diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..068288c2f7d9f5b486424c2304e77c4516ab803c
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+.envrc
+.ipynb_checkpoints
\ No newline at end of file
diff --git a/README.md b/README.md
index 531011c84e92743eb7f0ad07b985c4a23660e144..559bb6975fc38f8cfa314caff94b510510db5162 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,7 @@
 # analytics-tutorial-cmlkit
 
-Tutorial for [`cmlkit`](https://github.com/sirmarcel/cmlkit).
\ No newline at end of file
+Tutorial for [`cmlkit`](https://github.com/sirmarcel/cmlkit).
+
+In addition to the prerequisites in `setup.py`, this tutorial requires [`qmmlpack`](https://gitlab.com/qmml/qmmlpack/-/tree/development) on the DEVELOPMENT branch.
+
+It also requires the environment variables `CML_PLUGINS=cscribe` and `CML_DATASET_PATH=data/` to be set.
\ No newline at end of file
diff --git a/assets/.gitignore b/assets/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..86d0cb2726c6c7c179b99520c452dd1b68e7a813
--- /dev/null
+++ b/assets/.gitignore
@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore
\ No newline at end of file
diff --git a/cmlkit-tutorial.ipynb b/cmlkit-tutorial.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..2c8d24c8798f101a86c91174fb13b013f1047956
--- /dev/null
+++ b/cmlkit-tutorial.ipynb
@@ -0,0 +1,1443 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# `cmlkit` tutorial 🐫🧰\n",
+    "\n",
+    "by Marcel Langer, langer@fhi-berlin.mpg.de\n",
+    "\n",
+    "\n",
+    "## Prerequisites\n",
+    "\n",
+    "Hello! 👋 Welcome to the [`cmlkit`](https://marcel.science/cmlkit) tutorial. You will get the most out of this tutorial if you:\n",
+    "\n",
+    "- Have some familiarity with Python 3,\n",
+    "- Know a little bit about chemistry and/or physics,\n",
+    "- Know roughly how kernel ridge regression works.\n",
+    "\n",
+    "The contents of this tutorial will mostly be of interest for people researching the application of machine learning models to computational chemistry and computational condensed matter physics, and in particularly those interested in building computational experiments and toolkits in that domain.\n",
+    "\n",
+    "I'll use the following abbreviations and terms throughout:\n",
+    "\n",
+    "- \"Representation\": A way to transform the coordinates and atomic numbers (i.e. the \"structure\") of a molecule or material into a vector.\n",
+    "- \"ML\": Machine learning, another way of saying \"computational applied statistics\" or in our case \"fitting\".\n",
+    "- \"KRR\": Kernel ridge regression, a regression (i.e. \"fitting\") method.\n",
+    "- \"HP\": Hyper-parameters. These are all parameters of a ML model that aren't directly determined in the training set.\n",
+    "- \"SOAP\": Smooth Overlap of Atomic Positions representaton ([Bartók, Kondor, Csányi (2013)](https://doi.org/10.1103/PhysRevB.87.184115))\n",
+    "- \"MBTR\": Many-Body Tensor Representation [(Huo, Rupp (2017))](https://arxiv.org/abs/1704.06439).\n",
+    "\n",
+    "Let's get started.\n",
+    "\n",
+    "## What is `cmlkit`?\n",
+    "\n",
+    "According to the [Github repository](https://github.com/sirmarcel/cmlkit/tree/develop-2.0):\n",
+    "\n",
+    "> `cmlkit` is an extensible `python` package providing clean and concise infrastructure to specify, tune, and evaluate machine learning models for computational chemistry and condensed matter physics. Intended as a common foundation for more specialised systems, not a monolithic user-facing tool, it wants to help you build your own tools! ✨\n",
+    "\n",
+    "In this tutorial, I will give an overview of the things `cmlkit` can do, and hopefully make a case for why it is useful to you as a base to build your own projects on. (You can find a more compact feature list on the Github page, if that's more your kind of thing. This is the scenic route. 🌆)\n",
+    "\n",
+    "At this point, it's most useful if we go on a little `cmlkit` tour. Let's saddle up! 🐫\n",
+    "\n",
+    "## A Tour of `cmlkit`\n",
+    "\n",
+    "Conceptually, the \"core\" of `cmlkit` consists of:\n",
+    "\n",
+    "1. `Component` class and sub-classes that define how parts of ML models should be implemented, an\n",
+    "2. Engine that defines a way to specify parametrisations of these components in a special format (\"configs\"), and a\n",
+    "3. Plugin system to easily extend this architecture with custom components.\n",
+    "\n",
+    "On top of this, `cmlkit` then provides:\n",
+    "\n",
+    "1. Reference interfaces to commonly used representations of molecules and materials,\n",
+    "2. Reference interface to `qmmlpack` for fast kernel ridge regression, and finally\n",
+    "3. Tools to combine these into ML models.\n",
+    "\n",
+    "Additionally, `cmlkit` also contains a hyper-parameter tuning engine based on `hyperopt`.\n",
+    "\n",
+    "\n",
+    "\n",
+    "### Core 🌱\n",
+    "\n",
+    "#### Components\n",
+    "\n",
+    "In `cmlkit`, a `Component` is an object that:\n",
+    "\n",
+    "- Needs to be instantiated with a lot of complex parameters,\n",
+    "- Has little to no internal state, (i.e. once you create it, it can't change)\n",
+    "- Does one thing, deterministically (i.e. given the same input, it always produces the same output).\n",
+    "\n",
+    "In most cases, we can simply think of a `Component` as a function with a lot of parameters. Something along the lines of:\n",
+    "\n",
+    "```python\n",
+    "f(data, lots, of, other, parameters, ...)\n",
+    "```\n",
+    "\n",
+    "Instead of always passing around these parameters, we create the component `c` with these parameters, and then simply call `c(data)` instead of an extremely long, unwield expression. (For the technically-minded: This is basically a way of creating [partials](https://docs.python.org/3.7/library/functools.html). Components are mostly \"fancy functions\".)\n",
+    "\n",
+    "This is useful because the parts of a ML model can often be described in this way. For example, a *representation* is simply transformation of a set of coordinates into a vector, with a lot of parameters. Or a *kernel* in KRR is simply a function acting on representations. If we write down all the parameters for all the components of a model we can reconstruct it easily. And if there is no state, we can reconstruct it *exactly*!\n",
+    "\n",
+    "#### Configs\n",
+    "\n",
+    "`Components` can always be described as specially formatted dictionaries, called *configs*. Having a canonical, *non-code*, format forces the parametrisation to be separated from the code implementing the models. It also means that everything can be easily serialised, and remains human readable. This is surprisingly useful, as we'll see later.\n",
+    "\n",
+    "The config format is:\n",
+    "\n",
+    "```\n",
+    "{\"kind\": { ... }}\n",
+    "```\n",
+    "\n",
+    "Where `kind` is a unique name for the type of component being instantiated (essentially, the class name) and the \"inner\" dictionary contains all arguments that would normally be passed into the `__init__` call.\n",
+    "\n",
+    "This format is designed to print nicely to [`yaml`](https://en.wikipedia.org/wiki/YAML), a simple data-serialization language. Here is, for instance, the entire `config` of a SOAP+KRR model:\n",
+    "\n",
+    "```yaml\n",
+    "model:\n",
+    "  per: cell\n",
+    "  regression:\n",
+    "    krr:\n",
+    "      kernel:\n",
+    "        kernel_atomic:\n",
+    "          kernelf:\n",
+    "            gaussian:\n",
+    "              ls: 90.50966799187809\n",
+    "      nl: 9.5367431640625e-07\n",
+    "  representation:\n",
+    "    ds_soap:\n",
+    "      cutoff: 3\n",
+    "      elems: [8, 13, 31, 49]\n",
+    "      l_max: 8\n",
+    "      n_max: 2\n",
+    "      rbf: gto\n",
+    "      sigma: 0.5\n",
+    "```\n",
+    "\n",
+    "Calling `cmlkit.from_yaml()` on the this produces an instance of `Model` with KRR as regression method and the SOAP representation (implemented in `dscribe`), with these parameters. We'll return to this later.\n",
+    "\n",
+    "#### Plugins\n",
+    "\n",
+    "This deserialisation scheme lends itself to a simple plugin system: Since at some point, `cmlkit` has to look up the classes associated with the `kind` string in the config dict, we can simply add external classes to this lookup table.\n",
+    "\n",
+    "In practice, `cmlkit` plugins are python packages that, at module level, have a `components` attribute which is a list of classes (sub-classes of `Component`) to be included in the registry. `cmlkit` knows about these through an environment variable, `CML_PLUGINS`. It's rudimentary -- but it works!\n",
+    "\n",
+    "\n",
+    "### Parts 🌳\n",
+    "\n",
+    "`cmlkit` implements `Components` for ML models that follow the representation + regressor pattern. Currently supported are:\n",
+    "\n",
+    "#### Representations\n",
+    "- Many-Body Tensor Representation (MBTR) by [Huo, Rupp (2017)](https://arxiv.org/abs/1704.06439) (`qmmlpack` and `dscribe` implementation)\n",
+    "- Smooth Overlap of Atomic Positions (SOAP) representaton by [Bartók, Kondor, Csányi (2013)](https://doi.org/10.1103/PhysRevB.87.184115) (`quippy` and `dscribe` implementations)\n",
+    "- Symmetry Functions (SF) representation by [Behler (2011)](https://doi.org/10.1063/1.3553717) (`RuNNer` and `dscribe` implementation), with a semi-automatic parametrisation scheme taken from [Gastegger *et al.* (2018)](https://doi.org/10.1063/1.5019667).\n",
+    "\n",
+    "#### Regression methods\n",
+    "- Kernel Ridge Regression (KRR) as implemented in [`qmmlpack`](https://gitlab.com/qmml/qmmlpack) (supporting both global and local/atomic representations)\n",
+    "\n",
+    "\n",
+    "***\n",
+    "\n",
+    "And this brings us to the end of the tour of the `cmlkit` core. Let's get a bit more *practical*!\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading Data and Model Basics\n",
+    "\n",
+    "In this chapter, we'll take a look at how to load datasets, how to make subsets, and how to define, train and evaluate models. We'll do all of this on a small toy subset of the `nmd18u` dataset, which was created for the [\"Nomad2018 Predicting Transparent Conductors\" Kaggle challenge](https://www.kaggle.com/c/nomad2018-predict-transparent-conductors). It consists of 3000 Al<sub>x</sub>Ga<sub>y</sub>In<sub>z</sub> oxides, and we'll predict their formation energy. Having learned these basics, we'll then move on to hyper-parameter optimisation for the same problem!\n",
+    "\n",
+    "\n",
+    "Let's start by finally importing `cmlkit`!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import cmlkit"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Nice!\n",
+    "\n",
+    "### Datasets\n",
+    "\n",
+    "Let's now load some training data. `cmlkit` allows you to set a path where it'll automatically look for named datasets, so you can load a dataset by simply giving its name. We'll now load the training set for the Kaggle challenge, and look at what `cmlkit` can tell us about the dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# dataset: nmd18_train #\n",
+      "\n",
+      "Dataset (training portion) from the NOMAD2018 Kaggle challenge: Unrelaxed (Vegard's law) geometries and their properties.\n",
+      "Formation energy in eV per atom, bandgap in eV per structure, spacegroup number.\n",
+      "Properties given for relaxed structures.\n",
+      "\n",
+      "## Overview ##\n",
+      " 2400 periodic systems (materials)\n",
+      " 3 different properties: ['fe', 'bg', 'sg']\n",
+      " elements by charge: [ 8 13 31 49]\n",
+      " max #els/system: 4;  max same #el/system: 48;  max #atoms/system: 80\n",
+      " min dist: 1.32;  max dist: 25.91\n",
+      "\n",
+      "## Geometry ##\n",
+      "### Ranges ###\n",
+      " These are the ranges for various geometry properties.\n",
+      " count   : 0 to 48\n",
+      " dist    : 1.3202 to 25.9075\n",
+      " 1/dist  : 0.0386 to 0.7575\n",
+      " 1/dist^2: 0.0015 to 0.5738\n",
+      "\n",
+      "### Recommendations for d ###\n",
+      " We recommend using the intervals (-0.05*max, 1.05*max) for the parametrisation of the MBTR, i.e. a 5% padding.  In the following, we give (start, stop, n).\n",
+      " k=1 MBTR:\n",
+      " count     : (-2.40, 52.80, n)\n",
+      " k=2 MBTR:\n",
+      " 1/dist    : (-0.04, 0.83, n)\n",
+      " 1/dot     : (-0.03, 0.63, n)\n",
+      " k=3 MBTR (experimental):\n",
+      " angle     : (-0.16, 3.46, n)\n",
+      " cos_angle : (-1.05, 1.05, n)\n",
+      " dot/dotdot: (-0.03, 0.63, n)\n",
+      " It is still prudent to experiment with these settings!\n",
+      "\n",
+      "## Properties ##\n",
+      " Mean and standard deviation of properties:\n",
+      " fe: 0.0750 (0.0416)\n",
+      " bg: 2.0772 (1.0066)\n",
+      " sg: 141.5179 (84.6979)\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "nmd18_train = cmlkit.load_dataset(\"nmd18_train\")\n",
+    "print(nmd18_train.report)\n",
+    "# \"fe\" is short for formation energy, \"bg\" for bandgap, \"sg\" for spacegroup number"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Nice. We'll now generate our toy datasets for this chapter. `cmlkit.utility.threeway_split` is a convenience function to randomly draw two subsets, and also return the rest. (`_` is a python idiom that just means \"we don't care about this variable\".)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "N_train = 80\n",
+      "N_test = 20\n"
+     ]
+    }
+   ],
+   "source": [
+    "_, idx_toy_train, idx_toy_test = cmlkit.utility.threeway_split(nmd18_train.n, 80, 20)\n",
+    "toy_train = cmlkit.Subset.from_dataset(nmd18_train, idx=idx_toy_train)\n",
+    "toy_test = cmlkit.Subset.from_dataset(nmd18_train, idx=idx_toy_test)\n",
+    "print(f\"N_train = {toy_train.n}\")\n",
+    "print(f\"N_test = {toy_test.n}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now that we have some data, let's see how we can get a model trained!\n",
+    "\n",
+    "### Loading and Training a Model\n",
+    "\n",
+    "Here is a model config with all hyper-parameters already tuned. (It's the final SOAP model from the [repbench](marcel.science/repbench) paper, for the `nmd18u` dataset at `Ntrain=1600`.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<cmlkit.model.Model object at 0x11b06b940>\n"
+     ]
+    }
+   ],
+   "source": [
+    "config = {\n",
+    "    \"model\": {\n",
+    "        \"per\": \"cell\",  # this means that the model will internally be trained with energies per unit cell,\n",
+    "                        # this is needed because SOAP is a local representation, so the KRR model is extensive\n",
+    "        \"regression\": {\n",
+    "            \"krr\": {\n",
+    "                \"centering\": False,  # we subtract the mean from labels or kernel matrices\n",
+    "                \"kernel\": {\n",
+    "                    \"kernel_atomic\": {\n",
+    "                        \"kernelf\": {\"gaussian\": {\"ls\": 22.627416997969522}},  # gaussian kernel\n",
+    "                        \"norm\": False,  # we don't normalise the kernel by atom counts \n",
+    "                                        # (needed to predict intensive things)\n",
+    "                    }\n",
+    "                },\n",
+    "                \"nl\": 9.5367431640625e-07,  # regularisation parameter for KRR\n",
+    "            }\n",
+    "        },\n",
+    "        \"representation\": {\n",
+    "            \"ds_soap\": {  # we use the SOAP implemented in dscribe\n",
+    "                \"cutoff\": 3,  # 3 angstrom cutoff radius\n",
+    "                \"elems\": [8, 13, 31, 49],  # elements in the dataset\n",
+    "                \"l_max\": 5,  # number of angular basis functions\n",
+    "                \"n_max\": 3,  # number of radial basis functions\n",
+    "                \"rbf\": \"gto\",# radial basis: Gaussians\n",
+    "                \"sigma\": 0.3535533905932738, # broadening\n",
+    "            }\n",
+    "        },\n",
+    "    }\n",
+    "}\n",
+    "\n",
+    "model = cmlkit.from_config(config)\n",
+    "print(model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is the `config` mechanism at work! We've turned a dictionary into a whole hierarchy of objects, without having to import anything or write any additonal code. We're even using a class from outside `cmlkit`!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<cscribe.soap.SOAP object at 0x11b06b588>\n",
+      "<cmlkit.regression.qmml.krr.KRR object at 0x11be30b70>\n",
+      "<cmlkit.regression.qmml.kernel_atomic.KernelAtomic object at 0x11be30b00>\n",
+      "<cmlkit.regression.qmml.kernel_functions.KernelfGaussian object at 0x11be30da0>\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(model.representation)  # <- not implemented in cmlkit, but in the cscribe plugin!\n",
+    "print(model.regression)\n",
+    "print(model.regression.kernel)\n",
+    "print(model.regression.kernel.kernelf)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "So! Let's train this model on the formation energy (\"`fe`\"):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cmlkit.model.Model at 0x11b06b940>"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.train(toy_train, target=\"fe\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Well, that was not too difficult! Let's predict something."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.24491202 0.51724975 0.08694949 0.1087309  0.1063895  0.30525047\n",
+      " 0.07773991 0.28847395 0.33317674 0.05065187 0.26989161 0.29548776\n",
+      " 0.19181674 0.08721873 0.05401863 0.11288928 0.18865161 0.27037222\n",
+      " 0.3146872  0.20212072]\n"
+     ]
+    }
+   ],
+   "source": [
+    "pred = model.predict(toy_test, per=\"cation\")\n",
+    "print(pred)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Okay... what is the ground truth?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.2394 0.3684 0.0824 0.1093 0.0744 0.3366 0.2825 0.3269 0.3236 0.0465\n",
+      " 0.2809 0.2592 0.1841 0.1443 0.1073 0.1066 0.159  0.3556 0.4    0.1864]\n"
+     ]
+    }
+   ],
+   "source": [
+    "true = toy_test.pp(\"fe\", per=\"cation\")  # pp means \"property per\"\n",
+    "print(true)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Whelp! We did not do too well! But this is not surprising -- we've trained on only 80 points. Let's compute some popular loss functions in any case, just so we know how to do it."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'rmse': 0.06746430822326362, 'mae': 0.04336559392084678, 'maxae': 0.20476009443402288, 'r2': 0.6951943036629642, 'rmsle': 0.05399033994631003}\n"
+     ]
+    }
+   ],
+   "source": [
+    "loss = cmlkit.evaluation.get_loss(\"rmse\", \"mae\", \"maxae\", \"r2\", \"rmsle\")\n",
+    "print(loss(true, pred))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In essence, this concludes the \"core\" tutorial -- you now know the basics of how `cmlkit` is supposed to work, you can load models, and you know how to train and predict. At this point, you're in an excellent position to take a look at the [repository](https://github.com/sirmarcel/cmlkit) and take it from there!\n",
+    "\n",
+    "(But of course, then you'd be missing...)\n",
+    "\n",
+    "##  Hyper-parameter Optimisation\n",
+    "\n",
+    "We'll conclude the tutorial with the topic of hyper-parameter optimisation. Most state-of-the-art ML methods, representations and regression methods alike, have a number of free parameters that have a large impact on their performance, and no immediate way of setting these parameters. One approach, which we're exploring here, is to do it empirically: We pick some loss function (i.e. a quantitative measure of model quality) and minimise it using a global optimisation method. In this part of the tutorial, you'll first learn how such an optimiser is implemented in `cmlkit`, and finally, we'll explore the results of running such a search for `nmd18u`.\n",
+    "\n",
+    "### Exploring the Optimiser\n",
+    "\n",
+    "At its core, the `cmlkit.tune` module is an asynchronous, stochastic optimiser based on [`hyperopt`](https://github.com/hyperopt/hyperopt). It essentially allows you do specify a probability distribution over possible parameter choices, draws from that distribution, finds out which combination works best, and then updates the distribution to focus further on promising areas (if the \"Tree-Structured Parzen Estimators\" method is used, otherwise it's a random search). This type of method is most appropriate to high-dimensional search spaces, and can also deal with \"tree structured\" problems, where some paramaters are only needed based on a prior choice. (For a more formal introduction, please see [Bergstra *et al.* (2011)](https://papers.nips.cc/paper/4443-algorithms-for-hyper-parameter-optimization).)\n",
+    "\n",
+    "Let's first explore the mechanics of the `cmlkit.tune` module. We'll start by building a toy problem:\n",
+    "\n",
+    "```\n",
+    "Let f(x, y, z) = 2*(x*y - 2.0)**2 + (z - 1)**2 ;\n",
+    "Find x, y, z in [0, 2] to minimise f.\n",
+    "```\n",
+    "\n",
+    "In this case, `f` is our loss function, and `x, y, z in [0, 2]` is our parameter search space.\n",
+    "\n",
+    "The search space is simply a dictionary with special \"tokens\" that tell the system to use a \"uniform\" prior for \"variable name\" from \"start value\" to \"end value\":"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "space = {\"x\": [\"hp_uniform\", \"var_x\", 0, 2],\n",
+    "         \"y\": [\"hp_uniform\", \"var_y\", 0, 2],\n",
+    "         \"z\": [\"hp_uniform\", \"var_z\", 0, 2],}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Therefore, this `space` means that we would like to uniformly sample x, y and z from zero to two. (If you happen to be familiar with `hyperopt`, we are literally just calling the `hp.` functions here!)\n",
+    "\n",
+    "We implement `f`, our loss function, as a `Component` that follows the `Evaluator` interface:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<__main__.F object at 0x11c06c9e8>\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "class F(cmlkit.engine.Component):\n",
+    "    kind = \"f\"\n",
+    "\n",
+    "    def __call__(self, model):\n",
+    "        x, y, z = model[\"x\"], model[\"y\"], model[\"z\"]\n",
+    "        loss = 2*(x*y - 2.0)**2 + (z - 1)**2\n",
+    "        return {\"loss\": loss}\n",
+    "\n",
+    "    def _get_config(self):\n",
+    "        return {}\n",
+    "\n",
+    "cmlkit.register(F)  # registering the Component\n",
+    "\n",
+    "evaluator = cmlkit.from_config({\"f\": {}})\n",
+    "print(evaluator)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we're basically all set to get going. Let's instantiate a `Search`, which will take care of the optimisation part of our task. Without any additional information, the search will simply return random samples from our search space:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(0, {'x': 0.47430154100580957, 'y': 1.1808824523028227, 'z': 1.456060182509149})\n",
+      "(1, {'x': 0.17493917371880396, 'y': 0.7352477275170646, 'z': 1.7173875395185256})\n",
+      "(2, {'x': 1.6728847163897997, 'y': 1.5261760600348726, 'z': 1.985036214798903})\n",
+      "(3, {'x': 0.32432680763910393, 'y': 1.4008460612017275, 'z': 1.3469545085546486})\n",
+      "(4, {'x': 0.83375538564964, 'y': 0.7082089608839477, 'z': 1.125229835874551})\n"
+     ]
+    }
+   ],
+   "source": [
+    "search = cmlkit.tune.Hyperopt(space, method=\"tpe\")\n",
+    "\n",
+    "suggestions = [search.suggest() for i in range(50)]\n",
+    "for i in range(5):\n",
+    "    print(suggestions[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "(The first part of each of these is simply a unique identifier for this particular \"suggestion\", which we can later use to inform the search of the loss we have obtained for this suggestion.)\n",
+    "\n",
+    "Let's have a quick look at what the search has actually suggested by making a histogram of each of the variable suggestions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1239fc588>"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 3 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn\n",
+    "\n",
+    "fig, axs = plt.subplots(nrows=1, ncols=3)\n",
+    "fig.tight_layout(pad=1.0)\n",
+    "seaborn.distplot([s[1][\"x\"] for s in suggestions], ax=axs[0], kde=False, bins=8)\n",
+    "seaborn.distplot([s[1][\"y\"] for s in suggestions], ax=axs[1], kde=False, bins=8)\n",
+    "seaborn.distplot([s[1][\"z\"] for s in suggestions], ax=axs[2], kde=False, bins=8)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "So we see, it is (somewhat) uniform across the search space. Let's now see how this changes if we return some information back to the search:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(50):\n",
+    "    if suggestions[i][1][\"x\"] < 0.5:\n",
+    "        loss = 0.0\n",
+    "    else:\n",
+    "        loss = 100.0\n",
+    "    search.submit(i, loss=loss)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We're now pretending that only \"x\" matters, passing a low loss only if `x < 0.5`. This will cause the search to focus on this region of the search space. Let's see it for ourselves!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x123cefb70>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 3 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "new_suggestions = [search.suggest() for i in range(200)]\n",
+    "fig, axs = plt.subplots(nrows=1, ncols=3)\n",
+    "fig.tight_layout(pad=1.0)\n",
+    "seaborn.distplot([s[1][\"x\"] for s in new_suggestions], ax=axs[0], kde=False, bins=8)\n",
+    "seaborn.distplot([s[1][\"y\"] for s in new_suggestions], ax=axs[1], kde=False, bins=8)\n",
+    "seaborn.distplot([s[1][\"z\"] for s in new_suggestions], ax=axs[2], kde=False, bins=8)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Clearly, we have managed to shift the distribution towards `x < 0.5`.\n",
+    "\n",
+    "### Running an Optimisation\n",
+    "\n",
+    "With this basic understanding under our belt, we can now run an actual optimisation:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Prepared runner eliza-florence in folder run_eliza-florence.\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:21 ###\n",
+      " Running. Runtime: 0.0/inf. Active evaluations: 0.\n",
+      " Counted trials: 0/100.\n",
+      " Best 3:. Live: 0/T: 0 (0)/E: 0 (0).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:21 ###\n",
+      " Running. Runtime: 0.0/inf. Active evaluations: 2.\n",
+      " Counted trials: 0/100.\n",
+      " Best 3:. Live: 2/T: 0 (0)/E: 0 (0).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:21 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 2.\n",
+      " Counted trials: 2/100.\n",
+      " Best 3: 4.3546 7.5187. Live: 2/T: 2 (2)/E: 2 (2).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 2.\n",
+      " Counted trials: 4/100.\n",
+      " Best 3: 1.5822 4.3546 4.8986. Live: 2/T: 4 (4)/E: 4 (4).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 2.\n",
+      " Counted trials: 6/100.\n",
+      " Best 3: 1.5822 3.9892 4.3546. Live: 2/T: 6 (6)/E: 6 (6).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 2.\n",
+      " Counted trials: 8/100.\n",
+      " Best 3: 0.4750 0.4967 1.5822. Live: 2/T: 8 (8)/E: 8 (8).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 2.\n",
+      " Counted trials: 10/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 10 (10)/E: 10 (10).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 2.\n",
+      " Counted trials: 12/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 12 (12)/E: 12 (12).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 2.\n",
+      " Counted trials: 14/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 14 (14)/E: 14 (14).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 2.\n",
+      " Counted trials: 16/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 16 (16)/E: 16 (16).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 2.\n",
+      " Counted trials: 18/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 18 (18)/E: 18 (18).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 2.\n",
+      " Counted trials: 20/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 20 (20)/E: 20 (20).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 2.\n",
+      " Counted trials: 22/100.\n",
+      " Best 3: 0.4338 0.4750 0.4967. Live: 2/T: 22 (22)/E: 22 (22).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 2.\n",
+      " Counted trials: 24/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 24 (24)/E: 24 (24).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 2.\n",
+      " Counted trials: 26/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 26 (26)/E: 26 (26).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 2.\n",
+      " Counted trials: 28/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 28 (28)/E: 28 (28).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 2.\n",
+      " Counted trials: 30/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 30 (30)/E: 30 (30).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 2.\n",
+      " Counted trials: 32/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 32 (32)/E: 32 (32).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 2.\n",
+      " Counted trials: 34/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 34 (34)/E: 34 (34).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 2.\n",
+      " Counted trials: 36/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 36 (36)/E: 36 (36).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 2.\n",
+      " Counted trials: 38/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 38 (38)/E: 38 (38).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 2.\n",
+      " Counted trials: 40/100.\n",
+      " Best 3: 0.1865 0.4338 0.4750. Live: 2/T: 40 (40)/E: 40 (40).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 2.\n",
+      " Counted trials: 42/100.\n",
+      " Best 3: 0.1371 0.1865 0.4338. Live: 2/T: 42 (42)/E: 42 (42).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 2.\n",
+      " Counted trials: 44/100.\n",
+      " Best 3: 0.1371 0.1865 0.4338. Live: 2/T: 44 (44)/E: 44 (44).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 2.\n",
+      " Counted trials: 46/100.\n",
+      " Best 3: 0.0575 0.1371 0.1865. Live: 2/T: 46 (46)/E: 46 (46).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 2.\n",
+      " Counted trials: 48/100.\n",
+      " Best 3: 0.0575 0.1371 0.1865. Live: 2/T: 48 (48)/E: 48 (48).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 2.\n",
+      " Counted trials: 50/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 50 (50)/E: 50 (50).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 52/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 52 (52)/E: 52 (52).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 54/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 54 (54)/E: 54 (54).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 56/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 56 (56)/E: 56 (56).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 58/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 58 (58)/E: 58 (58).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 60/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 60 (60)/E: 60 (60).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 2.\n",
+      " Counted trials: 62/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 62 (62)/E: 62 (62).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 2.\n",
+      " Counted trials: 64/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 64 (64)/E: 64 (64).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 2.\n",
+      " Counted trials: 66/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 66 (66)/E: 66 (66).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 2.\n",
+      " Counted trials: 68/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 68 (68)/E: 68 (68).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 2.\n",
+      " Counted trials: 70/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 70 (70)/E: 70 (70).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 2.\n",
+      " Counted trials: 72/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 72 (72)/E: 72 (72).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 74/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 74 (74)/E: 74 (74).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 76/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 76 (76)/E: 76 (76).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 78/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 78 (78)/E: 78 (78).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 80/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 80 (80)/E: 80 (80).\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 82/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 82 (82)/E: 82 (82).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.8/inf. Active evaluations: 2.\n",
+      " Counted trials: 84/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 84 (84)/E: 84 (84).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 86/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 86 (86)/E: 86 (86).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 88/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 88 (88)/E: 88 (88).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 90/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 90 (90)/E: 90 (90).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 92/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 92 (92)/E: 92 (92).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 94/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 94 (94)/E: 94 (94).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 0.9/inf. Active evaluations: 2.\n",
+      " Counted trials: 96/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 96 (96)/E: 96 (96).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:22 ###\n",
+      " Running. Runtime: 1.0/inf. Active evaluations: 2.\n",
+      " Counted trials: 98/100.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 98 (98)/E: 98 (98).\n",
+      "Finished run eliza-florence in 0.97s. Starting shutdown...\n",
+      "Saved top 5 suggestions into run_eliza-florence.\n",
+      "Successfully and peacefully shut down pool.\n"
+     ]
+    }
+   ],
+   "source": [
+    "search = cmlkit.tune.Hyperopt(space, method=\"tpe\")  # reset the search\n",
+    "run = cmlkit.tune.Run(\n",
+    "    search=search,\n",
+    "    evaluator=F(),\n",
+    "    stop={\"stop_max\": {\"count\": 100}},  # specify the stopping mechanism: simply run until 100 trials\n",
+    "    context={\"max_workers\": 1},  # number of parallel workers\n",
+    ")\n",
+    "run.prepare()  # get ready...\n",
+    "run.run()  # let's go!\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "On the backend, a couple of notable things happened just now:\n",
+    "\n",
+    "- We made a new `Run`, which gave itself a randomly assigned, human-readable name,\n",
+    "- It made a folder for itself, called `run_{name}` (that's what `.prepare` does),\n",
+    "- It ran the optimisation (essentially, getting suggestions, dispatching their evaluation to the workers, and submitting the results back to the `Search`),\n",
+    "- It stored the results in an internal database, and\n",
+    "- It wrote every step of the run into a linear record, the `tape`.\n",
+    "\n",
+    "It also wrote out this `tape` into the folder as a starting point for continuing the run, and the top 5 results as `.yaml` files. (And a periodically updated `status.txt` file that you can easily `watch cat` on a remote system.)\n",
+    "\n",
+    "First, let's have a look at the results:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'x': 1.5818042514930213, 'y': 1.2657000758009747, 'z': 0.7601900721957833},\n",
+       " {'x': 1.3427491107976572, 'y': 1.3691821817415368, 'z': 1.245311886247032},\n",
+       " {'x': 1.1339357615854369, 'y': 1.9944778370469811, 'z': 1.014278646077928},\n",
+       " {'x': 1.9992908531539673, 'y': 0.9328044470562182, 'z': 1.3873738957769364},\n",
+       " {'x': 1.8024375112719662, 'y': 0.9385405419811872, 'z': 0.9343264250866565}]"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "run.state.evals.top_suggestions()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'x': 1.5818042514930213, 'y': 1.2657000758009747, 'z': 0.7601900721957833}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# or alternatively, we can just read from disk:\n",
+    "print(cmlkit.read_yaml(run.work_directory / \"suggestion-0\"))\n",
+    "# this is the current best result."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As you can see, we've done *alright* on our toy optimisation problem. `hyperopt` is really not build for such low-dimensional problems! But, as you've suspected, winning the toy problem was not the real point...\n",
+    "\n",
+    "Let's have a quick peek behind the curtain at the `tape`, the record of the optimisation:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'suggest': {'suggestion': {'x': 0.47430154100580957,\n",
+       "    'y': 1.1808824523028227,\n",
+       "    'z': 1.456060182509149},\n",
+       "   'tid': 0}},\n",
+       " {'suggest': {'suggestion': {'x': 0.17493917371880396,\n",
+       "    'y': 0.7352477275170646,\n",
+       "    'z': 1.7173875395185256},\n",
+       "   'tid': 1}},\n",
+       " {'submit': {'result': {'ok': {'loss': 7.518743918765714,\n",
+       "     'suggestion': {'x': 0.17493917371880396,\n",
+       "      'y': 0.7352477275170646,\n",
+       "      'z': 1.7173875395185256}}},\n",
+       "   'tid': 1}},\n",
+       " {'submit': {'result': {'ok': {'loss': 4.35464735468655,\n",
+       "     'suggestion': {'x': 0.47430154100580957,\n",
+       "      'y': 1.1808824523028227,\n",
+       "      'z': 1.456060182509149}}},\n",
+       "   'tid': 0}}]"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "run.state.tape.raw[0:4]  # raw just gets us something subscriptable"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We see that there are two types of entires: \n",
+    "\n",
+    "- `\"suggest\"`: We get a suggestion from the `Search`.\n",
+    "- `\"submit\"`: We return a result to the `Search`.\n",
+    "\n",
+    "If we replay them in order, we arrive at the exact same state of the optimisation. This is how we, for instance, restart a `Run`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Starting run restore...\n",
+      "Parallel support on macOS is a bit wonky. Proceed with caution.\n",
+      "Recovered runner eliza-florence in folder run_eliza-florence.\n",
+      "Re-submitting 2 trials to the pool.\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.0/inf. Active evaluations: 2.\n",
+      " Counted trials: 100/200.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 2/T: 100 (100)/E: 100 (100).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 5.\n",
+      " Counted trials: 102/200.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 5/T: 102 (102)/E: 102 (102).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.1/inf. Active evaluations: 5.\n",
+      " Counted trials: 107/200.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 5/T: 107 (107)/E: 107 (107).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 5.\n",
+      " Counted trials: 112/200.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 5/T: 112 (112)/E: 112 (112).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 5.\n",
+      " Counted trials: 117/200.\n",
+      " Best 3: 0.0575 0.1124 0.1371. Live: 5/T: 117 (117)/E: 117 (117).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.2/inf. Active evaluations: 5.\n",
+      " Counted trials: 122/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 122 (122)/E: 122 (122).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 5.\n",
+      " Counted trials: 127/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 127 (127)/E: 127 (127).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 5.\n",
+      " Counted trials: 132/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 132 (132)/E: 132 (132).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.3/inf. Active evaluations: 5.\n",
+      " Counted trials: 137/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 137 (137)/E: 137 (137).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 5.\n",
+      " Counted trials: 142/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 142 (142)/E: 142 (142).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 5.\n",
+      " Counted trials: 147/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 147 (147)/E: 147 (147).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.4/inf. Active evaluations: 5.\n",
+      " Counted trials: 152/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 152 (152)/E: 152 (152).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 5.\n",
+      " Counted trials: 157/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 157 (157)/E: 157 (157).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 5.\n",
+      " Counted trials: 162/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 162 (162)/E: 162 (162).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.5/inf. Active evaluations: 5.\n",
+      " Counted trials: 167/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 167 (167)/E: 167 (167).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 5.\n",
+      " Counted trials: 172/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 172 (172)/E: 172 (172).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.6/inf. Active evaluations: 5.\n",
+      " Counted trials: 177/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 177 (177)/E: 177 (177).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 5.\n",
+      " Counted trials: 182/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 182 (182)/E: 182 (182).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 5.\n",
+      " Counted trials: 187/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 187 (187)/E: 187 (187).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 5.\n",
+      " Counted trials: 192/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 192 (192)/E: 192 (192).\n",
+      "### Status of run eliza-florence at 2020-02-25 16:35:24 ###\n",
+      " Running. Runtime: 0.7/inf. Active evaluations: 5.\n",
+      " Counted trials: 197/200.\n",
+      " Best 3: 0.0575 0.1124 0.1255. Live: 5/T: 197 (197)/E: 197 (197).\n",
+      "Finished run eliza-florence in 0.78s. Starting shutdown...\n",
+      "Saved top 5 suggestions into run_eliza-florence.\n",
+      "Successfully and peacefully shut down pool.\n"
+     ]
+    }
+   ],
+   "source": [
+    "new = cmlkit.tune.Run.restore(\n",
+    "    run.work_directory,\n",
+    "    new_stop={\"stop_max\": {\"count\": 200}}, # we overwrite the stopping directive to run another 100 steps!\n",
+    ")\n",
+    "new.run()  # let's go"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Alright! At this point, we've seen most of what the `cmlkit.tune` module does. To end this tutorial, we will optimise an actual model, not a toy `Evaluator`. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### A Real Problem\n",
+    "\n",
+    "We will use a search space for SOAP:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "space = {\n",
+    "    \"model\": {\n",
+    "        \"per\": \"cell\",\n",
+    "        \"regression\": {\n",
+    "            \"krr\": {\n",
+    "                \"kernel\": {\n",
+    "                    \"kernel_atomic\": {\n",
+    "                        \"norm\": False,\n",
+    "                        \"kernelf\": {\n",
+    "                            \"gaussian\": {\n",
+    "                                \"ls\": [\"hp_loggrid\", \"ls_start\", -13, 13, 27]  # base2 loggrid, i.e 2**-13 to 2**13\n",
+    "                            }\n",
+    "                        },\n",
+    "                    }\n",
+    "                },\n",
+    "                \"nl\": [\"hp_loggrid\", \"nl_start\", -18, 0, 19]\n",
+    "            }\n",
+    "        },\n",
+    "        \"representation\": {\n",
+    "            \"ds_soap\": {\n",
+    "                \"elems\": [8, 13, 31, 49],\n",
+    "                \"n_max\": [\"hp_choice\", \"n_max\", [2, 3, 4, 5, 6, 7, 8]],\n",
+    "                \"l_max\": [\"hp_choice\", \"l_max\", [2, 3, 4, 5, 6, 7, 8]],\n",
+    "                \"cutoff\": [\"hp_choice\", \"cutoff\", [2, 3, 4, 5, 6, 7, 8, 9, 10]],\n",
+    "                \"sigma\": [\"hp_loggrid\", \"sigma\", -20, 6, 27],\n",
+    "                \"rbf\": \"gto\",\n",
+    "            }\n",
+    "        },\n",
+    "    }\n",
+    "}\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We'll use a \"simple\" evaluator, `cmlkit.tune.TuneEvaluatorHoldout`, which uses predefined training and test sets to compute a loss, without cross-validation.\n",
+    "\n",
+    "For parallelisation, these sets need to be saved to disk. In order to save us some time, I've already rolled these splits (from the original kaggle challenge training set) and saved them:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "800\n",
+      "200\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(cmlkit.load_dataset(\"nmd18_hpo_train\").n)\n",
+    "print(cmlkit.load_dataset(\"nmd18_hpo_test\").n)\n",
+    "evaluator = cmlkit.tune.TuneEvaluatorHoldout(\n",
+    "    train=\"nmd18_hpo_train\", test=\"nmd18_hpo_test\", target=\"fe\", lossf=\"rmse\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can also instantiate our Search!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'model': {'per': 'cell', 'regression': {'krr': {'kernel': {'kernel_atomic': {'kernelf': {'gaussian': {'ls': 512.0}}, 'norm': False}}, 'nl': 3.814697265625e-06}}, 'representation': {'ds_soap': {'cutoff': 3, 'elems': [8, 13, 31, 49], 'l_max': 4, 'n_max': 7, 'rbf': 'gto', 'sigma': 1.52587890625e-05}}}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "search = cmlkit.tune.Hyperopt(space, method=\"tpe\")\n",
+    "s = search.suggest()[1]\n",
+    "print(s)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, every sample from the `Search` is an entire `Model` config! We're ready to roll."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = cmlkit.tune.Hyperopt(space, method=\"tpe\")\n",
+    "run = cmlkit.tune.Run(\n",
+    "    search=search,\n",
+    "    evaluator=evaluator,\n",
+    "    stop={\"stop_max\": {\"count\": 400}},\n",
+    "    context={\"max_workers\": 2},\n",
+    "    name=\"nmd18_hpo\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ok, I'll come clean -- we will not actually run this optimisation, to spare you the experience of waiting for a couple of hours. The `nmd18` dataset contains large structures, and periodic boundary conditions, which makes calculations for any sizeable non-toy training/test sets impractically slow for a tutorial like this. So, let's skip straight to the results!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Starting run checkout... (this will not yield a runnable instance).\n"
+     ]
+    }
+   ],
+   "source": [
+    "run = cmlkit.tune.Run.checkout(\"run_nmd18_hpo\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "By the way, this is how you access the results of already finished runs! You simply run `checkout`.\n",
+    "\n",
+    "To end, let's check how our model would have done in the 2018 Kaggle challenge."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_config = run.state.evals.top_suggestions()[0]\n",
+    "model = cmlkit.from_config(model_config)\n",
+    "# print(evaluator(model))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train = cmlkit.load_dataset(\"nmd18_train\")\n",
+    "test = cmlkit.load_dataset(\"nmd18_test\")\n",
+    "\n",
+    "model.train(train, target=\"fe\")\n",
+    "pred = model.predict(test, per=\"cation\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'rmse': 0.028560676712279628,\n",
+       " 'rmsle': 0.021981674732855568,\n",
+       " 'mae': 0.014663798738294022,\n",
+       " 'r2': 0.9281975816871104}"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "true = test.pp(\"fe\", per=\"cation\")\n",
+    "loss = cmlkit.evaluation.get_loss(\"rmse\", \"rmsle\", \"mae\", \"r2\")\n",
+    "loss(true, pred)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Congratulations! We've gotten close to the top of the Kaggle 2018 challenge. (For the full results and discussion, please see [Sutton *et al.* (2019)](https://doi.org/10.1038/s41524-019-0239-3).)\n",
+    "\n",
+    "## Next steps ☀️\n",
+    "\n",
+    "And with this, we're at the end of this tutorial. Well done!\n",
+    "\n",
+    "As a next step, I would recommend taking a good look at the [repository](https://github.com/sirmarcel/cmlkit/). The readme will essentially reiterate this tutorial, so you can skip it, but it is recommended to simply [browse the source  code](https://github.com/sirmarcel/cmlkit/tree/develop-2.0/cmlkit). Every submodule has a detailed explanation of its mechanics and interfaces.\n",
+    "\n",
+    "If you're interested in how `cmlkit` is used in production, you can also take a look at [`repbench`]( https://marcel.science/repbench ), which is a benchmarking effort for multiple representations, and the origin of `cmlkit`.\n",
+    "\n",
+    "And then, start building! \n",
+    "\n",
+    "*festina lente*"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Thanks to: Xiaojuan Hu, Thomas Purcell, Daniel Speckhard, and Marcin Krynski for feedback on this tutorial.\n",
+    "\n",
+    "The technical requirements for running this tutorial are:\n",
+    "\n",
+    "- [`cmlkit`](https://marcel.science/cmlkit) with its dependencies (most notably `qmmlpack`)\n",
+    "- `cscribe` plugin for `cmlkit`\n",
+    "- `seaborn` (and `matplotlib`, etc.)\n",
+    "- `jupyter`\n",
+    "\n",
+    "You also need the tutorial repository, and the environment variables `CML_PLUGINS=cscribe` and `CML_DATASET_PATH=data/` to be set.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "cmlkit_tutorial_nomad",
+   "language": "python",
+   "name": "cmlkit_tutorial_nomad"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/data/.gitignore b/data/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..86d0cb2726c6c7c179b99520c452dd1b68e7a813
--- /dev/null
+++ b/data/.gitignore
@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore
\ No newline at end of file
diff --git a/metainfo.json b/metainfo.json
new file mode 100644
index 0000000000000000000000000000000000000000..ebdd0c065b4636a9b105ce53e73bb8c66674258f
--- /dev/null
+++ b/metainfo.json
@@ -0,0 +1,41 @@
+{
+  "authors": [
+    "Langer, Marcel"
+  ],
+  "email": "langer@fhi-berlin.mpg.de",
+  "title": "cmlkit tutorial",
+  "description": "In this tutorial we will get to know cmlkit, a python package for specifying, evaluating, and optimising machine learning models, and use it to compete in the Nomad 2018 Kaggle challenge.",
+  "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-tutorial-template",
+  "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/Welcome.ipynb",
+  "created": "",
+  "updated": "",
+  "flags":{
+    "isPublic": false,
+    "featured": false,
+    "top_of_list": false
+  },
+  "labels": {
+    "application_keyword": [
+      "Formation energy prediction"
+    ],
+    "application_section": [
+      "Materials property prediction"
+    ],
+    "application_system": [
+      "Group-III oxidess"
+    ],
+    "category": [
+      "Tutorial"
+    ],
+    "data_analytics_method": [
+      "Kernel ridge regression",
+      "SOAP",
+      "MBTR",
+      "Symmetry Functions",
+    ],
+    "platform": [
+      "jupyter"
+    ]
+
+  }
+}
\ No newline at end of file
diff --git a/run_nmd18_hpo/log.log b/run_nmd18_hpo/log.log
new file mode 100644
index 0000000000000000000000000000000000000000..d37ec42fae35e56e342d9bbcdb8f3eb7244b158e
--- /dev/null
+++ b/run_nmd18_hpo/log.log
@@ -0,0 +1,3085 @@
+Prepared runner nmd18_hpo in folder run_nmd18_hpo.
+### Status of run nmd18_hpo at 2020-02-24 11:56:47 ###
+ Running. Runtime: 0.0/inf. Active evaluations: 0.
+ Counted trials: 0/400.
+ Best 3:. Live: 0/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:56:48 ###
+ Running. Runtime: 0.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:56:53 ###
+ Running. Runtime: 5.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:56:58 ###
+ Running. Runtime: 10.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:03 ###
+ Running. Runtime: 15.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:08 ###
+ Running. Runtime: 20.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:13 ###
+ Running. Runtime: 25.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:18 ###
+ Running. Runtime: 30.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:23 ###
+ Running. Runtime: 35.9/inf. Active evaluations: 41.
+ Counted trials: 0/400.
+ Best 3:. Live: 41/T: 0 (0)/E: 0 (0).
+### Status of run nmd18_hpo at 2020-02-24 11:57:26 ###
+ Running. Runtime: 39.5/inf. Active evaluations: 41.
+ Counted trials: 1/400.
+ Best 3: 0.1038. Live: 41/T: 1 (1)/E: 1 (1).
+### Status of run nmd18_hpo at 2020-02-24 11:57:31 ###
+ Running. Runtime: 43.9/inf. Active evaluations: 41.
+ Counted trials: 2/400.
+ Best 3: 0.0483 0.1038. Live: 41/T: 2 (2)/E: 2 (2).
+### Status of run nmd18_hpo at 2020-02-24 11:57:32 ###
+ Running. Runtime: 45.2/inf. Active evaluations: 41.
+ Counted trials: 3/400.
+ Best 3: 0.0483 0.1038 0.1038. Live: 41/T: 3 (3)/E: 3 (3).
+### Status of run nmd18_hpo at 2020-02-24 11:57:32 ###
+ Running. Runtime: 45.5/inf. Active evaluations: 41.
+ Counted trials: 4/400.
+ Best 3: 0.0483 0.1038 0.1038. Live: 41/T: 4 (4)/E: 4 (4).
+### Status of run nmd18_hpo at 2020-02-24 11:57:35 ###
+ Running. Runtime: 48.1/inf. Active evaluations: 41.
+ Counted trials: 5/400.
+ Best 3: 0.0483 0.1038 0.1038. Live: 41/T: 5 (5)/E: 5 (5).
+### Status of run nmd18_hpo at 2020-02-24 11:57:36 ###
+ Running. Runtime: 49.4/inf. Active evaluations: 41.
+ Counted trials: 6/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 6 (6)/E: 6 (6).
+### Status of run nmd18_hpo at 2020-02-24 11:57:41 ###
+ Running. Runtime: 54.0/inf. Active evaluations: 41.
+ Counted trials: 7/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 7 (7)/E: 7 (7).
+### Status of run nmd18_hpo at 2020-02-24 11:57:46 ###
+ Running. Runtime: 59.0/inf. Active evaluations: 41.
+ Counted trials: 7/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 7 (7)/E: 7 (7).
+### Status of run nmd18_hpo at 2020-02-24 11:57:51 ###
+ Running. Runtime: 64.1/inf. Active evaluations: 41.
+ Counted trials: 7/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 7 (7)/E: 7 (7).
+### Status of run nmd18_hpo at 2020-02-24 11:57:56 ###
+ Running. Runtime: 69.1/inf. Active evaluations: 41.
+ Counted trials: 7/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 7 (7)/E: 7 (7).
+### Status of run nmd18_hpo at 2020-02-24 11:57:58 ###
+ Running. Runtime: 71.5/inf. Active evaluations: 41.
+ Counted trials: 8/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 8 (7)/E: 8 (7).
+ {'QMMLException': 1}
+### Status of run nmd18_hpo at 2020-02-24 11:57:59 ###
+ Running. Runtime: 72.2/inf. Active evaluations: 41.
+ Counted trials: 9/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 9 (8)/E: 9 (8).
+ {'QMMLException': 1}
+### Status of run nmd18_hpo at 2020-02-24 11:58:01 ###
+ Running. Runtime: 74.1/inf. Active evaluations: 41.
+ Counted trials: 10/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 10 (8)/E: 10 (8).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:06 ###
+ Running. Runtime: 79.1/inf. Active evaluations: 41.
+ Counted trials: 10/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 10 (8)/E: 10 (8).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:11 ###
+ Running. Runtime: 84.1/inf. Active evaluations: 41.
+ Counted trials: 10/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 10 (8)/E: 10 (8).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:16 ###
+ Running. Runtime: 89.1/inf. Active evaluations: 41.
+ Counted trials: 10/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 10 (8)/E: 10 (8).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:21 ###
+ Running. Runtime: 94.1/inf. Active evaluations: 41.
+ Counted trials: 10/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 10 (8)/E: 10 (8).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:22 ###
+ Running. Runtime: 95.5/inf. Active evaluations: 41.
+ Counted trials: 11/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 11 (9)/E: 11 (9).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:24 ###
+ Running. Runtime: 97.7/inf. Active evaluations: 41.
+ Counted trials: 12/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 12 (10)/E: 12 (10).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:26 ###
+ Running. Runtime: 99.8/inf. Active evaluations: 41.
+ Counted trials: 13/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 13 (11)/E: 13 (11).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:31 ###
+ Running. Runtime: 104.8/inf. Active evaluations: 41.
+ Counted trials: 13/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 13 (11)/E: 13 (11).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:34 ###
+ Running. Runtime: 107.0/inf. Active evaluations: 41.
+ Counted trials: 14/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 14 (12)/E: 14 (12).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:39 ###
+ Running. Runtime: 112.0/inf. Active evaluations: 41.
+ Counted trials: 14/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 14 (12)/E: 14 (12).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:44 ###
+ Running. Runtime: 117.1/inf. Active evaluations: 41.
+ Counted trials: 14/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 14 (12)/E: 14 (12).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:48 ###
+ Running. Runtime: 121.6/inf. Active evaluations: 41.
+ Counted trials: 15/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 15 (13)/E: 15 (13).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:49 ###
+ Running. Runtime: 122.4/inf. Active evaluations: 41.
+ Counted trials: 16/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 16 (14)/E: 16 (14).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:49 ###
+ Running. Runtime: 122.4/inf. Active evaluations: 41.
+ Counted trials: 17/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 17 (15)/E: 16 (14).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:51 ###
+ Running. Runtime: 124.7/inf. Active evaluations: 41.
+ Counted trials: 18/400.
+ Best 3: 0.0483 0.1034 0.1038. Live: 41/T: 18 (16)/E: 17 (15).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:56 ###
+ Running. Runtime: 129.6/inf. Active evaluations: 41.
+ Counted trials: 19/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 19 (17)/E: 18 (16).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:58:57 ###
+ Running. Runtime: 130.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:02 ###
+ Running. Runtime: 135.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:07 ###
+ Running. Runtime: 140.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:12 ###
+ Running. Runtime: 145.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:17 ###
+ Running. Runtime: 150.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:22 ###
+ Running. Runtime: 155.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:27 ###
+ Running. Runtime: 160.6/inf. Active evaluations: 41.
+ Counted trials: 20/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 20 (18)/E: 19 (17).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:31 ###
+ Running. Runtime: 164.3/inf. Active evaluations: 41.
+ Counted trials: 21/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 21 (19)/E: 20 (18).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:36 ###
+ Running. Runtime: 169.3/inf. Active evaluations: 41.
+ Counted trials: 21/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 21 (19)/E: 20 (18).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:36 ###
+ Running. Runtime: 169.7/inf. Active evaluations: 41.
+ Counted trials: 22/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 22 (20)/E: 21 (19).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:40 ###
+ Running. Runtime: 173.4/inf. Active evaluations: 41.
+ Counted trials: 23/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 23 (21)/E: 22 (20).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:41 ###
+ Running. Runtime: 174.5/inf. Active evaluations: 41.
+ Counted trials: 24/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 24 (22)/E: 23 (21).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:46 ###
+ Running. Runtime: 179.5/inf. Active evaluations: 41.
+ Counted trials: 24/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 24 (22)/E: 23 (21).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:46 ###
+ Running. Runtime: 179.6/inf. Active evaluations: 41.
+ Counted trials: 25/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 25 (23)/E: 24 (22).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:51 ###
+ Running. Runtime: 184.6/inf. Active evaluations: 41.
+ Counted trials: 25/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 25 (23)/E: 24 (22).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:56 ###
+ Running. Runtime: 189.6/inf. Active evaluations: 41.
+ Counted trials: 25/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 25 (23)/E: 24 (22).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:58 ###
+ Running. Runtime: 191.1/inf. Active evaluations: 41.
+ Counted trials: 26/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 26 (24)/E: 25 (23).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 11:59:59 ###
+ Running. Runtime: 192.7/inf. Active evaluations: 41.
+ Counted trials: 27/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 27 (25)/E: 26 (24).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:01 ###
+ Running. Runtime: 193.8/inf. Active evaluations: 41.
+ Counted trials: 28/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 28 (26)/E: 27 (25).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:03 ###
+ Running. Runtime: 196.8/inf. Active evaluations: 41.
+ Counted trials: 29/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 29 (27)/E: 28 (26).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:05 ###
+ Running. Runtime: 198.7/inf. Active evaluations: 41.
+ Counted trials: 30/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 30 (28)/E: 29 (27).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:10 ###
+ Running. Runtime: 203.7/inf. Active evaluations: 41.
+ Counted trials: 30/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 30 (28)/E: 29 (27).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:11 ###
+ Running. Runtime: 204.7/inf. Active evaluations: 41.
+ Counted trials: 31/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 31 (29)/E: 30 (28).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:12 ###
+ Running. Runtime: 205.2/inf. Active evaluations: 41.
+ Counted trials: 32/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 32 (30)/E: 31 (29).
+ {'QMMLException': 2}
+### Status of run nmd18_hpo at 2020-02-24 12:00:16 ###
+ Running. Runtime: 208.9/inf. Active evaluations: 41.
+ Counted trials: 33/400.
+ Best 3: 0.0483 0.0949 0.1034. Live: 41/T: 33 (30)/E: 32 (29).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:17 ###
+ Running. Runtime: 210.1/inf. Active evaluations: 41.
+ Counted trials: 34/400.
+ Best 3: 0.0359 0.0483 0.0949. Live: 41/T: 34 (31)/E: 33 (30).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:19 ###
+ Running. Runtime: 212.4/inf. Active evaluations: 41.
+ Counted trials: 35/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 35 (32)/E: 34 (31).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:21 ###
+ Running. Runtime: 214.0/inf. Active evaluations: 41.
+ Counted trials: 36/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 36 (33)/E: 35 (32).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:21 ###
+ Running. Runtime: 214.1/inf. Active evaluations: 41.
+ Counted trials: 37/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 37 (34)/E: 36 (33).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:26 ###
+ Running. Runtime: 219.1/inf. Active evaluations: 41.
+ Counted trials: 37/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 37 (34)/E: 36 (33).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:27 ###
+ Running. Runtime: 220.1/inf. Active evaluations: 41.
+ Counted trials: 38/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 38 (35)/E: 37 (34).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:27 ###
+ Running. Runtime: 220.3/inf. Active evaluations: 41.
+ Counted trials: 39/400.
+ Best 3: 0.0244 0.0359 0.0483. Live: 41/T: 39 (36)/E: 38 (35).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:29 ###
+ Running. Runtime: 222.4/inf. Active evaluations: 41.
+ Counted trials: 40/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 40 (37)/E: 39 (36).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:31 ###
+ Running. Runtime: 224.7/inf. Active evaluations: 41.
+ Counted trials: 41/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 41 (38)/E: 40 (37).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:35 ###
+ Running. Runtime: 228.6/inf. Active evaluations: 41.
+ Counted trials: 42/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 42 (39)/E: 41 (38).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:37 ###
+ Running. Runtime: 230.4/inf. Active evaluations: 41.
+ Counted trials: 43/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 43 (40)/E: 42 (39).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:42 ###
+ Running. Runtime: 235.4/inf. Active evaluations: 41.
+ Counted trials: 43/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 43 (40)/E: 42 (39).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:43 ###
+ Running. Runtime: 236.4/inf. Active evaluations: 41.
+ Counted trials: 44/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 44 (41)/E: 43 (40).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:47 ###
+ Running. Runtime: 240.3/inf. Active evaluations: 41.
+ Counted trials: 45/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 45 (42)/E: 44 (41).
+ {'QMMLException': 3}
+### Status of run nmd18_hpo at 2020-02-24 12:00:50 ###
+ Running. Runtime: 243.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:00:55 ###
+ Running. Runtime: 248.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:00 ###
+ Running. Runtime: 253.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:05 ###
+ Running. Runtime: 258.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:10 ###
+ Running. Runtime: 263.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:15 ###
+ Running. Runtime: 268.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:20 ###
+ Running. Runtime: 273.4/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:25 ###
+ Running. Runtime: 278.5/inf. Active evaluations: 41.
+ Counted trials: 46/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 46 (42)/E: 45 (41).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:29 ###
+ Running. Runtime: 282.4/inf. Active evaluations: 41.
+ Counted trials: 47/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 47 (43)/E: 46 (42).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:34 ###
+ Running. Runtime: 287.4/inf. Active evaluations: 41.
+ Counted trials: 47/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 47 (43)/E: 46 (42).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:34 ###
+ Running. Runtime: 287.7/inf. Active evaluations: 41.
+ Counted trials: 48/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 48 (44)/E: 47 (43).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:39 ###
+ Running. Runtime: 292.7/inf. Active evaluations: 41.
+ Counted trials: 48/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 48 (44)/E: 47 (43).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:41 ###
+ Running. Runtime: 294.2/inf. Active evaluations: 41.
+ Counted trials: 49/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 49 (45)/E: 48 (44).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:46 ###
+ Running. Runtime: 299.2/inf. Active evaluations: 41.
+ Counted trials: 49/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 49 (45)/E: 48 (44).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:47 ###
+ Running. Runtime: 300.2/inf. Active evaluations: 41.
+ Counted trials: 50/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 50 (46)/E: 49 (45).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:48 ###
+ Running. Runtime: 301.3/inf. Active evaluations: 41.
+ Counted trials: 51/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 51 (47)/E: 50 (46).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:52 ###
+ Running. Runtime: 305.2/inf. Active evaluations: 41.
+ Counted trials: 52/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 52 (48)/E: 51 (47).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:01:57 ###
+ Running. Runtime: 310.3/inf. Active evaluations: 41.
+ Counted trials: 52/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 52 (48)/E: 51 (47).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:02 ###
+ Running. Runtime: 315.3/inf. Active evaluations: 41.
+ Counted trials: 52/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 52 (48)/E: 51 (47).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:04 ###
+ Running. Runtime: 317.5/inf. Active evaluations: 41.
+ Counted trials: 53/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 53 (49)/E: 52 (48).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:04 ###
+ Running. Runtime: 317.7/inf. Active evaluations: 41.
+ Counted trials: 54/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 54 (50)/E: 53 (49).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:06 ###
+ Running. Runtime: 318.8/inf. Active evaluations: 41.
+ Counted trials: 55/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 55 (51)/E: 54 (50).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:11 ###
+ Running. Runtime: 323.9/inf. Active evaluations: 41.
+ Counted trials: 55/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 55 (51)/E: 54 (50).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:12 ###
+ Running. Runtime: 325.7/inf. Active evaluations: 41.
+ Counted trials: 56/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 56 (52)/E: 55 (51).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:12 ###
+ Running. Runtime: 325.8/inf. Active evaluations: 41.
+ Counted trials: 58/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 58 (54)/E: 56 (52).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:13 ###
+ Running. Runtime: 326.0/inf. Active evaluations: 41.
+ Counted trials: 59/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 59 (55)/E: 57 (53).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:18 ###
+ Running. Runtime: 331.0/inf. Active evaluations: 41.
+ Counted trials: 59/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 59 (55)/E: 57 (53).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:23 ###
+ Running. Runtime: 336.0/inf. Active evaluations: 41.
+ Counted trials: 59/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 59 (55)/E: 57 (53).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:26 ###
+ Running. Runtime: 339.3/inf. Active evaluations: 41.
+ Counted trials: 60/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 60 (56)/E: 58 (54).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:31 ###
+ Running. Runtime: 344.4/inf. Active evaluations: 41.
+ Counted trials: 60/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 60 (56)/E: 58 (54).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:32 ###
+ Running. Runtime: 345.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:37 ###
+ Running. Runtime: 350.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:42 ###
+ Running. Runtime: 355.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:47 ###
+ Running. Runtime: 360.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:52 ###
+ Running. Runtime: 365.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:57 ###
+ Running. Runtime: 370.2/inf. Active evaluations: 41.
+ Counted trials: 61/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 61 (57)/E: 59 (55).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:02:57 ###
+ Running. Runtime: 370.3/inf. Active evaluations: 41.
+ Counted trials: 62/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 62 (58)/E: 60 (56).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:01 ###
+ Running. Runtime: 374.1/inf. Active evaluations: 41.
+ Counted trials: 63/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 63 (59)/E: 61 (57).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:06 ###
+ Running. Runtime: 379.1/inf. Active evaluations: 41.
+ Counted trials: 63/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 63 (59)/E: 61 (57).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:06 ###
+ Running. Runtime: 379.3/inf. Active evaluations: 41.
+ Counted trials: 64/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 64 (60)/E: 62 (58).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:11 ###
+ Running. Runtime: 383.9/inf. Active evaluations: 41.
+ Counted trials: 65/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 65 (61)/E: 62 (58).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:12 ###
+ Running. Runtime: 385.6/inf. Active evaluations: 41.
+ Counted trials: 66/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 66 (62)/E: 62 (58).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:13 ###
+ Running. Runtime: 386.2/inf. Active evaluations: 41.
+ Counted trials: 67/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 67 (63)/E: 63 (59).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:14 ###
+ Running. Runtime: 387.1/inf. Active evaluations: 41.
+ Counted trials: 68/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 68 (64)/E: 64 (60).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:19 ###
+ Running. Runtime: 392.1/inf. Active evaluations: 41.
+ Counted trials: 68/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 68 (64)/E: 64 (60).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:24 ###
+ Running. Runtime: 397.1/inf. Active evaluations: 41.
+ Counted trials: 68/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 68 (64)/E: 64 (60).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:25 ###
+ Running. Runtime: 398.3/inf. Active evaluations: 41.
+ Counted trials: 69/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 69 (65)/E: 65 (61).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:30 ###
+ Running. Runtime: 403.3/inf. Active evaluations: 41.
+ Counted trials: 69/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 69 (65)/E: 65 (61).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:32 ###
+ Running. Runtime: 404.9/inf. Active evaluations: 41.
+ Counted trials: 70/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 70 (66)/E: 66 (62).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:32 ###
+ Running. Runtime: 405.3/inf. Active evaluations: 41.
+ Counted trials: 71/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 71 (67)/E: 67 (63).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:37 ###
+ Running. Runtime: 410.3/inf. Active evaluations: 41.
+ Counted trials: 71/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 71 (67)/E: 67 (63).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:42 ###
+ Running. Runtime: 415.0/inf. Active evaluations: 41.
+ Counted trials: 72/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 72 (68)/E: 68 (64).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:47 ###
+ Running. Runtime: 420.0/inf. Active evaluations: 41.
+ Counted trials: 72/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 72 (68)/E: 68 (64).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:49 ###
+ Running. Runtime: 422.6/inf. Active evaluations: 41.
+ Counted trials: 73/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 73 (69)/E: 69 (65).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:54 ###
+ Running. Runtime: 427.6/inf. Active evaluations: 41.
+ Counted trials: 73/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 73 (69)/E: 69 (65).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:03:59 ###
+ Running. Runtime: 432.4/inf. Active evaluations: 41.
+ Counted trials: 74/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 74 (70)/E: 69 (65).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:04 ###
+ Running. Runtime: 437.0/inf. Active evaluations: 41.
+ Counted trials: 75/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 75 (71)/E: 70 (66).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:07 ###
+ Running. Runtime: 440.3/inf. Active evaluations: 41.
+ Counted trials: 76/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 76 (72)/E: 71 (67).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:09 ###
+ Running. Runtime: 442.3/inf. Active evaluations: 41.
+ Counted trials: 77/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 77 (73)/E: 71 (67).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:14 ###
+ Running. Runtime: 447.3/inf. Active evaluations: 41.
+ Counted trials: 77/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 77 (73)/E: 71 (67).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:19 ###
+ Running. Runtime: 452.3/inf. Active evaluations: 41.
+ Counted trials: 77/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 77 (73)/E: 71 (67).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:20 ###
+ Running. Runtime: 453.1/inf. Active evaluations: 41.
+ Counted trials: 78/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 78 (74)/E: 72 (68).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:24 ###
+ Running. Runtime: 457.0/inf. Active evaluations: 41.
+ Counted trials: 79/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 79 (75)/E: 73 (69).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:26 ###
+ Running. Runtime: 458.8/inf. Active evaluations: 41.
+ Counted trials: 80/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 80 (76)/E: 74 (70).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:26 ###
+ Running. Runtime: 459.6/inf. Active evaluations: 41.
+ Counted trials: 81/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 81 (77)/E: 75 (71).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:29 ###
+ Running. Runtime: 461.8/inf. Active evaluations: 41.
+ Counted trials: 82/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 82 (78)/E: 76 (72).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:29 ###
+ Running. Runtime: 462.0/inf. Active evaluations: 41.
+ Counted trials: 83/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 83 (79)/E: 77 (73).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:34 ###
+ Running. Runtime: 467.0/inf. Active evaluations: 41.
+ Counted trials: 83/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 83 (79)/E: 77 (73).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:38 ###
+ Running. Runtime: 471.2/inf. Active evaluations: 41.
+ Counted trials: 84/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 84 (80)/E: 78 (74).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:38 ###
+ Running. Runtime: 471.6/inf. Active evaluations: 41.
+ Counted trials: 85/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 85 (81)/E: 78 (74).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:43 ###
+ Running. Runtime: 476.6/inf. Active evaluations: 41.
+ Counted trials: 85/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 85 (81)/E: 78 (74).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:47 ###
+ Running. Runtime: 480.2/inf. Active evaluations: 41.
+ Counted trials: 86/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 86 (82)/E: 79 (75).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:51 ###
+ Running. Runtime: 484.4/inf. Active evaluations: 41.
+ Counted trials: 87/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 87 (83)/E: 80 (76).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:55 ###
+ Running. Runtime: 488.6/inf. Active evaluations: 41.
+ Counted trials: 88/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 88 (84)/E: 81 (77).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:04:59 ###
+ Running. Runtime: 492.0/inf. Active evaluations: 41.
+ Counted trials: 89/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 89 (85)/E: 82 (78).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:01 ###
+ Running. Runtime: 494.8/inf. Active evaluations: 41.
+ Counted trials: 90/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 90 (86)/E: 83 (79).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:06 ###
+ Running. Runtime: 499.8/inf. Active evaluations: 41.
+ Counted trials: 90/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 90 (86)/E: 83 (79).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:11 ###
+ Running. Runtime: 504.8/inf. Active evaluations: 41.
+ Counted trials: 90/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 90 (86)/E: 83 (79).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:12 ###
+ Running. Runtime: 505.3/inf. Active evaluations: 41.
+ Counted trials: 91/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 91 (87)/E: 83 (79).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:12 ###
+ Running. Runtime: 505.6/inf. Active evaluations: 41.
+ Counted trials: 92/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 92 (88)/E: 84 (80).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:17 ###
+ Running. Runtime: 510.6/inf. Active evaluations: 41.
+ Counted trials: 92/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 92 (88)/E: 84 (80).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:18 ###
+ Running. Runtime: 511.8/inf. Active evaluations: 41.
+ Counted trials: 93/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 93 (89)/E: 85 (81).
+ {'QMMLException': 4}
+### Status of run nmd18_hpo at 2020-02-24 12:05:22 ###
+ Running. Runtime: 515.0/inf. Active evaluations: 41.
+ Counted trials: 94/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 94 (89)/E: 86 (81).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:22 ###
+ Running. Runtime: 515.0/inf. Active evaluations: 41.
+ Counted trials: 95/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 95 (90)/E: 86 (81).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:25 ###
+ Running. Runtime: 517.8/inf. Active evaluations: 41.
+ Counted trials: 96/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 96 (91)/E: 87 (82).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:30 ###
+ Running. Runtime: 522.8/inf. Active evaluations: 41.
+ Counted trials: 96/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 96 (91)/E: 87 (82).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:35 ###
+ Running. Runtime: 527.9/inf. Active evaluations: 41.
+ Counted trials: 97/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 97 (92)/E: 88 (83).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:37 ###
+ Running. Runtime: 530.7/inf. Active evaluations: 41.
+ Counted trials: 98/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 98 (93)/E: 89 (84).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:42 ###
+ Running. Runtime: 535.8/inf. Active evaluations: 41.
+ Counted trials: 98/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 98 (93)/E: 89 (84).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:47 ###
+ Running. Runtime: 540.8/inf. Active evaluations: 41.
+ Counted trials: 98/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 98 (93)/E: 89 (84).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:48 ###
+ Running. Runtime: 540.9/inf. Active evaluations: 41.
+ Counted trials: 99/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 99 (94)/E: 89 (84).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:53 ###
+ Running. Runtime: 545.8/inf. Active evaluations: 41.
+ Counted trials: 100/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 100 (95)/E: 90 (85).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:05:58 ###
+ Running. Runtime: 550.8/inf. Active evaluations: 41.
+ Counted trials: 100/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 100 (95)/E: 90 (85).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:03 ###
+ Running. Runtime: 555.8/inf. Active evaluations: 41.
+ Counted trials: 100/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 100 (95)/E: 90 (85).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:08 ###
+ Running. Runtime: 560.8/inf. Active evaluations: 41.
+ Counted trials: 100/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 100 (95)/E: 90 (85).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:09 ###
+ Running. Runtime: 562.3/inf. Active evaluations: 41.
+ Counted trials: 101/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 101 (96)/E: 91 (86).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:14 ###
+ Running. Runtime: 567.3/inf. Active evaluations: 41.
+ Counted trials: 101/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 101 (96)/E: 91 (86).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:17 ###
+ Running. Runtime: 570.2/inf. Active evaluations: 41.
+ Counted trials: 102/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 102 (97)/E: 92 (87).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:22 ###
+ Running. Runtime: 574.9/inf. Active evaluations: 41.
+ Counted trials: 103/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 103 (98)/E: 93 (88).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:27 ###
+ Running. Runtime: 579.9/inf. Active evaluations: 41.
+ Counted trials: 103/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 103 (98)/E: 93 (88).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:29 ###
+ Running. Runtime: 582.4/inf. Active evaluations: 41.
+ Counted trials: 104/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 104 (99)/E: 93 (88).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:31 ###
+ Running. Runtime: 584.6/inf. Active evaluations: 41.
+ Counted trials: 105/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 105 (100)/E: 94 (89).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:32 ###
+ Running. Runtime: 585.4/inf. Active evaluations: 41.
+ Counted trials: 106/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 106 (101)/E: 95 (90).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:37 ###
+ Running. Runtime: 590.4/inf. Active evaluations: 41.
+ Counted trials: 106/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 106 (101)/E: 95 (90).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:41 ###
+ Running. Runtime: 594.5/inf. Active evaluations: 41.
+ Counted trials: 107/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 107 (102)/E: 96 (91).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:42 ###
+ Running. Runtime: 595.7/inf. Active evaluations: 41.
+ Counted trials: 108/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 108 (103)/E: 96 (91).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:45 ###
+ Running. Runtime: 598.1/inf. Active evaluations: 41.
+ Counted trials: 109/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 109 (104)/E: 97 (92).
+ {'QMMLException': 5}
+### Status of run nmd18_hpo at 2020-02-24 12:06:47 ###
+ Running. Runtime: 600.5/inf. Active evaluations: 41.
+ Counted trials: 110/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 110 (104)/E: 98 (92).
+ {'QMMLException': 6}
+### Status of run nmd18_hpo at 2020-02-24 12:06:52 ###
+ Running. Runtime: 605.5/inf. Active evaluations: 41.
+ Counted trials: 110/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 110 (104)/E: 98 (92).
+ {'QMMLException': 6}
+### Status of run nmd18_hpo at 2020-02-24 12:06:57 ###
+ Running. Runtime: 610.5/inf. Active evaluations: 41.
+ Counted trials: 110/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 110 (104)/E: 98 (92).
+ {'QMMLException': 6}
+### Status of run nmd18_hpo at 2020-02-24 12:06:59 ###
+ Running. Runtime: 612.5/inf. Active evaluations: 41.
+ Counted trials: 111/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 111 (105)/E: 99 (93).
+ {'QMMLException': 6}
+### Status of run nmd18_hpo at 2020-02-24 12:07:04 ###
+ Running. Runtime: 617.1/inf. Active evaluations: 41.
+ Counted trials: 112/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 112 (105)/E: 100 (93).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:09 ###
+ Running. Runtime: 622.1/inf. Active evaluations: 41.
+ Counted trials: 112/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 112 (105)/E: 100 (93).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:09 ###
+ Running. Runtime: 622.4/inf. Active evaluations: 41.
+ Counted trials: 113/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 113 (106)/E: 100 (93).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:13 ###
+ Running. Runtime: 626.5/inf. Active evaluations: 41.
+ Counted trials: 114/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 114 (107)/E: 101 (94).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:14 ###
+ Running. Runtime: 627.1/inf. Active evaluations: 41.
+ Counted trials: 115/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 115 (108)/E: 101 (94).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:19 ###
+ Running. Runtime: 632.1/inf. Active evaluations: 41.
+ Counted trials: 115/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 115 (108)/E: 101 (94).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:20 ###
+ Running. Runtime: 633.4/inf. Active evaluations: 41.
+ Counted trials: 116/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 116 (109)/E: 102 (95).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:22 ###
+ Running. Runtime: 635.5/inf. Active evaluations: 41.
+ Counted trials: 117/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 117 (110)/E: 103 (96).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:25 ###
+ Running. Runtime: 638.7/inf. Active evaluations: 41.
+ Counted trials: 118/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 118 (111)/E: 104 (97).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:25 ###
+ Running. Runtime: 638.7/inf. Active evaluations: 41.
+ Counted trials: 119/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 119 (112)/E: 105 (98).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:26 ###
+ Running. Runtime: 638.8/inf. Active evaluations: 41.
+ Counted trials: 120/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 120 (113)/E: 106 (99).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:28 ###
+ Running. Runtime: 641.0/inf. Active evaluations: 41.
+ Counted trials: 121/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 121 (114)/E: 107 (100).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:30 ###
+ Running. Runtime: 643.4/inf. Active evaluations: 41.
+ Counted trials: 122/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 122 (115)/E: 108 (101).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:34 ###
+ Running. Runtime: 647.4/inf. Active evaluations: 41.
+ Counted trials: 123/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 123 (116)/E: 109 (102).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:38 ###
+ Running. Runtime: 651.4/inf. Active evaluations: 41.
+ Counted trials: 124/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 124 (117)/E: 109 (102).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:40 ###
+ Running. Runtime: 653.5/inf. Active evaluations: 41.
+ Counted trials: 125/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 125 (118)/E: 110 (103).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:40 ###
+ Running. Runtime: 653.6/inf. Active evaluations: 41.
+ Counted trials: 127/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 127 (120)/E: 110 (103).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:40 ###
+ Running. Runtime: 653.6/inf. Active evaluations: 41.
+ Counted trials: 128/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 128 (121)/E: 110 (103).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:45 ###
+ Running. Runtime: 658.6/inf. Active evaluations: 41.
+ Counted trials: 128/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 128 (121)/E: 110 (103).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:47 ###
+ Running. Runtime: 659.8/inf. Active evaluations: 41.
+ Counted trials: 129/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 129 (122)/E: 111 (104).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:48 ###
+ Running. Runtime: 661.0/inf. Active evaluations: 41.
+ Counted trials: 130/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 130 (123)/E: 112 (105).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:53 ###
+ Running. Runtime: 666.0/inf. Active evaluations: 41.
+ Counted trials: 130/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 130 (123)/E: 112 (105).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:55 ###
+ Running. Runtime: 668.7/inf. Active evaluations: 41.
+ Counted trials: 131/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 131 (124)/E: 113 (106).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:07:58 ###
+ Running. Runtime: 670.8/inf. Active evaluations: 41.
+ Counted trials: 132/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 132 (125)/E: 114 (107).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:01 ###
+ Running. Runtime: 674.3/inf. Active evaluations: 41.
+ Counted trials: 133/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 133 (126)/E: 115 (108).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:06 ###
+ Running. Runtime: 679.3/inf. Active evaluations: 41.
+ Counted trials: 133/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 133 (126)/E: 115 (108).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:11 ###
+ Running. Runtime: 684.1/inf. Active evaluations: 41.
+ Counted trials: 134/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 134 (127)/E: 116 (109).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:11 ###
+ Running. Runtime: 684.1/inf. Active evaluations: 41.
+ Counted trials: 135/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 135 (128)/E: 116 (109).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:16 ###
+ Running. Runtime: 689.1/inf. Active evaluations: 41.
+ Counted trials: 135/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 135 (128)/E: 116 (109).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:21 ###
+ Running. Runtime: 694.1/inf. Active evaluations: 41.
+ Counted trials: 135/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 135 (128)/E: 116 (109).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:23 ###
+ Running. Runtime: 695.8/inf. Active evaluations: 41.
+ Counted trials: 136/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 136 (129)/E: 117 (110).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:28 ###
+ Running. Runtime: 700.8/inf. Active evaluations: 41.
+ Counted trials: 136/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 136 (129)/E: 117 (110).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:33 ###
+ Running. Runtime: 705.8/inf. Active evaluations: 41.
+ Counted trials: 136/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 136 (129)/E: 117 (110).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:35 ###
+ Running. Runtime: 708.7/inf. Active evaluations: 41.
+ Counted trials: 137/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 137 (130)/E: 117 (110).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:40 ###
+ Running. Runtime: 713.7/inf. Active evaluations: 41.
+ Counted trials: 137/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 137 (130)/E: 117 (110).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:43 ###
+ Running. Runtime: 715.9/inf. Active evaluations: 41.
+ Counted trials: 138/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 138 (131)/E: 118 (111).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:44 ###
+ Running. Runtime: 717.5/inf. Active evaluations: 41.
+ Counted trials: 139/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 139 (132)/E: 119 (112).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:48 ###
+ Running. Runtime: 721.2/inf. Active evaluations: 41.
+ Counted trials: 140/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 140 (133)/E: 119 (112).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:48 ###
+ Running. Runtime: 721.3/inf. Active evaluations: 41.
+ Counted trials: 142/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 142 (135)/E: 119 (112).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:49 ###
+ Running. Runtime: 722.0/inf. Active evaluations: 41.
+ Counted trials: 143/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 143 (136)/E: 120 (113).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:54 ###
+ Running. Runtime: 727.0/inf. Active evaluations: 41.
+ Counted trials: 143/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 143 (136)/E: 120 (113).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:54 ###
+ Running. Runtime: 727.4/inf. Active evaluations: 41.
+ Counted trials: 144/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 144 (137)/E: 121 (114).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:55 ###
+ Running. Runtime: 728.5/inf. Active evaluations: 41.
+ Counted trials: 145/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 145 (138)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:57 ###
+ Running. Runtime: 730.4/inf. Active evaluations: 41.
+ Counted trials: 146/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 146 (139)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:08:59 ###
+ Running. Runtime: 732.2/inf. Active evaluations: 41.
+ Counted trials: 147/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 147 (140)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:04 ###
+ Running. Runtime: 737.2/inf. Active evaluations: 41.
+ Counted trials: 147/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 147 (140)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:09 ###
+ Running. Runtime: 742.2/inf. Active evaluations: 41.
+ Counted trials: 147/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 147 (140)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:14 ###
+ Running. Runtime: 747.2/inf. Active evaluations: 41.
+ Counted trials: 147/400.
+ Best 3: 0.0244 0.0257 0.0359. Live: 41/T: 147 (140)/E: 122 (115).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:17 ###
+ Running. Runtime: 749.9/inf. Active evaluations: 41.
+ Counted trials: 148/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 148 (141)/E: 123 (116).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:17 ###
+ Running. Runtime: 750.0/inf. Active evaluations: 41.
+ Counted trials: 149/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 149 (142)/E: 123 (116).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:17 ###
+ Running. Runtime: 750.2/inf. Active evaluations: 41.
+ Counted trials: 150/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 150 (143)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:17 ###
+ Running. Runtime: 750.5/inf. Active evaluations: 41.
+ Counted trials: 151/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 151 (144)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:18 ###
+ Running. Runtime: 751.7/inf. Active evaluations: 41.
+ Counted trials: 152/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 152 (145)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:23 ###
+ Running. Runtime: 756.7/inf. Active evaluations: 41.
+ Counted trials: 152/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 152 (145)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:28 ###
+ Running. Runtime: 761.7/inf. Active evaluations: 41.
+ Counted trials: 152/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 152 (145)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:33 ###
+ Running. Runtime: 766.7/inf. Active evaluations: 41.
+ Counted trials: 152/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 152 (145)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:38 ###
+ Running. Runtime: 771.7/inf. Active evaluations: 41.
+ Counted trials: 152/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 152 (145)/E: 124 (117).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:42 ###
+ Running. Runtime: 775.1/inf. Active evaluations: 41.
+ Counted trials: 153/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 153 (146)/E: 125 (118).
+ {'QMMLException': 7}
+### Status of run nmd18_hpo at 2020-02-24 12:09:46 ###
+ Running. Runtime: 778.9/inf. Active evaluations: 41.
+ Counted trials: 154/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 154 (146)/E: 126 (118).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:09:51 ###
+ Running. Runtime: 783.9/inf. Active evaluations: 41.
+ Counted trials: 155/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 155 (147)/E: 126 (118).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:09:56 ###
+ Running. Runtime: 788.9/inf. Active evaluations: 41.
+ Counted trials: 155/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 155 (147)/E: 126 (118).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:09:57 ###
+ Running. Runtime: 790.6/inf. Active evaluations: 41.
+ Counted trials: 156/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 156 (148)/E: 127 (119).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:09:59 ###
+ Running. Runtime: 792.3/inf. Active evaluations: 41.
+ Counted trials: 157/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 157 (149)/E: 128 (120).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:00 ###
+ Running. Runtime: 792.9/inf. Active evaluations: 41.
+ Counted trials: 158/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 158 (150)/E: 128 (120).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:05 ###
+ Running. Runtime: 797.9/inf. Active evaluations: 41.
+ Counted trials: 158/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 158 (150)/E: 128 (120).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:10 ###
+ Running. Runtime: 802.9/inf. Active evaluations: 41.
+ Counted trials: 158/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 158 (150)/E: 128 (120).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:12 ###
+ Running. Runtime: 805.1/inf. Active evaluations: 41.
+ Counted trials: 159/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 159 (151)/E: 129 (121).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:13 ###
+ Running. Runtime: 806.3/inf. Active evaluations: 41.
+ Counted trials: 160/400.
+ Best 3: 0.0244 0.0257 0.0349. Live: 41/T: 160 (152)/E: 130 (122).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:16 ###
+ Running. Runtime: 809.3/inf. Active evaluations: 41.
+ Counted trials: 161/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 161 (153)/E: 131 (123).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:20 ###
+ Running. Runtime: 812.8/inf. Active evaluations: 41.
+ Counted trials: 162/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 162 (154)/E: 132 (124).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:22 ###
+ Running. Runtime: 815.2/inf. Active evaluations: 41.
+ Counted trials: 163/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 163 (155)/E: 132 (124).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:27 ###
+ Running. Runtime: 820.2/inf. Active evaluations: 41.
+ Counted trials: 163/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 163 (155)/E: 132 (124).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:27 ###
+ Running. Runtime: 820.4/inf. Active evaluations: 41.
+ Counted trials: 164/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 164 (156)/E: 133 (125).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:27 ###
+ Running. Runtime: 820.7/inf. Active evaluations: 41.
+ Counted trials: 165/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 165 (157)/E: 134 (126).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:30 ###
+ Running. Runtime: 823.0/inf. Active evaluations: 41.
+ Counted trials: 166/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 166 (158)/E: 135 (127).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:32 ###
+ Running. Runtime: 825.6/inf. Active evaluations: 41.
+ Counted trials: 167/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 167 (159)/E: 136 (128).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:37 ###
+ Running. Runtime: 830.5/inf. Active evaluations: 41.
+ Counted trials: 168/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 168 (160)/E: 137 (129).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:42 ###
+ Running. Runtime: 835.5/inf. Active evaluations: 41.
+ Counted trials: 168/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 168 (160)/E: 137 (129).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:46 ###
+ Running. Runtime: 839.5/inf. Active evaluations: 41.
+ Counted trials: 169/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 169 (161)/E: 138 (130).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:46 ###
+ Running. Runtime: 839.7/inf. Active evaluations: 41.
+ Counted trials: 170/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 170 (162)/E: 139 (131).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:50 ###
+ Running. Runtime: 842.9/inf. Active evaluations: 41.
+ Counted trials: 171/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 171 (163)/E: 140 (132).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:10:55 ###
+ Running. Runtime: 847.9/inf. Active evaluations: 41.
+ Counted trials: 171/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 171 (163)/E: 140 (132).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:11:00 ###
+ Running. Runtime: 852.9/inf. Active evaluations: 41.
+ Counted trials: 171/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 171 (163)/E: 140 (132).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:11:05 ###
+ Running. Runtime: 857.9/inf. Active evaluations: 41.
+ Counted trials: 171/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 171 (163)/E: 140 (132).
+ {'QMMLException': 8}
+### Status of run nmd18_hpo at 2020-02-24 12:11:06 ###
+ Running. Runtime: 859.4/inf. Active evaluations: 41.
+ Counted trials: 172/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 172 (163)/E: 140 (132).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:06 ###
+ Running. Runtime: 859.4/inf. Active evaluations: 41.
+ Counted trials: 173/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 173 (164)/E: 140 (132).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:08 ###
+ Running. Runtime: 860.9/inf. Active evaluations: 41.
+ Counted trials: 174/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 174 (165)/E: 140 (132).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:10 ###
+ Running. Runtime: 863.0/inf. Active evaluations: 41.
+ Counted trials: 175/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 175 (166)/E: 141 (133).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:14 ###
+ Running. Runtime: 867.3/inf. Active evaluations: 41.
+ Counted trials: 176/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 176 (167)/E: 142 (134).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:15 ###
+ Running. Runtime: 867.9/inf. Active evaluations: 41.
+ Counted trials: 177/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 177 (168)/E: 142 (134).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:20 ###
+ Running. Runtime: 872.9/inf. Active evaluations: 41.
+ Counted trials: 177/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 177 (168)/E: 142 (134).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:24 ###
+ Running. Runtime: 877.7/inf. Active evaluations: 41.
+ Counted trials: 178/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 178 (169)/E: 143 (135).
+ {'QMMLException': 9}
+### Status of run nmd18_hpo at 2020-02-24 12:11:25 ###
+ Running. Runtime: 878.6/inf. Active evaluations: 41.
+ Counted trials: 179/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 179 (169)/E: 144 (135).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:30 ###
+ Running. Runtime: 883.6/inf. Active evaluations: 41.
+ Counted trials: 179/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 179 (169)/E: 144 (135).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:33 ###
+ Running. Runtime: 886.1/inf. Active evaluations: 41.
+ Counted trials: 180/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 180 (170)/E: 145 (136).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:33 ###
+ Running. Runtime: 886.6/inf. Active evaluations: 41.
+ Counted trials: 181/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 181 (171)/E: 146 (137).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:33 ###
+ Running. Runtime: 886.6/inf. Active evaluations: 41.
+ Counted trials: 182/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 182 (172)/E: 146 (137).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:37 ###
+ Running. Runtime: 890.1/inf. Active evaluations: 41.
+ Counted trials: 183/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 183 (173)/E: 147 (138).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:42 ###
+ Running. Runtime: 895.1/inf. Active evaluations: 41.
+ Counted trials: 183/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 183 (173)/E: 147 (138).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:46 ###
+ Running. Runtime: 899.7/inf. Active evaluations: 41.
+ Counted trials: 184/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 184 (174)/E: 148 (139).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:50 ###
+ Running. Runtime: 902.9/inf. Active evaluations: 41.
+ Counted trials: 185/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 185 (175)/E: 148 (139).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:50 ###
+ Running. Runtime: 903.2/inf. Active evaluations: 41.
+ Counted trials: 186/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 186 (176)/E: 149 (140).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:53 ###
+ Running. Runtime: 906.2/inf. Active evaluations: 41.
+ Counted trials: 187/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 187 (177)/E: 150 (141).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:58 ###
+ Running. Runtime: 911.2/inf. Active evaluations: 41.
+ Counted trials: 187/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 187 (177)/E: 150 (141).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:11:59 ###
+ Running. Runtime: 912.2/inf. Active evaluations: 41.
+ Counted trials: 188/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 188 (178)/E: 150 (141).
+ {'QMMLException': 10}
+### Status of run nmd18_hpo at 2020-02-24 12:12:02 ###
+ Running. Runtime: 915.2/inf. Active evaluations: 41.
+ Counted trials: 189/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 189 (178)/E: 151 (141).
+ {'QMMLException': 11}
+### Status of run nmd18_hpo at 2020-02-24 12:12:02 ###
+ Running. Runtime: 915.3/inf. Active evaluations: 41.
+ Counted trials: 190/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 190 (178)/E: 152 (141).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:07 ###
+ Running. Runtime: 920.3/inf. Active evaluations: 41.
+ Counted trials: 190/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 190 (178)/E: 152 (141).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:11 ###
+ Running. Runtime: 923.9/inf. Active evaluations: 41.
+ Counted trials: 191/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 191 (179)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:13 ###
+ Running. Runtime: 925.8/inf. Active evaluations: 41.
+ Counted trials: 192/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 192 (180)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:18 ###
+ Running. Runtime: 930.8/inf. Active evaluations: 41.
+ Counted trials: 192/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 192 (180)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:20 ###
+ Running. Runtime: 933.0/inf. Active evaluations: 41.
+ Counted trials: 193/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 193 (181)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:25 ###
+ Running. Runtime: 938.0/inf. Active evaluations: 41.
+ Counted trials: 193/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 193 (181)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:30 ###
+ Running. Runtime: 943.0/inf. Active evaluations: 41.
+ Counted trials: 193/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 193 (181)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:35 ###
+ Running. Runtime: 948.0/inf. Active evaluations: 41.
+ Counted trials: 193/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 193 (181)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:40 ###
+ Running. Runtime: 953.0/inf. Active evaluations: 41.
+ Counted trials: 193/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 193 (181)/E: 153 (142).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:42 ###
+ Running. Runtime: 955.4/inf. Active evaluations: 41.
+ Counted trials: 194/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 194 (182)/E: 154 (143).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:47 ###
+ Running. Runtime: 960.4/inf. Active evaluations: 41.
+ Counted trials: 194/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 194 (182)/E: 154 (143).
+ {'QMMLException': 12}
+### Status of run nmd18_hpo at 2020-02-24 12:12:49 ###
+ Running. Runtime: 962.5/inf. Active evaluations: 41.
+ Counted trials: 195/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 195 (182)/E: 155 (143).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:12:50 ###
+ Running. Runtime: 963.6/inf. Active evaluations: 41.
+ Counted trials: 196/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 196 (183)/E: 156 (144).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:12:54 ###
+ Running. Runtime: 967.0/inf. Active evaluations: 41.
+ Counted trials: 197/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 197 (184)/E: 157 (145).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:12:59 ###
+ Running. Runtime: 972.1/inf. Active evaluations: 41.
+ Counted trials: 197/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 197 (184)/E: 157 (145).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:00 ###
+ Running. Runtime: 973.0/inf. Active evaluations: 41.
+ Counted trials: 198/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 198 (185)/E: 158 (146).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:00 ###
+ Running. Runtime: 973.0/inf. Active evaluations: 41.
+ Counted trials: 199/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 199 (186)/E: 159 (147).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:05 ###
+ Running. Runtime: 978.1/inf. Active evaluations: 41.
+ Counted trials: 199/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 199 (186)/E: 159 (147).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:10 ###
+ Running. Runtime: 983.1/inf. Active evaluations: 41.
+ Counted trials: 199/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 199 (186)/E: 159 (147).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:12 ###
+ Running. Runtime: 984.9/inf. Active evaluations: 41.
+ Counted trials: 200/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 200 (187)/E: 160 (148).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:14 ###
+ Running. Runtime: 987.3/inf. Active evaluations: 41.
+ Counted trials: 201/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 201 (188)/E: 160 (148).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:15 ###
+ Running. Runtime: 988.4/inf. Active evaluations: 41.
+ Counted trials: 202/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 202 (189)/E: 161 (149).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:20 ###
+ Running. Runtime: 993.3/inf. Active evaluations: 41.
+ Counted trials: 203/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 203 (190)/E: 162 (150).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:22 ###
+ Running. Runtime: 995.5/inf. Active evaluations: 41.
+ Counted trials: 204/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 204 (191)/E: 163 (151).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:23 ###
+ Running. Runtime: 996.3/inf. Active evaluations: 41.
+ Counted trials: 205/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 205 (192)/E: 163 (151).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:27 ###
+ Running. Runtime: 1000.0/inf. Active evaluations: 41.
+ Counted trials: 206/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 206 (193)/E: 164 (152).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:28 ###
+ Running. Runtime: 1001.3/inf. Active evaluations: 41.
+ Counted trials: 207/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 207 (194)/E: 165 (153).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:33 ###
+ Running. Runtime: 1006.3/inf. Active evaluations: 41.
+ Counted trials: 207/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 207 (194)/E: 165 (153).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:38 ###
+ Running. Runtime: 1011.3/inf. Active evaluations: 41.
+ Counted trials: 207/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 207 (194)/E: 165 (153).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:43 ###
+ Running. Runtime: 1016.3/inf. Active evaluations: 41.
+ Counted trials: 207/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 207 (194)/E: 165 (153).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:48 ###
+ Running. Runtime: 1021.3/inf. Active evaluations: 41.
+ Counted trials: 207/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 207 (194)/E: 165 (153).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:52 ###
+ Running. Runtime: 1025.4/inf. Active evaluations: 41.
+ Counted trials: 208/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 208 (195)/E: 166 (154).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:52 ###
+ Running. Runtime: 1025.5/inf. Active evaluations: 41.
+ Counted trials: 209/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 209 (196)/E: 167 (155).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:13:57 ###
+ Running. Runtime: 1030.5/inf. Active evaluations: 41.
+ Counted trials: 209/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 209 (196)/E: 167 (155).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:14:00 ###
+ Running. Runtime: 1033.0/inf. Active evaluations: 41.
+ Counted trials: 210/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 210 (197)/E: 168 (156).
+ {'QMMLException': 13}
+### Status of run nmd18_hpo at 2020-02-24 12:14:02 ###
+ Running. Runtime: 1035.0/inf. Active evaluations: 41.
+ Counted trials: 211/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 211 (197)/E: 169 (156).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:02 ###
+ Running. Runtime: 1035.1/inf. Active evaluations: 41.
+ Counted trials: 212/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 212 (198)/E: 169 (156).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:04 ###
+ Running. Runtime: 1037.6/inf. Active evaluations: 41.
+ Counted trials: 213/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 213 (199)/E: 170 (157).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:04 ###
+ Running. Runtime: 1037.7/inf. Active evaluations: 41.
+ Counted trials: 214/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 214 (200)/E: 170 (157).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:06 ###
+ Running. Runtime: 1039.3/inf. Active evaluations: 41.
+ Counted trials: 215/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 215 (201)/E: 171 (158).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:11 ###
+ Running. Runtime: 1044.3/inf. Active evaluations: 41.
+ Counted trials: 215/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 215 (201)/E: 171 (158).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:14 ###
+ Running. Runtime: 1047.3/inf. Active evaluations: 41.
+ Counted trials: 216/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 216 (202)/E: 172 (159).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:15 ###
+ Running. Runtime: 1048.5/inf. Active evaluations: 41.
+ Counted trials: 217/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 217 (203)/E: 173 (160).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:18 ###
+ Running. Runtime: 1051.6/inf. Active evaluations: 41.
+ Counted trials: 218/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 218 (204)/E: 174 (161).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:20 ###
+ Running. Runtime: 1053.1/inf. Active evaluations: 41.
+ Counted trials: 219/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 219 (205)/E: 175 (162).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:24 ###
+ Running. Runtime: 1056.9/inf. Active evaluations: 41.
+ Counted trials: 220/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 220 (206)/E: 176 (163).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:29 ###
+ Running. Runtime: 1061.9/inf. Active evaluations: 41.
+ Counted trials: 220/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 220 (206)/E: 176 (163).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:34 ###
+ Running. Runtime: 1066.9/inf. Active evaluations: 41.
+ Counted trials: 220/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 220 (206)/E: 176 (163).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:34 ###
+ Running. Runtime: 1067.0/inf. Active evaluations: 41.
+ Counted trials: 221/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 221 (207)/E: 177 (164).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:37 ###
+ Running. Runtime: 1070.0/inf. Active evaluations: 41.
+ Counted trials: 222/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 222 (208)/E: 178 (165).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:42 ###
+ Running. Runtime: 1075.0/inf. Active evaluations: 41.
+ Counted trials: 222/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 222 (208)/E: 178 (165).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:43 ###
+ Running. Runtime: 1076.0/inf. Active evaluations: 41.
+ Counted trials: 223/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 223 (209)/E: 178 (165).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:43 ###
+ Running. Runtime: 1076.0/inf. Active evaluations: 41.
+ Counted trials: 224/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 224 (210)/E: 178 (165).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:44 ###
+ Running. Runtime: 1077.3/inf. Active evaluations: 41.
+ Counted trials: 225/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 225 (211)/E: 179 (166).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:49 ###
+ Running. Runtime: 1082.3/inf. Active evaluations: 41.
+ Counted trials: 225/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 225 (211)/E: 179 (166).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:50 ###
+ Running. Runtime: 1083.4/inf. Active evaluations: 41.
+ Counted trials: 226/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 226 (212)/E: 180 (167).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:52 ###
+ Running. Runtime: 1085.0/inf. Active evaluations: 41.
+ Counted trials: 227/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 227 (213)/E: 181 (168).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:52 ###
+ Running. Runtime: 1085.8/inf. Active evaluations: 41.
+ Counted trials: 228/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 228 (214)/E: 182 (169).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:54 ###
+ Running. Runtime: 1087.5/inf. Active evaluations: 41.
+ Counted trials: 229/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 229 (215)/E: 183 (170).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:14:59 ###
+ Running. Runtime: 1092.5/inf. Active evaluations: 41.
+ Counted trials: 230/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 230 (216)/E: 184 (171).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:04 ###
+ Running. Runtime: 1097.5/inf. Active evaluations: 41.
+ Counted trials: 230/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 230 (216)/E: 184 (171).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:09 ###
+ Running. Runtime: 1102.5/inf. Active evaluations: 41.
+ Counted trials: 230/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 230 (216)/E: 184 (171).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:11 ###
+ Running. Runtime: 1104.4/inf. Active evaluations: 41.
+ Counted trials: 231/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 231 (217)/E: 185 (172).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:16 ###
+ Running. Runtime: 1109.4/inf. Active evaluations: 41.
+ Counted trials: 231/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 231 (217)/E: 185 (172).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:21 ###
+ Running. Runtime: 1114.4/inf. Active evaluations: 41.
+ Counted trials: 231/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 231 (217)/E: 185 (172).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:26 ###
+ Running. Runtime: 1119.4/inf. Active evaluations: 41.
+ Counted trials: 231/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 231 (217)/E: 185 (172).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:31 ###
+ Running. Runtime: 1124.4/inf. Active evaluations: 41.
+ Counted trials: 231/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 231 (217)/E: 185 (172).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:34 ###
+ Running. Runtime: 1127.4/inf. Active evaluations: 41.
+ Counted trials: 232/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 232 (218)/E: 186 (173).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:37 ###
+ Running. Runtime: 1130.1/inf. Active evaluations: 41.
+ Counted trials: 233/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 233 (219)/E: 187 (174).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:37 ###
+ Running. Runtime: 1130.1/inf. Active evaluations: 41.
+ Counted trials: 234/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 234 (220)/E: 187 (174).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:41 ###
+ Running. Runtime: 1134.5/inf. Active evaluations: 41.
+ Counted trials: 235/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 235 (221)/E: 187 (174).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:42 ###
+ Running. Runtime: 1134.9/inf. Active evaluations: 41.
+ Counted trials: 236/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 236 (222)/E: 188 (175).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:42 ###
+ Running. Runtime: 1135.0/inf. Active evaluations: 41.
+ Counted trials: 237/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 237 (223)/E: 188 (175).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:42 ###
+ Running. Runtime: 1135.0/inf. Active evaluations: 41.
+ Counted trials: 238/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 238 (224)/E: 188 (175).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:42 ###
+ Running. Runtime: 1135.4/inf. Active evaluations: 41.
+ Counted trials: 239/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 239 (225)/E: 189 (176).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:46 ###
+ Running. Runtime: 1139.1/inf. Active evaluations: 41.
+ Counted trials: 240/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 240 (226)/E: 190 (177).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:49 ###
+ Running. Runtime: 1141.9/inf. Active evaluations: 41.
+ Counted trials: 241/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 241 (227)/E: 191 (178).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:50 ###
+ Running. Runtime: 1143.7/inf. Active evaluations: 41.
+ Counted trials: 242/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 242 (228)/E: 192 (179).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:55 ###
+ Running. Runtime: 1148.7/inf. Active evaluations: 41.
+ Counted trials: 242/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 242 (228)/E: 192 (179).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:58 ###
+ Running. Runtime: 1151.2/inf. Active evaluations: 41.
+ Counted trials: 243/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 243 (229)/E: 193 (180).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:15:58 ###
+ Running. Runtime: 1151.7/inf. Active evaluations: 41.
+ Counted trials: 244/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 244 (230)/E: 194 (181).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:00 ###
+ Running. Runtime: 1153.1/inf. Active evaluations: 41.
+ Counted trials: 245/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 245 (231)/E: 195 (182).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:02 ###
+ Running. Runtime: 1155.8/inf. Active evaluations: 41.
+ Counted trials: 246/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 246 (232)/E: 196 (183).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:07 ###
+ Running. Runtime: 1160.7/inf. Active evaluations: 41.
+ Counted trials: 247/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 247 (233)/E: 197 (184).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:09 ###
+ Running. Runtime: 1162.5/inf. Active evaluations: 41.
+ Counted trials: 248/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 248 (234)/E: 198 (185).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:14 ###
+ Running. Runtime: 1167.5/inf. Active evaluations: 41.
+ Counted trials: 248/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 248 (234)/E: 198 (185).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:18 ###
+ Running. Runtime: 1171.1/inf. Active evaluations: 41.
+ Counted trials: 249/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 249 (235)/E: 198 (185).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:19 ###
+ Running. Runtime: 1172.1/inf. Active evaluations: 41.
+ Counted trials: 250/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 250 (236)/E: 199 (186).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:24 ###
+ Running. Runtime: 1177.1/inf. Active evaluations: 41.
+ Counted trials: 250/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 250 (236)/E: 199 (186).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:29 ###
+ Running. Runtime: 1182.1/inf. Active evaluations: 41.
+ Counted trials: 250/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 250 (236)/E: 199 (186).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:29 ###
+ Running. Runtime: 1182.6/inf. Active evaluations: 41.
+ Counted trials: 251/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 251 (237)/E: 199 (186).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:34 ###
+ Running. Runtime: 1187.6/inf. Active evaluations: 41.
+ Counted trials: 251/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 251 (237)/E: 199 (186).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:35 ###
+ Running. Runtime: 1188.5/inf. Active evaluations: 41.
+ Counted trials: 252/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 252 (238)/E: 200 (187).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:40 ###
+ Running. Runtime: 1193.5/inf. Active evaluations: 41.
+ Counted trials: 252/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 252 (238)/E: 200 (187).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:45 ###
+ Running. Runtime: 1198.5/inf. Active evaluations: 41.
+ Counted trials: 252/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 252 (238)/E: 200 (187).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:50 ###
+ Running. Runtime: 1203.5/inf. Active evaluations: 41.
+ Counted trials: 252/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 252 (238)/E: 200 (187).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:53 ###
+ Running. Runtime: 1206.7/inf. Active evaluations: 41.
+ Counted trials: 253/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 253 (239)/E: 201 (188).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:16:58 ###
+ Running. Runtime: 1211.7/inf. Active evaluations: 41.
+ Counted trials: 253/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 253 (239)/E: 201 (188).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:01 ###
+ Running. Runtime: 1214.3/inf. Active evaluations: 41.
+ Counted trials: 254/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 254 (240)/E: 201 (188).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:02 ###
+ Running. Runtime: 1214.9/inf. Active evaluations: 41.
+ Counted trials: 255/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 255 (241)/E: 202 (189).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:02 ###
+ Running. Runtime: 1215.7/inf. Active evaluations: 41.
+ Counted trials: 256/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 256 (242)/E: 203 (190).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:04 ###
+ Running. Runtime: 1217.5/inf. Active evaluations: 41.
+ Counted trials: 257/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 257 (243)/E: 204 (191).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:09 ###
+ Running. Runtime: 1222.5/inf. Active evaluations: 41.
+ Counted trials: 257/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 257 (243)/E: 204 (191).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:13 ###
+ Running. Runtime: 1226.0/inf. Active evaluations: 41.
+ Counted trials: 258/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 258 (244)/E: 204 (191).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:17 ###
+ Running. Runtime: 1230.6/inf. Active evaluations: 41.
+ Counted trials: 259/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 259 (245)/E: 205 (192).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:18 ###
+ Running. Runtime: 1230.9/inf. Active evaluations: 41.
+ Counted trials: 260/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 260 (246)/E: 205 (192).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:23 ###
+ Running. Runtime: 1235.9/inf. Active evaluations: 41.
+ Counted trials: 260/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 260 (246)/E: 205 (192).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:24 ###
+ Running. Runtime: 1236.8/inf. Active evaluations: 41.
+ Counted trials: 261/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 261 (247)/E: 205 (192).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:29 ###
+ Running. Runtime: 1241.8/inf. Active evaluations: 41.
+ Counted trials: 261/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 261 (247)/E: 205 (192).
+ {'QMMLException': 14}
+### Status of run nmd18_hpo at 2020-02-24 12:17:32 ###
+ Running. Runtime: 1244.9/inf. Active evaluations: 41.
+ Counted trials: 262/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 262 (247)/E: 206 (192).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:32 ###
+ Running. Runtime: 1244.9/inf. Active evaluations: 41.
+ Counted trials: 263/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 263 (248)/E: 206 (192).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:32 ###
+ Running. Runtime: 1245.0/inf. Active evaluations: 41.
+ Counted trials: 264/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 264 (249)/E: 207 (193).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:34 ###
+ Running. Runtime: 1247.0/inf. Active evaluations: 41.
+ Counted trials: 265/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 265 (250)/E: 207 (193).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:36 ###
+ Running. Runtime: 1249.3/inf. Active evaluations: 41.
+ Counted trials: 266/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 266 (251)/E: 208 (194).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:36 ###
+ Running. Runtime: 1249.6/inf. Active evaluations: 41.
+ Counted trials: 267/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 267 (252)/E: 209 (195).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:41 ###
+ Running. Runtime: 1253.8/inf. Active evaluations: 41.
+ Counted trials: 268/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 268 (253)/E: 210 (196).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:41 ###
+ Running. Runtime: 1253.9/inf. Active evaluations: 41.
+ Counted trials: 269/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 269 (254)/E: 211 (197).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:46 ###
+ Running. Runtime: 1258.9/inf. Active evaluations: 41.
+ Counted trials: 269/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 269 (254)/E: 211 (197).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:51 ###
+ Running. Runtime: 1264.0/inf. Active evaluations: 41.
+ Counted trials: 269/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 269 (254)/E: 211 (197).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:53 ###
+ Running. Runtime: 1265.9/inf. Active evaluations: 41.
+ Counted trials: 270/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 270 (255)/E: 211 (197).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:17:58 ###
+ Running. Runtime: 1270.9/inf. Active evaluations: 41.
+ Counted trials: 270/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 270 (255)/E: 211 (197).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:00 ###
+ Running. Runtime: 1273.4/inf. Active evaluations: 41.
+ Counted trials: 271/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 271 (256)/E: 212 (198).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:05 ###
+ Running. Runtime: 1278.4/inf. Active evaluations: 41.
+ Counted trials: 271/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 271 (256)/E: 212 (198).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:08 ###
+ Running. Runtime: 1281.4/inf. Active evaluations: 41.
+ Counted trials: 272/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 272 (257)/E: 213 (199).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:13 ###
+ Running. Runtime: 1286.4/inf. Active evaluations: 41.
+ Counted trials: 272/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 272 (257)/E: 213 (199).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:14 ###
+ Running. Runtime: 1287.3/inf. Active evaluations: 41.
+ Counted trials: 273/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 273 (258)/E: 214 (200).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:16 ###
+ Running. Runtime: 1289.2/inf. Active evaluations: 41.
+ Counted trials: 274/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 274 (259)/E: 215 (201).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:21 ###
+ Running. Runtime: 1294.2/inf. Active evaluations: 41.
+ Counted trials: 274/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 274 (259)/E: 215 (201).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:24 ###
+ Running. Runtime: 1297.3/inf. Active evaluations: 41.
+ Counted trials: 275/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 275 (260)/E: 215 (201).
+ {'QMMLException': 15}
+### Status of run nmd18_hpo at 2020-02-24 12:18:27 ###
+ Running. Runtime: 1300.7/inf. Active evaluations: 41.
+ Counted trials: 276/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 276 (260)/E: 216 (201).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:30 ###
+ Running. Runtime: 1303.4/inf. Active evaluations: 41.
+ Counted trials: 277/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 277 (261)/E: 217 (202).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:35 ###
+ Running. Runtime: 1308.4/inf. Active evaluations: 41.
+ Counted trials: 277/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 277 (261)/E: 217 (202).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:40 ###
+ Running. Runtime: 1313.4/inf. Active evaluations: 41.
+ Counted trials: 277/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 277 (261)/E: 217 (202).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:40 ###
+ Running. Runtime: 1313.7/inf. Active evaluations: 41.
+ Counted trials: 278/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 278 (262)/E: 218 (203).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:41 ###
+ Running. Runtime: 1314.0/inf. Active evaluations: 41.
+ Counted trials: 279/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 279 (263)/E: 219 (204).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:46 ###
+ Running. Runtime: 1319.0/inf. Active evaluations: 41.
+ Counted trials: 279/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 279 (263)/E: 219 (204).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:46 ###
+ Running. Runtime: 1319.2/inf. Active evaluations: 41.
+ Counted trials: 280/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 280 (264)/E: 220 (205).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:51 ###
+ Running. Runtime: 1324.2/inf. Active evaluations: 41.
+ Counted trials: 280/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 280 (264)/E: 220 (205).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:52 ###
+ Running. Runtime: 1325.6/inf. Active evaluations: 41.
+ Counted trials: 281/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 281 (265)/E: 221 (206).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:54 ###
+ Running. Runtime: 1327.1/inf. Active evaluations: 41.
+ Counted trials: 282/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 282 (266)/E: 222 (207).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:18:59 ###
+ Running. Runtime: 1332.1/inf. Active evaluations: 41.
+ Counted trials: 282/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 282 (266)/E: 222 (207).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:00 ###
+ Running. Runtime: 1333.6/inf. Active evaluations: 41.
+ Counted trials: 283/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 283 (267)/E: 223 (208).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:01 ###
+ Running. Runtime: 1334.5/inf. Active evaluations: 41.
+ Counted trials: 284/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 284 (268)/E: 223 (208).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:06 ###
+ Running. Runtime: 1339.5/inf. Active evaluations: 41.
+ Counted trials: 284/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 284 (268)/E: 223 (208).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:11 ###
+ Running. Runtime: 1344.5/inf. Active evaluations: 41.
+ Counted trials: 285/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 285 (269)/E: 224 (209).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:14 ###
+ Running. Runtime: 1347.2/inf. Active evaluations: 41.
+ Counted trials: 286/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 286 (270)/E: 225 (210).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:15 ###
+ Running. Runtime: 1348.7/inf. Active evaluations: 41.
+ Counted trials: 287/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 287 (271)/E: 226 (211).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:19 ###
+ Running. Runtime: 1352.4/inf. Active evaluations: 41.
+ Counted trials: 288/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 288 (272)/E: 227 (212).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:21 ###
+ Running. Runtime: 1354.7/inf. Active evaluations: 41.
+ Counted trials: 289/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 289 (273)/E: 228 (213).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:26 ###
+ Running. Runtime: 1359.3/inf. Active evaluations: 41.
+ Counted trials: 290/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 290 (274)/E: 228 (213).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:29 ###
+ Running. Runtime: 1362.1/inf. Active evaluations: 41.
+ Counted trials: 291/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 291 (275)/E: 229 (214).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:32 ###
+ Running. Runtime: 1365.6/inf. Active evaluations: 41.
+ Counted trials: 292/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 292 (276)/E: 230 (215).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:37 ###
+ Running. Runtime: 1370.6/inf. Active evaluations: 41.
+ Counted trials: 293/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 293 (277)/E: 231 (216).
+ {'QMMLException': 16}
+### Status of run nmd18_hpo at 2020-02-24 12:19:39 ###
+ Running. Runtime: 1371.9/inf. Active evaluations: 41.
+ Counted trials: 294/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 294 (277)/E: 232 (216).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:39 ###
+ Running. Runtime: 1371.9/inf. Active evaluations: 41.
+ Counted trials: 295/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 295 (278)/E: 232 (216).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:44 ###
+ Running. Runtime: 1377.0/inf. Active evaluations: 41.
+ Counted trials: 295/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 295 (278)/E: 232 (216).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:46 ###
+ Running. Runtime: 1379.1/inf. Active evaluations: 41.
+ Counted trials: 296/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 296 (279)/E: 233 (217).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:48 ###
+ Running. Runtime: 1381.2/inf. Active evaluations: 41.
+ Counted trials: 297/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 297 (280)/E: 234 (218).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:49 ###
+ Running. Runtime: 1381.9/inf. Active evaluations: 41.
+ Counted trials: 298/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 298 (281)/E: 235 (219).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:49 ###
+ Running. Runtime: 1382.4/inf. Active evaluations: 41.
+ Counted trials: 299/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 299 (282)/E: 236 (220).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:51 ###
+ Running. Runtime: 1383.9/inf. Active evaluations: 41.
+ Counted trials: 300/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 300 (283)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:19:56 ###
+ Running. Runtime: 1388.9/inf. Active evaluations: 41.
+ Counted trials: 300/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 300 (283)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:01 ###
+ Running. Runtime: 1393.9/inf. Active evaluations: 41.
+ Counted trials: 300/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 300 (283)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:02 ###
+ Running. Runtime: 1395.7/inf. Active evaluations: 41.
+ Counted trials: 301/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 301 (284)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:07 ###
+ Running. Runtime: 1400.7/inf. Active evaluations: 41.
+ Counted trials: 301/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 301 (284)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:12 ###
+ Running. Runtime: 1405.7/inf. Active evaluations: 41.
+ Counted trials: 301/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 301 (284)/E: 237 (221).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:17 ###
+ Running. Runtime: 1410.5/inf. Active evaluations: 41.
+ Counted trials: 302/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 302 (285)/E: 238 (222).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:20 ###
+ Running. Runtime: 1413.7/inf. Active evaluations: 41.
+ Counted trials: 303/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 303 (286)/E: 239 (223).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:21 ###
+ Running. Runtime: 1414.0/inf. Active evaluations: 41.
+ Counted trials: 304/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 304 (287)/E: 239 (223).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:21 ###
+ Running. Runtime: 1414.6/inf. Active evaluations: 41.
+ Counted trials: 305/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 305 (288)/E: 240 (224).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:26 ###
+ Running. Runtime: 1419.6/inf. Active evaluations: 41.
+ Counted trials: 305/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 305 (288)/E: 240 (224).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:31 ###
+ Running. Runtime: 1424.6/inf. Active evaluations: 41.
+ Counted trials: 305/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 305 (288)/E: 240 (224).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:36 ###
+ Running. Runtime: 1429.6/inf. Active evaluations: 41.
+ Counted trials: 305/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 305 (288)/E: 240 (224).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:37 ###
+ Running. Runtime: 1430.8/inf. Active evaluations: 41.
+ Counted trials: 306/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 306 (289)/E: 241 (225).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:37 ###
+ Running. Runtime: 1430.8/inf. Active evaluations: 41.
+ Counted trials: 307/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 307 (290)/E: 241 (225).
+ {'QMMLException': 17}
+### Status of run nmd18_hpo at 2020-02-24 12:20:42 ###
+ Running. Runtime: 1435.6/inf. Active evaluations: 41.
+ Counted trials: 308/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 308 (290)/E: 242 (225).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:47 ###
+ Running. Runtime: 1440.1/inf. Active evaluations: 41.
+ Counted trials: 309/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 309 (291)/E: 242 (225).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:47 ###
+ Running. Runtime: 1440.1/inf. Active evaluations: 41.
+ Counted trials: 310/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 310 (292)/E: 242 (225).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:48 ###
+ Running. Runtime: 1441.3/inf. Active evaluations: 41.
+ Counted trials: 311/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 311 (293)/E: 243 (226).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:50 ###
+ Running. Runtime: 1443.2/inf. Active evaluations: 41.
+ Counted trials: 312/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 312 (294)/E: 244 (227).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:55 ###
+ Running. Runtime: 1448.2/inf. Active evaluations: 41.
+ Counted trials: 312/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 312 (294)/E: 244 (227).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:56 ###
+ Running. Runtime: 1449.4/inf. Active evaluations: 41.
+ Counted trials: 313/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 313 (295)/E: 245 (228).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:20:58 ###
+ Running. Runtime: 1451.3/inf. Active evaluations: 41.
+ Counted trials: 314/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 314 (296)/E: 246 (229).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:03 ###
+ Running. Runtime: 1456.3/inf. Active evaluations: 41.
+ Counted trials: 314/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 314 (296)/E: 246 (229).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:03 ###
+ Running. Runtime: 1456.5/inf. Active evaluations: 41.
+ Counted trials: 315/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 315 (297)/E: 247 (230).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:08 ###
+ Running. Runtime: 1461.5/inf. Active evaluations: 41.
+ Counted trials: 315/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 315 (297)/E: 247 (230).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:09 ###
+ Running. Runtime: 1462.1/inf. Active evaluations: 41.
+ Counted trials: 316/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 316 (298)/E: 247 (230).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:11 ###
+ Running. Runtime: 1464.0/inf. Active evaluations: 41.
+ Counted trials: 317/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 317 (299)/E: 247 (230).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:13 ###
+ Running. Runtime: 1466.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:18 ###
+ Running. Runtime: 1471.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:23 ###
+ Running. Runtime: 1476.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:29 ###
+ Running. Runtime: 1481.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:34 ###
+ Running. Runtime: 1486.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:39 ###
+ Running. Runtime: 1491.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:44 ###
+ Running. Runtime: 1496.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:49 ###
+ Running. Runtime: 1501.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:54 ###
+ Running. Runtime: 1506.8/inf. Active evaluations: 41.
+ Counted trials: 318/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 318 (300)/E: 248 (231).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:57 ###
+ Running. Runtime: 1510.5/inf. Active evaluations: 41.
+ Counted trials: 320/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 320 (302)/E: 249 (232).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:21:59 ###
+ Running. Runtime: 1512.7/inf. Active evaluations: 41.
+ Counted trials: 321/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 321 (303)/E: 249 (232).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:22:00 ###
+ Running. Runtime: 1513.5/inf. Active evaluations: 41.
+ Counted trials: 322/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 322 (304)/E: 250 (233).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:22:01 ###
+ Running. Runtime: 1514.2/inf. Active evaluations: 41.
+ Counted trials: 323/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 323 (305)/E: 251 (234).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:22:06 ###
+ Running. Runtime: 1519.2/inf. Active evaluations: 41.
+ Counted trials: 323/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 323 (305)/E: 251 (234).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:22:08 ###
+ Running. Runtime: 1520.9/inf. Active evaluations: 41.
+ Counted trials: 324/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 324 (306)/E: 252 (235).
+ {'QMMLException': 18}
+### Status of run nmd18_hpo at 2020-02-24 12:22:12 ###
+ Running. Runtime: 1525.0/inf. Active evaluations: 41.
+ Counted trials: 325/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 325 (306)/E: 253 (235).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:17 ###
+ Running. Runtime: 1530.1/inf. Active evaluations: 41.
+ Counted trials: 325/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 325 (306)/E: 253 (235).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:17 ###
+ Running. Runtime: 1530.2/inf. Active evaluations: 41.
+ Counted trials: 326/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 326 (307)/E: 254 (236).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:18 ###
+ Running. Runtime: 1531.4/inf. Active evaluations: 41.
+ Counted trials: 327/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 327 (308)/E: 255 (237).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:23 ###
+ Running. Runtime: 1536.4/inf. Active evaluations: 41.
+ Counted trials: 327/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 327 (308)/E: 255 (237).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:23 ###
+ Running. Runtime: 1536.4/inf. Active evaluations: 41.
+ Counted trials: 328/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 328 (309)/E: 255 (237).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:24 ###
+ Running. Runtime: 1537.2/inf. Active evaluations: 41.
+ Counted trials: 329/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 329 (310)/E: 256 (238).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:24 ###
+ Running. Runtime: 1537.4/inf. Active evaluations: 41.
+ Counted trials: 330/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 330 (311)/E: 257 (239).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:25 ###
+ Running. Runtime: 1538.4/inf. Active evaluations: 41.
+ Counted trials: 331/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 331 (312)/E: 257 (239).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:28 ###
+ Running. Runtime: 1541.0/inf. Active evaluations: 41.
+ Counted trials: 332/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 332 (313)/E: 258 (240).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:33 ###
+ Running. Runtime: 1546.0/inf. Active evaluations: 41.
+ Counted trials: 332/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 332 (313)/E: 258 (240).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:38 ###
+ Running. Runtime: 1551.1/inf. Active evaluations: 41.
+ Counted trials: 332/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 332 (313)/E: 258 (240).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:43 ###
+ Running. Runtime: 1556.1/inf. Active evaluations: 41.
+ Counted trials: 332/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 332 (313)/E: 258 (240).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:48 ###
+ Running. Runtime: 1561.1/inf. Active evaluations: 41.
+ Counted trials: 332/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 332 (313)/E: 258 (240).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:50 ###
+ Running. Runtime: 1562.9/inf. Active evaluations: 41.
+ Counted trials: 333/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 333 (314)/E: 259 (241).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:52 ###
+ Running. Runtime: 1565.6/inf. Active evaluations: 41.
+ Counted trials: 334/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 334 (315)/E: 260 (242).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:54 ###
+ Running. Runtime: 1567.4/inf. Active evaluations: 41.
+ Counted trials: 335/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 335 (316)/E: 261 (243).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:22:59 ###
+ Running. Runtime: 1572.4/inf. Active evaluations: 41.
+ Counted trials: 335/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 335 (316)/E: 261 (243).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:04 ###
+ Running. Runtime: 1577.4/inf. Active evaluations: 41.
+ Counted trials: 335/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 335 (316)/E: 261 (243).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:09 ###
+ Running. Runtime: 1582.4/inf. Active evaluations: 41.
+ Counted trials: 335/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 335 (316)/E: 261 (243).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:14 ###
+ Running. Runtime: 1587.4/inf. Active evaluations: 41.
+ Counted trials: 335/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 335 (316)/E: 261 (243).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:18 ###
+ Running. Runtime: 1591.6/inf. Active evaluations: 41.
+ Counted trials: 336/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 336 (317)/E: 262 (244).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:21 ###
+ Running. Runtime: 1594.3/inf. Active evaluations: 41.
+ Counted trials: 337/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 337 (318)/E: 262 (244).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:25 ###
+ Running. Runtime: 1598.4/inf. Active evaluations: 41.
+ Counted trials: 338/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 338 (319)/E: 263 (245).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:28 ###
+ Running. Runtime: 1601.0/inf. Active evaluations: 41.
+ Counted trials: 339/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 339 (320)/E: 263 (245).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:32 ###
+ Running. Runtime: 1605.2/inf. Active evaluations: 41.
+ Counted trials: 340/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 340 (321)/E: 264 (246).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:37 ###
+ Running. Runtime: 1610.2/inf. Active evaluations: 41.
+ Counted trials: 340/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 340 (321)/E: 264 (246).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:38 ###
+ Running. Runtime: 1611.4/inf. Active evaluations: 41.
+ Counted trials: 341/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 341 (322)/E: 265 (247).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:43 ###
+ Running. Runtime: 1616.4/inf. Active evaluations: 41.
+ Counted trials: 341/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 341 (322)/E: 265 (247).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:48 ###
+ Running. Runtime: 1621.4/inf. Active evaluations: 41.
+ Counted trials: 341/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 341 (322)/E: 265 (247).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:51 ###
+ Running. Runtime: 1624.0/inf. Active evaluations: 41.
+ Counted trials: 342/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 342 (323)/E: 266 (248).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:52 ###
+ Running. Runtime: 1625.3/inf. Active evaluations: 41.
+ Counted trials: 343/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 343 (324)/E: 267 (249).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:23:55 ###
+ Running. Runtime: 1628.3/inf. Active evaluations: 41.
+ Counted trials: 344/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 344 (325)/E: 267 (249).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:24:00 ###
+ Running. Runtime: 1633.3/inf. Active evaluations: 41.
+ Counted trials: 344/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 344 (325)/E: 267 (249).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:24:03 ###
+ Running. Runtime: 1636.1/inf. Active evaluations: 41.
+ Counted trials: 345/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 345 (326)/E: 267 (249).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:24:07 ###
+ Running. Runtime: 1640.8/inf. Active evaluations: 41.
+ Counted trials: 346/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 346 (327)/E: 268 (250).
+ {'QMMLException': 19}
+### Status of run nmd18_hpo at 2020-02-24 12:24:08 ###
+ Running. Runtime: 1641.2/inf. Active evaluations: 41.
+ Counted trials: 347/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 347 (327)/E: 269 (250).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:12 ###
+ Running. Runtime: 1645.7/inf. Active evaluations: 41.
+ Counted trials: 348/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 348 (328)/E: 269 (250).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:17 ###
+ Running. Runtime: 1650.7/inf. Active evaluations: 41.
+ Counted trials: 348/400.
+ Best 3: 0.0244 0.0256 0.0257. Live: 41/T: 348 (328)/E: 269 (250).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:21 ###
+ Running. Runtime: 1654.2/inf. Active evaluations: 41.
+ Counted trials: 349/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 349 (329)/E: 270 (251).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:26 ###
+ Running. Runtime: 1659.2/inf. Active evaluations: 41.
+ Counted trials: 349/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 349 (329)/E: 270 (251).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:31 ###
+ Running. Runtime: 1664.2/inf. Active evaluations: 41.
+ Counted trials: 349/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 349 (329)/E: 270 (251).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:33 ###
+ Running. Runtime: 1666.0/inf. Active evaluations: 41.
+ Counted trials: 350/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 350 (330)/E: 271 (252).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:33 ###
+ Running. Runtime: 1666.3/inf. Active evaluations: 41.
+ Counted trials: 351/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 351 (331)/E: 272 (253).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:38 ###
+ Running. Runtime: 1671.3/inf. Active evaluations: 41.
+ Counted trials: 351/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 351 (331)/E: 272 (253).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:43 ###
+ Running. Runtime: 1676.4/inf. Active evaluations: 41.
+ Counted trials: 351/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 351 (331)/E: 272 (253).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:48 ###
+ Running. Runtime: 1681.4/inf. Active evaluations: 41.
+ Counted trials: 351/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 351 (331)/E: 272 (253).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:50 ###
+ Running. Runtime: 1683.2/inf. Active evaluations: 41.
+ Counted trials: 352/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 352 (332)/E: 273 (254).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:50 ###
+ Running. Runtime: 1683.6/inf. Active evaluations: 41.
+ Counted trials: 353/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 353 (333)/E: 274 (255).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:55 ###
+ Running. Runtime: 1688.6/inf. Active evaluations: 41.
+ Counted trials: 353/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 353 (333)/E: 274 (255).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:24:57 ###
+ Running. Runtime: 1690.7/inf. Active evaluations: 41.
+ Counted trials: 354/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 354 (334)/E: 275 (256).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:02 ###
+ Running. Runtime: 1695.7/inf. Active evaluations: 41.
+ Counted trials: 354/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 354 (334)/E: 275 (256).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:07 ###
+ Running. Runtime: 1700.7/inf. Active evaluations: 41.
+ Counted trials: 354/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 354 (334)/E: 275 (256).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:11 ###
+ Running. Runtime: 1704.0/inf. Active evaluations: 41.
+ Counted trials: 355/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 355 (335)/E: 276 (257).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:11 ###
+ Running. Runtime: 1704.2/inf. Active evaluations: 41.
+ Counted trials: 356/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 356 (336)/E: 277 (258).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:11 ###
+ Running. Runtime: 1704.3/inf. Active evaluations: 41.
+ Counted trials: 357/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 357 (337)/E: 278 (259).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:15 ###
+ Running. Runtime: 1708.3/inf. Active evaluations: 41.
+ Counted trials: 358/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 358 (338)/E: 279 (260).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:20 ###
+ Running. Runtime: 1713.4/inf. Active evaluations: 41.
+ Counted trials: 358/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 358 (338)/E: 279 (260).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:25 ###
+ Running. Runtime: 1718.2/inf. Active evaluations: 41.
+ Counted trials: 359/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 359 (339)/E: 280 (261).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:27 ###
+ Running. Runtime: 1719.8/inf. Active evaluations: 41.
+ Counted trials: 360/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 360 (340)/E: 281 (262).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:29 ###
+ Running. Runtime: 1722.4/inf. Active evaluations: 41.
+ Counted trials: 361/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 361 (341)/E: 281 (262).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:32 ###
+ Running. Runtime: 1725.6/inf. Active evaluations: 41.
+ Counted trials: 362/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 362 (342)/E: 282 (263).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:33 ###
+ Running. Runtime: 1726.5/inf. Active evaluations: 41.
+ Counted trials: 363/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 363 (343)/E: 283 (264).
+ {'QMMLException': 20}
+### Status of run nmd18_hpo at 2020-02-24 12:25:34 ###
+ Running. Runtime: 1727.4/inf. Active evaluations: 41.
+ Counted trials: 364/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 364 (343)/E: 283 (264).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:37 ###
+ Running. Runtime: 1730.7/inf. Active evaluations: 41.
+ Counted trials: 365/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 365 (344)/E: 284 (265).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:42 ###
+ Running. Runtime: 1735.7/inf. Active evaluations: 41.
+ Counted trials: 365/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 365 (344)/E: 284 (265).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:46 ###
+ Running. Runtime: 1739.1/inf. Active evaluations: 41.
+ Counted trials: 366/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 366 (345)/E: 285 (266).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:51 ###
+ Running. Runtime: 1744.1/inf. Active evaluations: 41.
+ Counted trials: 366/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 366 (345)/E: 285 (266).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:56 ###
+ Running. Runtime: 1749.1/inf. Active evaluations: 41.
+ Counted trials: 366/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 366 (345)/E: 285 (266).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:25:59 ###
+ Running. Runtime: 1752.1/inf. Active evaluations: 41.
+ Counted trials: 367/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 367 (346)/E: 286 (267).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:03 ###
+ Running. Runtime: 1755.8/inf. Active evaluations: 41.
+ Counted trials: 368/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 368 (347)/E: 287 (268).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:08 ###
+ Running. Runtime: 1760.8/inf. Active evaluations: 41.
+ Counted trials: 368/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 368 (347)/E: 287 (268).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:10 ###
+ Running. Runtime: 1762.8/inf. Active evaluations: 41.
+ Counted trials: 369/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 369 (348)/E: 288 (269).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:14 ###
+ Running. Runtime: 1767.5/inf. Active evaluations: 41.
+ Counted trials: 370/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 370 (349)/E: 289 (270).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:19 ###
+ Running. Runtime: 1772.5/inf. Active evaluations: 41.
+ Counted trials: 370/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 370 (349)/E: 289 (270).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:20 ###
+ Running. Runtime: 1773.6/inf. Active evaluations: 41.
+ Counted trials: 371/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 371 (350)/E: 290 (271).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:25 ###
+ Running. Runtime: 1778.1/inf. Active evaluations: 41.
+ Counted trials: 372/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 372 (351)/E: 291 (272).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:29 ###
+ Running. Runtime: 1782.1/inf. Active evaluations: 41.
+ Counted trials: 373/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 373 (352)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:34 ###
+ Running. Runtime: 1787.1/inf. Active evaluations: 41.
+ Counted trials: 373/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 373 (352)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:39 ###
+ Running. Runtime: 1792.1/inf. Active evaluations: 41.
+ Counted trials: 373/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 373 (352)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:44 ###
+ Running. Runtime: 1797.1/inf. Active evaluations: 41.
+ Counted trials: 373/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 373 (352)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:46 ###
+ Running. Runtime: 1799.7/inf. Active evaluations: 41.
+ Counted trials: 374/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 374 (353)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:51 ###
+ Running. Runtime: 1804.7/inf. Active evaluations: 41.
+ Counted trials: 374/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 374 (353)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:56 ###
+ Running. Runtime: 1809.7/inf. Active evaluations: 41.
+ Counted trials: 374/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 374 (353)/E: 292 (273).
+ {'QMMLException': 21}
+### Status of run nmd18_hpo at 2020-02-24 12:26:57 ###
+ Running. Runtime: 1810.3/inf. Active evaluations: 41.
+ Counted trials: 375/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 375 (353)/E: 292 (273).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:26:58 ###
+ Running. Runtime: 1811.1/inf. Active evaluations: 41.
+ Counted trials: 376/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 376 (354)/E: 293 (274).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:00 ###
+ Running. Runtime: 1813.1/inf. Active evaluations: 41.
+ Counted trials: 377/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 377 (355)/E: 294 (275).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:01 ###
+ Running. Runtime: 1814.1/inf. Active evaluations: 41.
+ Counted trials: 378/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 378 (356)/E: 295 (276).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:06 ###
+ Running. Runtime: 1819.1/inf. Active evaluations: 41.
+ Counted trials: 378/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 378 (356)/E: 295 (276).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:10 ###
+ Running. Runtime: 1823.7/inf. Active evaluations: 41.
+ Counted trials: 379/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 379 (357)/E: 295 (276).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:10 ###
+ Running. Runtime: 1823.8/inf. Active evaluations: 41.
+ Counted trials: 380/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 380 (358)/E: 295 (276).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:11 ###
+ Running. Runtime: 1823.9/inf. Active evaluations: 41.
+ Counted trials: 381/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 381 (359)/E: 296 (277).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:16 ###
+ Running. Runtime: 1828.9/inf. Active evaluations: 41.
+ Counted trials: 381/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 381 (359)/E: 296 (277).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:16 ###
+ Running. Runtime: 1829.5/inf. Active evaluations: 41.
+ Counted trials: 382/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 382 (360)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:16 ###
+ Running. Runtime: 1829.6/inf. Active evaluations: 41.
+ Counted trials: 383/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 383 (361)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:16 ###
+ Running. Runtime: 1829.7/inf. Active evaluations: 41.
+ Counted trials: 384/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 384 (362)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:21 ###
+ Running. Runtime: 1834.7/inf. Active evaluations: 41.
+ Counted trials: 384/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 384 (362)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:23 ###
+ Running. Runtime: 1836.7/inf. Active evaluations: 41.
+ Counted trials: 385/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 385 (363)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:28 ###
+ Running. Runtime: 1841.7/inf. Active evaluations: 41.
+ Counted trials: 385/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 385 (363)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:33 ###
+ Running. Runtime: 1846.7/inf. Active evaluations: 41.
+ Counted trials: 385/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 385 (363)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:38 ###
+ Running. Runtime: 1851.7/inf. Active evaluations: 41.
+ Counted trials: 385/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 385 (363)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:43 ###
+ Running. Runtime: 1856.7/inf. Active evaluations: 41.
+ Counted trials: 385/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 385 (363)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:44 ###
+ Running. Runtime: 1857.7/inf. Active evaluations: 41.
+ Counted trials: 386/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 386 (364)/E: 297 (278).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:46 ###
+ Running. Runtime: 1859.7/inf. Active evaluations: 41.
+ Counted trials: 387/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 387 (365)/E: 298 (279).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:51 ###
+ Running. Runtime: 1864.7/inf. Active evaluations: 41.
+ Counted trials: 387/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 387 (365)/E: 298 (279).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:53 ###
+ Running. Runtime: 1866.4/inf. Active evaluations: 41.
+ Counted trials: 389/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 389 (367)/E: 299 (280).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:53 ###
+ Running. Runtime: 1866.5/inf. Active evaluations: 41.
+ Counted trials: 390/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 390 (368)/E: 299 (280).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:27:58 ###
+ Running. Runtime: 1871.5/inf. Active evaluations: 41.
+ Counted trials: 390/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 390 (368)/E: 299 (280).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:01 ###
+ Running. Runtime: 1874.6/inf. Active evaluations: 41.
+ Counted trials: 391/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 391 (369)/E: 300 (281).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:02 ###
+ Running. Runtime: 1875.5/inf. Active evaluations: 41.
+ Counted trials: 392/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 392 (370)/E: 301 (282).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:02 ###
+ Running. Runtime: 1875.8/inf. Active evaluations: 41.
+ Counted trials: 393/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 393 (371)/E: 302 (283).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:06 ###
+ Running. Runtime: 1878.9/inf. Active evaluations: 41.
+ Counted trials: 394/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 394 (372)/E: 303 (284).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:07 ###
+ Running. Runtime: 1880.7/inf. Active evaluations: 41.
+ Counted trials: 395/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 395 (373)/E: 303 (284).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:12 ###
+ Running. Runtime: 1885.7/inf. Active evaluations: 41.
+ Counted trials: 395/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 395 (373)/E: 303 (284).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:15 ###
+ Running. Runtime: 1888.8/inf. Active evaluations: 41.
+ Counted trials: 396/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 396 (374)/E: 304 (285).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:20 ###
+ Running. Runtime: 1893.8/inf. Active evaluations: 41.
+ Counted trials: 396/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 396 (374)/E: 304 (285).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:25 ###
+ Running. Runtime: 1898.8/inf. Active evaluations: 41.
+ Counted trials: 396/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 396 (374)/E: 304 (285).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:27 ###
+ Running. Runtime: 1900.5/inf. Active evaluations: 41.
+ Counted trials: 397/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 397 (375)/E: 305 (286).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:32 ###
+ Running. Runtime: 1905.0/inf. Active evaluations: 41.
+ Counted trials: 398/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 398 (376)/E: 305 (286).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:37 ###
+ Running. Runtime: 1910.0/inf. Active evaluations: 41.
+ Counted trials: 398/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 398 (376)/E: 305 (286).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:42 ###
+ Running. Runtime: 1915.1/inf. Active evaluations: 41.
+ Counted trials: 398/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 398 (376)/E: 305 (286).
+ {'QMMLException': 22}
+### Status of run nmd18_hpo at 2020-02-24 12:28:44 ###
+ Running. Runtime: 1916.8/inf. Active evaluations: 41.
+ Counted trials: 399/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 399 (377)/E: 305 (286).
+ {'QMMLException': 22}
+Finished run nmd18_hpo in 1918.80s. Starting shutdown...
+Saved top 5 suggestions into run_nmd18_hpo.
+Successfully and peacefully shut down pool.
diff --git a/run_nmd18_hpo/status.txt b/run_nmd18_hpo/status.txt
new file mode 100644
index 0000000000000000000000000000000000000000..81db727abef6286509f7f637f610c13c46942206
--- /dev/null
+++ b/run_nmd18_hpo/status.txt
@@ -0,0 +1,5 @@
+### Status of run nmd18_hpo at 2020-02-24 12:28:46 ###
+ nmd18_hpo: Done. Have a good day! Runtime: 1918.8/inf. Active evaluations: 0.
+ Counted trials: 400/400.
+ Best 3: 0.0240 0.0244 0.0256. Live: 41/T: 400 (378)/E: 306 (287).
+ {'QMMLException': 22}
diff --git a/run_nmd18_hpo/suggestion-0.yml b/run_nmd18_hpo/suggestion-0.yml
new file mode 100644
index 0000000000000000000000000000000000000000..b0179a7f7079ac6689bb8140f48a811a297c3076
--- /dev/null
+++ b/run_nmd18_hpo/suggestion-0.yml
@@ -0,0 +1,19 @@
+model:
+  per: cell
+  regression:
+    krr:
+      kernel:
+        kernel_atomic:
+          kernelf:
+            gaussian:
+              ls: 32.0
+          norm: false
+      nl: 0.00048828125
+  representation:
+    ds_soap:
+      cutoff: 8
+      elems: [8, 13, 31, 49]
+      l_max: 8
+      n_max: 3
+      rbf: gto
+      sigma: 0.25
diff --git a/run_nmd18_hpo/suggestion-1.yml b/run_nmd18_hpo/suggestion-1.yml
new file mode 100644
index 0000000000000000000000000000000000000000..a6d067f2dcba189b2171efba7babcb260e48dedc
--- /dev/null
+++ b/run_nmd18_hpo/suggestion-1.yml
@@ -0,0 +1,19 @@
+model:
+  per: cell
+  regression:
+    krr:
+      kernel:
+        kernel_atomic:
+          kernelf:
+            gaussian:
+              ls: 8.0
+          norm: false
+      nl: 0.03125
+  representation:
+    ds_soap:
+      cutoff: 7
+      elems: [8, 13, 31, 49]
+      l_max: 7
+      n_max: 5
+      rbf: gto
+      sigma: 0.25
diff --git a/run_nmd18_hpo/suggestion-2.yml b/run_nmd18_hpo/suggestion-2.yml
new file mode 100644
index 0000000000000000000000000000000000000000..6e9bd930078cad531d694a65b87b3ec5aa5c5feb
--- /dev/null
+++ b/run_nmd18_hpo/suggestion-2.yml
@@ -0,0 +1,19 @@
+model:
+  per: cell
+  regression:
+    krr:
+      kernel:
+        kernel_atomic:
+          kernelf:
+            gaussian:
+              ls: 64.0
+          norm: false
+      nl: 0.03125
+  representation:
+    ds_soap:
+      cutoff: 7
+      elems: [8, 13, 31, 49]
+      l_max: 6
+      n_max: 5
+      rbf: gto
+      sigma: 0.5
diff --git a/run_nmd18_hpo/suggestion-3.yml b/run_nmd18_hpo/suggestion-3.yml
new file mode 100644
index 0000000000000000000000000000000000000000..35b06a903475df95a12581552d5b01b5b8d03656
--- /dev/null
+++ b/run_nmd18_hpo/suggestion-3.yml
@@ -0,0 +1,19 @@
+model:
+  per: cell
+  regression:
+    krr:
+      kernel:
+        kernel_atomic:
+          kernelf:
+            gaussian:
+              ls: 2048.0
+          norm: false
+      nl: 3.814697265625e-06
+  representation:
+    ds_soap:
+      cutoff: 3
+      elems: [8, 13, 31, 49]
+      l_max: 7
+      n_max: 6
+      rbf: gto
+      sigma: 1.0
diff --git a/run_nmd18_hpo/suggestion-4.yml b/run_nmd18_hpo/suggestion-4.yml
new file mode 100644
index 0000000000000000000000000000000000000000..bd97325a213a091642fb1b0c07a206b74e87b0c0
--- /dev/null
+++ b/run_nmd18_hpo/suggestion-4.yml
@@ -0,0 +1,19 @@
+model:
+  per: cell
+  regression:
+    krr:
+      kernel:
+        kernel_atomic:
+          kernelf:
+            gaussian:
+              ls: 512.0
+          norm: false
+      nl: 0.0078125
+  representation:
+    ds_soap:
+      cutoff: 10
+      elems: [8, 13, 31, 49]
+      l_max: 5
+      n_max: 6
+      rbf: gto
+      sigma: 0.5
diff --git a/run_nmd18_hpo/tape.son b/run_nmd18_hpo/tape.son
new file mode 100644
index 0000000000000000000000000000000000000000..e28ac7c1b7cb8897dd31bdb26882987b725dcc47
--- /dev/null
+++ b/run_nmd18_hpo/tape.son
@@ -0,0 +1,22553 @@
+run:
+  caught_exceptions: [TimeoutError, QMMLException]
+  evaluator:
+    tune_eval_holdout:
+      lossf: rmse
+      per: cation
+      target: fe
+      test: nmd18_hpo_test
+      train: nmd18_hpo_train
+  name: nmd18_hpo
+  search:
+    search_hyperopt:
+      errors_ok: false
+      method: tpe
+      seed: 123
+      space:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: [hp_loggrid, ls_start, -13, 13, 27]
+                  norm: false
+              nl: [hp_loggrid, nl_start, -18, 0, 19]
+          representation:
+            ds_soap:
+              cutoff: [hp_choice, cutoff, [2, 3, 4, 5, 6, 7, 8, 9, 10]]
+              elems: [8, 13, 31, 49]
+              l_max: [hp_choice, l_max, [2, 3, 4, 5, 6, 7, 8]]
+              n_max: [hp_choice, n_max, [2, 3, 4, 5, 6, 7, 8]]
+              rbf: gto
+              sigma: [hp_loggrid, sigma, -20, 6, 27]
+  stop:
+    stop_max:
+      count: 400
+      errors: true
+      use: trials
+  trial_timeout: null
+
+===
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 0
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 8
+          rbf: gto
+          sigma: 16.0
+  tid: 1
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 8.0
+  tid: 2
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 6
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 3
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 5
+          rbf: gto
+          sigma: 0.03125
+  tid: 4
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 5
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.03125
+  tid: 6
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 6
+          rbf: gto
+          sigma: 0.5
+  tid: 7
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 8
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 0.03125
+  tid: 9
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.0625
+  tid: 10
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 7
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 11
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 4
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 12
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 13
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 32.0
+  tid: 14
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 4
+          rbf: gto
+          sigma: 0.0625
+  tid: 15
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 6
+          rbf: gto
+          sigma: 2.0
+  tid: 16
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 64.0
+  tid: 17
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 6
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 18
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 19
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 64.0
+  tid: 20
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 6
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 21
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 7
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 22
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 23
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 24
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 25
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 26
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.25
+  tid: 27
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 28
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 3
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 29
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.25
+  tid: 30
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.015625
+  tid: 31
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 3
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 32
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.125
+  tid: 33
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.015625
+  tid: 34
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 35
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 36
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 37
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 6
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 38
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 39
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 7
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 40
+
+---
+submit:
+  result:
+    ok:
+      duration: 38.71338482806459
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 3
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 29
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 41
+
+---
+submit:
+  result:
+    ok:
+      duration: 43.529965492896736
+      loss: 0.048287857529022
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.0625
+  tid: 10
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 42
+
+---
+submit:
+  result:
+    ok:
+      duration: 44.33474030881189
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 36
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 43
+
+---
+submit:
+  result:
+    ok:
+      duration: 44.77105527394451
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 26
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 44
+
+---
+submit:
+  result:
+    ok:
+      duration: 47.43141539697535
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 23
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 5
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 45
+
+---
+submit:
+  result:
+    ok:
+      duration: 49.02503896597773
+      loss: 0.10344554776925362
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 0.03125
+  tid: 9
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 46
+
+---
+submit:
+  result:
+    ok:
+      duration: 53.261690558865666
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 3
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 32
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 47
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 35
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 48
+
+---
+submit:
+  result:
+    ok:
+      duration: 71.62774299294688
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 19
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 49
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 8
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 50
+
+---
+submit:
+  result:
+    ok:
+      duration: 49.98540356406011
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 43
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 51
+
+---
+submit:
+  result:
+    ok:
+      duration: 49.65787776419893
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 44
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 3
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 52
+
+---
+submit:
+  result:
+    ok:
+      duration: 99.3995787340682
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 6
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 3
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 53
+
+---
+submit:
+  result:
+    ok:
+      duration: 61.86242737295106
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 3
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 42
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 54
+
+---
+submit:
+  result:
+    ok:
+      duration: 47.55277558416128
+      loss: 0.20483483865968063
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 49
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 55
+
+---
+submit:
+  result:
+    ok:
+      duration: 72.97008239314891
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 5
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 45
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 5
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 56
+
+---
+submit:
+  result:
+    ok:
+      duration: 47.55277558416128
+      loss: 0.20483483865968063
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 55
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 5
+          rbf: gto
+          sigma: 0.25
+  tid: 57
+
+---
+submit:
+  result:
+    ok:
+      duration: 124.2889526761137
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 256.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 4
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 12
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 58
+
+---
+submit:
+  result:
+    ok:
+      duration: 129.21876439498737
+      loss: 0.09485521756630565
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 4
+              rbf: gto
+              sigma: 0.0625
+  tid: 15
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 0.125
+  tid: 59
+
+---
+submit:
+  result:
+    ok:
+      duration: 130.21373465307988
+      loss: 0.10383117959939368
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 5
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 60
+
+---
+submit:
+  result:
+    ok:
+      duration: 120.39954068907537
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 41
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 61
+
+---
+submit:
+  result:
+    ok:
+      duration: 169.02550162794068
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 24
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 62
+
+---
+submit:
+  result:
+    ok:
+      duration: 173.04438808187842
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 0
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 63
+
+---
+submit:
+  result:
+    ok:
+      duration: 44.80081928195432
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 58
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 64
+
+---
+submit:
+  result:
+    ok:
+      duration: 178.92631172109395
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 25
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 65
+
+---
+submit:
+  result:
+    ok:
+      duration: 91.34112507803366
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 3
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 52
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 4
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 66
+
+---
+submit:
+  result:
+    ok:
+      duration: 191.98218956193887
+      loss: 0.10361274620131847
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.015625
+  tid: 31
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 3
+          rbf: gto
+          sigma: 16.0
+  tid: 67
+
+---
+submit:
+  result:
+    ok:
+      duration: 193.08016601204872
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 28
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 68
+
+---
+submit:
+  result:
+    ok:
+      duration: 74.36551896599121
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 5
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 56
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 69
+
+---
+submit:
+  result:
+    ok:
+      duration: 197.8150465679355
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 37
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 8.0
+  tid: 70
+
+---
+submit:
+  result:
+    ok:
+      duration: 203.86672343802638
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 6
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 38
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 71
+
+---
+submit:
+  result:
+    ok:
+      duration: 204.8884347290732
+      loss: 0.10383059366026019
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 5
+              rbf: gto
+              sigma: 0.03125
+  tid: 4
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 72
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 48
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 73
+
+---
+submit:
+  result:
+    ok:
+      duration: 209.38226642017253
+      loss: 0.03590872875701952
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.25
+  tid: 27
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 74
+
+---
+submit:
+  result:
+    ok:
+      duration: 211.61962286382914
+      loss: 0.02435950287997232
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.25
+  tid: 30
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 75
+
+---
+submit:
+  result:
+    ok:
+      duration: 89.33096970780753
+      loss: 0.20505544916122875
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 5
+              rbf: gto
+              sigma: 0.25
+  tid: 57
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 76
+
+---
+submit:
+  result:
+    ok:
+      duration: 213.4778200990986
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 7
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 22
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 0.125
+  tid: 77
+
+---
+submit:
+  result:
+    ok:
+      duration: 219.47380786994472
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 6
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 21
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 78
+
+---
+submit:
+  result:
+    ok:
+      duration: 219.91787422006018
+      loss: 0.10382972869482568
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 13
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 79
+
+---
+submit:
+  result:
+    ok:
+      duration: 221.48331616888754
+      loss: 0.025693522959511453
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 39
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 80
+
+---
+submit:
+  result:
+    ok:
+      duration: 45.06377268093638
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 64
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 81
+
+---
+submit:
+  result:
+    ok:
+      duration: 227.76429367414676
+      loss: 0.10070841703344365
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.015625
+  tid: 34
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 82
+
+---
+submit:
+  result:
+    ok:
+      duration: 229.60251940693706
+      loss: 0.04201069017329998
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.125
+  tid: 33
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 83
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.36465464299545
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 46
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 4
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 84
+
+---
+submit:
+  result:
+    ok:
+      duration: 118.71761186607182
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 54
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 3
+          rbf: gto
+          sigma: 16.0
+  tid: 85
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 71
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 86
+
+---
+submit:
+  result:
+    ok:
+      duration: 282.0142503499519
+      loss: 0.20602205776867663
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 6
+              rbf: gto
+              sigma: 0.5
+  tid: 7
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 87
+
+---
+submit:
+  result:
+    ok:
+      duration: 287.26389576797374
+      loss: 0.20523249110914948
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 256.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 6
+              rbf: gto
+              sigma: 2.0
+  tid: 16
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.015625
+  tid: 88
+
+---
+submit:
+  result:
+    ok:
+      duration: 163.65152356913313
+      loss: 0.07062176235508875
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 0.125
+  tid: 59
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 5
+          rbf: gto
+          sigma: 8.0
+  tid: 89
+
+---
+submit:
+  result:
+    ok:
+      duration: 228.68547546095215
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 47
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 90
+
+---
+submit:
+  result:
+    ok:
+      duration: 300.7986004729755
+      loss: 0.10383117959939368
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 6
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 18
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 91
+
+---
+submit:
+  result:
+    ok:
+      duration: 304.88641743478365
+      loss: 0.10358364403676697
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.03125
+  tid: 6
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 92
+
+---
+submit:
+  result:
+    ok:
+      duration: 118.84054062981158
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 69
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.0078125
+  tid: 93
+
+---
+submit:
+  result:
+    ok:
+      duration: 317.38823345978744
+      loss: 0.2062344151090033
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 8.0
+  tid: 2
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.00390625
+  tid: 94
+
+---
+submit:
+  result:
+    ok:
+      duration: 279.3625295171514
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 7
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 40
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 0.125
+  tid: 95
+
+---
+submit:
+  result:
+    ok:
+      duration: 111.67245118087158
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 75
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 96
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.0136189078912
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 61
+
+---
+submit:
+  result:
+    ok:
+      duration: 163.65152356913313
+      loss: 0.07062176235508875
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 0.125
+  tid: 95
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 97
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 98
+
+---
+submit:
+  result:
+    ok:
+      duration: 111.90537212905474
+      loss: 0.10383049909219845
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 76
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 2.0
+  tid: 99
+
+---
+submit:
+  result:
+    ok:
+      duration: 241.59355994290672
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 51
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 100
+
+---
+submit:
+  result:
+    ok:
+      duration: 238.10050903609954
+      loss: 0.036513093561166755
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 53
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 101
+
+---
+submit:
+  result:
+    ok:
+      duration: 44.31046494911425
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 98
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 102
+
+---
+submit:
+  result:
+    ok:
+      duration: 200.65877483203076
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 62
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 103
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.90337258111686
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 79
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 4
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 104
+
+---
+submit:
+  result:
+    ok:
+      duration: 187.11877151601948
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 68
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 105
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.55447298986837
+      loss: 0.07062176235508875
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 0.125
+  tid: 77
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 106
+
+---
+submit:
+  result:
+    ok:
+      duration: 103.82844077912159
+      loss: 0.10382941893518248
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 86
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 107
+
+---
+submit:
+  result:
+    ok:
+      duration: 85.78716066409834
+      loss: 0.2040022809100646
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+  tid: 90
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 108
+
+---
+submit:
+  result:
+    ok:
+      duration: 79.5052512360271
+      loss: 0.10383105405057214
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.00390625
+  tid: 94
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 109
+
+---
+submit:
+  result:
+    ok:
+      duration: 176.3047384051606
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 81
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.015625
+  tid: 110
+
+---
+submit:
+  result:
+    ok:
+      duration: 404.90692386287265
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 7
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 11
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.03125
+  tid: 111
+
+---
+submit:
+  result:
+    ok:
+      duration: 120.75519846589305
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 256.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.015625
+  tid: 88
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 112
+
+---
+submit:
+  result:
+    ok:
+      duration: 229.89875989896245
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 4
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 66
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 113
+
+---
+submit:
+  result:
+    ok:
+      duration: 114.65297945216298
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.0078125
+  tid: 93
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.0078125
+  tid: 114
+
+---
+submit:
+  result:
+    ok:
+      duration: 262.48884827503935
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 63
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 2
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 115
+
+---
+submit:
+  result:
+    ok:
+      duration: 35.02383028296754
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 256.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.015625
+  tid: 110
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 116
+
+---
+submit:
+  result:
+    ok:
+      duration: 232.20685877394862
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 73
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 117
+
+---
+submit:
+  result:
+    ok:
+      duration: 240.6889958800748
+      loss: 0.2049840184940296
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 74
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 2.0
+  tid: 118
+
+---
+submit:
+  result:
+    ok:
+      duration: 265.93863992299885
+      loss: 0.2049485620959723
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 65
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 119
+
+---
+submit:
+  result:
+    ok:
+      duration: 158.61107980203815
+      loss: 0.20215883694069545
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 5
+              rbf: gto
+              sigma: 8.0
+  tid: 89
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 120
+
+---
+submit:
+  result:
+    ok:
+      duration: 234.97981593501754
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 80
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 121
+
+---
+submit:
+  result:
+    ok:
+      duration: 297.48468499607407
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 60
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 6
+          rbf: gto
+          sigma: 0.0625
+  tid: 122
+
+---
+submit:
+  result:
+    ok:
+      duration: 78.13543592509814
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 4
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 104
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 123
+
+---
+submit:
+  result:
+    ok:
+      duration: 183.5126038659364
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 87
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 124
+
+---
+submit:
+  result:
+    ok:
+      duration: 231.3381226840429
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 4
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 84
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 125
+
+---
+submit:
+  result:
+    ok:
+      duration: 384.7379268000368
+      loss: 0.20465810190464573
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 16.0
+  tid: 50
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 126
+
+---
+submit:
+  result:
+    ok:
+      duration: 42.05562304100022
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 116
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 127
+
+---
+submit:
+  result:
+    ok:
+      duration: 102.34413167601451
+      loss: 0.1005964637227246
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 106
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 0.015625
+  tid: 128
+
+---
+submit:
+  result:
+    ok:
+      duration: 51.66752455988899
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 2
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 115
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 129
+
+---
+submit:
+  result:
+    ok:
+      duration: 264.3584633548744
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 82
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 130
+
+---
+submit:
+  result:
+    ok:
+      duration: 268.8974618401844
+      loss: 0.2049485620959723
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 83
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.03125
+  tid: 131
+
+---
+submit:
+  result:
+    ok:
+      duration: 188.11031589191407
+      loss: 0.20498398790359515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 92
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 132
+
+---
+submit:
+  result:
+    ok:
+      duration: 126.12156291282736
+      loss: 0.2051177820857939
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 105
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 133
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 109
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.0078125
+  tid: 134
+
+---
+submit:
+  result:
+    ok:
+      duration: 188.11031589191407
+      loss: 0.20498398790359515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 133
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 135
+
+---
+submit:
+  result:
+    ok:
+      duration: 297.5088144480251
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 78
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 136
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.70599854597822
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 100
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 137
+
+---
+submit:
+  result:
+    ok:
+      duration: 35.983034866862
+      loss: 0.0736562508986894
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.125
+  tid: 129
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 2.0
+  tid: 138
+
+---
+submit:
+  result:
+    ok:
+      duration: 235.63921169401146
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 91
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 139
+
+---
+submit:
+  result:
+    ok:
+      duration: 53.842507736058906
+      loss: 0.10378062579580764
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 0.015625
+  tid: 128
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 140
+
+---
+submit:
+  result:
+    ok:
+      duration: 357.59317949810065
+      loss: 0.20538071131313346
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 8.0
+  tid: 70
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 141
+
+---
+submit:
+  result:
+    ok:
+      duration: 113.14691868517548
+      loss: 0.20632396058357677
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 2.0
+  tid: 118
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 142
+
+---
+submit:
+  result:
+    ok:
+      duration: 187.77598016802222
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 107
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 6
+          rbf: gto
+          sigma: 0.015625
+  tid: 143
+
+---
+submit:
+  result:
+    ok:
+      duration: 184.08344093314372
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 108
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 0.125
+  tid: 144
+
+---
+submit:
+  result:
+    ok:
+      duration: 38.80093092098832
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 139
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 145
+
+---
+submit:
+  result:
+    ok:
+      duration: 170.4393964910414
+      loss: 0.10383105960025595
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.03125
+  tid: 111
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 146
+
+---
+submit:
+  result:
+    ok:
+      duration: 255.12760874605738
+      loss: 0.18065818892604577
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 2.0
+  tid: 99
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 147
+
+---
+submit:
+  result:
+    ok:
+      duration: 386.88271500589326
+      loss: 0.20465810190464573
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 16.0
+  tid: 72
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 148
+
+---
+submit:
+  result:
+    ok:
+      duration: 126.4331726951059
+      loss: 0.09932130460052928
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 124
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 149
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 3
+              rbf: gto
+              sigma: 16.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 85
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 150
+
+---
+submit:
+  result:
+    ok:
+      duration: 123.96626706793904
+      loss: 0.1038264249623632
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 127
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 16.0
+  tid: 151
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 130
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 152
+
+---
+submit:
+  result:
+    ok:
+      duration: 189.97237194795161
+      loss: 0.20498398790359515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 113
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 153
+
+---
+submit:
+  result:
+    ok:
+      duration: 300.7518409329932
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 97
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 154
+
+---
+submit:
+  result:
+    ok:
+      duration: 301.34994789911434
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 96
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 155
+
+---
+submit:
+  result:
+    ok:
+      duration: 196.46852785209194
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.0078125
+  tid: 114
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 8.0
+  tid: 156
+
+---
+submit:
+  result:
+    ok:
+      duration: 104.78109058202244
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 137
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 2.0
+  tid: 157
+
+---
+submit:
+  result:
+    ok:
+      duration: 167.4722070209682
+      loss: 0.20387800275838433
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 1.0
+  tid: 123
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 158
+
+---
+submit:
+  result:
+    ok:
+      duration: 158.55447900295258
+      loss: 0.10383110195035412
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 125
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 159
+
+---
+submit:
+  result:
+    ok:
+      duration: 268.49132332904264
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 101
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 160
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.16003911406733
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 119
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 6
+          rbf: gto
+          sigma: 0.015625
+  tid: 161
+
+---
+submit:
+  result:
+    ok:
+      duration: 269.33088824688457
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 102
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 162
+
+---
+submit:
+  result:
+    ok:
+      duration: 453.57500062300824
+      loss: 0.20430061246530526
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 3
+              rbf: gto
+              sigma: 16.0
+  tid: 67
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 163
+
+---
+submit:
+  result:
+    ok:
+      duration: 272.1108228720259
+      loss: 0.2049485620959723
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 103
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 164
+
+---
+submit:
+  result:
+    ok:
+      duration: 112.6598588230554
+      loss: 0.20545252197401148
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 2.0
+  tid: 138
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 165
+
+---
+submit:
+  result:
+    ok:
+      duration: 158.55447900295258
+      loss: 0.10383110195035412
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 165
+
+---
+submit:
+  result:
+    ok:
+      duration: 126.4331726951059
+      loss: 0.09932130460052928
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 164
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 166
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 167
+
+---
+submit:
+  result:
+    ok:
+      duration: 126.4331726951059
+      loss: 0.09932130460052928
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 166
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 168
+
+---
+submit:
+  result:
+    ok:
+      duration: 89.6208857158199
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 141
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 169
+
+---
+submit:
+  result:
+    ok:
+      duration: 238.31812319997698
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 112
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 170
+
+---
+submit:
+  result:
+    ok:
+      duration: 184.37846296909265
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 126
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 171
+
+---
+submit:
+  result:
+    ok:
+      duration: 58.32346189208329
+      loss: 0.20486711705363958
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+  tid: 150
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 16.0
+  tid: 172
+
+---
+submit:
+  result:
+    ok:
+      duration: 168.70265474612825
+      loss: 0.10383084849066351
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.03125
+  tid: 131
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.001953125
+  tid: 173
+
+---
+submit:
+  result:
+    ok:
+      duration: 98.64373886003159
+      loss: 0.07508953907195344
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 1.0
+  tid: 145
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 5
+          rbf: gto
+          sigma: 0.5
+  tid: 174
+
+---
+submit:
+  result:
+    ok:
+      duration: 238.31812319997698
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 173
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 0.03125
+  tid: 175
+
+---
+submit:
+  result:
+    ok:
+      duration: 111.16818027500995
+      loss: 0.10237769915355392
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 0.125
+  tid: 144
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 5
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 176
+
+---
+submit:
+  result:
+    ok:
+      duration: 193.6909942640923
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.0078125
+  tid: 134
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 8
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 177
+
+---
+submit:
+  result:
+    ok:
+      duration: 198.08475135499611
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 135
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 8.0
+  tid: 178
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.1736319558695
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 140
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 2.0
+  tid: 179
+
+---
+submit:
+  result:
+    ok:
+      duration: 126.76798089407384
+      loss: 0.09932130460052928
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 146
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 180
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.1736319558695
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 180
+
+---
+submit:
+  result:
+    ok:
+      duration: 112.6598588230554
+      loss: 0.20545252197401148
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 2.0
+  tid: 179
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.25
+  tid: 181
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 182
+
+---
+submit:
+  result:
+    ok:
+      duration: 121.49751251516864
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 149
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 183
+
+---
+submit:
+  result:
+    ok:
+      duration: 88.53541741496883
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 159
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 184
+
+---
+submit:
+  result:
+    ok:
+      duration: 268.8309658369981
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 120
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 6
+          rbf: gto
+          sigma: 0.015625
+  tid: 185
+
+---
+submit:
+  result:
+    ok:
+      duration: 268.6142704151571
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 121
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 186
+
+---
+submit:
+  result:
+    ok:
+      duration: 61.38437095400877
+      loss: 0.20486711705363958
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+  tid: 171
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 187
+
+---
+submit:
+  result:
+    ok:
+      duration: 98.51549138198607
+      loss: 0.03485728976852623
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 1.0
+  tid: 163
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 188
+
+---
+submit:
+  result:
+    ok:
+      duration: 111.33915800601244
+      loss: 0.20545252197401148
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 2.0
+  tid: 157
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 189
+
+---
+submit:
+  result:
+    ok:
+      duration: 297.1824511329178
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 117
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 3
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 190
+
+---
+submit:
+  result:
+    ok:
+      duration: 238.74754655500874
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 132
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 191
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.0596176078543
+      loss: 0.10383110195035412
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 147
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 192
+
+---
+submit:
+  result:
+    ok:
+      duration: 79.27362096286379
+      loss: 0.1038244354518172
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 0.03125
+  tid: 175
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 193
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 8.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 156
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 16.0
+  tid: 194
+
+---
+submit:
+  result:
+    ok:
+      duration: 185.80667403386906
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 148
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 0.5
+  tid: 195
+
+---
+submit:
+  result:
+    ok:
+      duration: 790.279776572017
+      loss: 0.20531825856850244
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 8
+              rbf: gto
+              sigma: 16.0
+  tid: 1
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 196
+
+---
+submit:
+  result:
+    ok:
+      duration: 123.53887783619575
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 170
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 197
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.14660874311812
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 158
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 198
+
+---
+submit:
+  result:
+    ok:
+      duration: 55.19143643998541
+      loss: 0.10383091902117964
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 0.125
+  tid: 187
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 199
+
+---
+submit:
+  result:
+    ok:
+      duration: 152.67034497996792
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 167
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.25
+  tid: 200
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.74905424797907
+      loss: 0.02558721174691995
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 153
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 201
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.03149431501515
+      loss: 0.10383110195035412
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 168
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 202
+
+---
+submit:
+  result:
+    ok:
+      duration: 87.87336062896065
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 183
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 203
+
+---
+submit:
+  result:
+    ok:
+      duration: 111.7025127990637
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 5
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 176
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 6
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 204
+
+---
+submit:
+  result:
+    ok:
+      duration: 193.62990895891562
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 154
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 205
+
+---
+submit:
+  result:
+    ok:
+      duration: 295.1177556270268
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 136
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 1.0
+  tid: 206
+
+---
+submit:
+  result:
+    ok:
+      duration: 104.2953376090154
+      loss: 0.034651777246882065
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 0.25
+  tid: 181
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 207
+
+---
+submit:
+  result:
+    ok:
+      duration: 38.216333616990596
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 196
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 208
+
+---
+submit:
+  result:
+    ok:
+      duration: 46.61864329315722
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 197
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.03125
+  tid: 209
+
+---
+submit:
+  result:
+    ok:
+      duration: 264.8203657909762
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 142
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 210
+
+---
+submit:
+  result:
+    ok:
+      duration: 181.95124051906168
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 169
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 211
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 8.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 178
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 212
+
+---
+submit:
+  result:
+    ok:
+      duration: 181.95124051906168
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 211
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 213
+
+---
+submit:
+  result:
+    ok:
+      duration: 238.55555403302424
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.001953125
+  tid: 152
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.0078125
+  tid: 214
+
+---
+submit:
+  result:
+    ok:
+      duration: 112.91307336301543
+      loss: 0.06487769828883207
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 4
+              rbf: gto
+              sigma: 1.0
+  tid: 188
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.001953125
+  tid: 215
+
+---
+submit:
+  result:
+    ok:
+      duration: 52.021850899094716
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 202
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 216
+
+---
+submit:
+  result:
+    ok:
+      duration: 183.74777347105555
+      loss: 0.02558721174691995
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 5
+              rbf: gto
+              sigma: 0.5
+  tid: 174
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 217
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.52248356794007
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 182
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 218
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 192
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 219
+
+---
+submit:
+  result:
+    ok:
+      duration: 424.09173270105384
+      loss: 0.0988555454253399
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 256.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 6
+              rbf: gto
+              sigma: 0.0625
+  tid: 122
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.25
+  tid: 220
+
+---
+submit:
+  result:
+    ok:
+      duration: 136.07829476799816
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 3
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 190
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.0625
+  tid: 221
+
+---
+submit:
+  result:
+    ok:
+      duration: 104.2953376090154
+      loss: 0.034651777246882065
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 0.25
+  tid: 220
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 222
+
+---
+submit:
+  result:
+    ok:
+      duration: 64.47128079715185
+      loss: 0.04126078950178142
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 1.0
+  tid: 206
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 223
+
+---
+submit:
+  result:
+    ok:
+      duration: 56.765920233912766
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 210
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 224
+
+---
+submit:
+  result:
+    ok:
+      duration: 124.01701759803109
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 193
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 225
+
+---
+submit:
+  result:
+    ok:
+      duration: 262.2322281070519
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 160
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 6
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 226
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.94715865002945
+      loss: 0.11279057457261044
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 189
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 227
+
+---
+submit:
+  result:
+    ok:
+      duration: 102.89071068703197
+      loss: 0.034651777246882065
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 0.25
+  tid: 200
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 228
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 199
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 229
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 198
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.03125
+  tid: 230
+
+---
+submit:
+  result:
+    ok:
+      duration: 37.72937403805554
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 219
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 231
+
+---
+submit:
+  result:
+    ok:
+      duration: 292.3887991348747
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 155
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 4.0
+  tid: 232
+
+---
+submit:
+  result:
+    ok:
+      duration: 181.25271550402977
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 191
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 233
+
+---
+submit:
+  result:
+    ok:
+      duration: 52.507093264954165
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 224
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 234
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 212
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.0078125
+  tid: 235
+
+---
+submit:
+  result:
+    ok:
+      duration: 37.83622665493749
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 231
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 7
+          rbf: gto
+          sigma: 0.0078125
+  tid: 236
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.2051525679417
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 201
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 237
+
+---
+submit:
+  result:
+    ok:
+      duration: 257.06084566004574
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 8
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 177
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 238
+
+---
+submit:
+  result:
+    ok:
+      duration: 73.351269580191
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 223
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 239
+
+---
+submit:
+  result:
+    ok:
+      duration: 60.90406023408286
+      loss: 0.10381457248107762
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.03125
+  tid: 230
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 240
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.81019788002595
+      loss: 0.11279057457261044
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 207
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 241
+
+---
+submit:
+  result:
+    ok:
+      duration: 125.4847538289614
+      loss: 0.10372111832056291
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.0078125
+  tid: 214
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 242
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.55844492604956
+      loss: 0.10038395136092833
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.03125
+  tid: 209
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.03125
+  tid: 243
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.03882700391114
+      loss: 0.10042018461976548
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 208
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 244
+
+---
+submit:
+  result:
+    ok:
+      duration: 267.7717870660126
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 184
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 245
+
+---
+submit:
+  result:
+    ok:
+      duration: 36.30384103092365
+      loss: 0.10380511506674568
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.0078125
+  tid: 235
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 246
+
+---
+submit:
+  result:
+    ok:
+      duration: 418.8489351870958
+      loss: 0.03957079526352539
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 6
+              rbf: gto
+              sigma: 0.015625
+  tid: 143
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 6
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 247
+
+---
+submit:
+  result:
+    ok:
+      duration: 146.80949094798416
+      loss: 0.20460021958837882
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+  tid: 218
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 248
+
+---
+submit:
+  result:
+    ok:
+      duration: 138.88181376620196
+      loss: 0.062329192711174736
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 0.0625
+  tid: 221
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 249
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.11879748897627
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 216
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 250
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 232
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 251
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.03882700391114
+      loss: 0.10042018461976548
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 250
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 252
+
+---
+submit:
+  result:
+    ok:
+      duration: 170.3886846981477
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.001953125
+  tid: 215
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 253
+
+---
+submit:
+  result:
+    ok:
+      duration: 156.03882700391114
+      loss: 0.10042018461976548
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 252
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 0.001953125
+  tid: 254
+
+---
+submit:
+  result:
+    ok:
+      duration: 54.50057107210159
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 239
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.00390625
+  tid: 255
+
+---
+submit:
+  result:
+    ok:
+      duration: 59.97495112312026
+      loss: 0.06060324242383636
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 240
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 256
+
+---
+submit:
+  result:
+    ok:
+      duration: 158.42257673293352
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 222
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 257
+
+---
+submit:
+  result:
+    ok:
+      duration: 145.38038607104681
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 6
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 226
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 258
+
+---
+submit:
+  result:
+    ok:
+      duration: 409.7078810390085
+      loss: 0.03660640153848157
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 6
+              rbf: gto
+              sigma: 0.015625
+  tid: 161
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 259
+
+---
+submit:
+  result:
+    ok:
+      duration: 195.94752826495096
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 213
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 260
+
+---
+submit:
+  result:
+    ok:
+      duration: 151.80617874208838
+      loss: 0.20545246845342446
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 228
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 261
+
+---
+submit:
+  result:
+    ok:
+      duration: 452.8072893470526
+      loss: 0.20484187420860211
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 16.0
+  tid: 151
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 262
+
+---
+submit:
+  result:
+    ok:
+      duration: 160.6760352770798
+      loss: 0.10042018461976548
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 229
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.03125
+  tid: 263
+
+---
+submit:
+  result:
+    ok:
+      duration: 146.80949094798416
+      loss: 0.20460021958837882
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+  tid: 262
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 3
+          rbf: gto
+          sigma: 4.0
+  tid: 264
+
+---
+submit:
+  result:
+    ok:
+      duration: 256.6104254198726
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 6
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 204
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 265
+
+---
+submit:
+  result:
+    ok:
+      duration: 262.98382097505964
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 203
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 266
+
+---
+submit:
+  result:
+    ok:
+      duration: 45.72394857299514
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 0.001953125
+  tid: 254
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 267
+
+---
+submit:
+  result:
+    ok:
+      duration: 34.1967422591988
+      loss: 0.03140320711605504
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 257
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 268
+
+---
+submit:
+  result:
+    ok:
+      duration: 40.21698891092092
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.00390625
+  tid: 255
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 269
+
+---
+submit:
+  result:
+    ok:
+      duration: 91.25319625111297
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 246
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 270
+
+---
+submit:
+  result:
+    ok:
+      duration: 51.26258114608936
+      loss: 0.10383117959939368
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 258
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 271
+
+---
+submit:
+  result:
+    ok:
+      duration: 453.07646330306306
+      loss: 0.20482944292324626
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 16.0
+  tid: 172
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 6
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 272
+
+---
+submit:
+  result:
+    ok:
+      duration: 134.53865132690407
+      loss: 0.09681436642885535
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 0.03125
+  tid: 243
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 256.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 32.0
+  tid: 273
+
+---
+submit:
+  result:
+    ok:
+      duration: 145.38038607104681
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 6
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 272
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 0.015625
+  tid: 274
+
+---
+submit:
+  result:
+    ok:
+      duration: 141.2757373759523
+      loss: 0.20460021958837882
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+  tid: 242
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 275
+
+---
+submit:
+  result:
+    ok:
+      duration: 57.62298376997933
+      loss: 0.2040614966846636
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 3
+              rbf: gto
+              sigma: 4.0
+  tid: 264
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 276
+
+---
+submit:
+  result:
+    ok:
+      duration: 151.80617874208838
+      loss: 0.20545246845342446
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 275
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 277
+
+---
+submit:
+  result:
+    ok:
+      duration: 151.80617874208838
+      loss: 0.20545246845342446
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 276
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 278
+
+---
+submit:
+  result:
+    ok:
+      duration: 47.87461855006404
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 268
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 279
+
+---
+submit:
+  result:
+    ok:
+      duration: 166.05739526008256
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 238
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 280
+
+---
+submit:
+  result:
+    ok:
+      duration: 179.42832431197166
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 234
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 281
+
+---
+submit:
+  result:
+    ok:
+      duration: 170.71024203882553
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 237
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 282
+
+---
+submit:
+  result:
+    ok:
+      duration: 195.8126929870341
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 233
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 283
+
+---
+submit:
+  result:
+    ok:
+      duration: 421.2801601740066
+      loss: 0.09376876233270946
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 6
+              rbf: gto
+              sigma: 0.015625
+  tid: 185
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 284
+
+---
+submit:
+  result:
+    ok:
+      duration: 48.70485143503174
+      loss: 0.20003098369703035
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 270
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 2
+          rbf: gto
+          sigma: 0.25
+  tid: 285
+
+---
+submit:
+  result:
+    ok:
+      duration: 159.51498597301543
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 244
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 286
+
+---
+submit:
+  result:
+    ok:
+      duration: 370.0594605959486
+      loss: 0.03174758669177583
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 0.5
+  tid: 195
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 8.0
+  tid: 287
+
+---
+submit:
+  result:
+    ok:
+      duration: 69.98385532898828
+      loss: 0.09396735841716994
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.125
+  tid: 269
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.03125
+  tid: 288
+
+---
+submit:
+  result:
+    ok:
+      duration: 145.74764651595615
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 6
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 247
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 289
+
+---
+submit:
+  result:
+    ok:
+      duration: 268.8582797080744
+      loss: 0.20647904617734497
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 225
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 290
+
+---
+submit:
+  result:
+    ok:
+      duration: 149.63865205808543
+      loss: 0.20545246845342446
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 249
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 291
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.46404007798992
+      loss: 0.027566296584837356
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 251
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 292
+
+---
+submit:
+  result:
+    ok:
+      duration: 35.56997698894702
+      loss: 0.10383030927343133
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.03125
+  tid: 288
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 293
+
+---
+submit:
+  result:
+    ok:
+      duration: 138.30627704993822
+      loss: 0.09681436642885535
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 0.03125
+  tid: 263
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 294
+
+---
+submit:
+  result:
+    ok:
+      duration: 59.1159619090613
+      loss: 0.20019668125098247
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 2
+              rbf: gto
+              sigma: 0.25
+  tid: 285
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 295
+
+---
+submit:
+  result:
+    ok:
+      duration: 88.24803829099983
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 271
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 0.015625
+  tid: 296
+
+---
+submit:
+  result:
+    ok:
+      duration: 250.41109119309112
+      loss: 0.10379334663056616
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 7
+              rbf: gto
+              sigma: 0.0078125
+  tid: 236
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 297
+
+---
+submit:
+  result:
+    ok:
+      duration: 158.98967400100082
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 260
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 298
+
+---
+submit:
+  result:
+    ok:
+      duration: 192.88727539777756
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 253
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 299
+
+---
+submit:
+  result:
+    ok:
+      duration: 174.03554271510802
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 259
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 300
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.4473352690693
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 265
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 7
+          rbf: gto
+          sigma: 0.00390625
+  tid: 301
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 279
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 302
+
+---
+submit:
+  result:
+    ok:
+      duration: 192.88727539777756
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 301
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.5
+  tid: 303
+
+---
+submit:
+  result:
+    ok:
+      duration: 82.5093692690134
+      loss: 0.2055618998160882
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 8.0
+  tid: 287
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.25
+  tid: 304
+
+---
+submit:
+  result:
+    ok:
+      duration: 463.1276366619859
+      loss: 0.20482944292324626
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 16.0
+  tid: 194
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 305
+
+---
+submit:
+  result:
+    ok:
+      duration: 114.66979594994336
+      loss: 0.10037400207489132
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 0.015625
+  tid: 274
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 306
+
+---
+submit:
+  result:
+    ok:
+      duration: 201.06726200995035
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 256
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 8
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 307
+
+---
+submit:
+  result:
+    ok:
+      duration: 376.2766528369393
+      loss: 0.10383105957732772
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 217
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 308
+
+---
+submit:
+  result:
+    ok:
+      duration: 39.63992436812259
+      loss: 0.027016434436748848
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.125
+  tid: 293
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 309
+
+---
+submit:
+  result:
+    ok:
+      duration: 265.90654635895044
+      loss: 0.20647904617734497
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 245
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 310
+
+---
+submit:
+  result:
+    ok:
+      duration: 55.96702950983308
+      loss: 0.09545681329621707
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 0.015625
+  tid: 296
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 0.015625
+  tid: 311
+
+---
+submit:
+  result:
+    ok:
+      duration: 74.70291378512047
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 292
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 312
+
+---
+submit:
+  result:
+    ok:
+      duration: 151.97520865197293
+      loss: 0.20545129882275046
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 278
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 313
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.22370424191467
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 277
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 0.000244140625
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 314
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.40146468998864
+      loss: 0.027566296584837356
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 280
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 315
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 299
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 316
+
+---
+submit:
+  result:
+    ok:
+      duration: 37.53346558404155
+      loss: 0.03834795531075314
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.125
+  tid: 309
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 317
+
+---
+submit:
+  result:
+    ok:
+      duration: 160.6268168198876
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 284
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 318
+
+---
+submit:
+  result:
+    ok:
+      duration: 141.9269868650008
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 289
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 2.0
+  tid: 319
+
+---
+submit:
+  result:
+    ok:
+      duration: 167.45527961011976
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 283
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 320
+
+---
+submit:
+  result:
+    ok:
+      duration: 109.8945280360058
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 295
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.03125
+  tid: 321
+
+---
+submit:
+  result:
+    ok:
+      duration: 90.27389772399329
+      loss: 0.04420818677616501
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 300
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 322
+
+---
+submit:
+  result:
+    ok:
+      duration: 52.20797124085948
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 2
+              rbf: gto
+              sigma: 0.015625
+  tid: 311
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 0.5
+  tid: 323
+
+---
+submit:
+  result:
+    ok:
+      duration: 190.84162346995436
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 7
+              rbf: gto
+              sigma: 0.00390625
+  tid: 281
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.25
+  tid: 324
+
+---
+submit:
+  result:
+    ok:
+      duration: 41.1324373530224
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 316
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 325
+
+---
+submit:
+  result:
+    ok:
+      duration: 196.0235880909022
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 282
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 326
+
+---
+submit:
+  result:
+    ok:
+      duration: 262.9152908050455
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 267
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 327
+
+---
+submit:
+  result:
+    ok:
+      duration: 137.48197308601812
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 294
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 328
+
+---
+submit:
+  result:
+    ok:
+      duration: 54.035388557007536
+      loss: 0.10383105904736012
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 1.0
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 315
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 2
+          rbf: gto
+          sigma: 0.015625
+  tid: 329
+
+---
+submit:
+  result:
+    ok:
+      duration: 274.3469560518861
+      loss: 0.20647904617734497
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 266
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 8.0
+  tid: 330
+
+---
+submit:
+  result:
+    ok:
+      duration: 173.58047741488554
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 291
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.0
+  tid: 331
+
+---
+submit:
+  result:
+    ok:
+      duration: 118.59851033403538
+      loss: 0.15670181860146912
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.25
+  tid: 304
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 332
+
+---
+submit:
+  result:
+    ok:
+      duration: 382.13998279511
+      loss: 0.10383105957732772
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 241
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 333
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 32.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 14
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 64.0
+  tid: 334
+
+---
+submit:
+  result:
+    ok:
+      duration: 173.58047741488554
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 333
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 0.0078125
+  tid: 335
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.12871261499822
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 297
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 336
+
+---
+submit:
+  result:
+    ok:
+      duration: 67.46033071703278
+      loss: 0.19386653525348765
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+  tid: 317
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 337
+
+---
+submit:
+  result:
+    ok:
+      duration: 34.66432754788548
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 325
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 338
+
+---
+submit:
+  result:
+    ok:
+      duration: 47.80470206285827
+      loss: 0.18450735125789275
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 0.5
+  tid: 323
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 339
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.30059169698507
+      loss: 0.20545129881657787
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+  tid: 298
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 4
+          rbf: gto
+          sigma: 2.0
+  tid: 340
+
+---
+submit:
+  result:
+    ok:
+      duration: 141.7755807088688
+      loss: 0.10383105957539464
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 308
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 341
+
+---
+submit:
+  result:
+    ok:
+      duration: 160.89257989800535
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 306
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.03125
+  tid: 342
+
+---
+submit:
+  result:
+    ok:
+      duration: 54.32956401119009
+      loss: 0.098488989149991
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 2
+              rbf: gto
+              sigma: 0.015625
+  tid: 329
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 343
+
+---
+submit:
+  result:
+    ok:
+      duration: 164.762937346939
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 305
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 5
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 344
+
+---
+submit:
+  result:
+    ok:
+      duration: 89.01388580398634
+      loss: 0.06887054881795253
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 320
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 0.25
+  tid: 345
+
+---
+submit:
+  result:
+    ok:
+      duration: 133.48374410299584
+      loss: 0.10383105898773777
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 0.000244140625
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 314
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 346
+
+---
+submit:
+  result:
+    ok:
+      duration: 118.59851033403538
+      loss: 0.15670181860146912
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.25
+  tid: 345
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 347
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 2.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 319
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 348
+
+---
+submit:
+  result:
+    ok:
+      duration: 195.1367598590441
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 302
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.015625
+  tid: 349
+
+---
+submit:
+  result:
+    ok:
+      duration: 160.89257989800535
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 348
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.00390625
+  tid: 350
+
+---
+submit:
+  result:
+    ok:
+      duration: 371.3323098560795
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 261
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 8.0
+  tid: 351
+
+---
+submit:
+  result:
+    ok:
+      duration: 198.18793416698463
+      loss: 0.053283418740583934
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.5
+  tid: 303
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.5
+  tid: 352
+
+---
+submit:
+  result:
+    ok:
+      duration: 266.7335924790241
+      loss: 0.20551966972887387
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 290
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 353
+
+---
+submit:
+  result:
+    ok:
+      duration: 40.804279956035316
+      loss: 0.08579612766854343
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 3.0517578125e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 341
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 354
+
+---
+submit:
+  result:
+    ok:
+      duration: 75.36239849589765
+      loss: 0.20068974374357354
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+  tid: 336
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 4.0
+  tid: 355
+
+---
+submit:
+  result:
+    ok:
+      duration: 117.57413408602588
+      loss: 0.15670181860146912
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 0.25
+  tid: 324
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 64.0
+  tid: 356
+
+---
+submit:
+  result:
+    ok:
+      duration: 174.76430354593322
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 313
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 0.0078125
+  tid: 357
+
+---
+submit:
+  result:
+    ok:
+      duration: 152.77711153798737
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 318
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.001953125
+  tid: 358
+
+---
+submit:
+  result:
+    ok:
+      duration: 95.82837782101706
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 5
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 344
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.12871261499822
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 358
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 0.0078125
+  tid: 359
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 360
+
+---
+submit:
+  result:
+    ok:
+      duration: 160.36454272293486
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 327
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 361
+
+---
+submit:
+  result:
+    ok:
+      duration: 164.84304977580905
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 326
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.125
+  tid: 362
+
+---
+submit:
+  result:
+    ok:
+      duration: 135.0250744128134
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 0.0078125
+  tid: 335
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 4
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 363
+
+---
+submit:
+  result:
+    ok:
+      duration: 193.83508909097873
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.03125
+  tid: 321
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.03125
+  tid: 364
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.125
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 4.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 355
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 365
+
+---
+submit:
+  result:
+    ok:
+      duration: 196.63576362584718
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 322
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 366
+
+---
+submit:
+  result:
+    ok:
+      duration: 74.78559151105583
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 354
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 367
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.53644653689116
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.001953125
+  tid: 337
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.001953125
+  tid: 368
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.8482858389616
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 338
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 4.0
+  tid: 369
+
+---
+submit:
+  result:
+    ok:
+      duration: 376.7467418939341
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 286
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.015625
+  tid: 370
+
+---
+submit:
+  result:
+    ok:
+      duration: 264.98095101700164
+      loss: 0.20551966972887387
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 310
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 371
+
+---
+submit:
+  result:
+    ok:
+      duration: 157.1903022560291
+      loss: 0.032365496302821886
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 339
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 8.0
+  tid: 372
+
+---
+submit:
+  result:
+    ok:
+      duration: 200.81682581198402
+      loss: 0.20231176719307986
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 8.0
+  tid: 330
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.5
+  tid: 373
+
+---
+submit:
+  result:
+    ok:
+      duration: 98.87221754412167
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 0.0078125
+  tid: 357
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 0.5
+  tid: 374
+
+---
+submit:
+  result:
+    ok:
+      duration: 153.40149382408708
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 343
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 375
+
+---
+submit:
+  result:
+    ok:
+      duration: 70.70209435396828
+      loss: 0.10383117959939368
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 4
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 363
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 376
+
+---
+submit:
+  result:
+    ok:
+      duration: 163.51050659711473
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 346
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.125
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 64.0
+  tid: 377
+
+---
+submit:
+  result:
+    ok:
+      duration: 84.21209206408821
+      loss: 0.07991238064147738
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.125
+  tid: 362
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0078125
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 378
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.36459418199956
+      loss: 0.10383095487486592
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.0009765625
+  tid: 347
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 0.0078125
+  tid: 379
+
+---
+submit:
+  result:
+    ok:
+      duration: 209.4577421308495
+      loss: 0.20545219127689893
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 4
+              rbf: gto
+              sigma: 2.0
+  tid: 340
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 380
+
+---
+submit:
+  result:
+    ok:
+      duration: 197.7367432769388
+      loss: 0.10383105957732772
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.03125
+  tid: 342
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.0625
+  tid: 381
+
+---
+submit:
+  result:
+    ok:
+      duration: 269.3251184169203
+      loss: 0.1038310596023975
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 328
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.125
+  tid: 382
+
+---
+submit:
+  result:
+    ok:
+      duration: 114.80498661799356
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 0.0078125
+  tid: 359
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 383
+
+---
+submit:
+  result:
+    ok:
+      duration: 374.4299032310955
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.5
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 8
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 307
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 384
+
+---
+submit:
+  result:
+    ok:
+      duration: 270.47459671716206
+      loss: 0.20551966972887387
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.0
+  tid: 331
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 5
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 385
+
+---
+submit:
+  result:
+    ok:
+      duration: 46.47158037405461
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 376
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8192.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 7
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 386
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 16.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 312
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 387
+
+---
+submit:
+  result:
+    ok:
+      duration: 202.5071908920072
+      loss: 0.20231176719307986
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 8.0
+  tid: 351
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 4.0
+  tid: 388
+
+---
+submit:
+  result:
+    ok:
+      duration: 141.4672286908608
+      loss: 0.024012271136856972
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 360
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 16.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 389
+
+---
+submit:
+  result:
+    ok:
+      duration: 152.45246855192818
+      loss: 0.04412857910848701
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.015625
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 361
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 390
+
+---
+submit:
+  result:
+    ok:
+      duration: 74.6172431060113
+      loss: 0.10383103767404345
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 375
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 391
+
+---
+submit:
+  result:
+    ok:
+      duration: 82.1906439899467
+      loss: 0.1038310602421515
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0078125
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 6
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 4
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 378
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 392
+
+---
+submit:
+  result:
+    ok:
+      duration: 152.30091872997582
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1024.0
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 366
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 2.0
+  tid: 393
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.25057560903952
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 367
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.03125
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 394
+
+---
+submit:
+  result:
+    ok:
+      duration: 262.75012400210835
+      loss: 0.10383105891901451
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.00390625
+  tid: 350
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 3
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 395
+
+---
+submit:
+  result:
+    ok:
+      duration: 264.1425420450978
+      loss: 0.10383105967049454
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.015625
+  tid: 349
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 3.0517578125e-05
+      representation:
+        ds_soap:
+          cutoff: 6
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 64.0
+  tid: 396
+
+---
+submit:
+  result:
+    ok:
+      duration: 167.12490746285766
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.001953125
+  tid: 368
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 397
+
+---
+submit:
+  result:
+    ok:
+      duration: 259.00205602683127
+      loss: 0.026255114970910733
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.5
+  tid: 352
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 398
+
+---
+submit:
+  result:
+    ok:
+      duration: 193.2131473349873
+      loss: 0.10379572184721791
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.03125
+  tid: 364
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 399
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.35874406900257
+      loss: 0.1947511763271488
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 4.0
+  tid: 369
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 400
+
+---
+submit:
+  result:
+    ok:
+      duration: 117.23426391696557
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 0.0078125
+  tid: 379
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 401
+
+---
+submit:
+  result:
+    ok:
+      duration: 84.80662742001005
+      loss: 0.10383106407375574
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 0.0001220703125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 5
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 385
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 5
+          rbf: gto
+          sigma: 0.001953125
+  tid: 402
+
+---
+submit:
+  result:
+    ok:
+      duration: 196.24029363505542
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 365
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 7
+          rbf: gto
+          sigma: 3.0517578125e-05
+  tid: 403
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 16.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 332
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0001220703125
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 404
+
+---
+submit:
+  result:
+    ok:
+      duration: 163.2812171841506
+      loss: 0.19364575731628808
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.5
+  tid: 374
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 405
+
+---
+submit:
+  result:
+    ok:
+      duration: 173.4544924639631
+      loss: 0.028003576211254735
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 512.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 0.5
+  tid: 373
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 4.0
+  tid: 406
+
+---
+submit:
+  result:
+    ok:
+      duration: 140.67774035409093
+      loss: 0.04430725365544303
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 380
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 407
+
+---
+submit:
+  result:
+    ok:
+      duration: 214.76729825814255
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 371
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 6.103515625e-05
+  tid: 408
+
+---
+submit:
+  result:
+    ok:
+      duration: 121.59680467983708
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8192.0
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 7
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 386
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 409
+
+---
+submit:
+  result:
+    ok:
+      duration: 36.778010939015076
+      loss: 0.1038310709301258
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0001220703125
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 1.9073486328125e-06
+  tid: 404
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 410
+
+---
+submit:
+  result:
+    ok:
+      duration: 69.31444849609397
+      loss: 0.10383105965764074
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.0078125
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 3
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 395
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 2
+          rbf: gto
+          sigma: 0.03125
+  tid: 411
+
+---
+submit:
+  result:
+    ok:
+      duration: 154.04995659110136
+      loss: 0.1037637870511256
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 8.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.0625
+  tid: 381
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0009765625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 7.62939453125e-06
+  tid: 412
+
+---
+submit:
+  result:
+    ok:
+      duration: 98.31674290704541
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 392
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 2.0
+  tid: 413
+
+---
+submit:
+  result:
+    ok:
+      duration: 261.2529670649674
+      loss: 0.10383105967049454
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 16.0
+                  norm: false
+              nl: 0.015625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 8
+              rbf: gto
+              sigma: 0.015625
+  tid: 370
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 1.52587890625e-05
+  tid: 414
+
+---
+submit:
+  result:
+    error:
+      error: QMMLException
+      error_text: Failed to train KernelRidgeRegression model due to kernel matrix
+        not being positive definite
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00390625
+                  norm: false
+              nl: 3.814697265625e-06
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 4
+              n_max: 2
+              rbf: gto
+              sigma: 16.0
+      traceback: "pebble.common.RemoteTraceback: Traceback (most recent call last):\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 64, in __init__\n    self._ll = np.linalg.cholesky(kkc)  # Kc + lambda\
+        \ I = L L^T\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 759, in cholesky\n    r = gufunc(a, signature=signature, extobj=extobj)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/numpy/linalg/linalg.py\"\
+        , line 100, in _raise_linalgerror_nonposdef\n    raise LinAlgError(\"Matrix\
+        \ is not positive definite\")\nnumpy.linalg.LinAlgError: Matrix is not positive\
+        \ definite\n\nDuring handling of the above exception, another exception occurred:\n\
+        \nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/pebble/common.py\"\
+        , line 174, in process_execute\n    return function(*args, **kwargs)\n  File\
+        \ \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 163, in evaluate\n    eval_result = evaluator(suggestion)\n  File \"\
+        /u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/evaluation/evaluator.py\"\
+        , line 38, in __call__\n    result, duration = timed(self.evaluate)(model)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/utility/timing.py\"\
+        , line 14, in wrapper\n    result = f(*args, **kwargs)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/evaluators/evaluator_holdout.py\"\
+        , line 45, in evaluate\n    model.train(self.train, target=self.target)\n\
+        \  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/model.py\"\
+        , line 93, in train\n    self.regression.train(x=x, y=y)\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/regression/qmml/krr.py\"\
+        , line 44, in train\n    kernel, y, theta=(self.nl,), centering=self.centering\n\
+        \  File \"/u/mlang/software/qmmlpack/python/qmmlpack/models/regression.py\"\
+        , line 66, in __init__\n    raise QMMLException(\"Failed to train KernelRidgeRegression\
+        \ model due to kernel matrix not being positive definite\")\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n\n\nThe above exception was the direct cause of the following\
+        \ exception:\n\nTraceback (most recent call last):\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/site-packages/cmlkit/tune/run/pool.py\"\
+        , line 118, in finish\n    result = future.result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 425, in result\n    return self.__get_result()\n  File \"/u/mlang/conda-envs/py37/lib/python3.7/concurrent/futures/_base.py\"\
+        , line 384, in __get_result\n    raise self._exception\nqmmlpack.library.QMMLException:\
+        \ Failed to train KernelRidgeRegression model due to kernel matrix not being\
+        \ positive definite\n"
+  tid: 353
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.0625
+  tid: 415
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.38394497707486
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 387
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 8.0
+              norm: false
+          nl: 0.001953125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 6
+          n_max: 4
+          rbf: gto
+          sigma: 1.0
+  tid: 416
+
+---
+submit:
+  result:
+    ok:
+      duration: 250.12155831512064
+      loss: 0.20500691465085288
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 8.0
+  tid: 372
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.5
+  tid: 417
+
+---
+submit:
+  result:
+    ok:
+      duration: 36.07857524394058
+      loss: 0.08904979097767202
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 6.103515625e-05
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 2
+              rbf: gto
+              sigma: 0.03125
+  tid: 411
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 32.0
+              norm: false
+          nl: 7.62939453125e-06
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.25
+  tid: 418
+
+---
+submit:
+  result:
+    ok:
+      duration: 195.44813533383422
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 383
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 419
+
+---
+submit:
+  result:
+    ok:
+      duration: 140.67774035409093
+      loss: 0.04430725365544303
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 418
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00390625
+              norm: false
+          nl: 0.25
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 0.00048828125
+  tid: 420
+
+---
+submit:
+  result:
+    ok:
+      duration: 198.5839437651448
+      loss: 0.03995967537235676
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.125
+  tid: 382
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1.0
+              norm: false
+          nl: 0.03125
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.125
+  tid: 421
+
+---
+submit:
+  result:
+    ok:
+      duration: 121.1939890619833
+      loss: 0.20325231946330846
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4.0
+                  norm: false
+              nl: 0.001953125
+          representation:
+            ds_soap:
+              cutoff: 5
+              elems: [8, 13, 31, 49]
+              l_max: 6
+              n_max: 4
+              rbf: gto
+              sigma: 1.0
+  tid: 397
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 422
+
+---
+submit:
+  result:
+    ok:
+      duration: 198.5839437651448
+      loss: 0.03995967537235676
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.125
+  tid: 421
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 128.0
+              norm: false
+          nl: 0.0009765625
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0078125
+  tid: 423
+
+---
+submit:
+  result:
+    ok:
+      duration: 195.44813533383422
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 422
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 9
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 7
+          rbf: gto
+          sigma: 0.0001220703125
+  tid: 424
+
+---
+submit:
+  result:
+    ok:
+      duration: 182.48920257412829
+      loss: 0.1947511763271488
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 2048.0
+                  norm: false
+              nl: 1.52587890625e-05
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 4.0
+  tid: 388
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.000244140625
+              norm: false
+          nl: 1.52587890625e-05
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 5
+          rbf: gto
+          sigma: 0.00390625
+  tid: 425
+
+---
+submit:
+  result:
+    ok:
+      duration: 139.41801510285586
+      loss: 0.04430725365544303
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.25
+  tid: 398
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 1024.0
+              norm: false
+          nl: 0.0001220703125
+      representation:
+        ds_soap:
+          cutoff: 5
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 7
+          rbf: gto
+          sigma: 0.03125
+  tid: 426
+
+---
+submit:
+  result:
+    ok:
+      duration: 176.49070922704414
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0625
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 3.814697265625e-06
+  tid: 391
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 427
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.38394497707486
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 427
+
+---
+submit:
+  result:
+    ok:
+      duration: 139.9341809139587
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.000244140625
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 10
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 5
+              rbf: gto
+              sigma: 0.001953125
+  tid: 402
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.25
+              norm: false
+          nl: 0.125
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 0.000244140625
+  tid: 428
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 4.0
+  tid: 429
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.38394497707486
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 428
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2048.0
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 3
+          elems: [8, 13, 31, 49]
+          l_max: 7
+          n_max: 5
+          rbf: gto
+          sigma: 4.0
+  tid: 430
+
+---
+submit:
+  result:
+    ok:
+      duration: 170.53114770306274
+      loss: 0.10383105932819918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.03125
+                  norm: false
+              nl: 0.5
+          representation:
+            ds_soap:
+              cutoff: 4
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 1.52587890625e-05
+  tid: 394
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 512.0
+              norm: false
+          nl: 0.015625
+      representation:
+        ds_soap:
+          cutoff: 7
+          elems: [8, 13, 31, 49]
+          l_max: 4
+          n_max: 8
+          rbf: gto
+          sigma: 0.0009765625
+  tid: 431
+
+---
+submit:
+  result:
+    ok:
+      duration: 184.7800991581753
+      loss: 0.1903897071779918
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 4096.0
+                  norm: false
+              nl: 0.0625
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 2
+              n_max: 8
+              rbf: gto
+              sigma: 2.0
+  tid: 393
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.00048828125
+              norm: false
+          nl: 1.0
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 6
+          rbf: gto
+          sigma: 8.0
+  tid: 432
+
+---
+submit:
+  result:
+    ok:
+      duration: 155.9527495659422
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 64.0
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.00048828125
+  tid: 399
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.0625
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 0.125
+  tid: 433
+
+---
+submit:
+  result:
+    ok:
+      duration: 55.12069165613502
+      loss: 0.10383105946549931
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.001953125
+                  norm: false
+              nl: 0.25
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 9.5367431640625e-07
+  tid: 419
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 64.0
+              norm: false
+          nl: 0.0625
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 6
+          rbf: gto
+          sigma: 3.814697265625e-06
+  tid: 434
+
+---
+submit:
+  result:
+    ok:
+      duration: 98.73673754394986
+      loss: 0.1038310597778542
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.0009765625
+                  norm: false
+              nl: 0.00390625
+          representation:
+            ds_soap:
+              cutoff: 7
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 2
+              rbf: gto
+              sigma: 7.62939453125e-06
+  tid: 412
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.001953125
+              norm: false
+          nl: 0.00390625
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 2
+          rbf: gto
+          sigma: 1.9073486328125e-06
+  tid: 435
+
+---
+submit:
+  result:
+    ok:
+      duration: 222.502446268918
+      loss: 0.10383105730378193
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.00048828125
+                  norm: false
+              nl: 0.00048828125
+          representation:
+            ds_soap:
+              cutoff: 8
+              elems: [8, 13, 31, 49]
+              l_max: 5
+              n_max: 6
+              rbf: gto
+              sigma: 6.103515625e-05
+  tid: 390
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 0.00048828125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 6
+          rbf: gto
+          sigma: 0.001953125
+  tid: 436
+
+---
+submit:
+  result:
+    ok:
+      duration: 86.35354730510153
+      loss: 0.05693554836423121
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 32.0
+                  norm: false
+              nl: 7.62939453125e-06
+          representation:
+            ds_soap:
+              cutoff: 2
+              elems: [8, 13, 31, 49]
+              l_max: 8
+              n_max: 3
+              rbf: gto
+              sigma: 0.5
+  tid: 417
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.015625
+              norm: false
+          nl: 6.103515625e-05
+      representation:
+        ds_soap:
+          cutoff: 2
+          elems: [8, 13, 31, 49]
+          l_max: 8
+          n_max: 3
+          rbf: gto
+          sigma: 9.5367431640625e-07
+  tid: 437
+
+---
+submit:
+  result:
+    ok:
+      duration: 165.92491489299573
+      loss: 0.10383105953946598
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 0.25
+                  norm: false
+              nl: 0.125
+          representation:
+            ds_soap:
+              cutoff: 3
+              elems: [8, 13, 31, 49]
+              l_max: 7
+              n_max: 5
+              rbf: gto
+              sigma: 0.000244140625
+  tid: 405
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 4096.0
+              norm: false
+          nl: 0.0078125
+      representation:
+        ds_soap:
+          cutoff: 8
+          elems: [8, 13, 31, 49]
+          l_max: 2
+          n_max: 8
+          rbf: gto
+          sigma: 0.5
+  tid: 438
+
+---
+submit:
+  result:
+    ok:
+      duration: 191.25674089603126
+      loss: 0.10383105810322947
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 128.0
+                  norm: false
+              nl: 0.0009765625
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 0.0001220703125
+  tid: 401
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 2.0
+              norm: false
+          nl: 0.5
+      representation:
+        ds_soap:
+          cutoff: 4
+          elems: [8, 13, 31, 49]
+          l_max: 5
+          n_max: 2
+          rbf: gto
+          sigma: 16.0
+  tid: 439
+
+---
+submit:
+  result:
+    ok:
+      duration: 196.3781150460709
+      loss: 0.10383105957732772
+      suggestion:
+        model:
+          per: cell
+          regression:
+            krr:
+              kernel:
+                kernel_atomic:
+                  kernelf:
+                    gaussian:
+                      ls: 1.0
+                  norm: false
+              nl: 0.03125
+          representation:
+            ds_soap:
+              cutoff: 9
+              elems: [8, 13, 31, 49]
+              l_max: 3
+              n_max: 7
+              rbf: gto
+              sigma: 3.0517578125e-05
+  tid: 400
+
+---
+suggest:
+  suggestion:
+    model:
+      per: cell
+      regression:
+        krr:
+          kernel:
+            kernel_atomic:
+              kernelf:
+                gaussian:
+                  ls: 0.5
+              norm: false
+          nl: 3.814697265625e-06
+      representation:
+        ds_soap:
+          cutoff: 10
+          elems: [8, 13, 31, 49]
+          l_max: 3
+          n_max: 4
+          rbf: gto
+          sigma: 0.0625
+  tid: 440
+
+---
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..8b1d68bdd2cd22d58ad9e20a5b8ae325b377de89
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,17 @@
+import json
+from setuptools import setup, find_packages
+
+with open('metainfo.json') as file:
+    metainfo = json.load(file)
+
+setup(
+    name='tutorial_cmlkit',
+    version='0.1',
+    author=', '.join(metainfo['authors']),
+    author_email=metainfo['email'],
+    url=metainfo['url'],
+    description=metainfo['title'],
+    long_description=metainfo['description'],
+    packages=find_packages(),
+    install_requires=['cmlkit', 'cscribe'],
+)