{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Tutorial - Implementing a custom analysis block in Lightwood\n",
    "\n",
    "\n",
    "## Introduction\n",
    "\n",
    "As you might already know, Lightwood is designed to be a flexible machine learning (ML) library that is able to abstract and automate the entire ML pipeline. Crucially, it is also designed to be extended or modified very easily according to your needs, essentially offering the entire spectrum between fully automated AutoML and a lightweight wrapper for customized ML pipelines.\n",
    "\n",
    "As such, we can identify several different customizable \"phases\" in the process. The relevant phase for this tutorial is the \"analysis\" that comes after a predictor has been trained. The goal of this phase is to generate useful insights, like accuracy metrics, confusion matrices, feature importance, etc. These particular examples are all included in the core analysis procedure that Lightwood executes.\n",
    "\n",
    "However, the analysis procedure is structured into a sequential execution of \"analysis blocks\". Each analysis block should generate a well-defined set of insights, as well as handling any actions regarding these at inference time.\n",
    "\n",
    "As an example, one of the core blocks is the Inductive Conformal Prediction (`ICP`) block, which handles the confidence estimation of all Lightwood predictors. The logic within can be complex at times, but thanks to the block abstraction we can deal with it in a structured manner. As this `ICP` block is used when generating predictions, it implements the two main methods that the `BaseAnalysisBlock` class specifies: `.analyze()` to setup everything that is needed, and `.explain()` to actually estimate the confidence in any given prediction.\n",
    "\n",
    "\n",
    "## Objective\n",
    "\n",
    "In this tutorial, we will go through the steps required to implement your own analysis blocks to customize the insights of any Lightwood predictor!\n",
    "\n",
    "In particular, we will implement a \"model correlation heatmap\" block: we want to compare the predictions of all mixers inside a `BestOf` ensemble object, to understand how they might differ in their overall behavior."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:31.030641Z",
     "iopub.status.busy": "2024-05-07T17:14:31.030447Z",
     "iopub.status.idle": "2024-05-07T17:14:33.836322Z",
     "shell.execute_reply": "2024-05-07T17:14:33.835659Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:No torchvision detected, image helpers not supported.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:No torchvision/pillow detected, image encoder not supported\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'24.3.3.1'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from typing import Dict, Tuple\n",
    "import pandas as pd\n",
    "import lightwood\n",
    "lightwood.__version__"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 1: figuring out what we need\n",
    "\n",
    "When designing an analysis block, an important choice needs to be made: will this block operate when calling the predictor? Or is it only going to describe its performance once in the held-out validation dataset?\n",
    "\n",
    "Being in the former case means we need to implement both `.analyze()` and `.explain()` methods, while the latter case only needs an `.analyze()` method. Our `ModelCorrelationHeatmap` belongs to this second category.\n",
    "\n",
    "Let's start the implementation by inheriting from `BaseAnalysisBlock`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.839521Z",
     "iopub.status.busy": "2024-05-07T17:14:33.838986Z",
     "iopub.status.idle": "2024-05-07T17:14:33.849334Z",
     "shell.execute_reply": "2024-05-07T17:14:33.848771Z"
    }
   },
   "outputs": [],
   "source": [
    "from lightwood.analysis import BaseAnalysisBlock\n",
    "\n",
    "class ModelCorrelationHeatmap(BaseAnalysisBlock):\n",
    "    def __init__(self, deps=tuple()):\n",
    "        super().__init__(deps=deps)\n",
    "        \n",
    "    def analyze(self, info: Dict[str, object], **kwargs) -> Dict[str, object]:\n",
    "        return info\n",
    "\n",
    "    def explain(self,\n",
    "                row_insights: pd.DataFrame,\n",
    "                global_insights: Dict[str, object], **kwargs) -> Tuple[pd.DataFrame, Dict[str, object]]:\n",
    "        \n",
    "        return row_insights, global_insights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.851774Z",
     "iopub.status.busy": "2024-05-07T17:14:33.851407Z",
     "iopub.status.idle": "2024-05-07T17:14:33.855417Z",
     "shell.execute_reply": "2024-05-07T17:14:33.854805Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<__main__.ModelCorrelationHeatmap at 0x7fc2b0565bb0>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ModelCorrelationHeatmap()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Right now, our newly created analysis block doesn't do much, apart from returning the `info` and insights (`row_insights` and `global_insights`) exactly as it received them from the previous block.\n",
    "\n",
    "As previously discussed, we only need to implement a procedure that runs post-training, no action is required at inference time. This means we can use the default `.explain()` behavior in the parent class:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.857861Z",
     "iopub.status.busy": "2024-05-07T17:14:33.857525Z",
     "iopub.status.idle": "2024-05-07T17:14:33.861130Z",
     "shell.execute_reply": "2024-05-07T17:14:33.860523Z"
    }
   },
   "outputs": [],
   "source": [
    "class ModelCorrelationHeatmap(BaseAnalysisBlock):\n",
    "    def __init__(self, deps=tuple()):\n",
    "        super().__init__(deps=deps)\n",
    "        \n",
    "    def analyze(self, info: Dict[str, object], **kwargs) -> Dict[str, object]:\n",
    "        return info"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2: Implementing the custom analysis block\n",
    "\n",
    "Okay, now for the fun bit: we have to implement a correlation heatmap between the predictions of all mixers inside a `BestOf` ensemble. This is currently the only ensemble implemented in Lightwood, but it is a good idea to explicitly check that the type of the ensemble is what we expect.\n",
    "\n",
    "A natural question to ask at this point is: what information do we have to implement the procedure? You'll note that, apart from the `info` dictionary, we receive a `kwargs` dictionary. You can check out the full documentation for more details, but the keys (and respective value types) exposed in this object by default are:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.863583Z",
     "iopub.status.busy": "2024-05-07T17:14:33.863244Z",
     "iopub.status.idle": "2024-05-07T17:14:33.866895Z",
     "shell.execute_reply": "2024-05-07T17:14:33.866297Z"
    }
   },
   "outputs": [],
   "source": [
    "kwargs = {\n",
    "        'predictor': 'lightwood.ensemble.BaseEnsemble',\n",
    "        'target': 'str',\n",
    "        'input_cols': 'list',\n",
    "        'dtype_dict': 'dict',\n",
    "        'normal_predictions': 'pd.DataFrame',\n",
    "        'data': 'pd.DataFrame',\n",
    "        'train_data': 'lightwood.data.encoded_ds.EncodedDs',\n",
    "        'encoded_val_data': 'lightwood.data.encoded_ds.EncodedDs',\n",
    "        'is_classification': 'bool',\n",
    "        'is_numerical': 'bool',\n",
    "        'is_multi_ts': 'bool',\n",
    "        'stats_info': 'lightwood.api.types.StatisticalAnalysis',\n",
    "        'ts_cfg': 'lightwood.api.types.TimeseriesSettings',\n",
    "        'accuracy_functions': 'list',\n",
    "        'has_pretrained_text_enc': 'bool'\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see there is lots to work with, but for this example we will focus on using:\n",
    "\n",
    "1. The `predictor` ensemble\n",
    "2. The `encoded_val_data` to generate predictions for each mixer inside the ensemble\n",
    "\n",
    "And the insight we're want to produce is a matrix that compares the output of all mixers and computes the correlation between them.\n",
    "\n",
    "Let's implement the algorithm:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.869275Z",
     "iopub.status.busy": "2024-05-07T17:14:33.869058Z",
     "iopub.status.idle": "2024-05-07T17:14:33.873606Z",
     "shell.execute_reply": "2024-05-07T17:14:33.872981Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing model_correlation.py\n"
     ]
    }
   ],
   "source": [
    "%%writefile model_correlation.py\n",
    "\n",
    "from typing import Dict\n",
    "from types import SimpleNamespace\n",
    "\n",
    "import numpy as np\n",
    "\n",
    "from lightwood.ensemble import BestOf\n",
    "from lightwood.analysis import BaseAnalysisBlock\n",
    "\n",
    "\n",
    "class ModelCorrelationHeatmap(BaseAnalysisBlock):\n",
    "    def __init__(self, deps=tuple()):\n",
    "        super().__init__(deps=deps)\n",
    "        \n",
    "    def analyze(self, info: Dict[str, object], **kwargs) -> Dict[str, object]:\n",
    "        ns = SimpleNamespace(**kwargs)\n",
    "        \n",
    "        # only triggered with the right type of ensemble\n",
    "        if isinstance(ns.predictor, BestOf):\n",
    "            \n",
    "            # store prediction from every mixer\n",
    "            all_predictions = []\n",
    "\n",
    "            for mixer in ns.predictor.mixers:\n",
    "                predictions = mixer(ns.encoded_val_data)['prediction'].values  # retrieve np.ndarray from the returned pd.DataFrame\n",
    "                all_predictions.append(predictions.flatten().astype(int))  # flatten and cast labels to int\n",
    "\n",
    "            # calculate correlation matrix\n",
    "            corrs = np.corrcoef(np.array(all_predictions))\n",
    "            \n",
    "            # save inside `info` object\n",
    "            info['mixer_correlation'] = corrs\n",
    "        \n",
    "        return info\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice the use of `SimpleNamespace` for dot notation accessors.\n",
    "\n",
    "The procedure above is fairly straightforward, as we leverage numpy's `corrcoef()` function to generate the matrix. \n",
    "\n",
    "Finally, it is very important to add the output to `info` so that it is saved inside the actual predictor object. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3: Exposing the block to Lightwood\n",
    "\n",
    "\n",
    "To use this in an arbitrary script, we need to add the above class (and all necessary imports) to a `.py` file inside one of the following directories:\n",
    "\n",
    "* `~/lightwood_modules` (where `~` is your home directory, e.g. `/Users/username/` for macOS and `/home/username/` for linux\n",
    "* `/etc/lightwood_modules`\n",
    "\n",
    "Lightwood will scan these directories and import any class so that they can be found and used by the `JsonAI` code generating module.\n",
    "\n",
    "**To continue, please save the code cell above as `model_correlation.py` in one of the indicated directories.**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 4: Final test run\n",
    "\n",
    "Ok! Everything looks set to try out our custom block. Let's generate a predictor for [this](https://github.com/mindsdb/lightwood/blob/stable/tests/data/hdi.csv) sample dataset, and see whether our new insights are any good.\n",
    "\n",
    "First, it is important to add our `ModelCorrelationHeatmap` to the `analysis_blocks` attribute of the Json AI object that will generate your predictor code. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:33.876146Z",
     "iopub.status.busy": "2024-05-07T17:14:33.875950Z",
     "iopub.status.idle": "2024-05-07T17:14:34.129692Z",
     "shell.execute_reply": "2024-05-07T17:14:34.129077Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Analyzing a sample of 222\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:from a total population of 225, this is equivalent to 98.7% of your data.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Population\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Population has data type integer\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Area (sq. mi.)\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Area (sq. mi.) has data type integer\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Pop. Density \u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Pop. Density  has data type float\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: GDP ($ per capita)\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column GDP ($ per capita) has data type integer\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Literacy (%)\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Literacy (%) has data type float\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Infant mortality \u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Infant mortality  has data type float\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Infering type for: Development Index\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:type_infer-2637:Column Development Index has data type categorical\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Starting statistical analysis\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Finished statistical analysis\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from lightwood.api.high_level import ProblemDefinition, json_ai_from_problem, load_custom_module\n",
    "\n",
    "# First, load the custom module we wrote\n",
    "load_custom_module('model_correlation.py')\n",
    "\n",
    "# read dataset\n",
    "df = pd.read_csv('https://raw.githubusercontent.com/mindsdb/lightwood/stable/tests/data/hdi.csv')\n",
    "\n",
    "# define the predictive task\n",
    "pdef = ProblemDefinition.from_dict({\n",
    "    'target': 'Development Index',         # column you want to predict\n",
    "    'time_aim': 100,\n",
    "})\n",
    "\n",
    "# generate the Json AI intermediate representation from the data and its corresponding settings\n",
    "json_ai = json_ai_from_problem(df, problem_definition=pdef)\n",
    "\n",
    "# add the custom list of analysis blocks; in this case, composed of a single block\n",
    "json_ai.analysis_blocks = [{\n",
    "    'module': 'model_correlation.ModelCorrelationHeatmap',\n",
    "    'args': {}\n",
    "}]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can take a look at the respective Json AI key just to confirm our newly added analysis block is in there:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:34.132452Z",
     "iopub.status.busy": "2024-05-07T17:14:34.131982Z",
     "iopub.status.idle": "2024-05-07T17:14:34.136887Z",
     "shell.execute_reply": "2024-05-07T17:14:34.136352Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'module': 'model_correlation.ModelCorrelationHeatmap', 'args': {}}]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "json_ai.analysis_blocks"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we are ready to create a predictor from this Json AI, and subsequently train it:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:34.139458Z",
     "iopub.status.busy": "2024-05-07T17:14:34.139087Z",
     "iopub.status.idle": "2024-05-07T17:14:39.647462Z",
     "shell.execute_reply": "2024-05-07T17:14:39.646873Z"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 1/8] - Statistical analysis\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Starting statistical analysis\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Finished statistical analysis\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `analyze_data` runtime: 0.02 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 2/8] - Data preprocessing\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Cleaning the data\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `preprocess` runtime: 0.01 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 3/8] - Data splitting\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Splitting the data into train/test\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `split` runtime: 0.01 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 4/8] - Preparing encoders\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing sequentially...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for Population...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for Area (sq. mi.)...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for Pop. Density ...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for GDP ($ per capita)...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for Literacy (%)...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:dataprep_ml-2637:Preparing encoder for Infant mortality ...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637:Encoding UNKNOWN categories as index 0\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `prepare` runtime: 0.01 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 5/8] - Feature generation\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Featurizing the data\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `featurize` runtime: 0.05 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 6/8] - Mixer training\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Training the mixers\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[33mWARNING:lightwood-2637:XGBoost running on CPU\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/torch/amp/grad_scaler.py:131: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[17:14:34] WARNING: ../src/learner.cc:339: No visible GPU is found, setting `gpu_id` to -1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/pytorch_ranger/ranger.py:172: UserWarning: This overload of addcmul_ is deprecated:\n",
      "\taddcmul_(Number value, Tensor tensor1, Tensor tensor2)\n",
      "Consider using one of the following signatures instead:\n",
      "\taddcmul_(Tensor tensor1, Tensor tensor2, *, Number value) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:1578.)\n",
      "  exp_avg_sq.mul_(beta2).addcmul_(1 - beta2, grad, grad)\n",
      "\u001b[32mINFO:lightwood-2637:Loss of 18.69619858264923 with learning rate 0.0001\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 16.93891429901123 with learning rate 0.0005\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 16.197376608848572 with learning rate 0.001\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 16.06481909751892 with learning rate 0.002\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 16.472004413604736 with learning rate 0.003\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 18.28026556968689 with learning rate 0.005\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 26.746760368347168 with learning rate 0.01\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss of 101.83524441719055 with learning rate 0.05\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Found learning rate of: 0.002\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 1: 1.319209337234497\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 2: 1.3220206499099731\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 3: 1.3063435554504395\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 4: 1.2932535409927368\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 5: 1.2823516130447388\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 6: 1.2705544233322144\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 7: 1.2418551445007324\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 8: 1.2208324670791626\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 9: 1.197828769683838\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 10: 1.1781431436538696\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 11: 1.161504864692688\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 12: 1.1442031860351562\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 13: 1.1058541536331177\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 14: 1.0935649871826172\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 15: 1.0802721977233887\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 16: 1.0696258544921875\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 17: 1.0607414245605469\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 18: 1.0493905544281006\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 19: 1.020617961883545\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 20: 1.0081787109375\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 21: 0.9943330883979797\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 22: 0.9842473268508911\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 23: 0.9762145280838013\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 24: 0.9653865098953247\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 25: 0.9380742311477661\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 26: 0.9271669387817383\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 27: 0.9147073030471802\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 28: 0.9064992070198059\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 29: 0.900122344493866\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 30: 0.8903173208236694\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 31: 0.8648637533187866\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 32: 0.8549227118492126\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 33: 0.8434366583824158\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 34: 0.8365358114242554\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 35: 0.831310510635376\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 36: 0.8222441673278809\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 37: 0.7981722950935364\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 38: 0.789170503616333\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 39: 0.7787192463874817\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 40: 0.7730110287666321\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 41: 0.7687097787857056\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 42: 0.7602015137672424\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 43: 0.7373268604278564\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 44: 0.7292225956916809\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 45: 0.7197889685630798\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 46: 0.7151773571968079\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 47: 0.7117206454277039\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 48: 0.7038285136222839\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 49: 0.682073175907135\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 50: 0.674643874168396\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 51: 0.6659626364707947\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 52: 0.6620772480964661\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 53: 0.6590715646743774\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 54: 0.6515910625457764\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 55: 0.6308077573776245\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 56: 0.6241987347602844\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 57: 0.6163835525512695\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 58: 0.6131908297538757\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 59: 0.6106155514717102\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 60: 0.6036757826805115\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 61: 0.5848420262336731\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 62: 0.5793871879577637\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 63: 0.5726662278175354\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 64: 0.5703645348548889\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 65: 0.5684641003608704\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 66: 0.5622180104255676\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 67: 0.5449516773223877\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 68: 0.5401747226715088\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 69: 0.5341063141822815\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 70: 0.5322306752204895\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 71: 0.5305425524711609\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 72: 0.5246548056602478\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 73: 0.5083626508712769\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 74: 0.5040708184242249\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 75: 0.49863335490226746\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 76: 0.49717265367507935\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 77: 0.49564701318740845\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 78: 0.4900944232940674\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 79: 0.47473227977752686\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 80: 0.4708785116672516\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 81: 0.46578508615493774\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 82: 0.4644494950771332\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 83: 0.4629424810409546\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 84: 0.4576236307621002\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 85: 0.44295966625213623\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 86: 0.4393518269062042\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 87: 0.4346559941768646\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 88: 0.43358123302459717\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 89: 0.43231165409088135\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 90: 0.42753666639328003\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 91: 0.41425880789756775\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 92: 0.4113253951072693\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 93: 0.4074642062187195\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 94: 0.40698081254959106\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 95: 0.4062195420265198\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 96: 0.4020974636077881\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 97: 0.3904534876346588\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 98: 0.3879585564136505\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 99: 0.38447296619415283\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 100: 0.3841344118118286\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 101: 0.3833732604980469\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 102: 0.37956172227859497\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 103: 0.36883822083473206\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 104: 0.3664571940898895\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 105: 0.36335548758506775\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 106: 0.36316758394241333\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 107: 0.3625164330005646\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 108: 0.359012246131897\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 109: 0.34912365674972534\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 110: 0.34696850180625916\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 111: 0.3441202938556671\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 112: 0.34398093819618225\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 113: 0.3432472050189972\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 114: 0.3399496376514435\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 115: 0.3308461308479309\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 116: 0.3289041221141815\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 117: 0.32627207040786743\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 118: 0.3261372447013855\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 119: 0.32546231150627136\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 120: 0.3224080502986908\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 121: 0.314008891582489\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 122: 0.31220486760139465\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 123: 0.3098214566707611\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 124: 0.30979809165000916\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 125: 0.3090403079986572\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 126: 0.30612480640411377\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 127: 0.29819032549858093\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 128: 0.29648637771606445\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 129: 0.2943042516708374\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 130: 0.29420480132102966\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 131: 0.2934538424015045\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 132: 0.2907505929470062\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 133: 0.2835786044597626\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 134: 0.28203263878822327\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 135: 0.2801313102245331\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 136: 0.2801584303379059\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 137: 0.27946653962135315\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 138: 0.2770102620124817\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 139: 0.2705138921737671\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 140: 0.2689667046070099\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 141: 0.26713839173316956\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 142: 0.26722976565361023\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 143: 0.26659274101257324\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 144: 0.26436734199523926\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 145: 0.2585783302783966\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 146: 0.25718021392822266\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 147: 0.25569674372673035\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 148: 0.25572293996810913\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 149: 0.254925012588501\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 150: 0.25273722410202026\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 151: 0.24740025401115417\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 152: 0.24594709277153015\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 153: 0.2445458471775055\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 154: 0.2445453554391861\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 155: 0.24368290603160858\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 156: 0.2416052669286728\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 157: 0.23683445155620575\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 158: 0.23561015725135803\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 159: 0.2342897355556488\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 160: 0.2342986762523651\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 161: 0.2334001511335373\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 162: 0.23141320049762726\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 163: 0.22705355286598206\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 164: 0.22583813965320587\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 165: 0.22455710172653198\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 166: 0.2245052307844162\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 167: 0.22359803318977356\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 168: 0.22173909842967987\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 169: 0.2178291231393814\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 170: 0.21670299768447876\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 171: 0.21559178829193115\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 172: 0.21557293832302094\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 173: 0.21463343501091003\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 174: 0.21291333436965942\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 175: 0.20953477919101715\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 176: 0.20840951800346375\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 177: 0.20733794569969177\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 178: 0.20730628073215485\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 179: 0.20635393261909485\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 180: 0.20470596849918365\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 181: 0.2016059160232544\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 182: 0.2004680186510086\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 183: 0.1995442509651184\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 184: 0.1995476931333542\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 185: 0.1985597461462021\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 186: 0.19704405963420868\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 187: 0.19429439306259155\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 188: 0.1931215077638626\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 189: 0.19224728643894196\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 190: 0.1922168731689453\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 191: 0.19120150804519653\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 192: 0.1897118091583252\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 193: 0.187192901968956\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 194: 0.18604235351085663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 195: 0.18525990843772888\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 196: 0.18517257273197174\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 197: 0.1841844767332077\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 198: 0.18275843560695648\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 199: 0.18052375316619873\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 200: 0.1795222908258438\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 201: 0.17878693342208862\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 202: 0.17881926894187927\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 203: 0.17786364257335663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 204: 0.17654098570346832\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 205: 0.17458021640777588\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 206: 0.17358489334583282\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 207: 0.1728101521730423\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 208: 0.17278429865837097\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 209: 0.17180292308330536\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 210: 0.17050613462924957\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 211: 0.16873842477798462\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 212: 0.1677248477935791\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 213: 0.16707710921764374\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 214: 0.1671123504638672\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 215: 0.16612616181373596\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 216: 0.16487975418567657\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 217: 0.16339382529258728\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 218: 0.1624278575181961\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 219: 0.16172048449516296\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 220: 0.16165515780448914\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 221: 0.16061937808990479\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 222: 0.1594206690788269\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 223: 0.15802235901355743\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 224: 0.15704363584518433\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 225: 0.15640243887901306\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 226: 0.15635541081428528\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 227: 0.15536457300186157\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 228: 0.154209703207016\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 229: 0.15291643142700195\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 230: 0.15191468596458435\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 231: 0.15118129551410675\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 232: 0.151133194565773\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 233: 0.1501670926809311\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 234: 0.14912192523479462\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 235: 0.1481197327375412\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 236: 0.14712536334991455\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 237: 0.14660944044589996\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 238: 0.14649781584739685\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 239: 0.145524799823761\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 240: 0.14443959295749664\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 241: 0.14341002702713013\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 242: 0.14249812066555023\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 243: 0.14185366034507751\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 244: 0.1419423222541809\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 245: 0.1409326195716858\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 246: 0.1399424970149994\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 247: 0.13920661807060242\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 248: 0.13832959532737732\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 249: 0.13784818351268768\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 250: 0.13769637048244476\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 251: 0.1367887407541275\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 252: 0.13588252663612366\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 253: 0.13521170616149902\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 254: 0.13428467512130737\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 255: 0.13384407758712769\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 256: 0.13372991979122162\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 257: 0.13274942338466644\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 258: 0.13186557590961456\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 259: 0.13135230541229248\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 260: 0.13046588003635406\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 261: 0.12980172038078308\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 262: 0.12982229888439178\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 263: 0.12882845103740692\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 264: 0.12798714637756348\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 265: 0.12758088111877441\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 266: 0.12660843133926392\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 267: 0.1261577606201172\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 268: 0.1260918229818344\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 269: 0.12515920400619507\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 270: 0.12436933070421219\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 271: 0.12405422329902649\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 272: 0.12305409461259842\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 273: 0.12272939085960388\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 274: 0.12267134338617325\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 275: 0.12182944267988205\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 276: 0.12103450298309326\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 277: 0.12083345651626587\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 278: 0.11998103559017181\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 279: 0.11937755346298218\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 280: 0.1195112019777298\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 281: 0.1185888797044754\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 282: 0.11789504438638687\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 283: 0.11783000081777573\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 284: 0.11681754887104034\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 285: 0.11649196594953537\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 286: 0.11648327857255936\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 287: 0.11562418192625046\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 288: 0.11489420384168625\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 289: 0.11485717445611954\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 290: 0.11407709866762161\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 291: 0.11348505318164825\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 292: 0.11358898878097534\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 293: 0.11268813163042068\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 294: 0.11207651346921921\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 295: 0.11220688372850418\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 296: 0.11118005961179733\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 297: 0.11089354008436203\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 298: 0.11088859289884567\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 299: 0.1100316271185875\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 300: 0.1093800961971283\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 301: 0.10955681651830673\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 302: 0.10869839787483215\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 303: 0.10815789550542831\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 304: 0.10832306742668152\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 305: 0.10742544382810593\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 306: 0.10682710260152817\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 307: 0.10698221623897552\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 308: 0.10616409033536911\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 309: 0.10568025708198547\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 310: 0.10574078559875488\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 311: 0.10493995994329453\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 312: 0.10438455641269684\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 313: 0.10449497401714325\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 314: 0.10372297465801239\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 315: 0.10320515185594559\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 316: 0.10330332815647125\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 317: 0.10239537805318832\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 318: 0.10185065120458603\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 319: 0.10217708349227905\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 320: 0.10135672241449356\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 321: 0.10087659955024719\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 322: 0.10087589174509048\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 323: 0.10005565732717514\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 324: 0.09949999302625656\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 325: 0.09970266371965408\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 326: 0.09918338060379028\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 327: 0.09840800613164902\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 328: 0.09882311522960663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 329: 0.09775345772504807\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 330: 0.09729817509651184\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 331: 0.09763044863939285\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 332: 0.0967596173286438\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 333: 0.09642492234706879\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 334: 0.09656761586666107\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 335: 0.09573261439800262\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 336: 0.09523642063140869\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 337: 0.09568659961223602\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 338: 0.09509280323982239\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 339: 0.09460369497537613\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 340: 0.09476538747549057\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 341: 0.09388881921768188\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 342: 0.09349637478590012\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 343: 0.09398090839385986\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 344: 0.09314301609992981\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 345: 0.09281699359416962\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 346: 0.09290202707052231\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 347: 0.09209518879652023\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 348: 0.09171803295612335\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 349: 0.09221566468477249\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 350: 0.09150414168834686\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 351: 0.0910501629114151\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 352: 0.09118885546922684\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 353: 0.09043896198272705\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 354: 0.09006913751363754\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 355: 0.09049264341592789\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 356: 0.0898597463965416\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 357: 0.08943390846252441\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 358: 0.0896739661693573\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 359: 0.08882326632738113\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 360: 0.08850156515836716\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 361: 0.08897048979997635\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 362: 0.08849596232175827\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 363: 0.08790712803602219\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 364: 0.08821234852075577\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 365: 0.08732891082763672\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 366: 0.08704856038093567\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 367: 0.08765564113855362\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 368: 0.08696923404932022\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 369: 0.08649873733520508\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 370: 0.08676613122224808\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 371: 0.08599219471216202\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 372: 0.08565033972263336\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 373: 0.08618329465389252\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 374: 0.08559156954288483\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 375: 0.08509930223226547\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 376: 0.08543801307678223\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 377: 0.084554523229599\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 378: 0.08425222337245941\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 379: 0.08496475219726562\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 380: 0.08428442478179932\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 381: 0.08389458060264587\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 382: 0.08416417241096497\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 383: 0.08331726491451263\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 384: 0.08304726332426071\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 385: 0.0837259590625763\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 386: 0.08301664143800735\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 387: 0.08279375731945038\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 388: 0.08285657316446304\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 389: 0.0822003185749054\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 390: 0.08189017325639725\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 391: 0.08244460821151733\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 392: 0.08176209777593613\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 393: 0.08143384009599686\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 394: 0.08153267949819565\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 395: 0.08074252307415009\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 396: 0.0804641842842102\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 397: 0.08112648874521255\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 398: 0.0804068073630333\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 399: 0.08000007271766663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 400: 0.08030638843774796\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 401: 0.07946185022592545\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 402: 0.07926557213068008\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 403: 0.07995376735925674\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 404: 0.07914069294929504\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 405: 0.07901032269001007\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 406: 0.07910943776369095\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 407: 0.07840055227279663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 408: 0.07814037799835205\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 409: 0.07874786853790283\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 410: 0.07819069921970367\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 411: 0.07780887931585312\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 412: 0.07802116870880127\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 413: 0.0772867277264595\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 414: 0.07709880918264389\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 415: 0.0776868537068367\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 416: 0.07716330885887146\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 417: 0.07688125967979431\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 418: 0.07698465138673782\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 419: 0.0762372612953186\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 420: 0.07603802531957626\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 421: 0.07675285637378693\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 422: 0.07623977214097977\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 423: 0.07567108422517776\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 424: 0.07615751028060913\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 425: 0.07526733726263046\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 426: 0.07509555667638779\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 427: 0.07569493353366852\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 428: 0.07537294924259186\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 429: 0.07467805594205856\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 430: 0.07528648525476456\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 431: 0.07435967028141022\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 432: 0.07422596961259842\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 433: 0.07503972947597504\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 434: 0.07434249669313431\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 435: 0.07409335672855377\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 436: 0.07420685887336731\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 437: 0.0735834538936615\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 438: 0.07333341240882874\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 439: 0.07391082495450974\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 440: 0.07348911464214325\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 441: 0.07308389991521835\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 442: 0.07328886538743973\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 443: 0.0725550651550293\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 444: 0.07240220904350281\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 445: 0.07308465242385864\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 446: 0.07288312911987305\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 447: 0.0722663402557373\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 448: 0.07264856994152069\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 449: 0.07182618230581284\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 450: 0.07167533785104752\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 451: 0.07241341471672058\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 452: 0.07208056002855301\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 453: 0.07154601812362671\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 454: 0.07190731167793274\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 455: 0.0710812360048294\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 456: 0.07096673548221588\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 457: 0.0718337818980217\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 458: 0.07134897261857986\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 459: 0.07083813846111298\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 460: 0.07124733179807663\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 461: 0.0705094262957573\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 462: 0.07036501169204712\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 463: 0.07111788541078568\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 464: 0.07069509476423264\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 465: 0.07026039808988571\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 466: 0.07056906819343567\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 467: 0.06981150805950165\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 468: 0.06967213749885559\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 469: 0.0704450011253357\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 470: 0.07002224773168564\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 471: 0.06954890489578247\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 472: 0.07001929730176926\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 473: 0.06918215751647949\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 474: 0.06905678659677505\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 475: 0.06994140148162842\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 476: 0.06957031041383743\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 477: 0.06890591233968735\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 478: 0.06942413747310638\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 479: 0.068662129342556\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 480: 0.0685315951704979\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 481: 0.06919320672750473\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 482: 0.06884051114320755\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 483: 0.06852498650550842\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 484: 0.06881336867809296\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 485: 0.0681278333067894\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 486: 0.06801153719425201\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 487: 0.0688665509223938\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 488: 0.06848578155040741\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 489: 0.0680362805724144\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 490: 0.0685308426618576\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 491: 0.06770123541355133\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 492: 0.06760372221469879\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 493: 0.06856502592563629\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 494: 0.0679614394903183\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 495: 0.0675961971282959\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 496: 0.06795072555541992\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 497: 0.06731095910072327\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 498: 0.06714644283056259\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 499: 0.06786693632602692\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 500: 0.06758256256580353\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 501: 0.06698315590620041\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 502: 0.06747950613498688\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 503: 0.06655343621969223\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 504: 0.06652842462062836\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 505: 0.06745205074548721\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 506: 0.0668550580739975\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 507: 0.06666403263807297\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 508: 0.06683854013681412\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 509: 0.06626935303211212\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 510: 0.06613652408123016\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 511: 0.06672576069831848\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 512: 0.0666651502251625\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 513: 0.06582488119602203\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 514: 0.06652247160673141\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 515: 0.06558185815811157\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 516: 0.0655498206615448\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 517: 0.06624851375818253\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 518: 0.06601088494062424\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 519: 0.06545697897672653\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 520: 0.0659414529800415\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 521: 0.06516807526350021\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 522: 0.06501934677362442\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 523: 0.06574487686157227\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 524: 0.06553597748279572\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 525: 0.06504649668931961\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 526: 0.06540416181087494\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 527: 0.06479271501302719\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 528: 0.06469936668872833\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 529: 0.0654490739107132\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 530: 0.06509881466627121\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 531: 0.06460769474506378\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 532: 0.06506450474262238\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 533: 0.06425388902425766\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 534: 0.06419297307729721\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 535: 0.06507144123315811\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 536: 0.06475593149662018\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 537: 0.0640476867556572\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 538: 0.06452148407697678\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 539: 0.063988097012043\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 540: 0.06390102207660675\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 541: 0.06427431106567383\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 542: 0.06461699306964874\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 543: 0.06366197764873505\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 544: 0.06439769268035889\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 545: 0.06354749947786331\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 546: 0.06346575170755386\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 547: 0.06415951251983643\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 548: 0.06416907906532288\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 549: 0.06350232660770416\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 1: 0.03389815576374531\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 2: 0.033698095567524435\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 3: 0.0372611828148365\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 4: 0.0382374182343483\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 5: 0.03677316829562187\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 6: 0.04194173291325569\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 7: 0.04046095162630081\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `fit_mixer` runtime: 4.59 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Started fitting XGBoost model\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0]\tvalidation_0-mlogloss:0.85953\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:A single GBM iteration takes 0.1 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Training XGBoost with 131 iterations given 16.483595143556595 seconds constraint\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0]\tvalidation_0-mlogloss:0.85953\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1]\tvalidation_0-mlogloss:0.58684\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2]\tvalidation_0-mlogloss:0.41458\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[3]\tvalidation_0-mlogloss:0.29824\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[4]\tvalidation_0-mlogloss:0.21700\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[5]\tvalidation_0-mlogloss:0.15916\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[6]\tvalidation_0-mlogloss:0.11747\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[7]\tvalidation_0-mlogloss:0.08717\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[8]\tvalidation_0-mlogloss:0.06502\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[9]\tvalidation_0-mlogloss:0.04876\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[10]\tvalidation_0-mlogloss:0.03678\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[11]\tvalidation_0-mlogloss:0.02793\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[12]\tvalidation_0-mlogloss:0.02138\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[13]\tvalidation_0-mlogloss:0.01651\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[14]\tvalidation_0-mlogloss:0.01288\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[15]\tvalidation_0-mlogloss:0.01017\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[16]\tvalidation_0-mlogloss:0.00813\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[17]\tvalidation_0-mlogloss:0.00659\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[18]\tvalidation_0-mlogloss:0.00542\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[19]\tvalidation_0-mlogloss:0.00455\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[20]\tvalidation_0-mlogloss:0.00392\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[21]\tvalidation_0-mlogloss:0.00351\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[22]\tvalidation_0-mlogloss:0.00320\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[23]\tvalidation_0-mlogloss:0.00296\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[24]\tvalidation_0-mlogloss:0.00296\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[25]\tvalidation_0-mlogloss:0.00295\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[26]\tvalidation_0-mlogloss:0.00295\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[27]\tvalidation_0-mlogloss:0.00295\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[28]\tvalidation_0-mlogloss:0.00296\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[29]\tvalidation_0-mlogloss:0.00296\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[30]\tvalidation_0-mlogloss:0.00297\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:XGBoost mixer does not have a `partial_fit` implementation\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `fit_mixer` runtime: 0.06 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[33mWARNING:dataprep_ml-2637:Exception: Unspported categorical type for regression when training mixer: <lightwood.mixer.regression.Regression object at 0x7fc2ae700bb0>\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Started fitting RandomForest model\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:RandomForest based correlation of (train data): 1.0\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:RandomForest based correlation of (dev data): 1.0\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `fit_mixer` runtime: 0.11 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Ensembling the mixer\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Mixer: Neural got accuracy: 0.922\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Mixer: XGBoostMixer got accuracy: 1.0\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Mixer: RandomForest got accuracy: 1.0\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Picked best mixer: RandomForest\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `fit` runtime: 4.8 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 7/8] - Ensemble analysis\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Analyzing the ensemble of mixers\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:The block ICP is now running its analyze() method\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/sklearn/preprocessing/_encoders.py:975: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n",
      "\u001b[32mINFO:lightwood-2637:The block ConfStats is now running its analyze() method\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:The block AccStats is now running its analyze() method\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:The block PermutationFeatureImportance is now running its analyze() method\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:[PFI] Using a random sample (1000 rows out of 22).\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:[PFI] Set to consider first 10 columns out of 6: ['Population', 'Area (sq. mi.)', 'Pop. Density ', 'GDP ($ per capita)', 'Literacy (%)', 'Infant mortality '].\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:The block ModelCorrelationHeatmap is now running its analyze() method\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `analyze_ensemble` runtime: 0.2 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:[Learn phase 8/8] - Adjustment on validation requested\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:dataprep_ml-2637:Updating the mixers\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/hostedtoolcache/Python/3.9.19/x64/lib/python3.9/site-packages/torch/amp/grad_scaler.py:131: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 1: 0.033697554686417185\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 2: 0.033981192080924906\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 3: 0.037426896315688886\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 4: 0.04428015494098266\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 5: 0.061086510928968586\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 6: 0.03466159128583968\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:Loss @ epoch 7: 0.03769115870818496\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32mINFO:lightwood-2637:XGBoost mixer does not have a `partial_fit` implementation\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `adjust` runtime: 0.06 seconds\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[37mDEBUG:lightwood-2637: `learn` runtime: 5.16 seconds\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from lightwood.api.high_level import code_from_json_ai, predictor_from_code\n",
    "\n",
    "code = code_from_json_ai(json_ai)\n",
    "predictor = predictor_from_code(code)\n",
    "\n",
    "predictor.learn(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, we can visualize the mixer correlation matrix:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-07T17:14:39.650371Z",
     "iopub.status.busy": "2024-05-07T17:14:39.649925Z",
     "iopub.status.idle": "2024-05-07T17:14:40.145476Z",
     "shell.execute_reply": "2024-05-07T17:14:40.144810Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "mc = predictor.runtime_analyzer['mixer_correlation']  # newly produced insight\n",
    "\n",
    "mixer_names = [c.__class__.__name__ for c in predictor.ensemble.mixers]\n",
    "\n",
    "# plotting code\n",
    "fig, ax = plt.subplots()\n",
    "im = ax.imshow(mc, cmap='seismic')\n",
    "\n",
    "# set ticks\n",
    "ax.set_xticks(np.arange(mc.shape[0]))\n",
    "ax.set_yticks(np.arange(mc.shape[1]))\n",
    "\n",
    "# set tick labels\n",
    "ax.set_xticklabels(mixer_names)\n",
    "ax.set_yticklabels(mixer_names)\n",
    "\n",
    "# show cell values\n",
    "for i in range(len(mixer_names)):\n",
    "    for j in range(len(mixer_names)):\n",
    "        text = ax.text(j, i, round(mc[i, j], 3), ha=\"center\", va=\"center\", color=\"w\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nice! We've just added an additional piece of insight regarding the predictor that Lightwood came up with for the task of predicting the Human Development Index of any given country.\n",
    "\n",
    "What this matrix is telling us is whether predictions of each pair of the mixers stored in the ensemble have a high correlation or not.\n",
    "\n",
    "This is, of course, a very simple example, but it shows the convenience of such an abstraction within the broader pipeline that Lightwood automates.\n",
    "\n",
    "For more complex examples, you can check out any of the three core analysis blocks that we use:\n",
    "\n",
    "* `lightwood.analysis.nc.calibrate.ICP`\n",
    "* `lightwood.analysis.helpers.acc_stats.AccStats`\n",
    "* `lightwood.analysis.helpers.feature_importance.PermutationFeatureImportance`\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}