn5+PkeOHAHgwIEDFBcXtxooiG+Vl5dTVVXl9bkVGhrKkCFD2LNnjx9r1rOox6wXcTqdLF26lPT0dJKSkvxdnV7r448/Zv/+/fz2t7/1d1V6vfLyctauXcvUqVO58847KSkp4fXXX8dutzNhwgR/V6/XueOOO6irq+ORRx7BZrPhdDr5wQ9+wLhx4/xdNQGqqqoA6Nevn9fxfv36eZ6TjlNg1ou8+uqrHDp0iN/85jf+rkqvVVFRwdKlS/n1r3+t+RgW4HQ6GTx4MDNnzgTg8ssv5+DBg6xdu1aBmR9s3ryZTZs2MWfOHAYNGsSBAwdYunQpUVFRag/pNRSY9RKvvvoqO3fuZO7cufTv39/f1em1SktLqa6u5vHHH/ccczqdFBUV8Y9//INly5Zhs2mGga9ERUWRmJjodSwxMZGtW7f6qUa925tvvsntt9/umauUlJTEsWPHyM3NVWBmAZGRkQBUV1cTFRXlOV5dXU1KSop/KtUDKTDr4UzT5LXXXmPbtm3k5ORoYrOfDR8+vNlKp9///vckJCRw++23KyjzsfT0dM98JrcjR44wYMAAP9Wod2toaGj2O2Cz2dCWztYQGxtLZGQku3fv9gRitbW17Nu3j5tuusm/letBFJj1cK+++iqbNm3iscceIyQkxDMPIDQ0VENpfhASEtJsfl+fPn0IDw/XvD8/mDp1Kk888QQrV67kuuuuY9++fXzwwQfMmjXL31Xrla688kpWrlxJTEwMiYmJHDhwgL///e9MnDjR31XrNerr6ykrK/M8Li8v58CBA4SFhRETE8OUKVNYuXIl8fHxxMbGsnz5cqKiojyrNKXjDFNfRXq06dOnt3h89uzZGhqwiJycHFJSUpRg1k8+/fRTli1bRllZGbGxsUydOpXvfOc7/q5Wr1RXV8fbb7/Ntm3bqK6uJjo6mrFjxzJt2jTsdvUj+EJBQQFz585tdvyGG27g4Ycf9iSYXbduHbW1tWRkZHDfffcpaXknUmAmIiIiYhGa0CIiIiJiEQrMRERERCxCgZmIiIiIRSgwExEREbEIBWYiIiIiFqHATERERMQiFJiJiIiIWIQCMxERERGLUGAmIj3eihUrmD59OjU1Nf6uiojIBSkwExEREbEIBWYiIiIiFqHATERERMQi7P6ugIj0HMePH2f58uV89tlnnDp1iri4OG699VZuvPFGAAoKCpg7dy4/+9nPOHDgABs2bKC+vp5hw4Zx3333ERMT43W+zZs3k5uby1dffUVwcDDf+ta3uOeee4iOjvYqd/jwYd5++20KCgqor68nJiaGa665hhkzZniVq62t5c9//jPbt2/HNE2uvvpq7rvvPvr06dO1b4yISBspMBORTlFVVUV2djYAkydPJiIigl27dvGHP/yBuro6pk6d6im7cuVKDMPg9ttvp6amhlWrVvHUU0+xaNEigoKCANi4cSMvvfQSgwcPZubMmVRXV7N69WqKi4tZuHAhffv2BeDLL7/kySefxG63M2nSJGJjYykrK+PTTz9tFpg999xzDBgwgJkzZ1JaWsr69euJiIjgnnvu8dG7JCJyYQrMRKRTLF++HKfTybPPPkt4eDgAN910E88//zx//etf+e53v+spe/LkSZ577jlCQkIAuPzyy3nuuedYt24dU6ZMweFw8NZbbzFo0CDmzp3rCdYyMjJ45plnWLVqFdOnTwfgtddeA2DBggVePW533313szqmpKTw0EMPedVjw4YNCsxExDI0x0xEOsw0TbZu3cqVV16JaZrU1NR4/owcOZLa2lpKS0s95cePH+8JygCuueYaoqKi+OyzzwAoLS2lurqayZMne4IygNGjRzNw4EB27twJQE1NDUVFRUycOLHZMKhhGM3qeW5wCK5A78SJE9TW1nb8TRAR6QTqMRORDqupqeHUqVOsW7eOdevWtVrGPfwYHx/v9ZxhGMTFxXHs2DEAz98JCQnNzpOQkMAXX3wBwNdffw3AoEGD2lTP84O3sLAwAE6dOkVoaGibziEi0pUUmIlIh5mmCcC4ceO44YYbWiyTnJzMV1995ctqNWOztTxI4K6/iIi/KTATkQ6LiIggJCQEp9PJiBEjWi3nDsyOHj3qddw0TcrKykhKSgJgwIABABw5coRhw4Z5lT1y5Ijn+csuuwyAQ4cOdc6NiIj4meaYiUiH2Ww2rr76arZu3crBgwebPX/+VkgfffQRdXV1nsdbtmyhsrKSUaNGAZCamkq/fv1Yu3YtjY2NnnKfffYZhw8fZvTo0YArIBw6dCgbNmygoqLC6xrqBROR7kg9ZiLSKWbOnElBQQHZ2dlMmjSJxMRETp48SWlpKbt37+b111/3lA0LC+PJJ59kwoQJVFdXs2rVKuLi4pg0aRIAdrudu+++m5deeomcnBzGjh1LVVUV77//PgMGDPBKvfHDH/6QJ598kscff9yTLuPYsWPs3LmTRYsW+fx9EBHpCAVmItIpIiMjefrpp3nnnXfYunUr//znPwkPD2fQoEHNUlfceeedfPnll+Tm5lJXV8fw4cO5//77vRK9TpgwgaCgIPLy8njrrbfo06cPV111Fffcc49nEQG4UmDMnz+ft99+m7Vr13L69GkGDBjAtdde67N7FxHpLIap/n4R8RF35v+f//znXHPNNf6ujoiI5WiOmYiIiIhFKDATERERsQgFZiIiIiIWoTlmIiIiIhahHjMRERERi1BgJiIiImIRCsxERERELEKBmYiIiIhFKDATERERsQgFZiIiIiIWocBMRERExCIUmImIiIhYxP8Hj8lrH2Wb7lEAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 35.80it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 26.93it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 34.19it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 29.60it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "enron_email1\n", + "{'before': 25.75173568725586, 'after': 25.71868133544922}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 11.83it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.35it/s]\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.1729, 'learning_rate': 2.5e-06, 'epoch': 1.0}\n", + "{'eval_loss': 2.7643606662750244, 'eval_runtime': 0.0794, 'eval_samples_per_second': 12.601, 'eval_steps_per_second': 12.601, 'epoch': 1.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2248, 'learning_rate': 5e-06, 'epoch': 2.0}\n", + "{'eval_loss': 2.764103651046753, 'eval_runtime': 0.0754, 'eval_samples_per_second': 13.266, 'eval_steps_per_second': 13.266, 'epoch': 2.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2077, 'learning_rate': 7.500000000000001e-06, 'epoch': 3.0}\n", + "{'eval_loss': 2.7643258571624756, 'eval_runtime': 0.0762, 'eval_samples_per_second': 13.132, 'eval_steps_per_second': 13.132, 'epoch': 3.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.1904, 'learning_rate': 1e-05, 'epoch': 4.0}\n", + "{'eval_loss': 2.764200210571289, 'eval_runtime': 0.0762, 'eval_samples_per_second': 13.12, 'eval_steps_per_second': 13.12, 'epoch': 4.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.1783, 'learning_rate': 8.333333333333334e-06, 'epoch': 5.0}\n", + "{'eval_loss': 2.764207363128662, 'eval_runtime': 0.0824, 'eval_samples_per_second': 12.139, 'eval_steps_per_second': 12.139, 'epoch': 5.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.1669, 'learning_rate': 6.666666666666667e-06, 'epoch': 6.0}\n", + "{'eval_loss': 2.7637062072753906, 'eval_runtime': 0.0775, 'eval_samples_per_second': 12.896, 'eval_steps_per_second': 12.896, 'epoch': 6.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2314, 'learning_rate': 5e-06, 'epoch': 7.0}\n", + "{'eval_loss': 2.763810396194458, 'eval_runtime': 0.0755, 'eval_samples_per_second': 13.249, 'eval_steps_per_second': 13.249, 'epoch': 7.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2212, 'learning_rate': 3.3333333333333333e-06, 'epoch': 8.0}\n", + "{'eval_loss': 2.7638185024261475, 'eval_runtime': 0.0757, 'eval_samples_per_second': 13.212, 'eval_steps_per_second': 13.212, 'epoch': 8.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2015, 'learning_rate': 1.6666666666666667e-06, 'epoch': 9.0}\n", + "{'eval_loss': 2.76403546333313, 'eval_runtime': 0.0768, 'eval_samples_per_second': 13.022, 'eval_steps_per_second': 13.022, 'epoch': 9.0}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n", + " warnings.warn('Was asked to gather along dimension 0, but all '\n", + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/torch/nn/parallel/data_parallel.py:33: UserWarning: \n", + " There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n", + " has less than 75% of the memory or cores of GPU 0. You can do so by setting\n", + " the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n", + " environment variable.\n", + " warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'loss': 2.2409, 'learning_rate': 0.0, 'epoch': 10.0}\n", + "{'eval_loss': 2.763981342315674, 'eval_runtime': 0.0766, 'eval_samples_per_second': 13.047, 'eval_steps_per_second': 13.047, 'epoch': 10.0}\n", + "{'train_runtime': 12.2564, 'train_samples_per_second': 1.632, 'train_steps_per_second': 0.816, 'train_loss': 2.2035992622375487, 'epoch': 10.0}\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 1/1 [00:00<00:00, 9.50it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 9.23it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.85it/s]\n", + "100%|██████████| 1/1 [00:00<00:00, 11.59it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "openai_board_ann\n", + "{'before': 15.866617202758789, 'after': 15.856237411499023}\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "data = []\n", + "for sample in samples:\n", + " r = learn_sample(sample)\n", + " print(sample['name'])\n", + " print(dict(before=r['before'], after=r['after']))\n", + " data.append(dict(**r, **sample))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df_hist = data[1]['hist']#.groupby('epoch').last().dropna(axis=1).drop(columns=['step'])\n", + "df_hist['loss'].plot(label='train')\n", + "plt.twinx()\n", + "df_hist['eval_loss'].plot(c='b', label='eval')\n", + "plt.legend()\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "### Perplexity\n", + "\n", + "Perplexity measures how well a language model predicts a text sample. Lower is better\n", + "\n", + "It’s calculated as the average number of bits per word a model needs to represent the same\n", + "\n", + "https://huggingface.co/docs/transformers/perplexity\n", + "https://thegradient.pub/understanding-evaluation-metrics-for-language-models/\n", + "\n", + "The **improvement** column, is perplexity decrease" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
beforeafterin_traininglenimprovement%improvement
name
I have a dream2.1248032.120472True8480.0020380.004331
wikipedia on LK-9932.22619232.183899False10380.0013120.042294
enron_email125.75173625.718681True4450.0012840.033054
Schmidhuber 2023 Subjective Novelty, Surprise29.60618629.573912False26540.0010900.032274
email_to_fauci25.08510025.058477False15590.0010610.026623
good_ml28.33909628.312433False10040.0009410.026663
bad_ml13.88527113.874103False23450.0008040.011168
openai_board_ann15.86661715.856237False11910.0006540.010380
Theory o. general relativity26.90251926.887775True13780.0005480.014744
AI gen fake paper7.6355347.631839False20310.0004840.003695
sokal hoax15.98831715.982531True24870.0003620.005786
lorem ipsum1.6004201.599928True4450.0003070.000492
\n", + "
" + ], + "text/plain": [ + " before after \\\n", + "name \n", + "I have a dream 2.124803 2.120472 \n", + "wikipedia on LK-99 32.226192 32.183899 \n", + "enron_email1 25.751736 25.718681 \n", + "Schmidhuber 2023 Subjective Novelty, Surprise 29.606186 29.573912 \n", + "email_to_fauci 25.085100 25.058477 \n", + "good_ml 28.339096 28.312433 \n", + "bad_ml 13.885271 13.874103 \n", + "openai_board_ann 15.866617 15.856237 \n", + "Theory o. general relativity 26.902519 26.887775 \n", + "AI gen fake paper 7.635534 7.631839 \n", + "sokal hoax 15.988317 15.982531 \n", + "lorem ipsum 1.600420 1.599928 \n", + "\n", + " in_training len \\\n", + "name \n", + "I have a dream True 848 \n", + "wikipedia on LK-99 False 1038 \n", + "enron_email1 True 445 \n", + "Schmidhuber 2023 Subjective Novelty, Surprise False 2654 \n", + "email_to_fauci False 1559 \n", + "good_ml False 1004 \n", + "bad_ml False 2345 \n", + "openai_board_ann False 1191 \n", + "Theory o. general relativity True 1378 \n", + "AI gen fake paper False 2031 \n", + "sokal hoax True 2487 \n", + "lorem ipsum True 445 \n", + "\n", + " improvement% improvement \n", + "name \n", + "I have a dream 0.002038 0.004331 \n", + "wikipedia on LK-99 0.001312 0.042294 \n", + "enron_email1 0.001284 0.033054 \n", + "Schmidhuber 2023 Subjective Novelty, Surprise 0.001090 0.032274 \n", + "email_to_fauci 0.001061 0.026623 \n", + "good_ml 0.000941 0.026663 \n", + "bad_ml 0.000804 0.011168 \n", + "openai_board_ann 0.000654 0.010380 \n", + "Theory o. general relativity 0.000548 0.014744 \n", + "AI gen fake paper 0.000484 0.003695 \n", + "sokal hoax 0.000362 0.005786 \n", + "lorem ipsum 0.000307 0.000492 " + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_res = pd.DataFrame(data)\n", + "df_res['len'] = df_res.text.str.len()\n", + "df_res = df_res[['before', 'after', 'name', 'in_training', 'len']].set_index('name')\n", + "df_res['improvement%'] = (df_res['before'] - df_res['after'])/ df_res['before']\n", + "df_res['improvement'] = (df_res['before'] - df_res['after'])\n", + "df_res.sort_values('improvement%', ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# DEBUG" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [], + "source": [ + "from IPython.display import display, HTML, Markdown\n", + "import torch\n", + "\n", + "@torch.no_grad()\n", + "def gen(model, inputs, tokenizer, clean=True):\n", + " s = model.generate(\n", + " input_ids=inputs[\"input_ids\"][None, :].to(model.device),\n", + " attention_mask=inputs[\"attention_mask\"][None, :].to(model.device),\n", + " use_cache=False,\n", + " max_new_tokens=100,\n", + " min_new_tokens=100,\n", + " do_sample=False,\n", + " early_stopping=False,\n", + " )\n", + " input_l = inputs[\"input_ids\"].shape[0]\n", + " tokenizer_kwargs=dict(clean_up_tokenization_spaces=clean, skip_special_tokens=clean)\n", + " old = tokenizer.decode(\n", + " s[0, :input_l], **tokenizer_kwargs\n", + " )\n", + " new = tokenizer.decode(\n", + " s[0, input_l:], **tokenizer_kwargs\n", + " )\n", + " s_old = \"\"+old.replace('\\n', '
')\n", + " s_new = '' + new.replace('\\n', '
')+ '

'\n", + " display(HTML(f\"{s_old}{s_new}\"))\n", + " # print([old, new])\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "sample = samples[1]\n", + "s = sample['text']\n", + "first_half = s[:len(s)//2]\n", + "second_half = s[len(s)//2:]\n", + "ds_train = Dataset.from_dict(tokenizer([first_half]))\n", + "ds_val = Dataset.from_dict(tokenizer([second_half]))" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/media/wassname/SGIronWolf/projects5/bs_writing_detector/.venv/lib/python3.11/site-packages/transformers/generation/utils.py:1421: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )\n", + " warnings.warn(\n" + ] + }, + { + "data": { + "text/html": [ + "We explored representation engineering (RepE), an approach to top-down transparency for AI systems. Inspired by the Hopfieldian view in cognitive neuroscience, RepE places representations and the transformations between them at the center of analysis. As neural networks exhibit more coherent internal structures, we believe analyzing them at the representation level can yield new insights, aiding in effective monitoring and control. Taking early steps in this direction, we proposed new RepE methods for visualizing and analyzing neural networks.

In the field of mathematics, logic plays a crucial role in understanding and solving complex problems. One fundamental concept in logic is the notion of a contradiction. A contradiction occurs when two statements cannot both be true at the same time. It is a fundamental principle that underlies the foundations of mathematics and reasoning.

To illustrate the concept of contradiction, let's consider a scenario involving three individuals: Alice, Bob, and Carol. Alice claims that she always

" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "with model.disable_adapter():\n", + " gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "We explored representation engineering (RepE), an approach to top-down transparency for AI systems. Inspired by the Hopfieldian view in cognitive neuroscience, RepE places representations and the transformations between them at the center of analysis. As neural networks exhibit more coherent internal structures, we believe analyzing them at the representation level can yield new insights, aiding in effective monitoring and control. Taking early steps in this direction, we proposed new RepE methods for visualizing and analyzing neural networks.

In the field of mathematics, logic plays a crucial role in understanding and solving complex problems. One fundamental concept in logic is the notion of a contradiction. A contradiction occurs when two statements cannot both be true at the same time. It is a fundamental principle that underlies the foundations of mathematics and reasoning.

To illustrate the concept of contradiction, let's consider a scenario involving three individuals: Alice, Bob, and Carol. Alice claims that she always

" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "gen(model, ds_train.with_format('pt')[0], tokenizer)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": ".venv", + "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": "3.11.0rc1" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}