diff --git "a/notebooks_tutorials/03_fine_tuning_posttrained_model.ipynb" "b/notebooks_tutorials/03_fine_tuning_posttrained_model.ipynb"
--- "a/notebooks_tutorials/03_fine_tuning_posttrained_model.ipynb"
+++ "b/notebooks_tutorials/03_fine_tuning_posttrained_model.ipynb"
@@ -6,11 +6,11 @@
    "source": [
     "# 🧬 Fine-Tuning a Post-trained Model on BigWig Tracks Prediction\n",
     "\n",
-    "This notebook demonstrates a **simplified fine-tuning setup** that enables training of a **post-trained Nucleotide Transformer v3 (NTv3) model** to predict BigWig signal tracks directly from DNA sequences. The streamlined approach leverages a pre-trained NTv3 backbone as a feature extractor and adds a custom prediction head that outputs single-nucleotide resolution signal values for various genomic tracks (e.g., ChIP-seq, ATAC-seq, RNA-seq).\n",
+    "This notebook demonstrates a **simplified fine-tuning setup** that enables training of a post-trained Nucleotide Transformer v3 (NTv3) model to predict BigWig signal tracks directly from DNA sequences. The streamlined approach leverages a pre-trained NTv3 backbone as a feature extractor and adds a custom prediction head that outputs single-nucleotide resolution signal values for various genomic tracks (e.g., ChIP-seq, ATAC-seq, RNA-seq).\n",
     "\n",
     "**🎯 Notebook purpose:**\n",
     "This notebook is configured to train the `NTv3_650M_post` model on the `human` species from the NTv3 benchmark dataset. To run this training, you will need a large GPU (either A100 or H100).\n",
-    "For a simplified version of this notebook that uses the `NTv3_8M_pre` model and runs on a CPU, please see the [02_fine_tuning.ipynb](https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/02_fine_tuning_pretrained_model.ipynb) notebook.\n",
+    "For a simplified version of this notebook that uses the `NTv3_8M_pre` model and runs on a CPU, please see the [02_fine_tuning.ipynb](https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/02_fine_tuning.ipynb) notebook.\n",
     "The notebook uses the same \"simplified setup\" as described there. \n",
     "\n",
     "📝 Note for Google Colab users: This notebook is compatible with Colab! This notebook is designed to be run on a high-performance GPU. The default parameters can be used with a H100 with 80GB of HBM."
@@ -25,9 +25,58 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pyfaidx in ./.venv/lib/python3.11/site-packages (0.9.0.3)\n",
+      "Requirement already satisfied: pyBigWig in ./.venv/lib/python3.11/site-packages (0.3.24)\n",
+      "Requirement already satisfied: torchmetrics in ./.venv/lib/python3.11/site-packages (1.8.2)\n",
+      "Requirement already satisfied: transformers in ./.venv/lib/python3.11/site-packages (4.57.1)\n",
+      "Requirement already satisfied: packaging in ./.venv/lib/python3.11/site-packages (from pyfaidx) (24.2)\n",
+      "Requirement already satisfied: numpy>1.20.0 in ./.venv/lib/python3.11/site-packages (from torchmetrics) (2.1.3)\n",
+      "Requirement already satisfied: torch>=2.0.0 in ./.venv/lib/python3.11/site-packages (from torchmetrics) (2.5.1+cu121)\n",
+      "Requirement already satisfied: lightning-utilities>=0.8.0 in ./.venv/lib/python3.11/site-packages (from torchmetrics) (0.15.2)\n",
+      "Requirement already satisfied: filelock in ./.venv/lib/python3.11/site-packages (from transformers) (3.17.0)\n",
+      "Requirement already satisfied: huggingface-hub<1.0,>=0.34.0 in ./.venv/lib/python3.11/site-packages (from transformers) (0.36.0)\n",
+      "Requirement already satisfied: pyyaml>=5.1 in ./.venv/lib/python3.11/site-packages (from transformers) (6.0.2)\n",
+      "Requirement already satisfied: regex!=2019.12.17 in ./.venv/lib/python3.11/site-packages (from transformers) (2024.11.6)\n",
+      "Requirement already satisfied: requests in ./.venv/lib/python3.11/site-packages (from transformers) (2.32.3)\n",
+      "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in ./.venv/lib/python3.11/site-packages (from transformers) (0.22.1)\n",
+      "Requirement already satisfied: safetensors>=0.4.3 in ./.venv/lib/python3.11/site-packages (from transformers) (0.7.0)\n",
+      "Requirement already satisfied: tqdm>=4.27 in ./.venv/lib/python3.11/site-packages (from transformers) (4.67.1)\n",
+      "Requirement already satisfied: fsspec>=2023.5.0 in ./.venv/lib/python3.11/site-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (2025.3.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.venv/lib/python3.11/site-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (4.12.2)\n",
+      "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in ./.venv/lib/python3.11/site-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (1.2.0)\n",
+      "Requirement already satisfied: setuptools in ./.venv/lib/python3.11/site-packages (from lightning-utilities>=0.8.0->torchmetrics) (77.0.1)\n",
+      "Requirement already satisfied: networkx in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (3.6.1)\n",
+      "Requirement already satisfied: jinja2 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (3.1.6)\n",
+      "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.105)\n",
+      "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.105)\n",
+      "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.105)\n",
+      "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (9.1.0.70)\n",
+      "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.3.1)\n",
+      "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (11.0.2.54)\n",
+      "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (10.3.2.106)\n",
+      "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (11.4.5.107)\n",
+      "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.0.106)\n",
+      "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (2.21.5)\n",
+      "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (12.1.105)\n",
+      "Requirement already satisfied: triton==3.1.0 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (3.1.0)\n",
+      "Requirement already satisfied: sympy==1.13.1 in ./.venv/lib/python3.11/site-packages (from torch>=2.0.0->torchmetrics) (1.13.1)\n",
+      "Requirement already satisfied: nvidia-nvjitlink-cu12 in ./.venv/lib/python3.11/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=2.0.0->torchmetrics) (12.9.86)\n",
+      "Requirement already satisfied: mpmath<1.4,>=1.1.0 in ./.venv/lib/python3.11/site-packages (from sympy==1.13.1->torch>=2.0.0->torchmetrics) (1.3.0)\n",
+      "Requirement already satisfied: MarkupSafe>=2.0 in ./.venv/lib/python3.11/site-packages (from jinja2->torch>=2.0.0->torchmetrics) (3.0.2)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in ./.venv/lib/python3.11/site-packages (from requests->transformers) (3.4.1)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in ./.venv/lib/python3.11/site-packages (from requests->transformers) (3.10)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in ./.venv/lib/python3.11/site-packages (from requests->transformers) (2.3.0)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in ./.venv/lib/python3.11/site-packages (from requests->transformers) (2025.1.31)\n"
+     ]
+    }
+   ],
    "source": [
     "# Install dependencies\n",
     "!pip install pyfaidx pyBigWig torchmetrics transformers"
@@ -35,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -97,14 +146,25 @@
     "### General\n",
     "- **`seed`**: Random seed for reproducibility\n",
     "- **`device`**: Device to run training on (\"cuda\" or \"cpu\")\n",
-    "- **`num_workers`**: Number of worker processes for DataLoader (0 = single-threaded)"
+    "- **`num_workers`**: Number of worker processes for DataLoader (0 = single-threaded)\n",
+    "\n",
+    "### Reproducing the results reported in the paper\n",
+    "This notebook is configured to train for 15k steps, which is ~2B tokens. To reproduce the results reported in the paper, you should train for 120k steps (~15B tokens).\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using device: cuda\n"
+     ]
+    }
+   ],
    "source": [
     "config = {\n",
     "    # Model\n",
@@ -157,7 +217,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -275,9 +335,178 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9128a6c975214f6c88ec724605e91a6b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Fetching 37 files:   0%|          | 0/37 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "59d8aafd88cd4e758f05f173f1207c85",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR701YIC.bigw(…):   0%|          | 0.00/977M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e16c5d9d14824bee8492a852f386ffe9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR814RGG.bigw(…):   0%|          | 0.00/2.63G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0029bc04826c417bbee823bd73ab3e82",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR862QCH_M.bi(…):   0%|          | 0.00/18.3M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "401af71b03eb431b9cb576d8131ad0eb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR682BFG.bigw(…):   0%|          | 0.00/2.45G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5617c59a79d14aeb8942efb3b935db02",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR754DRC.bigw(…):   0%|          | 0.00/2.64G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "759af66a8c45490eb1018a0d459d6030",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR863PSM.bigw(…):   0%|          | 0.00/2.45G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a67c62199c354a189c65117c55cd6a36",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR325NFE.bigw(…):   0%|          | 0.00/5.67G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6ed28bcaa060483285bd13dd644a3170",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR935RNW_M.bi(…):   0%|          | 0.00/27.8M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1ff039298a9248db8fb5b40a9b0c4980",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/functional_tracks/ENCSR962OTG.bigw(…):   0%|          | 0.00/2.22G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a623f734ad024d4fad6dfe8863e5f685",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "human/genome.fasta:   0%|          | 0.00/3.27G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "44515d984cf041d18f0934efca2182c1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "splits.bed:   0%|          | 0.00/9.95k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "os.makedirs(config[\"data_cache_dir\"], exist_ok=True)\n",
     "\n",
@@ -314,7 +543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -392,9 +621,206 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "493e87625559418c97a681c6657ec040",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer_config.json:   0%|          | 0.00/1.48k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a74a70e540534d4a85ec0cca14563a38",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenization_ntv3.py:   0%|          | 0.00/7.85k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
+      "- tokenization_ntv3.py\n",
+      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7a25dbf243824057832983a044896fbb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "vocab.json:   0%|          | 0.00/138 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b031140ae9194facab52d645ec3f5986",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "special_tokens_map.json:   0%|          | 0.00/149 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5957665fe0ad44d7aabcb7918bf8edb1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "config.json:   0%|          | 0.00/339k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4e8bddb643c647cab6af84c2ba41b8b6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "configuration_ntv3_posttrained.py:   0%|          | 0.00/4.70k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cac30fefe5594a2ca36dc60706c21736",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "configuration_ntv3_pretrained.py:   0%|          | 0.00/8.09k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
+      "- configuration_ntv3_pretrained.py\n",
+      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
+      "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
+      "- configuration_ntv3_posttrained.py\n",
+      "- configuration_ntv3_pretrained.py\n",
+      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ed5078d57c1c41aeb494f7e14cae7481",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "modeling_ntv3_posttrained.py:   0%|          | 0.00/44.3k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5d0a3edcf28d49eeae16e830add187b2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "modeling_ntv3_pretrained.py:   0%|          | 0.00/35.2k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
+      "- modeling_ntv3_pretrained.py\n",
+      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
+      "A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/ntv3_base_model:\n",
+      "- modeling_ntv3_posttrained.py\n",
+      "- modeling_ntv3_pretrained.py\n",
+      ". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n",
+      "2025-12-23 07:58:52.121333: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2025-12-23 07:58:52.135510: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
+      "E0000 00:00:1766473132.149342    2431 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "E0000 00:00:1766473132.153146    2431 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "W0000 00:00:1766473132.163710    2431 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1766473132.163723    2431 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1766473132.163725    2431 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1766473132.163726    2431 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "2025-12-23 07:58:52.167866: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI AVX512_BF16 AVX512_FP16 AVX_VNNI AMX_TILE AMX_INT8 AMX_BF16 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d69802317a344e1492bd69d1eb7ab4fc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model.safetensors:   0%|          | 0.00/2.72G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using species: human with ids: tensor([27])\n",
+      "Model loaded: InstaDeepAI/NTv3_650M_post\n",
+      "Number of bigwig tracks: 34\n",
+      "Model parameters: 679,842,582\n"
+     ]
+    }
+   ],
    "source": [
     "# Load tokenizer\n",
     "tokenizer = AutoTokenizer.from_pretrained(config[\"model_name\"], trust_remote_code=True)\n",
@@ -403,7 +829,7 @@
     "model = HFModelWithHead(\n",
     "    model_name=config[\"model_name\"],\n",
     "    bigwig_track_names=bigwig_ids,\n",
-    "    species_str=config[\"full_species_name\"],\n",
+    "    species_str=config[\"species_name\"],\n",
     "    keep_target_center_fraction=config[\"keep_target_center_fraction\"],\n",
     ")\n",
     "model = model.to(device)\n",
@@ -425,7 +851,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -583,7 +1009,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -619,9 +1045,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Track means: [0.0057952  0.0463601  0.00376132 0.0034627  0.01080696 0.00227474\n",
+      " 0.00494403 0.00370035 0.44757743 0.00211876 0.72501702 0.00400846\n",
+      " 0.01177604 0.00498001 0.00530738 0.00343102 0.00877379 0.00548278\n",
+      " 0.01612531 0.72625355 0.00622468 0.00574464 0.63734638 0.00820212\n",
+      " 0.00627039 0.00128605 0.00335876 0.48636405 0.66685837 0.64354244\n",
+      " 0.01549048 0.65863696 0.00219467 0.74402866]\n",
+      "Number of tracks: (34,)\n",
+      "\n",
+      "Train samples: 60000\n",
+      "Val samples: 1000\n",
+      "Test samples: 10000\n"
+     ]
+    }
+   ],
    "source": [
     "# Create datasets & dataloaders\n",
     "create_dataset_fn = functools.partial(\n",
@@ -689,9 +1133,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training configuration:\n",
+      "  Batch size: 4\n",
+      "  Total training steps: 15000\n",
+      "  Log metrics every: 40 steps\n",
+      "  Validate every: 400 steps\n",
+      "\n",
+      "Optimizer setup:\n",
+      "  Learning rate: 1e-05\n"
+     ]
+    }
+   ],
    "source": [
     "# Training setup\n",
     "print(f\"Training configuration:\")\n",
@@ -722,7 +1181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -812,7 +1271,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -832,7 +1291,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -906,7 +1365,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -981,9 +1440,1949 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Starting training for 15000 steps\n",
+      "\n",
+      "Step 40/15000 | Loss: 5.1443 | Mean Pearson: 0.0720\n",
+      "Step 80/15000 | Loss: 4.6615 | Mean Pearson: 0.1709\n",
+      "Step 120/15000 | Loss: 5.0776 | Mean Pearson: 0.2432\n",
+      "Step 160/15000 | Loss: 5.6502 | Mean Pearson: 0.3266\n",
+      "Step 200/15000 | Loss: 4.5638 | Mean Pearson: 0.3366\n",
+      "Step 240/15000 | Loss: 4.3083 | Mean Pearson: 0.3680\n",
+      "Step 280/15000 | Loss: 4.4393 | Mean Pearson: 0.3946\n",
+      "Step 320/15000 | Loss: 5.1535 | Mean Pearson: 0.4037\n",
+      "Step 360/15000 | Loss: 4.5303 | Mean Pearson: 0.3810\n",
+      "Step 400/15000 | Loss: 4.7998 | Mean Pearson: 0.4136\n",
+      "\n",
+      "Running validation at step 400...\n",
+      "Step 400/15000 | Loss: 4.9685 | Mean Pearson: 0.3564\n",
+      "    ENCSR154HRN_P/pearson: 0.3056\n",
+      "    ENCSR701YIC/pearson: 0.3415\n",
+      "    ENCSR935RNW_P/pearson: 0.2881\n",
+      "    ENCSR100LIJ_P/pearson: 0.2484\n",
+      "    ENCSR527JGN_P/pearson: 0.5866\n",
+      "    ENCSR114HGS_P/pearson: 0.1056\n",
+      "    ENCSR484LTQ_M/pearson: 0.2578\n",
+      "    ENCSR935RNW_M/pearson: 0.2584\n",
+      "    ENCSR410DWV/pearson: 0.5926\n",
+      "    ENCSR046BCI_M/pearson: 0.2597\n",
+      "    ENCSR814RGG/pearson: 0.5250\n",
+      "    ENCSR799DGV_P/pearson: 0.2899\n",
+      "    ENCSR527JGN_M/pearson: 0.4183\n",
+      "    ENCSR154HRN_M/pearson: 0.2784\n",
+      "    ENCSR862QCH_M/pearson: 0.2661\n",
+      "    ENCSR100LIJ_M/pearson: 0.2445\n",
+      "    ENCSR321PWZ_P/pearson: 0.3953\n",
+      "    ENCSR484LTQ_P/pearson: 0.2386\n",
+      "    ENCSR619DQO_P/pearson: 0.5103\n",
+      "    ENCSR325NFE/pearson: 0.5775\n",
+      "    ENCSR249ROI_P/pearson: 0.3969\n",
+      "    ENCSR249ROI_M/pearson: 0.3329\n",
+      "    ENCSR754DRC/pearson: 0.2812\n",
+      "    ENCSR321PWZ_M/pearson: 0.4385\n",
+      "    ENCSR862QCH_P/pearson: 0.2487\n",
+      "    ENCSR046BCI_P/pearson: 0.1867\n",
+      "    ENCSR799DGV_M/pearson: 0.2586\n",
+      "    ENCSR962OTG/pearson: 0.6789\n",
+      "    ENCSR682BFG/pearson: 0.4250\n",
+      "    ENCSR628PLS/pearson: 0.4246\n",
+      "    ENCSR619DQO_M/pearson: 0.4234\n",
+      "    ENCSR487QSB/pearson: 0.4621\n",
+      "    ENCSR114HGS_M/pearson: 0.0880\n",
+      "    ENCSR863PSM/pearson: 0.4828\n",
+      "    mean/pearson: 0.3564\n",
+      "    loss: 4.9685\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 440/15000 | Loss: 5.5448 | Mean Pearson: 0.4306\n",
+      "Step 480/15000 | Loss: 5.3340 | Mean Pearson: 0.4025\n",
+      "Step 520/15000 | Loss: 4.9919 | Mean Pearson: 0.4061\n",
+      "Step 560/15000 | Loss: 5.0562 | Mean Pearson: 0.4458\n",
+      "Step 600/15000 | Loss: 5.3090 | Mean Pearson: 0.4764\n",
+      "Step 640/15000 | Loss: 4.7469 | Mean Pearson: 0.4809\n",
+      "Step 680/15000 | Loss: 5.0041 | Mean Pearson: 0.4893\n",
+      "Step 720/15000 | Loss: 4.0422 | Mean Pearson: 0.4291\n",
+      "Step 760/15000 | Loss: 4.8683 | Mean Pearson: 0.5055\n",
+      "Step 800/15000 | Loss: 5.6680 | Mean Pearson: 0.4853\n",
+      "\n",
+      "Running validation at step 800...\n",
+      "Step 800/15000 | Loss: 4.8542 | Mean Pearson: 0.4117\n",
+      "    ENCSR154HRN_P/pearson: 0.3042\n",
+      "    ENCSR701YIC/pearson: 0.4846\n",
+      "    ENCSR935RNW_P/pearson: 0.3382\n",
+      "    ENCSR100LIJ_P/pearson: 0.2928\n",
+      "    ENCSR527JGN_P/pearson: 0.6317\n",
+      "    ENCSR114HGS_P/pearson: 0.1271\n",
+      "    ENCSR484LTQ_M/pearson: 0.3242\n",
+      "    ENCSR935RNW_M/pearson: 0.3392\n",
+      "    ENCSR410DWV/pearson: 0.6345\n",
+      "    ENCSR046BCI_M/pearson: 0.2658\n",
+      "    ENCSR814RGG/pearson: 0.6034\n",
+      "    ENCSR799DGV_P/pearson: 0.3595\n",
+      "    ENCSR527JGN_M/pearson: 0.4734\n",
+      "    ENCSR154HRN_M/pearson: 0.3520\n",
+      "    ENCSR862QCH_M/pearson: 0.3242\n",
+      "    ENCSR100LIJ_M/pearson: 0.3124\n",
+      "    ENCSR321PWZ_P/pearson: 0.4567\n",
+      "    ENCSR484LTQ_P/pearson: 0.2869\n",
+      "    ENCSR619DQO_P/pearson: 0.5343\n",
+      "    ENCSR325NFE/pearson: 0.6335\n",
+      "    ENCSR249ROI_P/pearson: 0.3936\n",
+      "    ENCSR249ROI_M/pearson: 0.3804\n",
+      "    ENCSR754DRC/pearson: 0.3738\n",
+      "    ENCSR321PWZ_M/pearson: 0.5571\n",
+      "    ENCSR862QCH_P/pearson: 0.2229\n",
+      "    ENCSR046BCI_P/pearson: 0.2508\n",
+      "    ENCSR799DGV_M/pearson: 0.3423\n",
+      "    ENCSR962OTG/pearson: 0.7294\n",
+      "    ENCSR682BFG/pearson: 0.5147\n",
+      "    ENCSR628PLS/pearson: 0.4834\n",
+      "    ENCSR619DQO_M/pearson: 0.4814\n",
+      "    ENCSR487QSB/pearson: 0.5424\n",
+      "    ENCSR114HGS_M/pearson: 0.1342\n",
+      "    ENCSR863PSM/pearson: 0.5127\n",
+      "    mean/pearson: 0.4117\n",
+      "    loss: 4.8542\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 840/15000 | Loss: 6.5052 | Mean Pearson: 0.5039\n",
+      "Step 880/15000 | Loss: 5.0075 | Mean Pearson: 0.5004\n",
+      "Step 920/15000 | Loss: 4.7188 | Mean Pearson: 0.4606\n",
+      "Step 960/15000 | Loss: 6.2880 | Mean Pearson: 0.5334\n",
+      "Step 1000/15000 | Loss: 6.0167 | Mean Pearson: 0.4927\n",
+      "Step 1040/15000 | Loss: 4.7617 | Mean Pearson: 0.5048\n",
+      "Step 1080/15000 | Loss: 5.0447 | Mean Pearson: 0.4986\n",
+      "Step 1120/15000 | Loss: 5.1553 | Mean Pearson: 0.5021\n",
+      "Step 1160/15000 | Loss: 5.0807 | Mean Pearson: 0.4975\n",
+      "Step 1200/15000 | Loss: 4.0829 | Mean Pearson: 0.4934\n",
+      "\n",
+      "Running validation at step 1200...\n",
+      "Step 1200/15000 | Loss: 4.8042 | Mean Pearson: 0.4360\n",
+      "    ENCSR154HRN_P/pearson: 0.3545\n",
+      "    ENCSR701YIC/pearson: 0.5642\n",
+      "    ENCSR935RNW_P/pearson: 0.3488\n",
+      "    ENCSR100LIJ_P/pearson: 0.3473\n",
+      "    ENCSR527JGN_P/pearson: 0.5724\n",
+      "    ENCSR114HGS_P/pearson: 0.1796\n",
+      "    ENCSR484LTQ_M/pearson: 0.3166\n",
+      "    ENCSR935RNW_M/pearson: 0.3428\n",
+      "    ENCSR410DWV/pearson: 0.6526\n",
+      "    ENCSR046BCI_M/pearson: 0.2905\n",
+      "    ENCSR814RGG/pearson: 0.6303\n",
+      "    ENCSR799DGV_P/pearson: 0.3780\n",
+      "    ENCSR527JGN_M/pearson: 0.5627\n",
+      "    ENCSR154HRN_M/pearson: 0.3158\n",
+      "    ENCSR862QCH_M/pearson: 0.3571\n",
+      "    ENCSR100LIJ_M/pearson: 0.3501\n",
+      "    ENCSR321PWZ_P/pearson: 0.4913\n",
+      "    ENCSR484LTQ_P/pearson: 0.3052\n",
+      "    ENCSR619DQO_P/pearson: 0.5458\n",
+      "    ENCSR325NFE/pearson: 0.6573\n",
+      "    ENCSR249ROI_P/pearson: 0.4414\n",
+      "    ENCSR249ROI_M/pearson: 0.3621\n",
+      "    ENCSR754DRC/pearson: 0.3784\n",
+      "    ENCSR321PWZ_M/pearson: 0.5069\n",
+      "    ENCSR862QCH_P/pearson: 0.3182\n",
+      "    ENCSR046BCI_P/pearson: 0.2874\n",
+      "    ENCSR799DGV_M/pearson: 0.3605\n",
+      "    ENCSR962OTG/pearson: 0.7423\n",
+      "    ENCSR682BFG/pearson: 0.5054\n",
+      "    ENCSR628PLS/pearson: 0.5186\n",
+      "    ENCSR619DQO_M/pearson: 0.5725\n",
+      "    ENCSR487QSB/pearson: 0.5765\n",
+      "    ENCSR114HGS_M/pearson: 0.1629\n",
+      "    ENCSR863PSM/pearson: 0.5292\n",
+      "    mean/pearson: 0.4360\n",
+      "    loss: 4.8042\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 1240/15000 | Loss: 4.6137 | Mean Pearson: 0.5280\n",
+      "Step 1280/15000 | Loss: 3.8971 | Mean Pearson: 0.4882\n",
+      "Step 1320/15000 | Loss: 4.9031 | Mean Pearson: 0.5391\n",
+      "Step 1360/15000 | Loss: 5.0854 | Mean Pearson: 0.5255\n",
+      "Step 1400/15000 | Loss: 4.4821 | Mean Pearson: 0.5281\n",
+      "Step 1440/15000 | Loss: 4.2530 | Mean Pearson: 0.5111\n",
+      "Step 1480/15000 | Loss: 4.1785 | Mean Pearson: 0.5090\n",
+      "Step 1520/15000 | Loss: 4.4080 | Mean Pearson: 0.4977\n",
+      "Step 1560/15000 | Loss: 5.3948 | Mean Pearson: 0.5603\n",
+      "Step 1600/15000 | Loss: 4.3933 | Mean Pearson: 0.5196\n",
+      "\n",
+      "Running validation at step 1600...\n",
+      "Step 1600/15000 | Loss: 4.8040 | Mean Pearson: 0.4472\n",
+      "    ENCSR154HRN_P/pearson: 0.3722\n",
+      "    ENCSR701YIC/pearson: 0.4901\n",
+      "    ENCSR935RNW_P/pearson: 0.3555\n",
+      "    ENCSR100LIJ_P/pearson: 0.3428\n",
+      "    ENCSR527JGN_P/pearson: 0.4848\n",
+      "    ENCSR114HGS_P/pearson: 0.1943\n",
+      "    ENCSR484LTQ_M/pearson: 0.3513\n",
+      "    ENCSR935RNW_M/pearson: 0.3849\n",
+      "    ENCSR410DWV/pearson: 0.6483\n",
+      "    ENCSR046BCI_M/pearson: 0.3297\n",
+      "    ENCSR814RGG/pearson: 0.6301\n",
+      "    ENCSR799DGV_P/pearson: 0.3798\n",
+      "    ENCSR527JGN_M/pearson: 0.5022\n",
+      "    ENCSR154HRN_M/pearson: 0.3745\n",
+      "    ENCSR862QCH_M/pearson: 0.3815\n",
+      "    ENCSR100LIJ_M/pearson: 0.3751\n",
+      "    ENCSR321PWZ_P/pearson: 0.5135\n",
+      "    ENCSR484LTQ_P/pearson: 0.3407\n",
+      "    ENCSR619DQO_P/pearson: 0.5723\n",
+      "    ENCSR325NFE/pearson: 0.6803\n",
+      "    ENCSR249ROI_P/pearson: 0.4475\n",
+      "    ENCSR249ROI_M/pearson: 0.4200\n",
+      "    ENCSR754DRC/pearson: 0.3624\n",
+      "    ENCSR321PWZ_M/pearson: 0.5836\n",
+      "    ENCSR862QCH_P/pearson: 0.3329\n",
+      "    ENCSR046BCI_P/pearson: 0.2941\n",
+      "    ENCSR799DGV_M/pearson: 0.3892\n",
+      "    ENCSR962OTG/pearson: 0.7367\n",
+      "    ENCSR682BFG/pearson: 0.5082\n",
+      "    ENCSR628PLS/pearson: 0.5042\n",
+      "    ENCSR619DQO_M/pearson: 0.5569\n",
+      "    ENCSR487QSB/pearson: 0.5636\n",
+      "    ENCSR114HGS_M/pearson: 0.2117\n",
+      "    ENCSR863PSM/pearson: 0.5907\n",
+      "    mean/pearson: 0.4472\n",
+      "    loss: 4.8040\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 1640/15000 | Loss: 4.7396 | Mean Pearson: 0.5206\n",
+      "Step 1680/15000 | Loss: 5.1905 | Mean Pearson: 0.5361\n",
+      "Step 1720/15000 | Loss: 4.3641 | Mean Pearson: 0.5098\n",
+      "Step 1760/15000 | Loss: 5.0826 | Mean Pearson: 0.5374\n",
+      "Step 1800/15000 | Loss: 5.9271 | Mean Pearson: 0.5698\n",
+      "Step 1840/15000 | Loss: 4.4543 | Mean Pearson: 0.5462\n",
+      "Step 1880/15000 | Loss: 4.9696 | Mean Pearson: 0.5420\n",
+      "Step 1920/15000 | Loss: 4.3736 | Mean Pearson: 0.5275\n",
+      "Step 1960/15000 | Loss: 4.3864 | Mean Pearson: 0.5413\n",
+      "Step 2000/15000 | Loss: 4.7990 | Mean Pearson: 0.5084\n",
+      "\n",
+      "Running validation at step 2000...\n",
+      "Step 2000/15000 | Loss: 4.7425 | Mean Pearson: 0.4309\n",
+      "    ENCSR154HRN_P/pearson: 0.3593\n",
+      "    ENCSR701YIC/pearson: 0.4430\n",
+      "    ENCSR935RNW_P/pearson: 0.3426\n",
+      "    ENCSR100LIJ_P/pearson: 0.3458\n",
+      "    ENCSR527JGN_P/pearson: 0.5066\n",
+      "    ENCSR114HGS_P/pearson: 0.2188\n",
+      "    ENCSR484LTQ_M/pearson: 0.2973\n",
+      "    ENCSR935RNW_M/pearson: 0.3201\n",
+      "    ENCSR410DWV/pearson: 0.6588\n",
+      "    ENCSR046BCI_M/pearson: 0.2825\n",
+      "    ENCSR814RGG/pearson: 0.6422\n",
+      "    ENCSR799DGV_P/pearson: 0.3693\n",
+      "    ENCSR527JGN_M/pearson: 0.5180\n",
+      "    ENCSR154HRN_M/pearson: 0.3396\n",
+      "    ENCSR862QCH_M/pearson: 0.3286\n",
+      "    ENCSR100LIJ_M/pearson: 0.3256\n",
+      "    ENCSR321PWZ_P/pearson: 0.4611\n",
+      "    ENCSR484LTQ_P/pearson: 0.3053\n",
+      "    ENCSR619DQO_P/pearson: 0.5327\n",
+      "    ENCSR325NFE/pearson: 0.6772\n",
+      "    ENCSR249ROI_P/pearson: 0.4834\n",
+      "    ENCSR249ROI_M/pearson: 0.4231\n",
+      "    ENCSR754DRC/pearson: 0.3684\n",
+      "    ENCSR321PWZ_M/pearson: 0.4788\n",
+      "    ENCSR862QCH_P/pearson: 0.3341\n",
+      "    ENCSR046BCI_P/pearson: 0.2751\n",
+      "    ENCSR799DGV_M/pearson: 0.3279\n",
+      "    ENCSR962OTG/pearson: 0.7665\n",
+      "    ENCSR682BFG/pearson: 0.5401\n",
+      "    ENCSR628PLS/pearson: 0.5144\n",
+      "    ENCSR619DQO_M/pearson: 0.4946\n",
+      "    ENCSR487QSB/pearson: 0.5761\n",
+      "    ENCSR114HGS_M/pearson: 0.1986\n",
+      "    ENCSR863PSM/pearson: 0.5953\n",
+      "    mean/pearson: 0.4309\n",
+      "    loss: 4.7425\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 2040/15000 | Loss: 5.5453 | Mean Pearson: 0.5738\n",
+      "Step 2080/15000 | Loss: 4.4107 | Mean Pearson: 0.5583\n",
+      "Step 2120/15000 | Loss: 5.7178 | Mean Pearson: 0.5533\n",
+      "Step 2160/15000 | Loss: 5.4947 | Mean Pearson: 0.5582\n",
+      "Step 2200/15000 | Loss: 4.1687 | Mean Pearson: 0.5212\n",
+      "Step 2240/15000 | Loss: 4.2301 | Mean Pearson: 0.5370\n",
+      "Step 2280/15000 | Loss: 5.0143 | Mean Pearson: 0.5361\n",
+      "Step 2320/15000 | Loss: 4.8299 | Mean Pearson: 0.5582\n",
+      "Step 2360/15000 | Loss: 4.9165 | Mean Pearson: 0.5603\n",
+      "Step 2400/15000 | Loss: 5.3800 | Mean Pearson: 0.5458\n",
+      "\n",
+      "Running validation at step 2400...\n",
+      "Step 2400/15000 | Loss: 4.9463 | Mean Pearson: 0.4866\n",
+      "    ENCSR154HRN_P/pearson: 0.3985\n",
+      "    ENCSR701YIC/pearson: 0.4962\n",
+      "    ENCSR935RNW_P/pearson: 0.4364\n",
+      "    ENCSR100LIJ_P/pearson: 0.4523\n",
+      "    ENCSR527JGN_P/pearson: 0.6138\n",
+      "    ENCSR114HGS_P/pearson: 0.2374\n",
+      "    ENCSR484LTQ_M/pearson: 0.3663\n",
+      "    ENCSR935RNW_M/pearson: 0.4312\n",
+      "    ENCSR410DWV/pearson: 0.6902\n",
+      "    ENCSR046BCI_M/pearson: 0.3752\n",
+      "    ENCSR814RGG/pearson: 0.6648\n",
+      "    ENCSR799DGV_P/pearson: 0.4611\n",
+      "    ENCSR527JGN_M/pearson: 0.6120\n",
+      "    ENCSR154HRN_M/pearson: 0.3606\n",
+      "    ENCSR862QCH_M/pearson: 0.3856\n",
+      "    ENCSR100LIJ_M/pearson: 0.4219\n",
+      "    ENCSR321PWZ_P/pearson: 0.5719\n",
+      "    ENCSR484LTQ_P/pearson: 0.3186\n",
+      "    ENCSR619DQO_P/pearson: 0.5605\n",
+      "    ENCSR325NFE/pearson: 0.6903\n",
+      "    ENCSR249ROI_P/pearson: 0.4781\n",
+      "    ENCSR249ROI_M/pearson: 0.4184\n",
+      "    ENCSR754DRC/pearson: 0.4058\n",
+      "    ENCSR321PWZ_M/pearson: 0.6017\n",
+      "    ENCSR862QCH_P/pearson: 0.3199\n",
+      "    ENCSR046BCI_P/pearson: 0.3689\n",
+      "    ENCSR799DGV_M/pearson: 0.4353\n",
+      "    ENCSR962OTG/pearson: 0.8105\n",
+      "    ENCSR682BFG/pearson: 0.5671\n",
+      "    ENCSR628PLS/pearson: 0.5601\n",
+      "    ENCSR619DQO_M/pearson: 0.5810\n",
+      "    ENCSR487QSB/pearson: 0.6183\n",
+      "    ENCSR114HGS_M/pearson: 0.2141\n",
+      "    ENCSR863PSM/pearson: 0.6207\n",
+      "    mean/pearson: 0.4866\n",
+      "    loss: 4.9463\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 2440/15000 | Loss: 4.6690 | Mean Pearson: 0.5640\n",
+      "Step 2480/15000 | Loss: 5.2668 | Mean Pearson: 0.5544\n",
+      "Step 2520/15000 | Loss: 4.6066 | Mean Pearson: 0.5578\n",
+      "Step 2560/15000 | Loss: 5.8552 | Mean Pearson: 0.5677\n",
+      "Step 2600/15000 | Loss: 5.1298 | Mean Pearson: 0.5923\n",
+      "Step 2640/15000 | Loss: 4.5565 | Mean Pearson: 0.5981\n",
+      "Step 2680/15000 | Loss: 4.2167 | Mean Pearson: 0.5521\n",
+      "Step 2720/15000 | Loss: 3.5633 | Mean Pearson: 0.5295\n",
+      "Step 2760/15000 | Loss: 4.5719 | Mean Pearson: 0.5763\n",
+      "Step 2800/15000 | Loss: 5.2513 | Mean Pearson: 0.5947\n",
+      "\n",
+      "Running validation at step 2800...\n",
+      "Step 2800/15000 | Loss: 5.0444 | Mean Pearson: 0.4768\n",
+      "    ENCSR154HRN_P/pearson: 0.3988\n",
+      "    ENCSR701YIC/pearson: 0.5542\n",
+      "    ENCSR935RNW_P/pearson: 0.3898\n",
+      "    ENCSR100LIJ_P/pearson: 0.3719\n",
+      "    ENCSR527JGN_P/pearson: 0.6657\n",
+      "    ENCSR114HGS_P/pearson: 0.2230\n",
+      "    ENCSR484LTQ_M/pearson: 0.3708\n",
+      "    ENCSR935RNW_M/pearson: 0.3848\n",
+      "    ENCSR410DWV/pearson: 0.7031\n",
+      "    ENCSR046BCI_M/pearson: 0.2998\n",
+      "    ENCSR814RGG/pearson: 0.6736\n",
+      "    ENCSR799DGV_P/pearson: 0.4135\n",
+      "    ENCSR527JGN_M/pearson: 0.4723\n",
+      "    ENCSR154HRN_M/pearson: 0.4082\n",
+      "    ENCSR862QCH_M/pearson: 0.4092\n",
+      "    ENCSR100LIJ_M/pearson: 0.3581\n",
+      "    ENCSR321PWZ_P/pearson: 0.5490\n",
+      "    ENCSR484LTQ_P/pearson: 0.3367\n",
+      "    ENCSR619DQO_P/pearson: 0.6279\n",
+      "    ENCSR325NFE/pearson: 0.6907\n",
+      "    ENCSR249ROI_P/pearson: 0.4753\n",
+      "    ENCSR249ROI_M/pearson: 0.4936\n",
+      "    ENCSR754DRC/pearson: 0.3842\n",
+      "    ENCSR321PWZ_M/pearson: 0.5650\n",
+      "    ENCSR862QCH_P/pearson: 0.3822\n",
+      "    ENCSR046BCI_P/pearson: 0.2827\n",
+      "    ENCSR799DGV_M/pearson: 0.3934\n",
+      "    ENCSR962OTG/pearson: 0.7592\n",
+      "    ENCSR682BFG/pearson: 0.5672\n",
+      "    ENCSR628PLS/pearson: 0.5677\n",
+      "    ENCSR619DQO_M/pearson: 0.5698\n",
+      "    ENCSR487QSB/pearson: 0.6144\n",
+      "    ENCSR114HGS_M/pearson: 0.2412\n",
+      "    ENCSR863PSM/pearson: 0.6157\n",
+      "    mean/pearson: 0.4768\n",
+      "    loss: 5.0444\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 2840/15000 | Loss: 5.2553 | Mean Pearson: 0.5655\n",
+      "Step 2880/15000 | Loss: 4.6948 | Mean Pearson: 0.5666\n",
+      "Step 2920/15000 | Loss: 4.5278 | Mean Pearson: 0.5383\n",
+      "Step 2960/15000 | Loss: 4.8155 | Mean Pearson: 0.5411\n",
+      "Step 3000/15000 | Loss: 4.4951 | Mean Pearson: 0.5509\n",
+      "Step 3040/15000 | Loss: 5.0086 | Mean Pearson: 0.5710\n",
+      "Step 3080/15000 | Loss: 4.9327 | Mean Pearson: 0.5709\n",
+      "Step 3120/15000 | Loss: 4.5701 | Mean Pearson: 0.5800\n",
+      "Step 3160/15000 | Loss: 4.6002 | Mean Pearson: 0.5421\n",
+      "Step 3200/15000 | Loss: 4.9664 | Mean Pearson: 0.5664\n",
+      "\n",
+      "Running validation at step 3200...\n",
+      "Step 3200/15000 | Loss: 4.5238 | Mean Pearson: 0.4700\n",
+      "    ENCSR154HRN_P/pearson: 0.3747\n",
+      "    ENCSR701YIC/pearson: 0.5456\n",
+      "    ENCSR935RNW_P/pearson: 0.4034\n",
+      "    ENCSR100LIJ_P/pearson: 0.3983\n",
+      "    ENCSR527JGN_P/pearson: 0.6502\n",
+      "    ENCSR114HGS_P/pearson: 0.2393\n",
+      "    ENCSR484LTQ_M/pearson: 0.3284\n",
+      "    ENCSR935RNW_M/pearson: 0.3929\n",
+      "    ENCSR410DWV/pearson: 0.7059\n",
+      "    ENCSR046BCI_M/pearson: 0.3068\n",
+      "    ENCSR814RGG/pearson: 0.6822\n",
+      "    ENCSR799DGV_P/pearson: 0.4415\n",
+      "    ENCSR527JGN_M/pearson: 0.5352\n",
+      "    ENCSR154HRN_M/pearson: 0.3715\n",
+      "    ENCSR862QCH_M/pearson: 0.3629\n",
+      "    ENCSR100LIJ_M/pearson: 0.3640\n",
+      "    ENCSR321PWZ_P/pearson: 0.5444\n",
+      "    ENCSR484LTQ_P/pearson: 0.3061\n",
+      "    ENCSR619DQO_P/pearson: 0.5297\n",
+      "    ENCSR325NFE/pearson: 0.7094\n",
+      "    ENCSR249ROI_P/pearson: 0.4596\n",
+      "    ENCSR249ROI_M/pearson: 0.3966\n",
+      "    ENCSR754DRC/pearson: 0.3996\n",
+      "    ENCSR321PWZ_M/pearson: 0.5038\n",
+      "    ENCSR862QCH_P/pearson: 0.3665\n",
+      "    ENCSR046BCI_P/pearson: 0.3351\n",
+      "    ENCSR799DGV_M/pearson: 0.3930\n",
+      "    ENCSR962OTG/pearson: 0.7791\n",
+      "    ENCSR682BFG/pearson: 0.5659\n",
+      "    ENCSR628PLS/pearson: 0.5813\n",
+      "    ENCSR619DQO_M/pearson: 0.5433\n",
+      "    ENCSR487QSB/pearson: 0.6317\n",
+      "    ENCSR114HGS_M/pearson: 0.2153\n",
+      "    ENCSR863PSM/pearson: 0.6169\n",
+      "    mean/pearson: 0.4700\n",
+      "    loss: 4.5238\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 3240/15000 | Loss: 4.5518 | Mean Pearson: 0.5475\n",
+      "Step 3280/15000 | Loss: 5.4448 | Mean Pearson: 0.5949\n",
+      "Step 3320/15000 | Loss: 5.1806 | Mean Pearson: 0.5789\n",
+      "Step 3360/15000 | Loss: 4.6534 | Mean Pearson: 0.5978\n",
+      "Step 3400/15000 | Loss: 4.7245 | Mean Pearson: 0.5842\n",
+      "Step 3440/15000 | Loss: 3.9659 | Mean Pearson: 0.5690\n",
+      "Step 3480/15000 | Loss: 4.4445 | Mean Pearson: 0.5918\n",
+      "Step 3520/15000 | Loss: 4.1439 | Mean Pearson: 0.5695\n",
+      "Step 3560/15000 | Loss: 5.5380 | Mean Pearson: 0.6013\n",
+      "Step 3600/15000 | Loss: 4.5076 | Mean Pearson: 0.5770\n",
+      "\n",
+      "Running validation at step 3600...\n",
+      "Step 3600/15000 | Loss: 5.0297 | Mean Pearson: 0.5012\n",
+      "    ENCSR154HRN_P/pearson: 0.4255\n",
+      "    ENCSR701YIC/pearson: 0.4534\n",
+      "    ENCSR935RNW_P/pearson: 0.3867\n",
+      "    ENCSR100LIJ_P/pearson: 0.3902\n",
+      "    ENCSR527JGN_P/pearson: 0.5929\n",
+      "    ENCSR114HGS_P/pearson: 0.2781\n",
+      "    ENCSR484LTQ_M/pearson: 0.4132\n",
+      "    ENCSR935RNW_M/pearson: 0.4581\n",
+      "    ENCSR410DWV/pearson: 0.7219\n",
+      "    ENCSR046BCI_M/pearson: 0.4187\n",
+      "    ENCSR814RGG/pearson: 0.6937\n",
+      "    ENCSR799DGV_P/pearson: 0.4079\n",
+      "    ENCSR527JGN_M/pearson: 0.6163\n",
+      "    ENCSR154HRN_M/pearson: 0.4501\n",
+      "    ENCSR862QCH_M/pearson: 0.4418\n",
+      "    ENCSR100LIJ_M/pearson: 0.4568\n",
+      "    ENCSR321PWZ_P/pearson: 0.3859\n",
+      "    ENCSR484LTQ_P/pearson: 0.3294\n",
+      "    ENCSR619DQO_P/pearson: 0.5187\n",
+      "    ENCSR325NFE/pearson: 0.7224\n",
+      "    ENCSR249ROI_P/pearson: 0.5492\n",
+      "    ENCSR249ROI_M/pearson: 0.5163\n",
+      "    ENCSR754DRC/pearson: 0.4783\n",
+      "    ENCSR321PWZ_M/pearson: 0.6269\n",
+      "    ENCSR862QCH_P/pearson: 0.3844\n",
+      "    ENCSR046BCI_P/pearson: 0.3143\n",
+      "    ENCSR799DGV_M/pearson: 0.4457\n",
+      "    ENCSR962OTG/pearson: 0.8147\n",
+      "    ENCSR682BFG/pearson: 0.5850\n",
+      "    ENCSR628PLS/pearson: 0.5949\n",
+      "    ENCSR619DQO_M/pearson: 0.5917\n",
+      "    ENCSR487QSB/pearson: 0.6512\n",
+      "    ENCSR114HGS_M/pearson: 0.2616\n",
+      "    ENCSR863PSM/pearson: 0.6637\n",
+      "    mean/pearson: 0.5012\n",
+      "    loss: 5.0297\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 3640/15000 | Loss: 4.5653 | Mean Pearson: 0.5973\n",
+      "Step 3680/15000 | Loss: 4.2206 | Mean Pearson: 0.5803\n",
+      "Step 3720/15000 | Loss: 4.3218 | Mean Pearson: 0.5621\n",
+      "Step 3760/15000 | Loss: 4.1544 | Mean Pearson: 0.5623\n",
+      "Step 3800/15000 | Loss: 4.7652 | Mean Pearson: 0.5916\n",
+      "Step 3840/15000 | Loss: 4.5291 | Mean Pearson: 0.5968\n",
+      "Step 3880/15000 | Loss: 4.4285 | Mean Pearson: 0.5497\n",
+      "Step 3920/15000 | Loss: 4.6456 | Mean Pearson: 0.6121\n",
+      "Step 3960/15000 | Loss: 6.1194 | Mean Pearson: 0.5865\n",
+      "Step 4000/15000 | Loss: 4.8061 | Mean Pearson: 0.6093\n",
+      "\n",
+      "Running validation at step 4000...\n",
+      "Step 4000/15000 | Loss: 4.6878 | Mean Pearson: 0.5041\n",
+      "    ENCSR154HRN_P/pearson: 0.3922\n",
+      "    ENCSR701YIC/pearson: 0.5032\n",
+      "    ENCSR935RNW_P/pearson: 0.4340\n",
+      "    ENCSR100LIJ_P/pearson: 0.4313\n",
+      "    ENCSR527JGN_P/pearson: 0.5417\n",
+      "    ENCSR114HGS_P/pearson: 0.2547\n",
+      "    ENCSR484LTQ_M/pearson: 0.4094\n",
+      "    ENCSR935RNW_M/pearson: 0.4379\n",
+      "    ENCSR410DWV/pearson: 0.7237\n",
+      "    ENCSR046BCI_M/pearson: 0.3959\n",
+      "    ENCSR814RGG/pearson: 0.7165\n",
+      "    ENCSR799DGV_P/pearson: 0.4631\n",
+      "    ENCSR527JGN_M/pearson: 0.6359\n",
+      "    ENCSR154HRN_M/pearson: 0.4190\n",
+      "    ENCSR862QCH_M/pearson: 0.4284\n",
+      "    ENCSR100LIJ_M/pearson: 0.4282\n",
+      "    ENCSR321PWZ_P/pearson: 0.4435\n",
+      "    ENCSR484LTQ_P/pearson: 0.3353\n",
+      "    ENCSR619DQO_P/pearson: 0.5668\n",
+      "    ENCSR325NFE/pearson: 0.7412\n",
+      "    ENCSR249ROI_P/pearson: 0.4756\n",
+      "    ENCSR249ROI_M/pearson: 0.5301\n",
+      "    ENCSR754DRC/pearson: 0.4552\n",
+      "    ENCSR321PWZ_M/pearson: 0.6538\n",
+      "    ENCSR862QCH_P/pearson: 0.3607\n",
+      "    ENCSR046BCI_P/pearson: 0.3758\n",
+      "    ENCSR799DGV_M/pearson: 0.4353\n",
+      "    ENCSR962OTG/pearson: 0.8352\n",
+      "    ENCSR682BFG/pearson: 0.5724\n",
+      "    ENCSR628PLS/pearson: 0.6164\n",
+      "    ENCSR619DQO_M/pearson: 0.5993\n",
+      "    ENCSR487QSB/pearson: 0.6698\n",
+      "    ENCSR114HGS_M/pearson: 0.2485\n",
+      "    ENCSR863PSM/pearson: 0.6079\n",
+      "    mean/pearson: 0.5041\n",
+      "    loss: 4.6878\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 4040/15000 | Loss: 5.9840 | Mean Pearson: 0.5963\n",
+      "Step 4080/15000 | Loss: 4.9377 | Mean Pearson: 0.5840\n",
+      "Step 4120/15000 | Loss: 4.1082 | Mean Pearson: 0.5748\n",
+      "Step 4160/15000 | Loss: 5.1416 | Mean Pearson: 0.6035\n",
+      "Step 4200/15000 | Loss: 4.2407 | Mean Pearson: 0.5628\n",
+      "Step 4240/15000 | Loss: 4.7651 | Mean Pearson: 0.5941\n",
+      "Step 4280/15000 | Loss: 4.3132 | Mean Pearson: 0.5887\n",
+      "Step 4320/15000 | Loss: 5.4356 | Mean Pearson: 0.5913\n",
+      "Step 4360/15000 | Loss: 4.9994 | Mean Pearson: 0.5724\n",
+      "Step 4400/15000 | Loss: 4.7708 | Mean Pearson: 0.6049\n",
+      "\n",
+      "Running validation at step 4400...\n",
+      "Step 4400/15000 | Loss: 4.5300 | Mean Pearson: 0.4873\n",
+      "    ENCSR154HRN_P/pearson: 0.3860\n",
+      "    ENCSR701YIC/pearson: 0.5630\n",
+      "    ENCSR935RNW_P/pearson: 0.4206\n",
+      "    ENCSR100LIJ_P/pearson: 0.4168\n",
+      "    ENCSR527JGN_P/pearson: 0.6836\n",
+      "    ENCSR114HGS_P/pearson: 0.2351\n",
+      "    ENCSR484LTQ_M/pearson: 0.3396\n",
+      "    ENCSR935RNW_M/pearson: 0.4066\n",
+      "    ENCSR410DWV/pearson: 0.7060\n",
+      "    ENCSR046BCI_M/pearson: 0.3658\n",
+      "    ENCSR814RGG/pearson: 0.6910\n",
+      "    ENCSR799DGV_P/pearson: 0.4228\n",
+      "    ENCSR527JGN_M/pearson: 0.5826\n",
+      "    ENCSR154HRN_M/pearson: 0.3808\n",
+      "    ENCSR862QCH_M/pearson: 0.3968\n",
+      "    ENCSR100LIJ_M/pearson: 0.4030\n",
+      "    ENCSR321PWZ_P/pearson: 0.5200\n",
+      "    ENCSR484LTQ_P/pearson: 0.3037\n",
+      "    ENCSR619DQO_P/pearson: 0.5708\n",
+      "    ENCSR325NFE/pearson: 0.7119\n",
+      "    ENCSR249ROI_P/pearson: 0.5067\n",
+      "    ENCSR249ROI_M/pearson: 0.4725\n",
+      "    ENCSR754DRC/pearson: 0.4352\n",
+      "    ENCSR321PWZ_M/pearson: 0.5352\n",
+      "    ENCSR862QCH_P/pearson: 0.3527\n",
+      "    ENCSR046BCI_P/pearson: 0.3252\n",
+      "    ENCSR799DGV_M/pearson: 0.4250\n",
+      "    ENCSR962OTG/pearson: 0.7960\n",
+      "    ENCSR682BFG/pearson: 0.5737\n",
+      "    ENCSR628PLS/pearson: 0.5857\n",
+      "    ENCSR619DQO_M/pearson: 0.5399\n",
+      "    ENCSR487QSB/pearson: 0.6340\n",
+      "    ENCSR114HGS_M/pearson: 0.2305\n",
+      "    ENCSR863PSM/pearson: 0.6507\n",
+      "    mean/pearson: 0.4873\n",
+      "    loss: 4.5300\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 4440/15000 | Loss: 5.2919 | Mean Pearson: 0.5923\n",
+      "Step 4480/15000 | Loss: 5.1676 | Mean Pearson: 0.6229\n",
+      "Step 4520/15000 | Loss: 4.3137 | Mean Pearson: 0.5773\n",
+      "Step 4560/15000 | Loss: 6.2511 | Mean Pearson: 0.6140\n",
+      "Step 4600/15000 | Loss: 4.6901 | Mean Pearson: 0.5928\n",
+      "Step 4640/15000 | Loss: 4.8336 | Mean Pearson: 0.5897\n",
+      "Step 4680/15000 | Loss: 4.9705 | Mean Pearson: 0.5660\n",
+      "Step 4720/15000 | Loss: 4.1555 | Mean Pearson: 0.5905\n",
+      "Step 4760/15000 | Loss: 4.2600 | Mean Pearson: 0.5888\n",
+      "Step 4800/15000 | Loss: 4.0882 | Mean Pearson: 0.5940\n",
+      "\n",
+      "Running validation at step 4800...\n",
+      "Step 4800/15000 | Loss: 4.6850 | Mean Pearson: 0.5074\n",
+      "    ENCSR154HRN_P/pearson: 0.4234\n",
+      "    ENCSR701YIC/pearson: 0.5161\n",
+      "    ENCSR935RNW_P/pearson: 0.4464\n",
+      "    ENCSR100LIJ_P/pearson: 0.4523\n",
+      "    ENCSR527JGN_P/pearson: 0.5427\n",
+      "    ENCSR114HGS_P/pearson: 0.2625\n",
+      "    ENCSR484LTQ_M/pearson: 0.3751\n",
+      "    ENCSR935RNW_M/pearson: 0.4767\n",
+      "    ENCSR410DWV/pearson: 0.7367\n",
+      "    ENCSR046BCI_M/pearson: 0.4119\n",
+      "    ENCSR814RGG/pearson: 0.7155\n",
+      "    ENCSR799DGV_P/pearson: 0.4566\n",
+      "    ENCSR527JGN_M/pearson: 0.6363\n",
+      "    ENCSR154HRN_M/pearson: 0.4056\n",
+      "    ENCSR862QCH_M/pearson: 0.4106\n",
+      "    ENCSR100LIJ_M/pearson: 0.4720\n",
+      "    ENCSR321PWZ_P/pearson: 0.5463\n",
+      "    ENCSR484LTQ_P/pearson: 0.3085\n",
+      "    ENCSR619DQO_P/pearson: 0.5731\n",
+      "    ENCSR325NFE/pearson: 0.7391\n",
+      "    ENCSR249ROI_P/pearson: 0.5296\n",
+      "    ENCSR249ROI_M/pearson: 0.4523\n",
+      "    ENCSR754DRC/pearson: 0.4502\n",
+      "    ENCSR321PWZ_M/pearson: 0.5942\n",
+      "    ENCSR862QCH_P/pearson: 0.3736\n",
+      "    ENCSR046BCI_P/pearson: 0.3673\n",
+      "    ENCSR799DGV_M/pearson: 0.4664\n",
+      "    ENCSR962OTG/pearson: 0.8525\n",
+      "    ENCSR682BFG/pearson: 0.5709\n",
+      "    ENCSR628PLS/pearson: 0.6012\n",
+      "    ENCSR619DQO_M/pearson: 0.5626\n",
+      "    ENCSR487QSB/pearson: 0.6532\n",
+      "    ENCSR114HGS_M/pearson: 0.2394\n",
+      "    ENCSR863PSM/pearson: 0.6299\n",
+      "    mean/pearson: 0.5074\n",
+      "    loss: 4.6850\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 4840/15000 | Loss: 4.3209 | Mean Pearson: 0.5670\n",
+      "Step 4880/15000 | Loss: 4.7077 | Mean Pearson: 0.6160\n",
+      "Step 4920/15000 | Loss: 4.6265 | Mean Pearson: 0.5975\n",
+      "Step 4960/15000 | Loss: 4.5031 | Mean Pearson: 0.5779\n",
+      "Step 5000/15000 | Loss: 4.9482 | Mean Pearson: 0.6081\n",
+      "Step 5040/15000 | Loss: 4.6602 | Mean Pearson: 0.6035\n",
+      "Step 5080/15000 | Loss: 5.5697 | Mean Pearson: 0.5246\n",
+      "Step 5120/15000 | Loss: 4.5694 | Mean Pearson: 0.6161\n",
+      "Step 5160/15000 | Loss: 5.5093 | Mean Pearson: 0.5933\n",
+      "Step 5200/15000 | Loss: 4.7067 | Mean Pearson: 0.5489\n",
+      "\n",
+      "Running validation at step 5200...\n",
+      "Step 5200/15000 | Loss: 4.7660 | Mean Pearson: 0.5208\n",
+      "    ENCSR154HRN_P/pearson: 0.4041\n",
+      "    ENCSR701YIC/pearson: 0.5634\n",
+      "    ENCSR935RNW_P/pearson: 0.4589\n",
+      "    ENCSR100LIJ_P/pearson: 0.4815\n",
+      "    ENCSR527JGN_P/pearson: 0.6875\n",
+      "    ENCSR114HGS_P/pearson: 0.2728\n",
+      "    ENCSR484LTQ_M/pearson: 0.3726\n",
+      "    ENCSR935RNW_M/pearson: 0.4567\n",
+      "    ENCSR410DWV/pearson: 0.7479\n",
+      "    ENCSR046BCI_M/pearson: 0.4150\n",
+      "    ENCSR814RGG/pearson: 0.7186\n",
+      "    ENCSR799DGV_P/pearson: 0.5044\n",
+      "    ENCSR527JGN_M/pearson: 0.5979\n",
+      "    ENCSR154HRN_M/pearson: 0.3971\n",
+      "    ENCSR862QCH_M/pearson: 0.4236\n",
+      "    ENCSR100LIJ_M/pearson: 0.4528\n",
+      "    ENCSR321PWZ_P/pearson: 0.5710\n",
+      "    ENCSR484LTQ_P/pearson: 0.3149\n",
+      "    ENCSR619DQO_P/pearson: 0.6483\n",
+      "    ENCSR325NFE/pearson: 0.7446\n",
+      "    ENCSR249ROI_P/pearson: 0.4821\n",
+      "    ENCSR249ROI_M/pearson: 0.4851\n",
+      "    ENCSR754DRC/pearson: 0.4558\n",
+      "    ENCSR321PWZ_M/pearson: 0.6146\n",
+      "    ENCSR862QCH_P/pearson: 0.3624\n",
+      "    ENCSR046BCI_P/pearson: 0.4120\n",
+      "    ENCSR799DGV_M/pearson: 0.4872\n",
+      "    ENCSR962OTG/pearson: 0.8390\n",
+      "    ENCSR682BFG/pearson: 0.5768\n",
+      "    ENCSR628PLS/pearson: 0.6091\n",
+      "    ENCSR619DQO_M/pearson: 0.6120\n",
+      "    ENCSR487QSB/pearson: 0.6586\n",
+      "    ENCSR114HGS_M/pearson: 0.2538\n",
+      "    ENCSR863PSM/pearson: 0.6254\n",
+      "    mean/pearson: 0.5208\n",
+      "    loss: 4.7660\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 5240/15000 | Loss: 4.3923 | Mean Pearson: 0.6021\n",
+      "Step 5280/15000 | Loss: 4.2263 | Mean Pearson: 0.5950\n",
+      "Step 5320/15000 | Loss: 5.4918 | Mean Pearson: 0.6238\n",
+      "Step 5360/15000 | Loss: 4.3407 | Mean Pearson: 0.6104\n",
+      "Step 5400/15000 | Loss: 4.5763 | Mean Pearson: 0.6010\n",
+      "Step 5440/15000 | Loss: 5.2467 | Mean Pearson: 0.6449\n",
+      "Step 5480/15000 | Loss: 4.1830 | Mean Pearson: 0.5981\n",
+      "Step 5520/15000 | Loss: 5.0144 | Mean Pearson: 0.6176\n",
+      "Step 5560/15000 | Loss: 4.9472 | Mean Pearson: 0.6031\n",
+      "Step 5600/15000 | Loss: 4.7462 | Mean Pearson: 0.5946\n",
+      "\n",
+      "Running validation at step 5600...\n",
+      "Step 5600/15000 | Loss: 4.6823 | Mean Pearson: 0.4856\n",
+      "    ENCSR154HRN_P/pearson: 0.3662\n",
+      "    ENCSR701YIC/pearson: 0.5677\n",
+      "    ENCSR935RNW_P/pearson: 0.3736\n",
+      "    ENCSR100LIJ_P/pearson: 0.3661\n",
+      "    ENCSR527JGN_P/pearson: 0.4855\n",
+      "    ENCSR114HGS_P/pearson: 0.2414\n",
+      "    ENCSR484LTQ_M/pearson: 0.3664\n",
+      "    ENCSR935RNW_M/pearson: 0.4197\n",
+      "    ENCSR410DWV/pearson: 0.7206\n",
+      "    ENCSR046BCI_M/pearson: 0.3558\n",
+      "    ENCSR814RGG/pearson: 0.7010\n",
+      "    ENCSR799DGV_P/pearson: 0.3811\n",
+      "    ENCSR527JGN_M/pearson: 0.5794\n",
+      "    ENCSR154HRN_M/pearson: 0.4449\n",
+      "    ENCSR862QCH_M/pearson: 0.4132\n",
+      "    ENCSR100LIJ_M/pearson: 0.4178\n",
+      "    ENCSR321PWZ_P/pearson: 0.5417\n",
+      "    ENCSR484LTQ_P/pearson: 0.2972\n",
+      "    ENCSR619DQO_P/pearson: 0.5967\n",
+      "    ENCSR325NFE/pearson: 0.7258\n",
+      "    ENCSR249ROI_P/pearson: 0.4557\n",
+      "    ENCSR249ROI_M/pearson: 0.5102\n",
+      "    ENCSR754DRC/pearson: 0.4468\n",
+      "    ENCSR321PWZ_M/pearson: 0.5791\n",
+      "    ENCSR862QCH_P/pearson: 0.3609\n",
+      "    ENCSR046BCI_P/pearson: 0.2787\n",
+      "    ENCSR799DGV_M/pearson: 0.4086\n",
+      "    ENCSR962OTG/pearson: 0.7932\n",
+      "    ENCSR682BFG/pearson: 0.5852\n",
+      "    ENCSR628PLS/pearson: 0.5937\n",
+      "    ENCSR619DQO_M/pearson: 0.6128\n",
+      "    ENCSR487QSB/pearson: 0.6437\n",
+      "    ENCSR114HGS_M/pearson: 0.2526\n",
+      "    ENCSR863PSM/pearson: 0.6271\n",
+      "    mean/pearson: 0.4856\n",
+      "    loss: 4.6823\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 5640/15000 | Loss: 3.7773 | Mean Pearson: 0.5427\n",
+      "Step 5680/15000 | Loss: 4.5242 | Mean Pearson: 0.5837\n",
+      "Step 5720/15000 | Loss: 4.2097 | Mean Pearson: 0.5543\n",
+      "Step 5760/15000 | Loss: 4.9089 | Mean Pearson: 0.6005\n",
+      "Step 5800/15000 | Loss: 4.5546 | Mean Pearson: 0.6212\n",
+      "Step 5840/15000 | Loss: 4.8205 | Mean Pearson: 0.6190\n",
+      "Step 5880/15000 | Loss: 5.0661 | Mean Pearson: 0.6311\n",
+      "Step 5920/15000 | Loss: 4.9546 | Mean Pearson: 0.6339\n",
+      "Step 5960/15000 | Loss: 5.7313 | Mean Pearson: 0.6076\n",
+      "Step 6000/15000 | Loss: 8.1549 | Mean Pearson: 0.5538\n",
+      "\n",
+      "Running validation at step 6000...\n",
+      "Step 6000/15000 | Loss: 4.7019 | Mean Pearson: 0.5005\n",
+      "    ENCSR154HRN_P/pearson: 0.4249\n",
+      "    ENCSR701YIC/pearson: 0.5447\n",
+      "    ENCSR935RNW_P/pearson: 0.4656\n",
+      "    ENCSR100LIJ_P/pearson: 0.4653\n",
+      "    ENCSR527JGN_P/pearson: 0.7041\n",
+      "    ENCSR114HGS_P/pearson: 0.2715\n",
+      "    ENCSR484LTQ_M/pearson: 0.3139\n",
+      "    ENCSR935RNW_M/pearson: 0.4496\n",
+      "    ENCSR410DWV/pearson: 0.7370\n",
+      "    ENCSR046BCI_M/pearson: 0.3674\n",
+      "    ENCSR814RGG/pearson: 0.7042\n",
+      "    ENCSR799DGV_P/pearson: 0.4556\n",
+      "    ENCSR527JGN_M/pearson: 0.4935\n",
+      "    ENCSR154HRN_M/pearson: 0.3519\n",
+      "    ENCSR862QCH_M/pearson: 0.3561\n",
+      "    ENCSR100LIJ_M/pearson: 0.4545\n",
+      "    ENCSR321PWZ_P/pearson: 0.6129\n",
+      "    ENCSR484LTQ_P/pearson: 0.4107\n",
+      "    ENCSR619DQO_P/pearson: 0.6447\n",
+      "    ENCSR325NFE/pearson: 0.7234\n",
+      "    ENCSR249ROI_P/pearson: 0.4896\n",
+      "    ENCSR249ROI_M/pearson: 0.4427\n",
+      "    ENCSR754DRC/pearson: 0.4342\n",
+      "    ENCSR321PWZ_M/pearson: 0.5082\n",
+      "    ENCSR862QCH_P/pearson: 0.4375\n",
+      "    ENCSR046BCI_P/pearson: 0.3641\n",
+      "    ENCSR799DGV_M/pearson: 0.4220\n",
+      "    ENCSR962OTG/pearson: 0.7942\n",
+      "    ENCSR682BFG/pearson: 0.5958\n",
+      "    ENCSR628PLS/pearson: 0.5940\n",
+      "    ENCSR619DQO_M/pearson: 0.5024\n",
+      "    ENCSR487QSB/pearson: 0.6419\n",
+      "    ENCSR114HGS_M/pearson: 0.2181\n",
+      "    ENCSR863PSM/pearson: 0.6201\n",
+      "    mean/pearson: 0.5005\n",
+      "    loss: 4.7019\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 6040/15000 | Loss: 5.0549 | Mean Pearson: 0.5872\n",
+      "Step 6080/15000 | Loss: 4.0109 | Mean Pearson: 0.6245\n",
+      "Step 6120/15000 | Loss: 5.0091 | Mean Pearson: 0.6152\n",
+      "Step 6160/15000 | Loss: 5.0773 | Mean Pearson: 0.6005\n",
+      "Step 6200/15000 | Loss: 4.5555 | Mean Pearson: 0.6187\n",
+      "Step 6240/15000 | Loss: 3.9988 | Mean Pearson: 0.6035\n",
+      "Step 6280/15000 | Loss: 4.2132 | Mean Pearson: 0.6284\n",
+      "Step 6320/15000 | Loss: 4.7366 | Mean Pearson: 0.6289\n",
+      "Step 6360/15000 | Loss: 4.3103 | Mean Pearson: 0.6078\n",
+      "Step 6400/15000 | Loss: 4.2883 | Mean Pearson: 0.6158\n",
+      "\n",
+      "Running validation at step 6400...\n",
+      "Step 6400/15000 | Loss: 4.9016 | Mean Pearson: 0.5130\n",
+      "    ENCSR154HRN_P/pearson: 0.3673\n",
+      "    ENCSR701YIC/pearson: 0.5459\n",
+      "    ENCSR935RNW_P/pearson: 0.4142\n",
+      "    ENCSR100LIJ_P/pearson: 0.4216\n",
+      "    ENCSR527JGN_P/pearson: 0.6012\n",
+      "    ENCSR114HGS_P/pearson: 0.2636\n",
+      "    ENCSR484LTQ_M/pearson: 0.4475\n",
+      "    ENCSR935RNW_M/pearson: 0.4454\n",
+      "    ENCSR410DWV/pearson: 0.7344\n",
+      "    ENCSR046BCI_M/pearson: 0.3642\n",
+      "    ENCSR814RGG/pearson: 0.7185\n",
+      "    ENCSR799DGV_P/pearson: 0.4204\n",
+      "    ENCSR527JGN_M/pearson: 0.5031\n",
+      "    ENCSR154HRN_M/pearson: 0.4856\n",
+      "    ENCSR862QCH_M/pearson: 0.4839\n",
+      "    ENCSR100LIJ_M/pearson: 0.4224\n",
+      "    ENCSR321PWZ_P/pearson: 0.5789\n",
+      "    ENCSR484LTQ_P/pearson: 0.3202\n",
+      "    ENCSR619DQO_P/pearson: 0.5910\n",
+      "    ENCSR325NFE/pearson: 0.7439\n",
+      "    ENCSR249ROI_P/pearson: 0.4951\n",
+      "    ENCSR249ROI_M/pearson: 0.5321\n",
+      "    ENCSR754DRC/pearson: 0.4643\n",
+      "    ENCSR321PWZ_M/pearson: 0.6766\n",
+      "    ENCSR862QCH_P/pearson: 0.3801\n",
+      "    ENCSR046BCI_P/pearson: 0.3535\n",
+      "    ENCSR799DGV_M/pearson: 0.4156\n",
+      "    ENCSR962OTG/pearson: 0.8379\n",
+      "    ENCSR682BFG/pearson: 0.6208\n",
+      "    ENCSR628PLS/pearson: 0.6171\n",
+      "    ENCSR619DQO_M/pearson: 0.5538\n",
+      "    ENCSR487QSB/pearson: 0.6699\n",
+      "    ENCSR114HGS_M/pearson: 0.3038\n",
+      "    ENCSR863PSM/pearson: 0.6496\n",
+      "    mean/pearson: 0.5130\n",
+      "    loss: 4.9016\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 6440/15000 | Loss: 3.7394 | Mean Pearson: 0.5438\n",
+      "Step 6480/15000 | Loss: 4.9569 | Mean Pearson: 0.6041\n",
+      "Step 6520/15000 | Loss: 4.8864 | Mean Pearson: 0.6236\n",
+      "Step 6560/15000 | Loss: 3.8833 | Mean Pearson: 0.5467\n",
+      "Step 6600/15000 | Loss: 4.1832 | Mean Pearson: 0.6063\n",
+      "Step 6640/15000 | Loss: 4.5012 | Mean Pearson: 0.6162\n",
+      "Step 6680/15000 | Loss: 4.8798 | Mean Pearson: 0.6259\n",
+      "Step 6720/15000 | Loss: 3.8760 | Mean Pearson: 0.5854\n",
+      "Step 6760/15000 | Loss: 4.7026 | Mean Pearson: 0.6214\n",
+      "Step 6800/15000 | Loss: 4.4444 | Mean Pearson: 0.6232\n",
+      "\n",
+      "Running validation at step 6800...\n",
+      "Step 6800/15000 | Loss: 4.7729 | Mean Pearson: 0.4980\n",
+      "    ENCSR154HRN_P/pearson: 0.3655\n",
+      "    ENCSR701YIC/pearson: 0.5531\n",
+      "    ENCSR935RNW_P/pearson: 0.4220\n",
+      "    ENCSR100LIJ_P/pearson: 0.4068\n",
+      "    ENCSR527JGN_P/pearson: 0.7239\n",
+      "    ENCSR114HGS_P/pearson: 0.2314\n",
+      "    ENCSR484LTQ_M/pearson: 0.3776\n",
+      "    ENCSR935RNW_M/pearson: 0.3945\n",
+      "    ENCSR410DWV/pearson: 0.7198\n",
+      "    ENCSR046BCI_M/pearson: 0.3056\n",
+      "    ENCSR814RGG/pearson: 0.7171\n",
+      "    ENCSR799DGV_P/pearson: 0.4070\n",
+      "    ENCSR527JGN_M/pearson: 0.6303\n",
+      "    ENCSR154HRN_M/pearson: 0.4435\n",
+      "    ENCSR862QCH_M/pearson: 0.4019\n",
+      "    ENCSR100LIJ_M/pearson: 0.3674\n",
+      "    ENCSR321PWZ_P/pearson: 0.5619\n",
+      "    ENCSR484LTQ_P/pearson: 0.3159\n",
+      "    ENCSR619DQO_P/pearson: 0.6532\n",
+      "    ENCSR325NFE/pearson: 0.7398\n",
+      "    ENCSR249ROI_P/pearson: 0.4438\n",
+      "    ENCSR249ROI_M/pearson: 0.4998\n",
+      "    ENCSR754DRC/pearson: 0.4263\n",
+      "    ENCSR321PWZ_M/pearson: 0.5715\n",
+      "    ENCSR862QCH_P/pearson: 0.3569\n",
+      "    ENCSR046BCI_P/pearson: 0.3444\n",
+      "    ENCSR799DGV_M/pearson: 0.3725\n",
+      "    ENCSR962OTG/pearson: 0.8142\n",
+      "    ENCSR682BFG/pearson: 0.6123\n",
+      "    ENCSR628PLS/pearson: 0.6066\n",
+      "    ENCSR619DQO_M/pearson: 0.5903\n",
+      "    ENCSR487QSB/pearson: 0.6610\n",
+      "    ENCSR114HGS_M/pearson: 0.2435\n",
+      "    ENCSR863PSM/pearson: 0.6507\n",
+      "    mean/pearson: 0.4980\n",
+      "    loss: 4.7729\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 6840/15000 | Loss: 4.8048 | Mean Pearson: 0.6133\n",
+      "Step 6880/15000 | Loss: 4.6466 | Mean Pearson: 0.6217\n",
+      "Step 6920/15000 | Loss: 5.0558 | Mean Pearson: 0.6122\n",
+      "Step 6960/15000 | Loss: 4.9485 | Mean Pearson: 0.6304\n",
+      "Step 7000/15000 | Loss: 6.3132 | Mean Pearson: 0.6349\n",
+      "Step 7040/15000 | Loss: 5.2999 | Mean Pearson: 0.6495\n",
+      "Step 7080/15000 | Loss: 4.5199 | Mean Pearson: 0.6049\n",
+      "Step 7120/15000 | Loss: 5.5136 | Mean Pearson: 0.6396\n",
+      "Step 7160/15000 | Loss: 5.4657 | Mean Pearson: 0.6275\n",
+      "Step 7200/15000 | Loss: 4.6520 | Mean Pearson: 0.5946\n",
+      "\n",
+      "Running validation at step 7200...\n",
+      "Step 7200/15000 | Loss: 5.0746 | Mean Pearson: 0.5180\n",
+      "    ENCSR154HRN_P/pearson: 0.4328\n",
+      "    ENCSR701YIC/pearson: 0.5693\n",
+      "    ENCSR935RNW_P/pearson: 0.4205\n",
+      "    ENCSR100LIJ_P/pearson: 0.4226\n",
+      "    ENCSR527JGN_P/pearson: 0.6437\n",
+      "    ENCSR114HGS_P/pearson: 0.2710\n",
+      "    ENCSR484LTQ_M/pearson: 0.4232\n",
+      "    ENCSR935RNW_M/pearson: 0.4369\n",
+      "    ENCSR410DWV/pearson: 0.7300\n",
+      "    ENCSR046BCI_M/pearson: 0.3835\n",
+      "    ENCSR814RGG/pearson: 0.7193\n",
+      "    ENCSR799DGV_P/pearson: 0.4446\n",
+      "    ENCSR527JGN_M/pearson: 0.4976\n",
+      "    ENCSR154HRN_M/pearson: 0.4337\n",
+      "    ENCSR862QCH_M/pearson: 0.4583\n",
+      "    ENCSR100LIJ_M/pearson: 0.4189\n",
+      "    ENCSR321PWZ_P/pearson: 0.6050\n",
+      "    ENCSR484LTQ_P/pearson: 0.3749\n",
+      "    ENCSR619DQO_P/pearson: 0.6131\n",
+      "    ENCSR325NFE/pearson: 0.7482\n",
+      "    ENCSR249ROI_P/pearson: 0.5271\n",
+      "    ENCSR249ROI_M/pearson: 0.5023\n",
+      "    ENCSR754DRC/pearson: 0.5008\n",
+      "    ENCSR321PWZ_M/pearson: 0.6419\n",
+      "    ENCSR862QCH_P/pearson: 0.4198\n",
+      "    ENCSR046BCI_P/pearson: 0.3628\n",
+      "    ENCSR799DGV_M/pearson: 0.4533\n",
+      "    ENCSR962OTG/pearson: 0.8671\n",
+      "    ENCSR682BFG/pearson: 0.5994\n",
+      "    ENCSR628PLS/pearson: 0.6147\n",
+      "    ENCSR619DQO_M/pearson: 0.5055\n",
+      "    ENCSR487QSB/pearson: 0.6684\n",
+      "    ENCSR114HGS_M/pearson: 0.2612\n",
+      "    ENCSR863PSM/pearson: 0.6393\n",
+      "    mean/pearson: 0.5180\n",
+      "    loss: 5.0746\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 7240/15000 | Loss: 4.4867 | Mean Pearson: 0.6222\n",
+      "Step 7280/15000 | Loss: 3.7016 | Mean Pearson: 0.5778\n",
+      "Step 7320/15000 | Loss: 5.1025 | Mean Pearson: 0.6593\n",
+      "Step 7360/15000 | Loss: 4.5291 | Mean Pearson: 0.6384\n",
+      "Step 7400/15000 | Loss: 4.7604 | Mean Pearson: 0.6064\n",
+      "Step 7440/15000 | Loss: 4.5972 | Mean Pearson: 0.6045\n",
+      "Step 7480/15000 | Loss: 4.6235 | Mean Pearson: 0.6352\n",
+      "Step 7520/15000 | Loss: 5.1422 | Mean Pearson: 0.6120\n",
+      "Step 7560/15000 | Loss: 4.7828 | Mean Pearson: 0.6282\n",
+      "Step 7600/15000 | Loss: 5.6790 | Mean Pearson: 0.6426\n",
+      "\n",
+      "Running validation at step 7600...\n",
+      "Step 7600/15000 | Loss: 4.6679 | Mean Pearson: 0.5262\n",
+      "    ENCSR154HRN_P/pearson: 0.3733\n",
+      "    ENCSR701YIC/pearson: 0.5867\n",
+      "    ENCSR935RNW_P/pearson: 0.4465\n",
+      "    ENCSR100LIJ_P/pearson: 0.4736\n",
+      "    ENCSR527JGN_P/pearson: 0.4807\n",
+      "    ENCSR114HGS_P/pearson: 0.2434\n",
+      "    ENCSR484LTQ_M/pearson: 0.4640\n",
+      "    ENCSR935RNW_M/pearson: 0.4441\n",
+      "    ENCSR410DWV/pearson: 0.7329\n",
+      "    ENCSR046BCI_M/pearson: 0.4170\n",
+      "    ENCSR814RGG/pearson: 0.7233\n",
+      "    ENCSR799DGV_P/pearson: 0.4637\n",
+      "    ENCSR527JGN_M/pearson: 0.6896\n",
+      "    ENCSR154HRN_M/pearson: 0.4322\n",
+      "    ENCSR862QCH_M/pearson: 0.4872\n",
+      "    ENCSR100LIJ_M/pearson: 0.4580\n",
+      "    ENCSR321PWZ_P/pearson: 0.5755\n",
+      "    ENCSR484LTQ_P/pearson: 0.3565\n",
+      "    ENCSR619DQO_P/pearson: 0.6561\n",
+      "    ENCSR325NFE/pearson: 0.7500\n",
+      "    ENCSR249ROI_P/pearson: 0.4776\n",
+      "    ENCSR249ROI_M/pearson: 0.5055\n",
+      "    ENCSR754DRC/pearson: 0.4731\n",
+      "    ENCSR321PWZ_M/pearson: 0.6849\n",
+      "    ENCSR862QCH_P/pearson: 0.3601\n",
+      "    ENCSR046BCI_P/pearson: 0.3663\n",
+      "    ENCSR799DGV_M/pearson: 0.4511\n",
+      "    ENCSR962OTG/pearson: 0.8388\n",
+      "    ENCSR682BFG/pearson: 0.6230\n",
+      "    ENCSR628PLS/pearson: 0.6282\n",
+      "    ENCSR619DQO_M/pearson: 0.6311\n",
+      "    ENCSR487QSB/pearson: 0.6804\n",
+      "    ENCSR114HGS_M/pearson: 0.2570\n",
+      "    ENCSR863PSM/pearson: 0.6597\n",
+      "    mean/pearson: 0.5262\n",
+      "    loss: 4.6679\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 7640/15000 | Loss: 4.5026 | Mean Pearson: 0.5968\n",
+      "Step 7680/15000 | Loss: 4.5894 | Mean Pearson: 0.6092\n",
+      "Step 7720/15000 | Loss: 5.0146 | Mean Pearson: 0.6104\n",
+      "Step 7760/15000 | Loss: 5.1612 | Mean Pearson: 0.6366\n",
+      "Step 7800/15000 | Loss: 3.8651 | Mean Pearson: 0.6198\n",
+      "Step 7840/15000 | Loss: 4.2320 | Mean Pearson: 0.6173\n",
+      "Step 7880/15000 | Loss: 4.6963 | Mean Pearson: 0.6090\n",
+      "Step 7920/15000 | Loss: 4.5210 | Mean Pearson: 0.6004\n",
+      "Step 7960/15000 | Loss: 4.3583 | Mean Pearson: 0.6341\n",
+      "Step 8000/15000 | Loss: 5.5322 | Mean Pearson: 0.6146\n",
+      "\n",
+      "Running validation at step 8000...\n",
+      "Step 8000/15000 | Loss: 4.9696 | Mean Pearson: 0.5312\n",
+      "    ENCSR154HRN_P/pearson: 0.3788\n",
+      "    ENCSR701YIC/pearson: 0.5796\n",
+      "    ENCSR935RNW_P/pearson: 0.4603\n",
+      "    ENCSR100LIJ_P/pearson: 0.4862\n",
+      "    ENCSR527JGN_P/pearson: 0.6586\n",
+      "    ENCSR114HGS_P/pearson: 0.2487\n",
+      "    ENCSR484LTQ_M/pearson: 0.4131\n",
+      "    ENCSR935RNW_M/pearson: 0.4697\n",
+      "    ENCSR410DWV/pearson: 0.7580\n",
+      "    ENCSR046BCI_M/pearson: 0.4306\n",
+      "    ENCSR814RGG/pearson: 0.7488\n",
+      "    ENCSR799DGV_P/pearson: 0.5083\n",
+      "    ENCSR527JGN_M/pearson: 0.6985\n",
+      "    ENCSR154HRN_M/pearson: 0.4051\n",
+      "    ENCSR862QCH_M/pearson: 0.4435\n",
+      "    ENCSR100LIJ_M/pearson: 0.4708\n",
+      "    ENCSR321PWZ_P/pearson: 0.5531\n",
+      "    ENCSR484LTQ_P/pearson: 0.2931\n",
+      "    ENCSR619DQO_P/pearson: 0.5926\n",
+      "    ENCSR325NFE/pearson: 0.7674\n",
+      "    ENCSR249ROI_P/pearson: 0.4594\n",
+      "    ENCSR249ROI_M/pearson: 0.4692\n",
+      "    ENCSR754DRC/pearson: 0.5079\n",
+      "    ENCSR321PWZ_M/pearson: 0.6590\n",
+      "    ENCSR862QCH_P/pearson: 0.3369\n",
+      "    ENCSR046BCI_P/pearson: 0.4054\n",
+      "    ENCSR799DGV_M/pearson: 0.4811\n",
+      "    ENCSR962OTG/pearson: 0.8573\n",
+      "    ENCSR682BFG/pearson: 0.6371\n",
+      "    ENCSR628PLS/pearson: 0.6506\n",
+      "    ENCSR619DQO_M/pearson: 0.6166\n",
+      "    ENCSR487QSB/pearson: 0.6962\n",
+      "    ENCSR114HGS_M/pearson: 0.2587\n",
+      "    ENCSR863PSM/pearson: 0.6612\n",
+      "    mean/pearson: 0.5312\n",
+      "    loss: 4.9696\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 8040/15000 | Loss: 4.2074 | Mean Pearson: 0.6351\n",
+      "Step 8080/15000 | Loss: 4.7238 | Mean Pearson: 0.6481\n",
+      "Step 8120/15000 | Loss: 5.1969 | Mean Pearson: 0.6304\n",
+      "Step 8160/15000 | Loss: 4.3186 | Mean Pearson: 0.6199\n",
+      "Step 8200/15000 | Loss: 5.0482 | Mean Pearson: 0.6313\n",
+      "Step 8240/15000 | Loss: 5.0099 | Mean Pearson: 0.6391\n",
+      "Step 8280/15000 | Loss: 4.4641 | Mean Pearson: 0.6262\n",
+      "Step 8320/15000 | Loss: 5.1754 | Mean Pearson: 0.6433\n",
+      "Step 8360/15000 | Loss: 5.0818 | Mean Pearson: 0.6118\n",
+      "Step 8400/15000 | Loss: 4.2639 | Mean Pearson: 0.6199\n",
+      "\n",
+      "Running validation at step 8400...\n",
+      "Step 8400/15000 | Loss: 4.6186 | Mean Pearson: 0.5054\n",
+      "    ENCSR154HRN_P/pearson: 0.3771\n",
+      "    ENCSR701YIC/pearson: 0.5666\n",
+      "    ENCSR935RNW_P/pearson: 0.4496\n",
+      "    ENCSR100LIJ_P/pearson: 0.4442\n",
+      "    ENCSR527JGN_P/pearson: 0.4934\n",
+      "    ENCSR114HGS_P/pearson: 0.2204\n",
+      "    ENCSR484LTQ_M/pearson: 0.3554\n",
+      "    ENCSR935RNW_M/pearson: 0.4191\n",
+      "    ENCSR410DWV/pearson: 0.7357\n",
+      "    ENCSR046BCI_M/pearson: 0.3589\n",
+      "    ENCSR814RGG/pearson: 0.7293\n",
+      "    ENCSR799DGV_P/pearson: 0.4509\n",
+      "    ENCSR527JGN_M/pearson: 0.5771\n",
+      "    ENCSR154HRN_M/pearson: 0.4595\n",
+      "    ENCSR862QCH_M/pearson: 0.4231\n",
+      "    ENCSR100LIJ_M/pearson: 0.4054\n",
+      "    ENCSR321PWZ_P/pearson: 0.5786\n",
+      "    ENCSR484LTQ_P/pearson: 0.3204\n",
+      "    ENCSR619DQO_P/pearson: 0.6038\n",
+      "    ENCSR325NFE/pearson: 0.7584\n",
+      "    ENCSR249ROI_P/pearson: 0.4554\n",
+      "    ENCSR249ROI_M/pearson: 0.5299\n",
+      "    ENCSR754DRC/pearson: 0.4640\n",
+      "    ENCSR321PWZ_M/pearson: 0.6120\n",
+      "    ENCSR862QCH_P/pearson: 0.3596\n",
+      "    ENCSR046BCI_P/pearson: 0.3527\n",
+      "    ENCSR799DGV_M/pearson: 0.4113\n",
+      "    ENCSR962OTG/pearson: 0.8361\n",
+      "    ENCSR682BFG/pearson: 0.6203\n",
+      "    ENCSR628PLS/pearson: 0.6128\n",
+      "    ENCSR619DQO_M/pearson: 0.5797\n",
+      "    ENCSR487QSB/pearson: 0.6670\n",
+      "    ENCSR114HGS_M/pearson: 0.2962\n",
+      "    ENCSR863PSM/pearson: 0.6603\n",
+      "    mean/pearson: 0.5054\n",
+      "    loss: 4.6186\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 8440/15000 | Loss: 4.5697 | Mean Pearson: 0.6194\n",
+      "Step 8480/15000 | Loss: 4.7857 | Mean Pearson: 0.6137\n",
+      "Step 8520/15000 | Loss: 4.9848 | Mean Pearson: 0.6509\n",
+      "Step 8560/15000 | Loss: 5.1571 | Mean Pearson: 0.6403\n",
+      "Step 8600/15000 | Loss: 4.2129 | Mean Pearson: 0.5945\n",
+      "Step 8640/15000 | Loss: 5.2840 | Mean Pearson: 0.6266\n",
+      "Step 8680/15000 | Loss: 4.0469 | Mean Pearson: 0.6371\n",
+      "Step 8720/15000 | Loss: 4.8656 | Mean Pearson: 0.6183\n",
+      "Step 8760/15000 | Loss: 4.1634 | Mean Pearson: 0.6340\n",
+      "Step 8800/15000 | Loss: 4.6567 | Mean Pearson: 0.6208\n",
+      "\n",
+      "Running validation at step 8800...\n",
+      "Step 8800/15000 | Loss: 4.6639 | Mean Pearson: 0.5182\n",
+      "    ENCSR154HRN_P/pearson: 0.4416\n",
+      "    ENCSR701YIC/pearson: 0.5792\n",
+      "    ENCSR935RNW_P/pearson: 0.4588\n",
+      "    ENCSR100LIJ_P/pearson: 0.4525\n",
+      "    ENCSR527JGN_P/pearson: 0.6327\n",
+      "    ENCSR114HGS_P/pearson: 0.2641\n",
+      "    ENCSR484LTQ_M/pearson: 0.3579\n",
+      "    ENCSR935RNW_M/pearson: 0.4635\n",
+      "    ENCSR410DWV/pearson: 0.7476\n",
+      "    ENCSR046BCI_M/pearson: 0.4190\n",
+      "    ENCSR814RGG/pearson: 0.7309\n",
+      "    ENCSR799DGV_P/pearson: 0.4663\n",
+      "    ENCSR527JGN_M/pearson: 0.5723\n",
+      "    ENCSR154HRN_M/pearson: 0.4369\n",
+      "    ENCSR862QCH_M/pearson: 0.4143\n",
+      "    ENCSR100LIJ_M/pearson: 0.4476\n",
+      "    ENCSR321PWZ_P/pearson: 0.4517\n",
+      "    ENCSR484LTQ_P/pearson: 0.4106\n",
+      "    ENCSR619DQO_P/pearson: 0.6173\n",
+      "    ENCSR325NFE/pearson: 0.7561\n",
+      "    ENCSR249ROI_P/pearson: 0.5271\n",
+      "    ENCSR249ROI_M/pearson: 0.5435\n",
+      "    ENCSR754DRC/pearson: 0.4535\n",
+      "    ENCSR321PWZ_M/pearson: 0.5516\n",
+      "    ENCSR862QCH_P/pearson: 0.4407\n",
+      "    ENCSR046BCI_P/pearson: 0.3724\n",
+      "    ENCSR799DGV_M/pearson: 0.4581\n",
+      "    ENCSR962OTG/pearson: 0.8303\n",
+      "    ENCSR682BFG/pearson: 0.5964\n",
+      "    ENCSR628PLS/pearson: 0.6250\n",
+      "    ENCSR619DQO_M/pearson: 0.5314\n",
+      "    ENCSR487QSB/pearson: 0.6798\n",
+      "    ENCSR114HGS_M/pearson: 0.2548\n",
+      "    ENCSR863PSM/pearson: 0.6347\n",
+      "    mean/pearson: 0.5182\n",
+      "    loss: 4.6639\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 8840/15000 | Loss: 4.1950 | Mean Pearson: 0.6123\n",
+      "Step 8880/15000 | Loss: 5.6013 | Mean Pearson: 0.6319\n",
+      "Step 8920/15000 | Loss: 4.6914 | Mean Pearson: 0.5911\n",
+      "Step 8960/15000 | Loss: 4.6713 | Mean Pearson: 0.6210\n",
+      "Step 9000/15000 | Loss: 4.9609 | Mean Pearson: 0.6437\n",
+      "Step 9040/15000 | Loss: 5.0535 | Mean Pearson: 0.6442\n",
+      "Step 9080/15000 | Loss: 3.7833 | Mean Pearson: 0.6300\n",
+      "Step 9120/15000 | Loss: 3.8431 | Mean Pearson: 0.6259\n",
+      "Step 9160/15000 | Loss: 3.9874 | Mean Pearson: 0.6444\n",
+      "Step 9200/15000 | Loss: 4.5631 | Mean Pearson: 0.6535\n",
+      "\n",
+      "Running validation at step 9200...\n",
+      "Step 9200/15000 | Loss: 4.7676 | Mean Pearson: 0.5118\n",
+      "    ENCSR154HRN_P/pearson: 0.3748\n",
+      "    ENCSR701YIC/pearson: 0.5698\n",
+      "    ENCSR935RNW_P/pearson: 0.4453\n",
+      "    ENCSR100LIJ_P/pearson: 0.4259\n",
+      "    ENCSR527JGN_P/pearson: 0.6002\n",
+      "    ENCSR114HGS_P/pearson: 0.2664\n",
+      "    ENCSR484LTQ_M/pearson: 0.3395\n",
+      "    ENCSR935RNW_M/pearson: 0.4823\n",
+      "    ENCSR410DWV/pearson: 0.7508\n",
+      "    ENCSR046BCI_M/pearson: 0.4352\n",
+      "    ENCSR814RGG/pearson: 0.7540\n",
+      "    ENCSR799DGV_P/pearson: 0.4405\n",
+      "    ENCSR527JGN_M/pearson: 0.4716\n",
+      "    ENCSR154HRN_M/pearson: 0.3645\n",
+      "    ENCSR862QCH_M/pearson: 0.3884\n",
+      "    ENCSR100LIJ_M/pearson: 0.4610\n",
+      "    ENCSR321PWZ_P/pearson: 0.5489\n",
+      "    ENCSR484LTQ_P/pearson: 0.3691\n",
+      "    ENCSR619DQO_P/pearson: 0.6513\n",
+      "    ENCSR325NFE/pearson: 0.7631\n",
+      "    ENCSR249ROI_P/pearson: 0.4969\n",
+      "    ENCSR249ROI_M/pearson: 0.4558\n",
+      "    ENCSR754DRC/pearson: 0.5234\n",
+      "    ENCSR321PWZ_M/pearson: 0.5688\n",
+      "    ENCSR862QCH_P/pearson: 0.4004\n",
+      "    ENCSR046BCI_P/pearson: 0.3420\n",
+      "    ENCSR799DGV_M/pearson: 0.4646\n",
+      "    ENCSR962OTG/pearson: 0.8670\n",
+      "    ENCSR682BFG/pearson: 0.6145\n",
+      "    ENCSR628PLS/pearson: 0.6301\n",
+      "    ENCSR619DQO_M/pearson: 0.5488\n",
+      "    ENCSR487QSB/pearson: 0.6883\n",
+      "    ENCSR114HGS_M/pearson: 0.2492\n",
+      "    ENCSR863PSM/pearson: 0.6474\n",
+      "    mean/pearson: 0.5118\n",
+      "    loss: 4.7676\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 9240/15000 | Loss: 4.5566 | Mean Pearson: 0.6533\n",
+      "Step 9280/15000 | Loss: 4.7908 | Mean Pearson: 0.6185\n",
+      "Step 9320/15000 | Loss: 5.2750 | Mean Pearson: 0.6664\n",
+      "Step 9360/15000 | Loss: 4.3142 | Mean Pearson: 0.6327\n",
+      "Step 9400/15000 | Loss: 4.8458 | Mean Pearson: 0.6447\n",
+      "Step 9440/15000 | Loss: 5.2655 | Mean Pearson: 0.6372\n",
+      "Step 9480/15000 | Loss: 5.0080 | Mean Pearson: 0.6650\n",
+      "Step 9520/15000 | Loss: 3.9779 | Mean Pearson: 0.6357\n",
+      "Step 9560/15000 | Loss: 4.7296 | Mean Pearson: 0.6444\n",
+      "Step 9600/15000 | Loss: 3.9311 | Mean Pearson: 0.6412\n",
+      "\n",
+      "Running validation at step 9600...\n",
+      "Step 9600/15000 | Loss: 4.6970 | Mean Pearson: 0.5268\n",
+      "    ENCSR154HRN_P/pearson: 0.3722\n",
+      "    ENCSR701YIC/pearson: 0.6193\n",
+      "    ENCSR935RNW_P/pearson: 0.4695\n",
+      "    ENCSR100LIJ_P/pearson: 0.4675\n",
+      "    ENCSR527JGN_P/pearson: 0.6729\n",
+      "    ENCSR114HGS_P/pearson: 0.2664\n",
+      "    ENCSR484LTQ_M/pearson: 0.3587\n",
+      "    ENCSR935RNW_M/pearson: 0.4551\n",
+      "    ENCSR410DWV/pearson: 0.7424\n",
+      "    ENCSR046BCI_M/pearson: 0.4020\n",
+      "    ENCSR814RGG/pearson: 0.7425\n",
+      "    ENCSR799DGV_P/pearson: 0.4892\n",
+      "    ENCSR527JGN_M/pearson: 0.5192\n",
+      "    ENCSR154HRN_M/pearson: 0.4430\n",
+      "    ENCSR862QCH_M/pearson: 0.3983\n",
+      "    ENCSR100LIJ_M/pearson: 0.4340\n",
+      "    ENCSR321PWZ_P/pearson: 0.6228\n",
+      "    ENCSR484LTQ_P/pearson: 0.3478\n",
+      "    ENCSR619DQO_P/pearson: 0.6461\n",
+      "    ENCSR325NFE/pearson: 0.7528\n",
+      "    ENCSR249ROI_P/pearson: 0.4748\n",
+      "    ENCSR249ROI_M/pearson: 0.5223\n",
+      "    ENCSR754DRC/pearson: 0.5001\n",
+      "    ENCSR321PWZ_M/pearson: 0.6216\n",
+      "    ENCSR862QCH_P/pearson: 0.3815\n",
+      "    ENCSR046BCI_P/pearson: 0.4188\n",
+      "    ENCSR799DGV_M/pearson: 0.4545\n",
+      "    ENCSR962OTG/pearson: 0.8726\n",
+      "    ENCSR682BFG/pearson: 0.6153\n",
+      "    ENCSR628PLS/pearson: 0.6358\n",
+      "    ENCSR619DQO_M/pearson: 0.5741\n",
+      "    ENCSR487QSB/pearson: 0.6918\n",
+      "    ENCSR114HGS_M/pearson: 0.2610\n",
+      "    ENCSR863PSM/pearson: 0.6637\n",
+      "    mean/pearson: 0.5268\n",
+      "    loss: 4.6970\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 9640/15000 | Loss: 5.2175 | Mean Pearson: 0.6499\n",
+      "Step 9680/15000 | Loss: 3.9056 | Mean Pearson: 0.5972\n",
+      "Step 9720/15000 | Loss: 3.9999 | Mean Pearson: 0.6358\n",
+      "Step 9760/15000 | Loss: 4.1700 | Mean Pearson: 0.6140\n",
+      "Step 9800/15000 | Loss: 4.6878 | Mean Pearson: 0.6356\n",
+      "Step 9840/15000 | Loss: 5.0660 | Mean Pearson: 0.6405\n",
+      "Step 9880/15000 | Loss: 4.3475 | Mean Pearson: 0.6447\n",
+      "Step 9920/15000 | Loss: 5.3046 | Mean Pearson: 0.6592\n",
+      "Step 9960/15000 | Loss: 4.6615 | Mean Pearson: 0.6217\n",
+      "Step 10000/15000 | Loss: 5.3068 | Mean Pearson: 0.6735\n",
+      "\n",
+      "Running validation at step 10000...\n",
+      "Step 10000/15000 | Loss: 4.8571 | Mean Pearson: 0.5284\n",
+      "    ENCSR154HRN_P/pearson: 0.4462\n",
+      "    ENCSR701YIC/pearson: 0.5576\n",
+      "    ENCSR935RNW_P/pearson: 0.4504\n",
+      "    ENCSR100LIJ_P/pearson: 0.4701\n",
+      "    ENCSR527JGN_P/pearson: 0.6198\n",
+      "    ENCSR114HGS_P/pearson: 0.2725\n",
+      "    ENCSR484LTQ_M/pearson: 0.3604\n",
+      "    ENCSR935RNW_M/pearson: 0.4635\n",
+      "    ENCSR410DWV/pearson: 0.7672\n",
+      "    ENCSR046BCI_M/pearson: 0.4141\n",
+      "    ENCSR814RGG/pearson: 0.7445\n",
+      "    ENCSR799DGV_P/pearson: 0.4818\n",
+      "    ENCSR527JGN_M/pearson: 0.5730\n",
+      "    ENCSR154HRN_M/pearson: 0.4431\n",
+      "    ENCSR862QCH_M/pearson: 0.4085\n",
+      "    ENCSR100LIJ_M/pearson: 0.4757\n",
+      "    ENCSR321PWZ_P/pearson: 0.4761\n",
+      "    ENCSR484LTQ_P/pearson: 0.3869\n",
+      "    ENCSR619DQO_P/pearson: 0.6228\n",
+      "    ENCSR325NFE/pearson: 0.7744\n",
+      "    ENCSR249ROI_P/pearson: 0.5467\n",
+      "    ENCSR249ROI_M/pearson: 0.5130\n",
+      "    ENCSR754DRC/pearson: 0.5148\n",
+      "    ENCSR321PWZ_M/pearson: 0.5749\n",
+      "    ENCSR862QCH_P/pearson: 0.4300\n",
+      "    ENCSR046BCI_P/pearson: 0.3764\n",
+      "    ENCSR799DGV_M/pearson: 0.4696\n",
+      "    ENCSR962OTG/pearson: 0.8490\n",
+      "    ENCSR682BFG/pearson: 0.6296\n",
+      "    ENCSR628PLS/pearson: 0.6463\n",
+      "    ENCSR619DQO_M/pearson: 0.5911\n",
+      "    ENCSR487QSB/pearson: 0.6959\n",
+      "    ENCSR114HGS_M/pearson: 0.2611\n",
+      "    ENCSR863PSM/pearson: 0.6578\n",
+      "    mean/pearson: 0.5284\n",
+      "    loss: 4.8571\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 10040/15000 | Loss: 5.0694 | Mean Pearson: 0.6266\n",
+      "Step 10080/15000 | Loss: 4.6203 | Mean Pearson: 0.6167\n",
+      "Step 10120/15000 | Loss: 5.0187 | Mean Pearson: 0.6440\n",
+      "Step 10160/15000 | Loss: 3.6263 | Mean Pearson: 0.6001\n",
+      "Step 10200/15000 | Loss: 3.9933 | Mean Pearson: 0.6140\n",
+      "Step 10240/15000 | Loss: 4.6684 | Mean Pearson: 0.6316\n",
+      "Step 10280/15000 | Loss: 4.5576 | Mean Pearson: 0.6429\n",
+      "Step 10320/15000 | Loss: 4.8142 | Mean Pearson: 0.6363\n",
+      "Step 10360/15000 | Loss: 4.5618 | Mean Pearson: 0.6279\n",
+      "Step 10400/15000 | Loss: 5.2742 | Mean Pearson: 0.6470\n",
+      "\n",
+      "Running validation at step 10400...\n",
+      "Step 10400/15000 | Loss: 4.9511 | Mean Pearson: 0.5194\n",
+      "    ENCSR154HRN_P/pearson: 0.4000\n",
+      "    ENCSR701YIC/pearson: 0.5971\n",
+      "    ENCSR935RNW_P/pearson: 0.4072\n",
+      "    ENCSR100LIJ_P/pearson: 0.4174\n",
+      "    ENCSR527JGN_P/pearson: 0.5352\n",
+      "    ENCSR114HGS_P/pearson: 0.2574\n",
+      "    ENCSR484LTQ_M/pearson: 0.4118\n",
+      "    ENCSR935RNW_M/pearson: 0.4408\n",
+      "    ENCSR410DWV/pearson: 0.7562\n",
+      "    ENCSR046BCI_M/pearson: 0.4120\n",
+      "    ENCSR814RGG/pearson: 0.7423\n",
+      "    ENCSR799DGV_P/pearson: 0.4373\n",
+      "    ENCSR527JGN_M/pearson: 0.6028\n",
+      "    ENCSR154HRN_M/pearson: 0.4349\n",
+      "    ENCSR862QCH_M/pearson: 0.4733\n",
+      "    ENCSR100LIJ_M/pearson: 0.4532\n",
+      "    ENCSR321PWZ_P/pearson: 0.5984\n",
+      "    ENCSR484LTQ_P/pearson: 0.3312\n",
+      "    ENCSR619DQO_P/pearson: 0.5798\n",
+      "    ENCSR325NFE/pearson: 0.7740\n",
+      "    ENCSR249ROI_P/pearson: 0.4786\n",
+      "    ENCSR249ROI_M/pearson: 0.5103\n",
+      "    ENCSR754DRC/pearson: 0.4823\n",
+      "    ENCSR321PWZ_M/pearson: 0.6312\n",
+      "    ENCSR862QCH_P/pearson: 0.2625\n",
+      "    ENCSR046BCI_P/pearson: 0.3850\n",
+      "    ENCSR799DGV_M/pearson: 0.4569\n",
+      "    ENCSR962OTG/pearson: 0.8354\n",
+      "    ENCSR682BFG/pearson: 0.6386\n",
+      "    ENCSR628PLS/pearson: 0.6584\n",
+      "    ENCSR619DQO_M/pearson: 0.6470\n",
+      "    ENCSR487QSB/pearson: 0.6993\n",
+      "    ENCSR114HGS_M/pearson: 0.2530\n",
+      "    ENCSR863PSM/pearson: 0.6597\n",
+      "    mean/pearson: 0.5194\n",
+      "    loss: 4.9511\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 10440/15000 | Loss: 4.3543 | Mean Pearson: 0.6345\n",
+      "Step 10480/15000 | Loss: 3.9304 | Mean Pearson: 0.6226\n",
+      "Step 10520/15000 | Loss: 5.2240 | Mean Pearson: 0.6278\n",
+      "Step 10560/15000 | Loss: 4.2276 | Mean Pearson: 0.6473\n",
+      "Step 10600/15000 | Loss: 4.9587 | Mean Pearson: 0.6456\n",
+      "Step 10640/15000 | Loss: 4.6883 | Mean Pearson: 0.6376\n",
+      "Step 10680/15000 | Loss: 4.1185 | Mean Pearson: 0.6266\n",
+      "Step 10720/15000 | Loss: 4.1436 | Mean Pearson: 0.6439\n",
+      "Step 10760/15000 | Loss: 4.3562 | Mean Pearson: 0.6437\n",
+      "Step 10800/15000 | Loss: 5.6151 | Mean Pearson: 0.6460\n",
+      "\n",
+      "Running validation at step 10800...\n",
+      "Step 10800/15000 | Loss: 4.7170 | Mean Pearson: 0.5267\n",
+      "    ENCSR154HRN_P/pearson: 0.4008\n",
+      "    ENCSR701YIC/pearson: 0.5344\n",
+      "    ENCSR935RNW_P/pearson: 0.4980\n",
+      "    ENCSR100LIJ_P/pearson: 0.4772\n",
+      "    ENCSR527JGN_P/pearson: 0.7013\n",
+      "    ENCSR114HGS_P/pearson: 0.2749\n",
+      "    ENCSR484LTQ_M/pearson: 0.3857\n",
+      "    ENCSR935RNW_M/pearson: 0.4524\n",
+      "    ENCSR410DWV/pearson: 0.7520\n",
+      "    ENCSR046BCI_M/pearson: 0.3989\n",
+      "    ENCSR814RGG/pearson: 0.7394\n",
+      "    ENCSR799DGV_P/pearson: 0.4928\n",
+      "    ENCSR527JGN_M/pearson: 0.5380\n",
+      "    ENCSR154HRN_M/pearson: 0.4079\n",
+      "    ENCSR862QCH_M/pearson: 0.4351\n",
+      "    ENCSR100LIJ_M/pearson: 0.4278\n",
+      "    ENCSR321PWZ_P/pearson: 0.5850\n",
+      "    ENCSR484LTQ_P/pearson: 0.3501\n",
+      "    ENCSR619DQO_P/pearson: 0.6135\n",
+      "    ENCSR325NFE/pearson: 0.7724\n",
+      "    ENCSR249ROI_P/pearson: 0.5126\n",
+      "    ENCSR249ROI_M/pearson: 0.4750\n",
+      "    ENCSR754DRC/pearson: 0.5051\n",
+      "    ENCSR321PWZ_M/pearson: 0.6229\n",
+      "    ENCSR862QCH_P/pearson: 0.3912\n",
+      "    ENCSR046BCI_P/pearson: 0.3817\n",
+      "    ENCSR799DGV_M/pearson: 0.4537\n",
+      "    ENCSR962OTG/pearson: 0.8684\n",
+      "    ENCSR682BFG/pearson: 0.6378\n",
+      "    ENCSR628PLS/pearson: 0.6311\n",
+      "    ENCSR619DQO_M/pearson: 0.5794\n",
+      "    ENCSR487QSB/pearson: 0.6820\n",
+      "    ENCSR114HGS_M/pearson: 0.2672\n",
+      "    ENCSR863PSM/pearson: 0.6610\n",
+      "    mean/pearson: 0.5267\n",
+      "    loss: 4.7170\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 10840/15000 | Loss: 3.8045 | Mean Pearson: 0.5885\n",
+      "Step 10880/15000 | Loss: 4.5544 | Mean Pearson: 0.6280\n",
+      "Step 10920/15000 | Loss: 4.9438 | Mean Pearson: 0.6499\n",
+      "Step 10960/15000 | Loss: 5.0784 | Mean Pearson: 0.6772\n",
+      "Step 11000/15000 | Loss: 3.9221 | Mean Pearson: 0.6467\n",
+      "Step 11040/15000 | Loss: 4.7498 | Mean Pearson: 0.6416\n",
+      "Step 11080/15000 | Loss: 4.4623 | Mean Pearson: 0.6326\n",
+      "Step 11120/15000 | Loss: 4.6796 | Mean Pearson: 0.6392\n",
+      "Step 11160/15000 | Loss: 4.9762 | Mean Pearson: 0.6308\n",
+      "Step 11200/15000 | Loss: 4.5617 | Mean Pearson: 0.6547\n",
+      "\n",
+      "Running validation at step 11200...\n",
+      "Step 11200/15000 | Loss: 4.7266 | Mean Pearson: 0.5186\n",
+      "    ENCSR154HRN_P/pearson: 0.4051\n",
+      "    ENCSR701YIC/pearson: 0.5351\n",
+      "    ENCSR935RNW_P/pearson: 0.4391\n",
+      "    ENCSR100LIJ_P/pearson: 0.4358\n",
+      "    ENCSR527JGN_P/pearson: 0.5541\n",
+      "    ENCSR114HGS_P/pearson: 0.2679\n",
+      "    ENCSR484LTQ_M/pearson: 0.4385\n",
+      "    ENCSR935RNW_M/pearson: 0.4303\n",
+      "    ENCSR410DWV/pearson: 0.7589\n",
+      "    ENCSR046BCI_M/pearson: 0.3739\n",
+      "    ENCSR814RGG/pearson: 0.7535\n",
+      "    ENCSR799DGV_P/pearson: 0.4401\n",
+      "    ENCSR527JGN_M/pearson: 0.5131\n",
+      "    ENCSR154HRN_M/pearson: 0.4806\n",
+      "    ENCSR862QCH_M/pearson: 0.4836\n",
+      "    ENCSR100LIJ_M/pearson: 0.4266\n",
+      "    ENCSR321PWZ_P/pearson: 0.5788\n",
+      "    ENCSR484LTQ_P/pearson: 0.3524\n",
+      "    ENCSR619DQO_P/pearson: 0.6460\n",
+      "    ENCSR325NFE/pearson: 0.7866\n",
+      "    ENCSR249ROI_P/pearson: 0.4813\n",
+      "    ENCSR249ROI_M/pearson: 0.5204\n",
+      "    ENCSR754DRC/pearson: 0.4948\n",
+      "    ENCSR321PWZ_M/pearson: 0.6729\n",
+      "    ENCSR862QCH_P/pearson: 0.3755\n",
+      "    ENCSR046BCI_P/pearson: 0.3361\n",
+      "    ENCSR799DGV_M/pearson: 0.4245\n",
+      "    ENCSR962OTG/pearson: 0.8185\n",
+      "    ENCSR682BFG/pearson: 0.6234\n",
+      "    ENCSR628PLS/pearson: 0.6413\n",
+      "    ENCSR619DQO_M/pearson: 0.5339\n",
+      "    ENCSR487QSB/pearson: 0.6943\n",
+      "    ENCSR114HGS_M/pearson: 0.2681\n",
+      "    ENCSR863PSM/pearson: 0.6472\n",
+      "    mean/pearson: 0.5186\n",
+      "    loss: 4.7266\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 11240/15000 | Loss: 3.8669 | Mean Pearson: 0.6097\n",
+      "Step 11280/15000 | Loss: 4.6282 | Mean Pearson: 0.6402\n",
+      "Step 11320/15000 | Loss: 4.6603 | Mean Pearson: 0.6227\n",
+      "Step 11360/15000 | Loss: 4.8491 | Mean Pearson: 0.6268\n",
+      "Step 11400/15000 | Loss: 5.2377 | Mean Pearson: 0.6388\n",
+      "Step 11440/15000 | Loss: 3.9692 | Mean Pearson: 0.6218\n",
+      "Step 11480/15000 | Loss: 4.4700 | Mean Pearson: 0.6366\n",
+      "Step 11520/15000 | Loss: 5.1038 | Mean Pearson: 0.6657\n",
+      "Step 11560/15000 | Loss: 4.6329 | Mean Pearson: 0.6632\n",
+      "Step 11600/15000 | Loss: 3.7508 | Mean Pearson: 0.6069\n",
+      "\n",
+      "Running validation at step 11600...\n",
+      "Step 11600/15000 | Loss: 4.5875 | Mean Pearson: 0.5211\n",
+      "    ENCSR154HRN_P/pearson: 0.4288\n",
+      "    ENCSR701YIC/pearson: 0.6119\n",
+      "    ENCSR935RNW_P/pearson: 0.4597\n",
+      "    ENCSR100LIJ_P/pearson: 0.4542\n",
+      "    ENCSR527JGN_P/pearson: 0.6030\n",
+      "    ENCSR114HGS_P/pearson: 0.2462\n",
+      "    ENCSR484LTQ_M/pearson: 0.3806\n",
+      "    ENCSR935RNW_M/pearson: 0.4287\n",
+      "    ENCSR410DWV/pearson: 0.7558\n",
+      "    ENCSR046BCI_M/pearson: 0.3341\n",
+      "    ENCSR814RGG/pearson: 0.7412\n",
+      "    ENCSR799DGV_P/pearson: 0.4708\n",
+      "    ENCSR527JGN_M/pearson: 0.5064\n",
+      "    ENCSR154HRN_M/pearson: 0.4276\n",
+      "    ENCSR862QCH_M/pearson: 0.4518\n",
+      "    ENCSR100LIJ_M/pearson: 0.3972\n",
+      "    ENCSR321PWZ_P/pearson: 0.6133\n",
+      "    ENCSR484LTQ_P/pearson: 0.3724\n",
+      "    ENCSR619DQO_P/pearson: 0.6602\n",
+      "    ENCSR325NFE/pearson: 0.7632\n",
+      "    ENCSR249ROI_P/pearson: 0.5274\n",
+      "    ENCSR249ROI_M/pearson: 0.5092\n",
+      "    ENCSR754DRC/pearson: 0.4856\n",
+      "    ENCSR321PWZ_M/pearson: 0.5865\n",
+      "    ENCSR862QCH_P/pearson: 0.4081\n",
+      "    ENCSR046BCI_P/pearson: 0.3779\n",
+      "    ENCSR799DGV_M/pearson: 0.3981\n",
+      "    ENCSR962OTG/pearson: 0.8584\n",
+      "    ENCSR682BFG/pearson: 0.6203\n",
+      "    ENCSR628PLS/pearson: 0.6338\n",
+      "    ENCSR619DQO_M/pearson: 0.5745\n",
+      "    ENCSR487QSB/pearson: 0.6913\n",
+      "    ENCSR114HGS_M/pearson: 0.2756\n",
+      "    ENCSR863PSM/pearson: 0.6619\n",
+      "    mean/pearson: 0.5211\n",
+      "    loss: 4.5875\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 11640/15000 | Loss: 4.4032 | Mean Pearson: 0.6109\n",
+      "Step 11680/15000 | Loss: 4.8202 | Mean Pearson: 0.6361\n",
+      "Step 11720/15000 | Loss: 4.3182 | Mean Pearson: 0.6347\n",
+      "Step 11760/15000 | Loss: 5.1427 | Mean Pearson: 0.6590\n",
+      "Step 11800/15000 | Loss: 4.9927 | Mean Pearson: 0.6392\n",
+      "Step 11840/15000 | Loss: 3.9896 | Mean Pearson: 0.6297\n",
+      "Step 11880/15000 | Loss: 3.8648 | Mean Pearson: 0.6277\n",
+      "Step 11920/15000 | Loss: 5.0026 | Mean Pearson: 0.6250\n",
+      "Step 11960/15000 | Loss: 4.8273 | Mean Pearson: 0.6450\n",
+      "Step 12000/15000 | Loss: 5.3339 | Mean Pearson: 0.6889\n",
+      "\n",
+      "Running validation at step 12000...\n",
+      "Step 12000/15000 | Loss: 4.8074 | Mean Pearson: 0.5546\n",
+      "    ENCSR154HRN_P/pearson: 0.4481\n",
+      "    ENCSR701YIC/pearson: 0.6039\n",
+      "    ENCSR935RNW_P/pearson: 0.4611\n",
+      "    ENCSR100LIJ_P/pearson: 0.4838\n",
+      "    ENCSR527JGN_P/pearson: 0.7295\n",
+      "    ENCSR114HGS_P/pearson: 0.2693\n",
+      "    ENCSR484LTQ_M/pearson: 0.4276\n",
+      "    ENCSR935RNW_M/pearson: 0.5056\n",
+      "    ENCSR410DWV/pearson: 0.7654\n",
+      "    ENCSR046BCI_M/pearson: 0.4645\n",
+      "    ENCSR814RGG/pearson: 0.7639\n",
+      "    ENCSR799DGV_P/pearson: 0.4873\n",
+      "    ENCSR527JGN_M/pearson: 0.5920\n",
+      "    ENCSR154HRN_M/pearson: 0.4530\n",
+      "    ENCSR862QCH_M/pearson: 0.4695\n",
+      "    ENCSR100LIJ_M/pearson: 0.5159\n",
+      "    ENCSR321PWZ_P/pearson: 0.6308\n",
+      "    ENCSR484LTQ_P/pearson: 0.3892\n",
+      "    ENCSR619DQO_P/pearson: 0.6949\n",
+      "    ENCSR325NFE/pearson: 0.7812\n",
+      "    ENCSR249ROI_P/pearson: 0.5434\n",
+      "    ENCSR249ROI_M/pearson: 0.4633\n",
+      "    ENCSR754DRC/pearson: 0.5144\n",
+      "    ENCSR321PWZ_M/pearson: 0.6753\n",
+      "    ENCSR862QCH_P/pearson: 0.4266\n",
+      "    ENCSR046BCI_P/pearson: 0.4055\n",
+      "    ENCSR799DGV_M/pearson: 0.5116\n",
+      "    ENCSR962OTG/pearson: 0.8702\n",
+      "    ENCSR682BFG/pearson: 0.6142\n",
+      "    ENCSR628PLS/pearson: 0.6231\n",
+      "    ENCSR619DQO_M/pearson: 0.6611\n",
+      "    ENCSR487QSB/pearson: 0.6822\n",
+      "    ENCSR114HGS_M/pearson: 0.2678\n",
+      "    ENCSR863PSM/pearson: 0.6621\n",
+      "    mean/pearson: 0.5546\n",
+      "    loss: 4.8074\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 12040/15000 | Loss: 5.2460 | Mean Pearson: 0.6721\n",
+      "Step 12080/15000 | Loss: 4.9065 | Mean Pearson: 0.6564\n",
+      "Step 12120/15000 | Loss: 4.1748 | Mean Pearson: 0.6146\n",
+      "Step 12160/15000 | Loss: 4.4647 | Mean Pearson: 0.6361\n",
+      "Step 12200/15000 | Loss: 4.6404 | Mean Pearson: 0.6334\n",
+      "Step 12240/15000 | Loss: 3.5224 | Mean Pearson: 0.6217\n",
+      "Step 12280/15000 | Loss: 4.6211 | Mean Pearson: 0.6234\n",
+      "Step 12320/15000 | Loss: 4.2050 | Mean Pearson: 0.6304\n",
+      "Step 12360/15000 | Loss: 4.2159 | Mean Pearson: 0.6287\n",
+      "Step 12400/15000 | Loss: 4.1988 | Mean Pearson: 0.6430\n",
+      "\n",
+      "Running validation at step 12400...\n",
+      "Step 12400/15000 | Loss: 4.7452 | Mean Pearson: 0.5192\n",
+      "    ENCSR154HRN_P/pearson: 0.4100\n",
+      "    ENCSR701YIC/pearson: 0.4997\n",
+      "    ENCSR935RNW_P/pearson: 0.4645\n",
+      "    ENCSR100LIJ_P/pearson: 0.4589\n",
+      "    ENCSR527JGN_P/pearson: 0.4681\n",
+      "    ENCSR114HGS_P/pearson: 0.2572\n",
+      "    ENCSR484LTQ_M/pearson: 0.3970\n",
+      "    ENCSR935RNW_M/pearson: 0.4557\n",
+      "    ENCSR410DWV/pearson: 0.7515\n",
+      "    ENCSR046BCI_M/pearson: 0.4190\n",
+      "    ENCSR814RGG/pearson: 0.7437\n",
+      "    ENCSR799DGV_P/pearson: 0.4772\n",
+      "    ENCSR527JGN_M/pearson: 0.5553\n",
+      "    ENCSR154HRN_M/pearson: 0.4274\n",
+      "    ENCSR862QCH_M/pearson: 0.4297\n",
+      "    ENCSR100LIJ_M/pearson: 0.4649\n",
+      "    ENCSR321PWZ_P/pearson: 0.5819\n",
+      "    ENCSR484LTQ_P/pearson: 0.3660\n",
+      "    ENCSR619DQO_P/pearson: 0.5077\n",
+      "    ENCSR325NFE/pearson: 0.7795\n",
+      "    ENCSR249ROI_P/pearson: 0.5405\n",
+      "    ENCSR249ROI_M/pearson: 0.5333\n",
+      "    ENCSR754DRC/pearson: 0.5055\n",
+      "    ENCSR321PWZ_M/pearson: 0.6255\n",
+      "    ENCSR862QCH_P/pearson: 0.4036\n",
+      "    ENCSR046BCI_P/pearson: 0.4049\n",
+      "    ENCSR799DGV_M/pearson: 0.4643\n",
+      "    ENCSR962OTG/pearson: 0.8519\n",
+      "    ENCSR682BFG/pearson: 0.6124\n",
+      "    ENCSR628PLS/pearson: 0.6264\n",
+      "    ENCSR619DQO_M/pearson: 0.5313\n",
+      "    ENCSR487QSB/pearson: 0.6861\n",
+      "    ENCSR114HGS_M/pearson: 0.2677\n",
+      "    ENCSR863PSM/pearson: 0.6839\n",
+      "    mean/pearson: 0.5192\n",
+      "    loss: 4.7452\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 12440/15000 | Loss: 3.8185 | Mean Pearson: 0.6327\n",
+      "Step 12480/15000 | Loss: 4.0088 | Mean Pearson: 0.6786\n",
+      "Step 12520/15000 | Loss: 4.3552 | Mean Pearson: 0.6442\n",
+      "Step 12560/15000 | Loss: 4.7379 | Mean Pearson: 0.6483\n",
+      "Step 12600/15000 | Loss: 4.5551 | Mean Pearson: 0.6451\n",
+      "Step 12640/15000 | Loss: 4.3603 | Mean Pearson: 0.6438\n",
+      "Step 12680/15000 | Loss: 4.0020 | Mean Pearson: 0.6186\n",
+      "Step 12720/15000 | Loss: 4.7898 | Mean Pearson: 0.6497\n",
+      "Step 12760/15000 | Loss: 4.4810 | Mean Pearson: 0.6218\n",
+      "Step 12800/15000 | Loss: 4.6235 | Mean Pearson: 0.6781\n",
+      "\n",
+      "Running validation at step 12800...\n",
+      "Step 12800/15000 | Loss: 4.6845 | Mean Pearson: 0.5332\n",
+      "    ENCSR154HRN_P/pearson: 0.4127\n",
+      "    ENCSR701YIC/pearson: 0.4948\n",
+      "    ENCSR935RNW_P/pearson: 0.4712\n",
+      "    ENCSR100LIJ_P/pearson: 0.4745\n",
+      "    ENCSR527JGN_P/pearson: 0.6043\n",
+      "    ENCSR114HGS_P/pearson: 0.2476\n",
+      "    ENCSR484LTQ_M/pearson: 0.4809\n",
+      "    ENCSR935RNW_M/pearson: 0.4723\n",
+      "    ENCSR410DWV/pearson: 0.7677\n",
+      "    ENCSR046BCI_M/pearson: 0.4323\n",
+      "    ENCSR814RGG/pearson: 0.7494\n",
+      "    ENCSR799DGV_P/pearson: 0.4844\n",
+      "    ENCSR527JGN_M/pearson: 0.6943\n",
+      "    ENCSR154HRN_M/pearson: 0.4341\n",
+      "    ENCSR862QCH_M/pearson: 0.4673\n",
+      "    ENCSR100LIJ_M/pearson: 0.4675\n",
+      "    ENCSR321PWZ_P/pearson: 0.4265\n",
+      "    ENCSR484LTQ_P/pearson: 0.3283\n",
+      "    ENCSR619DQO_P/pearson: 0.5373\n",
+      "    ENCSR325NFE/pearson: 0.7717\n",
+      "    ENCSR249ROI_P/pearson: 0.5103\n",
+      "    ENCSR249ROI_M/pearson: 0.5116\n",
+      "    ENCSR754DRC/pearson: 0.4807\n",
+      "    ENCSR321PWZ_M/pearson: 0.7467\n",
+      "    ENCSR862QCH_P/pearson: 0.3699\n",
+      "    ENCSR046BCI_P/pearson: 0.4134\n",
+      "    ENCSR799DGV_M/pearson: 0.4709\n",
+      "    ENCSR962OTG/pearson: 0.8545\n",
+      "    ENCSR682BFG/pearson: 0.6575\n",
+      "    ENCSR628PLS/pearson: 0.6493\n",
+      "    ENCSR619DQO_M/pearson: 0.6374\n",
+      "    ENCSR487QSB/pearson: 0.6952\n",
+      "    ENCSR114HGS_M/pearson: 0.2595\n",
+      "    ENCSR863PSM/pearson: 0.6515\n",
+      "    mean/pearson: 0.5332\n",
+      "    loss: 4.6845\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 12840/15000 | Loss: 4.2992 | Mean Pearson: 0.6402\n",
+      "Step 12880/15000 | Loss: 5.5076 | Mean Pearson: 0.6632\n",
+      "Step 12920/15000 | Loss: 5.5635 | Mean Pearson: 0.6591\n",
+      "Step 12960/15000 | Loss: 3.9789 | Mean Pearson: 0.6265\n",
+      "Step 13000/15000 | Loss: 4.8339 | Mean Pearson: 0.6446\n",
+      "Step 13040/15000 | Loss: 5.4930 | Mean Pearson: 0.6675\n",
+      "Step 13080/15000 | Loss: 4.9746 | Mean Pearson: 0.6699\n",
+      "Step 13120/15000 | Loss: 4.3281 | Mean Pearson: 0.6529\n",
+      "Step 13160/15000 | Loss: 5.2502 | Mean Pearson: 0.6697\n",
+      "Step 13200/15000 | Loss: 5.5072 | Mean Pearson: 0.6461\n",
+      "\n",
+      "Running validation at step 13200...\n",
+      "Step 13200/15000 | Loss: 4.6937 | Mean Pearson: 0.5366\n",
+      "    ENCSR154HRN_P/pearson: 0.4101\n",
+      "    ENCSR701YIC/pearson: 0.5539\n",
+      "    ENCSR935RNW_P/pearson: 0.4752\n",
+      "    ENCSR100LIJ_P/pearson: 0.4726\n",
+      "    ENCSR527JGN_P/pearson: 0.6327\n",
+      "    ENCSR114HGS_P/pearson: 0.2788\n",
+      "    ENCSR484LTQ_M/pearson: 0.3722\n",
+      "    ENCSR935RNW_M/pearson: 0.4936\n",
+      "    ENCSR410DWV/pearson: 0.7582\n",
+      "    ENCSR046BCI_M/pearson: 0.4396\n",
+      "    ENCSR814RGG/pearson: 0.7543\n",
+      "    ENCSR799DGV_P/pearson: 0.4735\n",
+      "    ENCSR527JGN_M/pearson: 0.6780\n",
+      "    ENCSR154HRN_M/pearson: 0.4404\n",
+      "    ENCSR862QCH_M/pearson: 0.4342\n",
+      "    ENCSR100LIJ_M/pearson: 0.4812\n",
+      "    ENCSR321PWZ_P/pearson: 0.6397\n",
+      "    ENCSR484LTQ_P/pearson: 0.3487\n",
+      "    ENCSR619DQO_P/pearson: 0.6446\n",
+      "    ENCSR325NFE/pearson: 0.7824\n",
+      "    ENCSR249ROI_P/pearson: 0.5022\n",
+      "    ENCSR249ROI_M/pearson: 0.4987\n",
+      "    ENCSR754DRC/pearson: 0.5224\n",
+      "    ENCSR321PWZ_M/pearson: 0.5785\n",
+      "    ENCSR862QCH_P/pearson: 0.4064\n",
+      "    ENCSR046BCI_P/pearson: 0.3767\n",
+      "    ENCSR799DGV_M/pearson: 0.4887\n",
+      "    ENCSR962OTG/pearson: 0.8724\n",
+      "    ENCSR682BFG/pearson: 0.6312\n",
+      "    ENCSR628PLS/pearson: 0.6321\n",
+      "    ENCSR619DQO_M/pearson: 0.5810\n",
+      "    ENCSR487QSB/pearson: 0.6817\n",
+      "    ENCSR114HGS_M/pearson: 0.2566\n",
+      "    ENCSR863PSM/pearson: 0.6525\n",
+      "    mean/pearson: 0.5366\n",
+      "    loss: 4.6937\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 13240/15000 | Loss: 5.3471 | Mean Pearson: 0.6811\n",
+      "Step 13280/15000 | Loss: 4.3604 | Mean Pearson: 0.6466\n",
+      "Step 13320/15000 | Loss: 4.3807 | Mean Pearson: 0.6383\n",
+      "Step 13360/15000 | Loss: 4.9433 | Mean Pearson: 0.6696\n",
+      "Step 13400/15000 | Loss: 4.0765 | Mean Pearson: 0.6113\n",
+      "Step 13440/15000 | Loss: 4.4406 | Mean Pearson: 0.6798\n",
+      "Step 13480/15000 | Loss: 4.7390 | Mean Pearson: 0.6664\n",
+      "Step 13520/15000 | Loss: 3.9976 | Mean Pearson: 0.6575\n",
+      "Step 13560/15000 | Loss: 5.0625 | Mean Pearson: 0.6752\n",
+      "Step 13600/15000 | Loss: 4.3868 | Mean Pearson: 0.6308\n",
+      "\n",
+      "Running validation at step 13600...\n",
+      "Step 13600/15000 | Loss: 4.4344 | Mean Pearson: 0.5499\n",
+      "    ENCSR154HRN_P/pearson: 0.4327\n",
+      "    ENCSR701YIC/pearson: 0.6137\n",
+      "    ENCSR935RNW_P/pearson: 0.4864\n",
+      "    ENCSR100LIJ_P/pearson: 0.4898\n",
+      "    ENCSR527JGN_P/pearson: 0.7368\n",
+      "    ENCSR114HGS_P/pearson: 0.2707\n",
+      "    ENCSR484LTQ_M/pearson: 0.4055\n",
+      "    ENCSR935RNW_M/pearson: 0.5195\n",
+      "    ENCSR410DWV/pearson: 0.7598\n",
+      "    ENCSR046BCI_M/pearson: 0.4745\n",
+      "    ENCSR814RGG/pearson: 0.7437\n",
+      "    ENCSR799DGV_P/pearson: 0.5015\n",
+      "    ENCSR527JGN_M/pearson: 0.4945\n",
+      "    ENCSR154HRN_M/pearson: 0.3992\n",
+      "    ENCSR862QCH_M/pearson: 0.4725\n",
+      "    ENCSR100LIJ_M/pearson: 0.5181\n",
+      "    ENCSR321PWZ_P/pearson: 0.6862\n",
+      "    ENCSR484LTQ_P/pearson: 0.4025\n",
+      "    ENCSR619DQO_P/pearson: 0.6322\n",
+      "    ENCSR325NFE/pearson: 0.7808\n",
+      "    ENCSR249ROI_P/pearson: 0.5061\n",
+      "    ENCSR249ROI_M/pearson: 0.5660\n",
+      "    ENCSR754DRC/pearson: 0.5032\n",
+      "    ENCSR321PWZ_M/pearson: 0.6452\n",
+      "    ENCSR862QCH_P/pearson: 0.4465\n",
+      "    ENCSR046BCI_P/pearson: 0.4008\n",
+      "    ENCSR799DGV_M/pearson: 0.5093\n",
+      "    ENCSR962OTG/pearson: 0.8417\n",
+      "    ENCSR682BFG/pearson: 0.6323\n",
+      "    ENCSR628PLS/pearson: 0.6398\n",
+      "    ENCSR619DQO_M/pearson: 0.5385\n",
+      "    ENCSR487QSB/pearson: 0.6942\n",
+      "    ENCSR114HGS_M/pearson: 0.2948\n",
+      "    ENCSR863PSM/pearson: 0.6569\n",
+      "    mean/pearson: 0.5499\n",
+      "    loss: 4.4344\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 13640/15000 | Loss: 4.3399 | Mean Pearson: 0.6570\n",
+      "Step 13680/15000 | Loss: 5.2155 | Mean Pearson: 0.6428\n",
+      "Step 13720/15000 | Loss: 5.3429 | Mean Pearson: 0.6849\n",
+      "Step 13760/15000 | Loss: 4.5167 | Mean Pearson: 0.6481\n",
+      "Step 13800/15000 | Loss: 5.6447 | Mean Pearson: 0.6756\n",
+      "Step 13840/15000 | Loss: 5.1568 | Mean Pearson: 0.6771\n",
+      "Step 13880/15000 | Loss: 3.9445 | Mean Pearson: 0.6160\n",
+      "Step 13920/15000 | Loss: 4.7225 | Mean Pearson: 0.6563\n",
+      "Step 13960/15000 | Loss: 3.8466 | Mean Pearson: 0.6261\n",
+      "Step 14000/15000 | Loss: 4.7853 | Mean Pearson: 0.6534\n",
+      "\n",
+      "Running validation at step 14000...\n",
+      "Step 14000/15000 | Loss: 4.4524 | Mean Pearson: 0.5219\n",
+      "    ENCSR154HRN_P/pearson: 0.4164\n",
+      "    ENCSR701YIC/pearson: 0.4743\n",
+      "    ENCSR935RNW_P/pearson: 0.4061\n",
+      "    ENCSR100LIJ_P/pearson: 0.4163\n",
+      "    ENCSR527JGN_P/pearson: 0.6822\n",
+      "    ENCSR114HGS_P/pearson: 0.2693\n",
+      "    ENCSR484LTQ_M/pearson: 0.3799\n",
+      "    ENCSR935RNW_M/pearson: 0.4643\n",
+      "    ENCSR410DWV/pearson: 0.7590\n",
+      "    ENCSR046BCI_M/pearson: 0.4382\n",
+      "    ENCSR814RGG/pearson: 0.7503\n",
+      "    ENCSR799DGV_P/pearson: 0.4031\n",
+      "    ENCSR527JGN_M/pearson: 0.5795\n",
+      "    ENCSR154HRN_M/pearson: 0.4289\n",
+      "    ENCSR862QCH_M/pearson: 0.4177\n",
+      "    ENCSR100LIJ_M/pearson: 0.4784\n",
+      "    ENCSR321PWZ_P/pearson: 0.4981\n",
+      "    ENCSR484LTQ_P/pearson: 0.3248\n",
+      "    ENCSR619DQO_P/pearson: 0.6096\n",
+      "    ENCSR325NFE/pearson: 0.7740\n",
+      "    ENCSR249ROI_P/pearson: 0.5363\n",
+      "    ENCSR249ROI_M/pearson: 0.4964\n",
+      "    ENCSR754DRC/pearson: 0.5210\n",
+      "    ENCSR321PWZ_M/pearson: 0.6150\n",
+      "    ENCSR862QCH_P/pearson: 0.3682\n",
+      "    ENCSR046BCI_P/pearson: 0.3173\n",
+      "    ENCSR799DGV_M/pearson: 0.4568\n",
+      "    ENCSR962OTG/pearson: 0.8673\n",
+      "    ENCSR682BFG/pearson: 0.6705\n",
+      "    ENCSR628PLS/pearson: 0.6426\n",
+      "    ENCSR619DQO_M/pearson: 0.6533\n",
+      "    ENCSR487QSB/pearson: 0.6971\n",
+      "    ENCSR114HGS_M/pearson: 0.2601\n",
+      "    ENCSR863PSM/pearson: 0.6719\n",
+      "    mean/pearson: 0.5219\n",
+      "    loss: 4.4524\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 14040/15000 | Loss: 4.9552 | Mean Pearson: 0.6841\n",
+      "Step 14080/15000 | Loss: 5.0718 | Mean Pearson: 0.6713\n",
+      "Step 14120/15000 | Loss: 4.9621 | Mean Pearson: 0.6572\n",
+      "Step 14160/15000 | Loss: 5.1255 | Mean Pearson: 0.6477\n",
+      "Step 14200/15000 | Loss: 4.7304 | Mean Pearson: 0.6228\n",
+      "Step 14240/15000 | Loss: 4.4672 | Mean Pearson: 0.6865\n",
+      "Step 14280/15000 | Loss: 4.1539 | Mean Pearson: 0.6530\n",
+      "Step 14320/15000 | Loss: 4.1564 | Mean Pearson: 0.6383\n",
+      "Step 14360/15000 | Loss: 4.6041 | Mean Pearson: 0.6662\n",
+      "Step 14400/15000 | Loss: 4.7404 | Mean Pearson: 0.6282\n",
+      "\n",
+      "Running validation at step 14400...\n",
+      "Step 14400/15000 | Loss: 4.8076 | Mean Pearson: 0.5492\n",
+      "    ENCSR154HRN_P/pearson: 0.4514\n",
+      "    ENCSR701YIC/pearson: 0.6005\n",
+      "    ENCSR935RNW_P/pearson: 0.4926\n",
+      "    ENCSR100LIJ_P/pearson: 0.5145\n",
+      "    ENCSR527JGN_P/pearson: 0.6275\n",
+      "    ENCSR114HGS_P/pearson: 0.2842\n",
+      "    ENCSR484LTQ_M/pearson: 0.3703\n",
+      "    ENCSR935RNW_M/pearson: 0.5076\n",
+      "    ENCSR410DWV/pearson: 0.7596\n",
+      "    ENCSR046BCI_M/pearson: 0.4802\n",
+      "    ENCSR814RGG/pearson: 0.7434\n",
+      "    ENCSR799DGV_P/pearson: 0.5150\n",
+      "    ENCSR527JGN_M/pearson: 0.6605\n",
+      "    ENCSR154HRN_M/pearson: 0.3869\n",
+      "    ENCSR862QCH_M/pearson: 0.4135\n",
+      "    ENCSR100LIJ_M/pearson: 0.5163\n",
+      "    ENCSR321PWZ_P/pearson: 0.6514\n",
+      "    ENCSR484LTQ_P/pearson: 0.3750\n",
+      "    ENCSR619DQO_P/pearson: 0.6377\n",
+      "    ENCSR325NFE/pearson: 0.7808\n",
+      "    ENCSR249ROI_P/pearson: 0.5284\n",
+      "    ENCSR249ROI_M/pearson: 0.4789\n",
+      "    ENCSR754DRC/pearson: 0.5036\n",
+      "    ENCSR321PWZ_M/pearson: 0.6233\n",
+      "    ENCSR862QCH_P/pearson: 0.4158\n",
+      "    ENCSR046BCI_P/pearson: 0.4479\n",
+      "    ENCSR799DGV_M/pearson: 0.5274\n",
+      "    ENCSR962OTG/pearson: 0.8745\n",
+      "    ENCSR682BFG/pearson: 0.6112\n",
+      "    ENCSR628PLS/pearson: 0.6266\n",
+      "    ENCSR619DQO_M/pearson: 0.6186\n",
+      "    ENCSR487QSB/pearson: 0.6880\n",
+      "    ENCSR114HGS_M/pearson: 0.2711\n",
+      "    ENCSR863PSM/pearson: 0.6898\n",
+      "    mean/pearson: 0.5492\n",
+      "    loss: 4.8076\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 14440/15000 | Loss: 4.8250 | Mean Pearson: 0.6561\n",
+      "Step 14480/15000 | Loss: 4.8791 | Mean Pearson: 0.6753\n",
+      "Step 14520/15000 | Loss: 5.5909 | Mean Pearson: 0.6726\n",
+      "Step 14560/15000 | Loss: 4.9725 | Mean Pearson: 0.6533\n",
+      "Step 14600/15000 | Loss: 5.1408 | Mean Pearson: 0.6521\n",
+      "Step 14640/15000 | Loss: 4.3326 | Mean Pearson: 0.6527\n",
+      "Step 14680/15000 | Loss: 4.3786 | Mean Pearson: 0.6623\n",
+      "Step 14720/15000 | Loss: 5.2528 | Mean Pearson: 0.6719\n",
+      "Step 14760/15000 | Loss: 3.9199 | Mean Pearson: 0.6293\n",
+      "Step 14800/15000 | Loss: 5.2127 | Mean Pearson: 0.6577\n",
+      "\n",
+      "Running validation at step 14800...\n",
+      "Step 14800/15000 | Loss: 4.9888 | Mean Pearson: 0.5322\n",
+      "    ENCSR154HRN_P/pearson: 0.4084\n",
+      "    ENCSR701YIC/pearson: 0.5975\n",
+      "    ENCSR935RNW_P/pearson: 0.4611\n",
+      "    ENCSR100LIJ_P/pearson: 0.4555\n",
+      "    ENCSR527JGN_P/pearson: 0.6579\n",
+      "    ENCSR114HGS_P/pearson: 0.2534\n",
+      "    ENCSR484LTQ_M/pearson: 0.3348\n",
+      "    ENCSR935RNW_M/pearson: 0.4776\n",
+      "    ENCSR410DWV/pearson: 0.7563\n",
+      "    ENCSR046BCI_M/pearson: 0.4519\n",
+      "    ENCSR814RGG/pearson: 0.7607\n",
+      "    ENCSR799DGV_P/pearson: 0.4687\n",
+      "    ENCSR527JGN_M/pearson: 0.5748\n",
+      "    ENCSR154HRN_M/pearson: 0.4010\n",
+      "    ENCSR862QCH_M/pearson: 0.3980\n",
+      "    ENCSR100LIJ_M/pearson: 0.4792\n",
+      "    ENCSR321PWZ_P/pearson: 0.6193\n",
+      "    ENCSR484LTQ_P/pearson: 0.3823\n",
+      "    ENCSR619DQO_P/pearson: 0.6699\n",
+      "    ENCSR325NFE/pearson: 0.7831\n",
+      "    ENCSR249ROI_P/pearson: 0.4769\n",
+      "    ENCSR249ROI_M/pearson: 0.4687\n",
+      "    ENCSR754DRC/pearson: 0.5287\n",
+      "    ENCSR321PWZ_M/pearson: 0.5780\n",
+      "    ENCSR862QCH_P/pearson: 0.4431\n",
+      "    ENCSR046BCI_P/pearson: 0.4050\n",
+      "    ENCSR799DGV_M/pearson: 0.4777\n",
+      "    ENCSR962OTG/pearson: 0.8373\n",
+      "    ENCSR682BFG/pearson: 0.6086\n",
+      "    ENCSR628PLS/pearson: 0.6475\n",
+      "    ENCSR619DQO_M/pearson: 0.6023\n",
+      "    ENCSR487QSB/pearson: 0.6969\n",
+      "    ENCSR114HGS_M/pearson: 0.2727\n",
+      "    ENCSR863PSM/pearson: 0.6603\n",
+      "    mean/pearson: 0.5322\n",
+      "    loss: 4.9888\n",
+      "\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Training metrics:\n",
+      "Step 14840/15000 | Loss: 3.9079 | Mean Pearson: 0.6560\n",
+      "Step 14880/15000 | Loss: 4.0723 | Mean Pearson: 0.6546\n",
+      "Step 14920/15000 | Loss: 5.1775 | Mean Pearson: 0.6582\n",
+      "Step 14960/15000 | Loss: 5.6660 | Mean Pearson: 0.6209\n",
+      "Step 15000/15000 | Loss: 5.1007 | Mean Pearson: 0.6686\n",
+      "\n",
+      "Training completed after 15000 steps.\n"
+     ]
+    }
+   ],
    "source": [
     "# Training loop\n",
     "print(f\"Starting training for {config['num_steps_training']} steps\\n\")\n",
@@ -1031,9 +3430,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# Plot training results\n",
     "fig, axes = plt.subplots(1, 2, figsize=(12, 5))\n",
@@ -1071,9 +3481,78 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 18,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running test evaluation with 2500 steps (10000 samples)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Test evaluation: 100%|██████████| 2500/2500 [11:09<00:00,  3.74it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "==================================================\n",
+      "Test Set Results\n",
+      "==================================================\n",
+      "\n",
+      "Metrics:\n",
+      "  Mean Pearson: 0.5413\n",
+      "    ENCSR154HRN_P/pearson: 0.4806\n",
+      "    ENCSR701YIC/pearson: 0.5618\n",
+      "    ENCSR935RNW_P/pearson: 0.4262\n",
+      "    ENCSR100LIJ_P/pearson: 0.4342\n",
+      "    ENCSR527JGN_P/pearson: 0.6413\n",
+      "    ENCSR114HGS_P/pearson: 0.2809\n",
+      "    ENCSR484LTQ_M/pearson: 0.5097\n",
+      "    ENCSR935RNW_M/pearson: 0.4451\n",
+      "    ENCSR410DWV/pearson: 0.7197\n",
+      "    ENCSR046BCI_M/pearson: 0.4100\n",
+      "    ENCSR814RGG/pearson: 0.7306\n",
+      "    ENCSR799DGV_P/pearson: 0.4292\n",
+      "    ENCSR527JGN_M/pearson: 0.5838\n",
+      "    ENCSR154HRN_M/pearson: 0.4915\n",
+      "    ENCSR862QCH_M/pearson: 0.5296\n",
+      "    ENCSR100LIJ_M/pearson: 0.4482\n",
+      "    ENCSR321PWZ_P/pearson: 0.6399\n",
+      "    ENCSR484LTQ_P/pearson: 0.4387\n",
+      "    ENCSR619DQO_P/pearson: 0.6396\n",
+      "    ENCSR325NFE/pearson: 0.7549\n",
+      "    ENCSR249ROI_P/pearson: 0.5665\n",
+      "    ENCSR249ROI_M/pearson: 0.5497\n",
+      "    ENCSR754DRC/pearson: 0.4786\n",
+      "    ENCSR321PWZ_M/pearson: 0.6713\n",
+      "    ENCSR862QCH_P/pearson: 0.4601\n",
+      "    ENCSR046BCI_P/pearson: 0.3657\n",
+      "    ENCSR799DGV_M/pearson: 0.4400\n",
+      "    ENCSR962OTG/pearson: 0.8034\n",
+      "    ENCSR682BFG/pearson: 0.6500\n",
+      "    ENCSR628PLS/pearson: 0.6073\n",
+      "    ENCSR619DQO_M/pearson: 0.5792\n",
+      "    ENCSR487QSB/pearson: 0.6684\n",
+      "    ENCSR114HGS_M/pearson: 0.2939\n",
+      "    ENCSR863PSM/pearson: 0.6735\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "# Calculate number of test steps (based on deepspeed pipeline)\n",
     "num_test_samples = len(test_dataset)\n",
@@ -1108,7 +3587,44 @@
    "source": [
     " ## Test set results\n",
     "\n",
-    "#TODO: Add test set results after run!"
+    "Mean Pearson: 0.5413\n",
+    "\n",
+    "- ENCSR154HRN_P/pearson: 0.4806\n",
+    "- ENCSR701YIC/pearson: 0.5618\n",
+    "- ENCSR935RNW_P/pearson: 0.4262\n",
+    "- ENCSR100LIJ_P/pearson: 0.4342\n",
+    "- ENCSR527JGN_P/pearson: 0.6413\n",
+    "- ENCSR114HGS_P/pearson: 0.2809\n",
+    "- ENCSR484LTQ_M/pearson: 0.5097\n",
+    "- ENCSR935RNW_M/pearson: 0.4451\n",
+    "- ENCSR410DWV/pearson: 0.7197\n",
+    "- ENCSR046BCI_M/pearson: 0.4100\n",
+    "- ENCSR814RGG/pearson: 0.7306\n",
+    "- ENCSR799DGV_P/pearson: 0.4292\n",
+    "- ENCSR527JGN_M/pearson: 0.5838\n",
+    "- ENCSR154HRN_M/pearson: 0.4915\n",
+    "- ENCSR862QCH_M/pearson: 0.5296\n",
+    "- ENCSR100LIJ_M/pearson: 0.4482\n",
+    "- ENCSR321PWZ_P/pearson: 0.6399\n",
+    "- ENCSR484LTQ_P/pearson: 0.4387\n",
+    "- ENCSR619DQO_P/pearson: 0.6396\n",
+    "- ENCSR325NFE/pearson: 0.7549\n",
+    "- ENCSR249ROI_P/pearson: 0.5665\n",
+    "- ENCSR249ROI_M/pearson: 0.5497\n",
+    "- ENCSR754DRC/pearson: 0.4786\n",
+    "- ENCSR321PWZ_M/pearson: 0.6713\n",
+    "- ENCSR862QCH_P/pearson: 0.4601\n",
+    "- ENCSR046BCI_P/pearson: 0.3657\n",
+    "- ENCSR799DGV_M/pearson: 0.4400\n",
+    "- ENCSR962OTG/pearson: 0.8034\n",
+    "- ENCSR682BFG/pearson: 0.6500\n",
+    "- ENCSR628PLS/pearson: 0.6073\n",
+    "- ENCSR619DQO_M/pearson: 0.5792\n",
+    "- ENCSR487QSB/pearson: 0.6684\n",
+    "- ENCSR114HGS_M/pearson: 0.2939\n",
+    "- ENCSR863PSM/pearson: 0.6735\n",
+    "\n",
+    "NOTE: the performance reported in the paper is reached after ~15B tokens (~8x more than this notebook)"
    ]
   },
   {