diff --git "a/notebooks_tutorials/03_fine_tuning_posttrained_model_biwig.ipynb" "b/notebooks_tutorials/03_fine_tuning_posttrained_model_biwig.ipynb" --- "a/notebooks_tutorials/03_fine_tuning_posttrained_model_biwig.ipynb" +++ "b/notebooks_tutorials/03_fine_tuning_posttrained_model_biwig.ipynb" @@ -4,16 +4,26 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# 🧬 Fine-Tuning a Post-trained Model on BigWig Tracks Prediction\n", + "# 🧬 Fine-Tuning a Post-trained Model on BigWig Tracks Prediction (reproduce paper results)\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 is designed to enable the reproduction of the results in the paper. In contrast to the simplified fine tuning setup in [02_fine_tuning_pretrained_model_biwig.ipynb](https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/02_fine_tuning_pretrained_model_biwig.ipynb), this more complex setup is designed to mirror the internal JAX pipeline used to run the evaluations.\n", + "As in the benchmark, the notebook finetunes a post-trained Nucleotide Transformer v3 (`NTv3_650M_post`) model to predict BigWig signal tracks directly from DNA sequences. The streamlined approach leverages a post-trained NTv3 backbone as a feature extractor. A new prediction head is added to the model, which outputs single-nucleotide resolution signal values for each of the 34 tracks in the NTv3 benchmark for the `human` species.\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_pretrained_model_biwig.ipynb](https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/02_fine_tuning_pretrained_model_biwig.ipynb) notebook.\n", - "The notebook uses the same \"simplified setup\" as described there. \n", + "**🦚 Features:**\n", + "In addition to the simplifed version, the following features are added:\n", + "- Learning rate scheduling\n", + "- Use fixed dataset regions for training\n", + "- Implement gradient accumulation for large batch sizes\n", + "- Use the best model (selected via validation Pearson) for evaluation \n", + "- Save the latest and best models for future use\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." + "**🔦 JAX vs PyTorch:**\n", + "The values achieved by this pipeline are close (within 0.01 mean Pearson) to those reported in the paper. They differ slightly due to using here a PyTorch pipeline to make it easier for users, as opposed to the JAX pipeline used for the results in the paper. For most accurate performance, it is recommended to use 3x seeds and average the results, as shown in the paper.\n", + "\n", + "**🚆 Training:**\n", + "To run this training, you will need a large GPU (either A100 or H100). It takes around 28 hours on an H100 with the default settings. It might be possible to improve the tuning of the number of workers to improve efficiency. Our JAX pipeline is able to complete the training in around 12 hours.\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.\n" ] }, { @@ -25,9 +35,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "7def2b35ebeb45bc97960837f8a7041c", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "VBox(children=(HTML(value='
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", @@ -56,13 +81,13 @@ "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: tokenizers<=0.23.0,>=0.22.0 in ./.venv/lib/python3.11/site-packages (from transformers) (0.22.2)\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: setuptools in ./.venv/lib/python3.11/site-packages (from lightning-utilities>=0.8.0->torchmetrics) (80.9.0)\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", @@ -78,7 +103,7 @@ "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: nvidia-nvjitlink-cu12 in ./.venv/lib/python3.11/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=2.0.0->torchmetrics) (12.8.93)\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", @@ -95,13 +120,13 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ - "import random\n", + "import bisect\n", "import functools\n", - "from typing import List, Dict, Callable\n", + "from typing import List, Dict, Callable, Any, cast\n", "import os\n", "import fnmatch\n", "from pathlib import Path\n", @@ -112,6 +137,7 @@ "import torch.nn.functional as F\n", "from torch.utils.data import Dataset, DataLoader\n", "from torch.optim import AdamW\n", + "from torch.optim.lr_scheduler import LambdaLR\n", "from transformers import AutoConfig, AutoModel, AutoTokenizer\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", @@ -132,6 +158,7 @@ "\n", "### Model\n", "- **`model_name`**: HuggingFace model name/identifier for the pretrained backbone model\n", + "- **`best_model_checkpoint_path`**: Path to use when saving the best model checkpoint\n", "\n", "### Data\n", "- **`hf_repo_id`**: HuggingFace dataset repository ID containing the benchmark data\n", @@ -139,33 +166,31 @@ "- **`data_cache_dir`**: Directory where downloaded data files (FASTA, bigWig) will be stored\n", "- **`sequence_length`**: Length of input sequences in base pairs (bp)\n", "- **`keep_target_center_fraction`**: Fraction of center sequence to keep for target prediction (crops edges to focus on center)\n", + "- **`train_overlap`**: Fraction of sequence that overlaps between unique training samples\n", "\n", "### Training\n", - "- **`batch_size`**: Number of samples per batch\n", - "- **`learning_rate`**: Constant learning rate for optimizer\n", + "- **`mini_batch_size`**: Number of samples per mini batch on the device\n", + "- **`num_accumulation_gradient`**: Number of gradient accumulation steps\n", + "- **`num_steps_training`**: Total number of training steps (each step has an effective batch size of `mini_batch_size * num_accumulation_gradient`)\n", + "- **`initial_learning_rate`**: Initial learning rate for optimizer\n", + "- **`num_steps_warmup`**: Number of warmup steps (3% of `num_steps_training`)\n", + "- **`end_learning_rate`**: Peak learning rate after warmup\n", "- **`weight_decay`**: L2 regularization coefficient for optimizer\n", - "- **`num_steps_training`**: Total number of training steps\n", "- **`log_every_n_steps`**: Log training metrics every N steps\n", "\n", "### Validation\n", "- **`validate_every_n_steps`**: Run validation every N steps\n", - "- **`num_validation_samples`**: Number of samples to use for validation set\n", - "\n", - "### Test\n", - "- **`num_test_samples`**: Number of samples to use for test set evaluation\n", + "- **`num_validation_samples`**: Number of samples to use for each validation \n", "\n", "### 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)\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" + "- **`num_workers`**: Number of worker processes for DataLoader (0 = single-threaded)\n" ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -178,8 +203,9 @@ ], "source": [ "config = {\n", - " # Model\n", + " # Model\n", " \"model_name\": \"InstaDeepAI/NTv3_650M_post\",\n", + " \"best_model_checkpoint_path\": \"best_model_checkpoint.pth\",\n", " \n", " # Data\n", " \"hf_repo_id\": \"InstaDeepAI/NTv3_benchmark_dataset\",\n", @@ -187,21 +213,22 @@ " \"data_cache_dir\": \"./data\",\n", " \"sequence_length\": 32_768,\n", " \"keep_target_center_fraction\": 0.375,\n", + " \"train_overlap\": 0.999,\n", " \n", " # Training\n", - " \"batch_size\": 4,\n", - " \"num_steps_training\": 15000, #~2B tokens\n", - " \"log_every_n_steps\": 40,\n", - " \"learning_rate\": 1e-5,\n", + " \"mini_batch_size\": 4,\n", + " \"num_accumulation_gradient\": 8, # For an effective batch size of 32\n", + " \"num_steps_training\": 19932, # Calculated to provide ~20.9B tokens\n", " \"weight_decay\": 0.01,\n", + " \"initial_learning_rate\": 1e-5,\n", + " \"num_steps_warmup\": 598, # Calculated as 3% of 19932 steps\n", + " \"end_learning_rate\": 5e-5, \n", + " \"log_every_n_steps\": 50,\n", " \n", " # Validation\n", - " \"validate_every_n_steps\": 400, \n", + " \"validate_every_n_steps\": 500, \n", " \"num_validation_samples\": 1000,\n", "\n", - " # Test\n", - " \"num_test_samples\": 10000,\n", - " \n", " # General\n", " \"seed\": 0,\n", " \"device\": \"cuda\" if torch.cuda.is_available() else \"cpu\",\n", @@ -228,7 +255,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -236,7 +263,6 @@ " species: str,\n", " data_cache_dir: str | Path = \"data\",\n", " hf_repo_id: str = \"InstaDeepAI/NTv3_benchmark_dataset\",\n", - " bigwig_file_ids: list[str] | None = None,\n", ") -> tuple[str, list[str], list[str], pd.DataFrame, pd.DataFrame]:\n", " \"\"\"\n", " Downloads:\n", @@ -250,8 +276,6 @@ " species: Species name (e.g., \"human\", \"arabidopsis\")\n", " data_cache_dir: Directory where downloaded data files will be stored\n", " hf_repo_id: HuggingFace dataset repository ID\n", - " bigwig_file_ids: Optional list of BigWig file IDs to download. If None,\n", - " downloads all available BigWig files for the species.\n", " \n", " Returns:\n", " (fasta_path, bigwig_path_list, bigwig_file_ids)\n", @@ -263,33 +287,8 @@ " metadata_file = \"benchmark_metadata.tsv\"\n", " download_patterns = [metadata_file, f\"{species}/genome.fasta\", f\"{species}/splits.bed\"]\n", " \n", - " if bigwig_file_ids is not None:\n", - " # List files to validate requested BigWig files exist\n", - " api = HfApi()\n", - " files = api.list_repo_files(repo_id=hf_repo_id, repo_type=\"dataset\")\n", - " species_pattern = f\"{species}/**\"\n", - " species_files = [p for p in files if fnmatch.fnmatch(p, species_pattern)]\n", - " \n", - " # Get all available BigWig file IDs and their paths\n", - " available_bigwig_files = {\n", - " Path(p).stem: p for p in species_files \n", - " if Path(p).suffix == \".bigwig\"\n", - " }\n", - " \n", - " # Check that all requested files exist\n", - " missing_files = set(bigwig_file_ids) - set(available_bigwig_files.keys())\n", - " if missing_files:\n", - " raise ValueError(\n", - " f\"Requested BigWig files not found: {missing_files}. \"\n", - " f\"Available files: {list(available_bigwig_files.keys())}\"\n", - " )\n", - " \n", - " # Add specific patterns for requested BigWig files only\n", - " for file_id in bigwig_file_ids:\n", - " download_patterns.append(available_bigwig_files[file_id])\n", - " else:\n", - " # Download all BigWig files\n", - " download_patterns.append(f\"{species}/functional_tracks/*.bigwig\")\n", + " # Download all BigWig files\n", + " download_patterns.append(f\"{species}/functional_tracks/*.bigwig\")\n", " local_dir = Path(\n", " snapshot_download(\n", " repo_id=hf_repo_id,\n", @@ -307,14 +306,10 @@ " # BigWig files - use downloaded files directly\n", " bigwig_dir = local_dir / species / \"functional_tracks\"\n", " \n", - " if bigwig_file_ids is not None:\n", - " bigwig_paths = [str(bigwig_dir / f\"{file_id}.bigwig\") for file_id in bigwig_file_ids]\n", - " bigwig_ids = bigwig_file_ids\n", - " else:\n", - " # Find all downloaded BigWig files\n", - " bigwig_paths = [str(bigwig_file) for bigwig_file in bigwig_dir.glob(\"*.bigwig\")]\n", - " bigwig_ids = [bigwig_file.stem for bigwig_file in bigwig_dir.glob(\"*.bigwig\")] \n", - " \n", + " # Find all downloaded BigWig files\n", + " bigwig_paths = [str(bigwig_file) for bigwig_file in bigwig_dir.glob(\"*.bigwig\")]\n", + " bigwig_ids = [bigwig_file.stem for bigwig_file in bigwig_dir.glob(\"*.bigwig\")] \n", + "\n", " # Splits file\n", " splits_path_repo = f\"{species}/splits.bed\"\n", " splits_path = local_dir / splits_path_repo\n", @@ -331,33 +326,363 @@ " metadata_path = local_dir / metadata_file\n", " metadata_df = pd.read_csv(metadata_path, sep=\"\\t\")\n", "\n", - " # Filter metadata according to species\n", + " # Filter and order metadata \n", " metadata_df = metadata_df[metadata_df[\"species_name\"] == species].reset_index(drop=True)\n", - "\n", - " # Order metadata according to bigwig file ids\n", - " metadata_df = (\n", - " metadata_df.set_index(\"file_id\")\n", - " .loc[bigwig_ids]\n", - " .reset_index()\n", - " )\n", + " metadata_df = metadata_df.set_index(\"file_id\").loc[bigwig_ids].reset_index()\n", "\n", " return fasta_path, bigwig_paths, bigwig_ids, splits_df, metadata_df" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "9128a6c975214f6c88ec724605e91a6b", + "model_id": "93c67d6f058848d5b6e162815ccb4103", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Fetching 37 files: 0%| | 0/37 [00:00 list[tuple[str, int, int]]:\n", + " \"\"\"\n", + " Sample fixed regions for a total length.\n", + " \"\"\"\n", + " # For each region, sample a window until we have total_length_needed\n", + " sampled_regions = []\n", + " rng = np.random.RandomState(seed)\n", + " accumulated_length = 0\n", + "\n", + " for _, (chr_name, start, end) in enumerate(regions):\n", + " region_length = end - start\n", + " remaining_length_needed = total_length_needed - accumulated_length\n", + "\n", + " if region_length >= remaining_length_needed:\n", + " # Sample a random start position for the window\n", + " max_start = region_length - remaining_length_needed\n", + " if max_start > 0:\n", + " window_start_offset = rng.randint(0, max_start + 1)\n", + " else:\n", + " window_start_offset = 0\n", + "\n", + " window_start = start + window_start_offset\n", + " window_end = start + window_start_offset + remaining_length_needed\n", + "\n", + " sampled_regions.append((chr_name, window_start, window_end))\n", + " accumulated_length += remaining_length_needed\n", + " print(\n", + " f\"Sampled window from {chr_name}:{start}-{end} -> \"\n", + " f\"{chr_name}:{window_start}-{window_end} \"\n", + " )\n", + " break # Stop after getting enough length\n", + " else:\n", + " # Add this smaller region and continue accumulating\n", + " sampled_regions.append((chr_name, start, end))\n", + " accumulated_length += region_length\n", + " print(f\"Added region {chr_name}:{start}-{end}, {accumulated_length=}\")\n", + "\n", + " # Check if we have enough accumulated length\n", + " if accumulated_length >= total_length_needed:\n", + " print(f\"Sufficient length ({accumulated_length} >= {total_length_needed})\")\n", + " break\n", + "\n", + " print(f\"Sampled {len(sampled_regions)=} with total {accumulated_length=}\")\n", + "\n", + " return sampled_regions\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -926,10 +1338,11 @@ " chrom_regions: pd.DataFrame,\n", " split: str,\n", " sequence_length: int,\n", - " num_samples: int,\n", " tokenizer: AutoTokenizer,\n", " transform_fn: Callable[[torch.Tensor], torch.Tensor],\n", + " overlap: float = 0.0,\n", " keep_target_center_fraction: float = 1.0,\n", + " limit_num_samples: int | None = None,\n", " ):\n", " super().__init__()\n", "\n", @@ -937,36 +1350,42 @@ " self.fasta_path = fasta_path\n", " self.bigwig_path_list = bigwig_path_list\n", " self.sequence_length = sequence_length\n", - " self.num_samples = num_samples\n", " self.tokenizer = tokenizer\n", " self.transform_fn = transform_fn\n", " self.keep_target_center_fraction = keep_target_center_fraction\n", " self.chrom_regions = chrom_regions\n", + " self.stride = int((1 - overlap) * sequence_length)\n", "\n", " # Filter regions by split\n", " split_regions = self.chrom_regions[self.chrom_regions[\"split\"] == split].copy()\n", - "\n", - " # Filter valid regions (must be large enough for sequence_length)\n", - " self.valid_regions = []\n", - " for _, row in split_regions.iterrows():\n", - "\n", - " region_length = row.end - row.start\n", - " if region_length < self.sequence_length:\n", - " continue\n", - " \n", - " # Store valid region\n", - " self.valid_regions.append((row.chr_name, row.start, row.end))\n", + " region_list = [\n", + " (row.chr_name, row.start, row.end) for _, row in split_regions.iterrows()\n", + " ]\n", + " if limit_num_samples is not None:\n", + " length_required = limit_num_samples * self.sequence_length\n", + " region_list = _sample_regions_for_a_total_length(region_list, length_required)\n", + " \n", + " # Build an index structure for efficient sequence access across genomic regions\n", + " self.chromosome_info, self._cumulative_starts, self.num_samples = (\n", + " self._process_regions(region_list)\n", + " )\n", "\n", " def __len__(self):\n", " return self.num_samples\n", "\n", " def __getitem__(self, idx):\n", - " # Sample a random region from the valid regions\n", - " chrom, region_start, region_end = random.choice(self.valid_regions)\n", - " \n", - " # Sample a random window within this region\n", - " max_start = region_end - self.sequence_length\n", - " start = random.randint(region_start, max_start)\n", + " # Select the chromosome for the given index using binary search\n", + " chromosome_idx = bisect.bisect_right(self._cumulative_starts, idx) - 1\n", + "\n", + " # Explicitly cast types from dictionary of chromosome information\n", + " chrom: str = cast(str, self.chromosome_info[chromosome_idx][\"chr_name\"])\n", + " region_start: int = cast(int, self.chromosome_info[chromosome_idx][\"region_start_offset\"])\n", + "\n", + " # Calculate the index of the sample *within* the selected chromosome region\n", + " index_within_region = idx - self._cumulative_starts[chromosome_idx]\n", + "\n", + " # Calculate 0-based start and end for the specific sample in genome coordinates\n", + " start = region_start + index_within_region * self.stride\n", " end = start + self.sequence_length\n", "\n", " # Sequence - get FASTA handle lazily (cached per worker process)\n", @@ -1008,7 +1427,54 @@ " \"start\": start,\n", " \"end\": end,\n", " }\n", - " return sample" + " return sample\n", + "\n", + " def _process_regions(\n", + " self, actual_regions_list: list[tuple[str, int, int]]\n", + " ) -> tuple[list[dict[str, Any]], list[int], int]:\n", + " \"\"\"\n", + " Build an index structure for efficient sequence access across genomic regions.\n", + "\n", + " This method analyzes each genomic region to determine how many sequences of\n", + " fixed length can be extracted from it, accounting for stride and overlap\n", + " settings. It creates an index that maps global sequence indices to their\n", + " genomic locations.\n", + "\n", + " Args:\n", + " actual_regions_list: List of genomic regions as (chromosome, start, end).\n", + "\n", + " Returns:\n", + " region_info: List of dictionaries containing chromosome, start position,\n", + " and number of sequences for each valid region.\n", + " cumulative_starts: List of cumulative sequence counts for binary search.\n", + " total_sequences: Total number of sequences across all regions.\n", + " \"\"\"\n", + " region_info = []\n", + " cumulative_starts = [] # For bisect\n", + " total_sequences = 0\n", + "\n", + " for chr_name, region_s, region_e in actual_regions_list:\n", + " region_length: int = region_e - region_s\n", + "\n", + " num_sequences: int = 0\n", + " if region_length >= self.sequence_length:\n", + " num_sequences = (\n", + " region_length - self.sequence_length\n", + " ) // self.stride + 1\n", + "\n", + " if num_sequences > 0:\n", + " region_info.append(\n", + " {\n", + " \"chr_name\": chr_name,\n", + " \"region_start_offset\": region_s,\n", + " \"num_samples\": num_sequences,\n", + " \"region_length\": region_length,\n", + " }\n", + " )\n", + " cumulative_starts.append(total_sequences)\n", + " total_sequences += num_sequences\n", + "\n", + " return region_info, cumulative_starts, int(total_sequences)\n" ] }, { @@ -1020,7 +1486,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 11, "metadata": {}, "outputs": [], "source": [ @@ -1056,24 +1522,33 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 12, "metadata": {}, "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", + "Track means: [0.00219467 0.00128605 0.65863696 0.01080696 0.00494403 0.00370035\n", + " 0.72501702 0.00227474 0.48636405 0.00211876 0.00530738 0.00877379\n", + " 0.00627039 0.00400846 0.44757743 0.66685837 0.00335876 0.00820212\n", + " 0.0034627 0.72625355 0.00622468 0.00548278 0.00574464 0.63734638\n", + " 0.01177604 0.74402866 0.64354244 0.00343102 0.01549048 0.0463601\n", + " 0.0057952 0.00376132 0.00498001 0.01612531]\n", "Number of tracks: (34,)\n", - "\n", - "Train samples: 60000\n", - "Val samples: 1000\n", - "Test samples: 10000\n" + "Added region chr2:52738399-68719540, accumulated_length=15981141\n", + "Added region chr2:94594361-95921948, accumulated_length=17308728\n", + "Added region chr2:95922032-97200446, accumulated_length=18587142\n", + "Added region chr2:97538791-106291501, accumulated_length=27339852\n", + "Added region chr2:110035770-110281551, accumulated_length=27585633\n", + "Added region chr2:110576673-111363357, accumulated_length=28372317\n", + "Added region chr2:111510960-112936893, accumulated_length=29798250\n", + "Sampled window from chr2:114061575-121781652 -> chr2:118561590-121531340 \n", + "Sampled len(sampled_regions)=8 with total accumulated_length=32768000\n", + "\n", + "Train samples: 65051340\n", + "Val samples: 997\n", + "Test samples: 10531\n" ] } ], @@ -1092,37 +1567,33 @@ "\n", "train_dataset = create_dataset_fn(\n", " split=\"train\",\n", - " num_samples=config[\"num_steps_training\"] * config[\"batch_size\"],\n", + " overlap=config[\"train_overlap\"],\n", ")\n", "\n", "val_dataset = create_dataset_fn(\n", - " split=\"val\",\n", - " num_samples=config[\"num_validation_samples\"],\n", + " split=\"val\", limit_num_samples=config[\"num_validation_samples\"]\n", ")\n", + "test_dataset = create_dataset_fn(split=\"test\") # Use all test samples\n", "\n", - "test_dataset = create_dataset_fn(\n", - " split=\"test\",\n", - " num_samples=config[\"num_test_samples\"],\n", - ")\n", "\n", "# Create dataloaders\n", "train_loader = DataLoader(\n", " train_dataset,\n", - " batch_size=config[\"batch_size\"],\n", + " batch_size=config[\"mini_batch_size\"],\n", " shuffle=True,\n", " num_workers=config[\"num_workers\"],\n", ")\n", "\n", "val_loader = DataLoader(\n", " val_dataset,\n", - " batch_size=config[\"batch_size\"],\n", + " batch_size=config[\"mini_batch_size\"],\n", " shuffle=False,\n", " num_workers=config[\"num_workers\"],\n", ")\n", "\n", "test_loader = DataLoader(\n", " test_dataset,\n", - " batch_size=config[\"batch_size\"],\n", + " batch_size=config[\"mini_batch_size\"],\n", " shuffle=False,\n", " num_workers=config[\"num_workers\"],\n", ")\n", @@ -1139,12 +1610,12 @@ "# 5. ⚙️ Optimizer setup\n", "\n", "Configure the AdamW optimizer with learning rate and weight decay hyperparameters. This optimizer will update the model parameters during training to minimize the loss function.\n", - "\n" + "A variable learning rate is used with linear warmup, followed by a polynomial decay." ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1152,33 +1623,76 @@ "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" + " Mini batch size: 4\n", + " Gradient accumulation steps: 8\n", + " Effective batch size: 32\n", + " Total training steps: 19932\n", + " Log metrics every: 50 steps\n", + " Validate every: 500 steps\n", + "\n", + "Optimiser & learning rate scheduler:\n", + " Optimizer base LR (peak): 5e-05\n", + " Initial LR: 1e-05\n", + " Peak LR: 5e-05\n", + " Warmup steps: 598\n", + " Alpha polynomial decay: 0.1977\n", + " Final LR multiplier: 0.5\n" ] } ], "source": [ - "# Training setup\n", "print(f\"Training configuration:\")\n", - "print(f\" Batch size: {config['batch_size']}\")\n", + "print(f\" Mini batch size: {config['mini_batch_size']}\")\n", + "print(f\" Gradient accumulation steps: {config['num_accumulation_gradient']}\")\n", + "print(f\" Effective batch size: {config['mini_batch_size'] * config['num_accumulation_gradient']}\")\n", "print(f\" Total training steps: {config['num_steps_training']}\")\n", "print(f\" Log metrics every: {config['log_every_n_steps']} steps\")\n", "print(f\" Validate every: {config['validate_every_n_steps']} steps\")\n", "\n", + "# Setup optimizer (LR is set to peak LR for scheduler)\n", + "optimizer_lr = config[\"end_learning_rate\"]\n", + "\n", "# Setup optimizer\n", "optimizer = AdamW(\n", " model.parameters(),\n", - " lr=config[\"learning_rate\"],\n", + " lr=optimizer_lr,\n", " weight_decay=config[\"weight_decay\"],\n", ")\n", "\n", - "print(f\"\\nOptimizer setup:\")\n", - "print(f\" Learning rate: {config['learning_rate']}\")" + "# Setup learning rate scheduler\n", + "final_lr_multiplier = 0.5\n", + "num = np.log(1.0 / final_lr_multiplier)\n", + "denom = np.log(float(config[\"num_steps_training\"]) / float(config[\"num_steps_warmup\"]))\n", + "alpha_polynomial_decay = num / denom\n", + "\n", + "def _modified_square_decay(current_step: int) -> float:\n", + " \"\"\"LR multiplier function matching the pipeline's modified_square_decay.\"\"\"\n", + " if current_step < 0:\n", + " current_step = 0\n", + " if optimizer_lr == 0:\n", + " return 0.0\n", + " \n", + " # Phase 1: Warmup (linear increase from initial LR to peak LR)\n", + " if current_step < config[\"num_steps_warmup\"]:\n", + " start_multiplier = config[\"initial_learning_rate\"] / optimizer_lr\n", + " progress = float(current_step) / float(config[\"num_steps_warmup\"])\n", + " return start_multiplier + (1.0 - start_multiplier) * progress\n", + " \n", + " # Phase 2: Polynomial decay\n", + " denominator = float(current_step + 1)\n", + " decay_multiplier = (float(config[\"num_steps_warmup\"]) / denominator) ** alpha_polynomial_decay\n", + " decay_multiplier = min(decay_multiplier, 1.0)\n", + " \n", + " return decay_multiplier\n", + "\n", + "scheduler = LambdaLR(optimizer, lr_lambda=_modified_square_decay)\n", + "print(f\"\\nOptimiser & learning rate scheduler:\")\n", + "print(f\" Optimizer base LR (peak): {optimizer_lr}\")\n", + "print(f\" Initial LR: {config['initial_learning_rate']}\")\n", + "print(f\" Peak LR: {config['end_learning_rate']}\")\n", + "print(f\" Warmup steps: {config['num_steps_warmup']}\")\n", + "print(f\" Alpha polynomial decay: {alpha_polynomial_decay:.4f}\")\n", + "print(f\" Final LR multiplier: {final_lr_multiplier}\")\n" ] }, { @@ -1192,7 +1706,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -1265,11 +1779,15 @@ " }\n", " df = pd.DataFrame(data)\n", " df.to_csv(f\"metrics_{self.split}.csv\", index=False)\n", + "\n", + " return self.mean_pearsons[-1]\n", " \n", - " def print_metrics(self, print_per_track: bool = False):\n", + " def print_metrics(self, print_per_track: bool = False, current_lr: float | None = None):\n", " \"\"\"Print a summary of the metrics.\"\"\"\n", + " lr_str = f\"LR: {current_lr:.2e} | \" if current_lr is not None else \"\"\n", " print(\n", " f\"Step {self.step_idxs[-1]}/{config['num_steps_training']} | \"\n", + " f\"{lr_str}\"\n", " f\"Loss: {self.mean_losses[-1]:.4f} | \"\n", " f\"Mean Pearson: {self.mean_pearsons[-1]:.4f}\"\n", " )\n", @@ -1282,7 +1800,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -1302,7 +1820,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -1376,17 +1894,25 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "def train_step(\n", " model: nn.Module,\n", - " optimizer: torch.optim.Optimizer,\n", " batch: Dict[str, torch.Tensor],\n", " train_metrics: TracksMetrics,\n", + " num_accumulation_gradient_steps: int = 1,\n", ") -> None:\n", - " \"\"\"Single training step.\"\"\"\n", + " \"\"\"\n", + " Single training step for one batch (gradient accumulation handled in training loop).\n", + " \n", + " Args:\n", + " model: The model to train\n", + " batch: Batch of data\n", + " train_metrics: Metrics tracker\n", + " num_accumulation_gradient_steps: Number of gradient accumulation steps (for loss scaling)\n", + " \"\"\"\n", " tokens = batch[\"tokens\"].to(device)\n", " bigwig_targets = batch[\"bigwig_targets\"].to(device)\n", " \n", @@ -1399,19 +1925,17 @@ " logits=bigwig_logits,\n", " targets=bigwig_targets,\n", " )\n", - "\n", - " # Backward pass\n", - " optimizer.zero_grad()\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " # Update metrics\n", + " scaled_loss = loss / num_accumulation_gradient_steps\n", + " \n", + " # Backward pass (accumulate gradients)\n", + " scaled_loss.backward()\n", + " \n", + " # Update metrics (use unscaled loss for logging)\n", " train_metrics.update(\n", " predictions=bigwig_logits,\n", " targets=bigwig_targets,\n", " loss=loss.item()\n", " )\n", - " \n", "\n", "\n", "def validation_step(\n", @@ -1451,1946 +1975,27 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 19, "metadata": {}, "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" + "Starting training for 19932 steps\n", + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Step 50/19932 | LR: 1.34e-05 | Loss: 4.9725 | Mean Pearson: 0.1257\n", + "Step 100/19932 | LR: 1.68e-05 | Loss: 4.7497 | Mean Pearson: 0.3412\n", + "Step 150/19932 | LR: 2.01e-05 | Loss: 4.6592 | Mean Pearson: 0.3977\n", + "Step 200/19932 | LR: 2.34e-05 | Loss: 4.4238 | Mean Pearson: 0.4344\n", + "Step 250/19932 | LR: 2.68e-05 | Loss: 4.7748 | Mean Pearson: 0.4435\n", + "Step 300/19932 | LR: 3.01e-05 | Loss: 4.3888 | Mean Pearson: 0.4834\n" ] } ], @@ -3402,22 +2007,36 @@ "train_iter = iter(train_loader)\n", "model.train()\n", "\n", + "highest_mean_pearson = 0.0\n", "# Main training loop\n", "for step_idx in range(config[\"num_steps_training\"]):\n", - " try:\n", - " batch = next(train_iter)\n", - " except StopIteration:\n", - " # Restart iterator if we run out of data\n", - " train_iter = iter(train_loader)\n", - " batch = next(train_iter)\n", + " # Zero gradients once before accumulation\n", + " optimizer.zero_grad()\n", + " \n", + " # Gradient accumulation: process multiple batches before optimizer step\n", + " for acc_idx in range(config[\"num_accumulation_gradient\"]):\n", + " try:\n", + " batch = next(train_iter)\n", + " except StopIteration:\n", + " # Restart iterator if we run out of data\n", + " train_iter = iter(train_loader)\n", + " batch = next(train_iter)\n", + " \n", + " # Process batch (accumulates gradients)\n", + " train_step(\n", + " model,\n", + " batch,\n", + " train_metrics,\n", + " num_accumulation_gradient_steps=config[\"num_accumulation_gradient\"]\n", + " )\n", " \n", - " # Take a training step\n", - " train_step(model, optimizer, batch, train_metrics)\n", + " optimizer.step() # Update optimizer once after all accumulation steps\n", + " scheduler.step() # Update learning rate scheduler\n", "\n", " # Logging\n", " if (step_idx + 1) % config[\"log_every_n_steps\"] == 0:\n", " train_metrics.update_mean_metrics(step_idx + 1)\n", - " train_metrics.print_metrics()\n", + " train_metrics.print_metrics(current_lr=scheduler.get_last_lr()[0])\n", " train_metrics.reset()\n", " \n", " # Validation\n", @@ -3428,7 +2047,7 @@ " for val_batch in val_loader:\n", " validation_step(model, val_batch, val_metrics)\n", " \n", - " val_metrics.update_mean_metrics(step_idx + 1)\n", + " mean_pearson_idx = val_metrics.update_mean_metrics(step_idx + 1)\n", " val_metrics.print_metrics(print_per_track=True)\n", " val_metrics.reset()\n", "\n", @@ -3436,17 +2055,28 @@ " print(\"\\n\" + \"-\"*100 + \"\\nTraining metrics:\")\n", " model.train() \n", "\n", + " # Save model checkpoint\n", + " torch.save(model.state_dict(), f\"model_checkpoint_{step_idx + 1}.pth\")\n", + " previous_checkpoint_path = f\"model_checkpoint_{step_idx + 1 - config['validate_every_n_steps']}.pth\"\n", + " if os.path.exists(previous_checkpoint_path):\n", + " os.remove(previous_checkpoint_path)\n", + "\n", + " if mean_pearson_idx > highest_mean_pearson:\n", + " highest_mean_pearson = mean_pearson_idx\n", + " print(f\"New highest mean Pearson: {highest_mean_pearson}\")\n", + " torch.save(model.state_dict(), f\"best_model_checkpoint.pth\")\n", + "\n", "print(f\"\\nTraining completed after {config['num_steps_training']} steps.\")\n" ] }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 22, "metadata": {}, "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -3492,84 +2122,20 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": null, "metadata": {}, - "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" - ] - } - ], + "outputs": [], "source": [ "# Calculate number of test steps (based on deepspeed pipeline)\n", "num_test_samples = len(test_dataset)\n", - "num_test_steps = num_test_samples // config[\"batch_size\"]\n", + "num_test_steps = num_test_samples // config[\"mini_batch_size\"]\n", "print(f\"Running test evaluation with {num_test_steps} steps ({num_test_samples} samples)\")\n", "\n", + "# Load the best model checkpoint\n", + "model.load_state_dict(torch.load(config[\"best_model_checkpoint_path\"]))\n", + "model.to(device)\n", + "print(f\"Loaded model from {config['best_model_checkpoint_path']=!s}\")\n", + "\n", "# Set model to eval mode\n", "model.eval()\n", "\n", @@ -3596,46 +2162,45 @@ "cell_type": "markdown", "metadata": {}, "source": [ - " ## Test set results obtained for reference\n", - "\n", - "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)" + "## Test set results obtained for reference\n", + "\n", + "===== Test Set Results =====\n", + "\n", + "Metrics:\n", + "Mean Pearson: 0.6050\n", + "- ENCSR154HRN_M/pearson: 0.5132\n", + "- ENCSR154HRN_P/pearson: 0.5095\n", + "- ENCSR935RNW_P/pearson: 0.5690\n", + "- ENCSR114HGS_M/pearson: 0.3433\n", + "- ENCSR487QSB/pearson: 0.7101\n", + "- ENCSR046BCI_M/pearson: 0.5188\n", + "- ENCSR100LIJ_M/pearson: 0.5632\n", + "- ENCSR754DRC/pearson: 0.6046\n", + "- ENCSR682BFG/pearson: 0.6839\n", + "- ENCSR862QCH_M/pearson: 0.5441\n", + "- ENCSR046BCI_P/pearson: 0.4872\n", + "- ENCSR249ROI_M/pearson: 0.6077\n", + "- ENCSR484LTQ_P/pearson: 0.4738\n", + "- ENCSR410DWV/pearson: 0.7949\n", + "- ENCSR619DQO_P/pearson: 0.6981\n", + "- ENCSR321PWZ_M/pearson: 0.6895\n", + "- ENCSR962OTG/pearson: 0.9150\n", + "- ENCSR321PWZ_P/pearson: 0.6903\n", + "- ENCSR484LTQ_M/pearson: 0.4812\n", + "- ENCSR628PLS/pearson: 0.6479\n", + "- ENCSR249ROI_P/pearson: 0.5761\n", + "- ENCSR799DGV_P/pearson: 0.5704\n", + "- ENCSR862QCH_P/pearson: 0.5402\n", + "- ENCSR527JGN_M/pearson: 0.5144\n", + "- ENCSR619DQO_M/pearson: 0.6975\n", + "- ENCSR814RGG/pearson: 0.7958\n", + "- ENCSR935RNW_M/pearson: 0.5600\n", + "- ENCSR863PSM/pearson: 0.6915\n", + "- ENCSR114HGS_P/pearson: 0.3447\n", + "- ENCSR325NFE/pearson: 0.8314\n", + "- ENCSR701YIC/pearson: 0.5613\n", + "- ENCSR527JGN_P/pearson: 0.7226\n", + "- ENCSR100LIJ_P/pearson: 0.5643" ] }, {