diff --git a/binder/requirements.txt b/binder/requirements.txt index 72b13b2..516ac50 100644 --- a/binder/requirements.txt +++ b/binder/requirements.txt @@ -10,16 +10,16 @@ importlib-metadata==1.7.0 Keras-Applications==1.0.8 Keras-Preprocessing==1.1.2 Markdown==3.2.2 -numpy==1.16.0 +numpy==1.19.5 opt-einsum==3.2.1 pandas==0.24.2 protobuf==3.12.2 python-dateutil==2.8.1 pytz==2020.1 six==1.15.0 -tensorboard==1.15.0 -tensorflow==1.15.0 -tensorflow-estimator==1.15.1 +tensorboard==2.6.0 +tensorflow==2.6.2 +tensorflow-estimator==2.6.0 termcolor==1.1.0 Werkzeug==1.0.1 wrapt==1.12.1 diff --git a/cellbox/cellbox/dataset.py b/cellbox/cellbox/dataset.py index bf676d0..15854f7 100644 --- a/cellbox/cellbox/dataset.py +++ b/cellbox/cellbox/dataset.py @@ -7,8 +7,9 @@ import os import numpy as np import pandas as pd -import tensorflow as tf +import tensorflow.compat.v1 as tf from scipy import sparse +tf.disable_v2_behavior() def factory(cfg): diff --git a/cellbox/cellbox/kernel.py b/cellbox/cellbox/kernel.py index dd33244..5d5af21 100644 --- a/cellbox/cellbox/kernel.py +++ b/cellbox/cellbox/kernel.py @@ -3,7 +3,8 @@ degree of ODEs, and the envelope forms """ -import tensorflow as tf +import tensorflow.compat.v1 as tf +tf.disable_v2_behavior() def get_envelope(args): diff --git a/cellbox/cellbox/model.py b/cellbox/cellbox/model.py index 43bd08b..7477d2d 100644 --- a/cellbox/cellbox/model.py +++ b/cellbox/cellbox/model.py @@ -4,10 +4,11 @@ """ import numpy as np -import tensorflow as tf +import tensorflow.compat.v1 as tf import cellbox.kernel from cellbox.utils import loss, optimize # import tensorflow_probability as tfp +tf.disable_v2_behavior() def factory(args): diff --git a/cellbox/cellbox/train.py b/cellbox/cellbox/train.py index 628296f..963468a 100644 --- a/cellbox/cellbox/train.py +++ b/cellbox/cellbox/train.py @@ -7,10 +7,11 @@ import time import numpy as np import pandas as pd -import tensorflow as tf +import tensorflow.compat.v1 as tf from tensorflow.compat.v1.errors import OutOfRangeError import cellbox from cellbox.utils import TimeLogger +tf.disable_v2_behavior() def train_substage(model, sess, lr_val, l1_lambda, l2_lambda, n_epoch, n_iter, n_iter_buffer, n_iter_patience, args): @@ -59,7 +60,7 @@ def train_substage(model, sess, lr_val, l1_lambda, l2_lambda, n_epoch, n_iter, n while True: if idx_iter > n_iter or n_unchanged > n_iter_patience: break - t0 = time.clock() + t0 = time.perf_counter() try: _, loss_train_i, loss_train_mse_i = sess.run( (model.op_optimize, model.train_loss, model.train_mse_loss), feed_dict=args.feed_dicts['train_set']) @@ -78,7 +79,7 @@ def train_substage(model, sess, lr_val, l1_lambda, l2_lambda, n_epoch, n_iter, n n_iter_patience)) append_record("record_eval.csv", [idx_epoch, idx_iter, loss_train_i, loss_valid_i, loss_train_mse_i, - loss_valid_mse_i, None, time.clock() - t0]) + loss_valid_mse_i, None, time.perf_counter() - t0]) # early stopping idx_iter += 1 if new_loss < best_params.loss_min: @@ -89,18 +90,18 @@ def train_substage(model, sess, lr_val, l1_lambda, l2_lambda, n_epoch, n_iter, n n_unchanged += 1 # Evaluation on valid set - t0 = time.clock() + t0 = time.perf_counter() sess.run(model.iter_eval.initializer, feed_dict=args.feed_dicts['valid_set']) loss_valid_i, loss_valid_mse_i = eval_model(sess, model.iter_eval, (model.eval_loss, model.eval_mse_loss), args.feed_dicts['valid_set'], n_batches_eval=args.n_batches_eval) - append_record("record_eval.csv", [-1, None, None, loss_valid_i, None, loss_valid_mse_i, None, time.clock() - t0]) + append_record("record_eval.csv", [-1, None, None, loss_valid_i, None, loss_valid_mse_i, None, time.perf_counter() - t0]) # Evaluation on test set - t0 = time.clock() + t0 = time.perf_counter() sess.run(model.iter_eval.initializer, feed_dict=args.feed_dicts['test_set']) loss_test_mse = eval_model(sess, model.iter_eval, model.eval_mse_loss, args.feed_dicts['test_set'], n_batches_eval=args.n_batches_eval) - append_record("record_eval.csv", [-1, None, None, None, None, None, loss_test_mse, time.clock() - t0]) + append_record("record_eval.csv", [-1, None, None, None, None, None, loss_test_mse, time.perf_counter() - t0]) best_params.save() args.logger.log("------------------ Substage {} finished!-------------------".format(substage_i)) diff --git a/cellbox/cellbox/utils.py b/cellbox/cellbox/utils.py index 4631881..32647fc 100644 --- a/cellbox/cellbox/utils.py +++ b/cellbox/cellbox/utils.py @@ -5,9 +5,9 @@ import time import hashlib -import tensorflow as tf +import tensorflow.compat.v1 as tf import json - +tf.disable_v2_behavior() def loss(x_gold, x_hat, W, l1=0, l2=0, weight=1.): """evaluate loss""" diff --git a/cellbox/cellbox/version.py b/cellbox/cellbox/version.py index 7636046..90e5768 100644 --- a/cellbox/cellbox/version.py +++ b/cellbox/cellbox/version.py @@ -2,7 +2,7 @@ This module defines the version of the package """ -__version__ = '0.3.1' +__version__ = '0.3.2' VERSION = __version__ @@ -104,14 +104,14 @@ def get_msg(): """ version 0.2.3 - -- June 8, 2020 -- + -- Jun 8, 2020 -- * Add support to L2 loss (alone or together with L1, i.e. elastic net) * Clean the example configs folder """, """ version 0.3.0 - -- June 8, 2020 -- + -- Jun 8, 2020 -- Add support for alternative form of perturbation * Previous: add u on activity nodes * New: fix activity nodes directly @@ -123,10 +123,16 @@ def get_msg(): """ version 0.3.1 - -- Sept 25, 2020 -- + -- Sep 25, 2020 -- * Release version for publication * Add documentation * Rename package to 'cellbox' + """, + + """ + version 0.3.2 + -- Feb 10, 2023 -- + * Modify CellBox to support TF2 """ ] print( @@ -138,12 +144,12 @@ def get_msg(): " | |___| __/ | | |_) | (_) > < \n" " \_____\___|_|_|____/ \___/_/\_\ \n" "Running CellBox scripts developed in Sander lab\n" - "Maintained by Bo Yuan, Judy Shen, and Augustin Luna" + "Maintained by Bo Yuan, Judy Shen, and Augustin Luna; contributions by Daniel Ritter" ) print(changelog[-1]) print( - "Tutorials and documentations are available at https://github.com/dfci/CellBox\n" + "Tutorials and documentations are available at https://github.com/sanderlab/CellBox\n" "If you want to discuss the usage or to report a bug, please use the 'Issues' function at GitHub.\n" "If you find CellBox useful for your research, please consider citing the corresponding publication.\n" "For more information, please email us at boyuan@g.harvard.edu and c_shen@g.harvard.edu, " diff --git a/cellbox/setup.py b/cellbox/setup.py index 7d4adec..f63a554 100644 --- a/cellbox/setup.py +++ b/cellbox/setup.py @@ -17,7 +17,7 @@ url="https://github.com/dfci/CellBox", packages=['cellbox'], python_requires='>=3.6', - install_requires=['tensorflow==1.15.0', 'numpy==1.16.0', 'pandas==0.24.2', 'scipy==1.3.0'], + install_requires=['tensorflow==2.11.0', 'numpy==1.24.1', 'pandas==1.5.3', 'scipy==1.10.0'], tests_require=['pytest', 'pandas', 'numpy', 'scipy'], setup_requires=['pytest-runner', "pytest"], zip_safe=True, diff --git a/notebooks/cellbox_example_tf2.ipynb b/notebooks/cellbox_example_tf2.ipynb new file mode 100644 index 0000000..9874a2f --- /dev/null +++ b/notebooks/cellbox_example_tf2.ipynb @@ -0,0 +1,2296 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# Introduction\n", + "\n", + "This notebook shows how to install and run a small example using a refactored version of CellBox compatible with TensorFlow 2. \n" + ], + "metadata": { + "id": "1Y_YbRz1vCtw" + } + }, + { + "cell_type": "markdown", + "source": [ + "# Installation" + ], + "metadata": { + "id": "_cx6OHHku7uT" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Download Code" + ], + "metadata": { + "id": "HrulKQMvu-Zx" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "i-FnF3TV17ZC", + "outputId": "e21e673b-ea37-42f6-a0c9-a173e033a977" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Cloning into 'CellBox'...\n", + "remote: Enumerating objects: 1262, done.\u001b[K\n", + "remote: Counting objects: 100% (328/328), done.\u001b[K\n", + "remote: Compressing objects: 100% (100/100), done.\u001b[K\n", + "remote: Total 1262 (delta 255), reused 284 (delta 227), pack-reused 934\u001b[K\n", + "Receiving objects: 100% (1262/1262), 91.97 MiB | 14.96 MiB/s, done.\n", + "Resolving deltas: 100% (832/832), done.\n" + ] + } + ], + "source": [ + "!git clone https://github.com/sanderlab/CellBox.git" + ] + }, + { + "cell_type": "code", + "source": [ + "!cd /content/CellBox; git checkout tf2_refactor" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Wu7nlNmx2GKg", + "outputId": "d69fd8c0-4744-4103-f81b-dda6ec628a5c" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Branch 'tf2_refactor' set up to track remote branch 'tf2_refactor' from 'origin'.\n", + "Switched to a new branch 'tf2_refactor'\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!cd /content/CellBox/cellbox; python setup.py install" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "rLVVLscd2MCM", + "outputId": "deb4bc95-3578-4705-c6f6-e8f396fd80a9" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "/usr/local/lib/python3.8/dist-packages/setuptools/dist.py:697: UserWarning: Usage of dash-separated 'description-file' will not be supported in future versions. Please use the underscore name 'description_file' instead\n", + " warnings.warn(\n", + "/usr/local/lib/python3.8/dist-packages/setuptools/dist.py:697: UserWarning: Usage of dash-separated 'description-file' will not be supported in future versions. Please use the underscore name 'description_file' instead\n", + " warnings.warn(\n", + "running install\n", + "running bdist_egg\n", + "running egg_info\n", + "creating cellbox.egg-info\n", + "writing cellbox.egg-info/PKG-INFO\n", + "writing dependency_links to cellbox.egg-info/dependency_links.txt\n", + "writing requirements to cellbox.egg-info/requires.txt\n", + "writing top-level names to cellbox.egg-info/top_level.txt\n", + "writing manifest file 'cellbox.egg-info/SOURCES.txt'\n", + "reading manifest file 'cellbox.egg-info/SOURCES.txt'\n", + "adding license file 'LICENSE'\n", + "writing manifest file 'cellbox.egg-info/SOURCES.txt'\n", + "installing library code to build/bdist.linux-x86_64/egg\n", + "running install_lib\n", + "running build_py\n", + "creating build\n", + "creating build/lib\n", + "creating build/lib/cellbox\n", + "copying cellbox/model.py -> build/lib/cellbox\n", + "copying cellbox/utils.py -> build/lib/cellbox\n", + "copying cellbox/dataset.py -> build/lib/cellbox\n", + "copying cellbox/version.py -> build/lib/cellbox\n", + "copying cellbox/__init__.py -> build/lib/cellbox\n", + "copying cellbox/kernel.py -> build/lib/cellbox\n", + "copying cellbox/train.py -> build/lib/cellbox\n", + "copying cellbox/config.py -> build/lib/cellbox\n", + "creating build/bdist.linux-x86_64\n", + "creating build/bdist.linux-x86_64/egg\n", + "creating build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/model.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/utils.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/dataset.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/version.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/__init__.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/kernel.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/train.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "copying build/lib/cellbox/config.py -> build/bdist.linux-x86_64/egg/cellbox\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/model.py to model.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/utils.py to utils.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/dataset.py to dataset.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/version.py to version.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/__init__.py to __init__.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/kernel.py to kernel.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/train.py to train.cpython-38.pyc\n", + "byte-compiling build/bdist.linux-x86_64/egg/cellbox/config.py to config.cpython-38.pyc\n", + "creating build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/requires.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "copying cellbox.egg-info/zip-safe -> build/bdist.linux-x86_64/egg/EGG-INFO\n", + "creating dist\n", + "creating 'dist/cellbox-0.3.1-py3.8.egg' and adding 'build/bdist.linux-x86_64/egg' to it\n", + "removing 'build/bdist.linux-x86_64/egg' (and everything under it)\n", + "Processing cellbox-0.3.1-py3.8.egg\n", + "Copying cellbox-0.3.1-py3.8.egg to /usr/local/lib/python3.8/dist-packages\n", + "Adding cellbox 0.3.1 to easy-install.pth file\n", + "\n", + "Installed /usr/local/lib/python3.8/dist-packages/cellbox-0.3.1-py3.8.egg\n", + "Processing dependencies for cellbox==0.3.1\n", + "Searching for scipy==1.10.0\n", + "Reading https://pypi.org/simple/scipy/\n", + "Downloading https://files.pythonhosted.org/packages/d9/9c/ed263f84bb54ce0a4b0774f8ef21b45a70d54196a1b4bca9bb7a3c837437/scipy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=5cd7a30970c29d9768a7164f564d1fbf2842bfc77b7d114a99bc32703ce0bf48\n", + "Best match: scipy 1.10.0\n", + "Processing scipy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl\n", + "Installing scipy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl to /usr/local/lib/python3.8/dist-packages\n", + "Adding scipy 1.10.0 to easy-install.pth file\n", + "\n", + "Installed /usr/local/lib/python3.8/dist-packages/scipy-1.10.0-py3.8-linux-x86_64.egg\n", + "Searching for pandas==1.5.3\n", + "Reading https://pypi.org/simple/pandas/\n", + "Downloading https://files.pythonhosted.org/packages/54/a0/c62d63c5c69be9aae07836e4d7e25e7a6f5590be3d8f2d53f43eeec5c475/pandas-1.5.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=565fa34a5434d38e9d250af3c12ff931abaf88050551d9fbcdfafca50d62babf\n", + "Best match: pandas 1.5.3\n", + "Processing pandas-1.5.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl\n", + "Installing pandas-1.5.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl to /usr/local/lib/python3.8/dist-packages\n", + "Adding pandas 1.5.3 to easy-install.pth file\n", + "\n", + "Installed /usr/local/lib/python3.8/dist-packages/pandas-1.5.3-py3.8-linux-x86_64.egg\n", + "Searching for numpy==1.24.1\n", + "Reading https://pypi.org/simple/numpy/\n", + "Downloading https://files.pythonhosted.org/packages/3b/2b/75d7ed116b17202a89e6cf1eba7e91ba83abb79ece7924d5b2c820f59025/numpy-1.24.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=b0677a52f5d896e84414761531947c7a330d1adc07c3a4372262f25d84af7bf7\n", + "Best match: numpy 1.24.1\n", + "Processing numpy-1.24.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl\n", + "Installing numpy-1.24.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl to /usr/local/lib/python3.8/dist-packages\n", + "Adding numpy 1.24.1 to easy-install.pth file\n", + "Installing f2py script to /usr/local/bin\n", + "Installing f2py3 script to /usr/local/bin\n", + "Installing f2py3.8 script to /usr/local/bin\n", + "\n", + "Installed /usr/local/lib/python3.8/dist-packages/numpy-1.24.1-py3.8-linux-x86_64.egg\n", + "Searching for tensorflow==2.11.0\n", + "Best match: tensorflow 2.11.0\n", + "Adding tensorflow 2.11.0 to easy-install.pth file\n", + "Installing estimator_ckpt_converter script to /usr/local/bin\n", + "Installing import_pb_to_tensorboard script to /usr/local/bin\n", + "Installing saved_model_cli script to /usr/local/bin\n", + "Installing tensorboard script to /usr/local/bin\n", + "Installing tf_upgrade_v2 script to /usr/local/bin\n", + "Installing tflite_convert script to /usr/local/bin\n", + "Installing toco script to /usr/local/bin\n", + "Installing toco_from_protos script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for pytz==2022.7.1\n", + "Best match: pytz 2022.7.1\n", + "Adding pytz 2022.7.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for python-dateutil==2.8.2\n", + "Best match: python-dateutil 2.8.2\n", + "Adding python-dateutil 2.8.2 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for protobuf==3.19.6\n", + "Best match: protobuf 3.19.6\n", + "Adding protobuf 3.19.6 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for absl-py==1.4.0\n", + "Best match: absl-py 1.4.0\n", + "Adding absl-py 1.4.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for keras==2.11.0\n", + "Best match: keras 2.11.0\n", + "Adding keras 2.11.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for tensorflow-estimator==2.11.0\n", + "Best match: tensorflow-estimator 2.11.0\n", + "Adding tensorflow-estimator 2.11.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for astunparse==1.6.3\n", + "Best match: astunparse 1.6.3\n", + "Adding astunparse 1.6.3 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for tensorboard==2.11.2\n", + "Best match: tensorboard 2.11.2\n", + "Adding tensorboard 2.11.2 to easy-install.pth file\n", + "Installing tensorboard script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for google-pasta==0.2.0\n", + "Best match: google-pasta 0.2.0\n", + "Adding google-pasta 0.2.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for grpcio==1.51.1\n", + "Best match: grpcio 1.51.1\n", + "Adding grpcio 1.51.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for typing-extensions==4.4.0\n", + "Best match: typing-extensions 4.4.0\n", + "Adding typing-extensions 4.4.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for libclang==15.0.6.1\n", + "Best match: libclang 15.0.6.1\n", + "Adding libclang 15.0.6.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for termcolor==2.2.0\n", + "Best match: termcolor 2.2.0\n", + "Adding termcolor 2.2.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for packaging==23.0\n", + "Best match: packaging 23.0\n", + "Adding packaging 23.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for flatbuffers==23.1.21\n", + "Best match: flatbuffers 23.1.21\n", + "Adding flatbuffers 23.1.21 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for opt-einsum==3.3.0\n", + "Best match: opt-einsum 3.3.0\n", + "Adding opt-einsum 3.3.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for setuptools==57.4.0\n", + "Best match: setuptools 57.4.0\n", + "Adding setuptools 57.4.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for h5py==3.1.0\n", + "Best match: h5py 3.1.0\n", + "Adding h5py 3.1.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for gast==0.4.0\n", + "Best match: gast 0.4.0\n", + "Adding gast 0.4.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for wrapt==1.14.1\n", + "Best match: wrapt 1.14.1\n", + "Adding wrapt 1.14.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for tensorflow-io-gcs-filesystem==0.30.0\n", + "Best match: tensorflow-io-gcs-filesystem 0.30.0\n", + "Adding tensorflow-io-gcs-filesystem 0.30.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for six==1.15.0\n", + "Best match: six 1.15.0\n", + "Adding six 1.15.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for wheel==0.38.4\n", + "Best match: wheel 0.38.4\n", + "Adding wheel 0.38.4 to easy-install.pth file\n", + "Installing wheel script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for requests==2.25.1\n", + "Best match: requests 2.25.1\n", + "Adding requests 2.25.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for tensorboard-data-server==0.6.1\n", + "Best match: tensorboard-data-server 0.6.1\n", + "Adding tensorboard-data-server 0.6.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for google-auth-oauthlib==0.4.6\n", + "Best match: google-auth-oauthlib 0.4.6\n", + "Adding google-auth-oauthlib 0.4.6 to easy-install.pth file\n", + "Installing google-oauthlib-tool script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for Markdown==3.4.1\n", + "Best match: Markdown 3.4.1\n", + "Adding Markdown 3.4.1 to easy-install.pth file\n", + "Installing markdown_py script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for google-auth==2.16.0\n", + "Best match: google-auth 2.16.0\n", + "Adding google-auth 2.16.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for Werkzeug==1.0.1\n", + "Best match: Werkzeug 1.0.1\n", + "Adding Werkzeug 1.0.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for tensorboard-plugin-wit==1.8.1\n", + "Best match: tensorboard-plugin-wit 1.8.1\n", + "Adding tensorboard-plugin-wit 1.8.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for certifi==2022.12.7\n", + "Best match: certifi 2022.12.7\n", + "Adding certifi 2022.12.7 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for urllib3==1.24.3\n", + "Best match: urllib3 1.24.3\n", + "Adding urllib3 1.24.3 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for idna==2.10\n", + "Best match: idna 2.10\n", + "Adding idna 2.10 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for chardet==4.0.0\n", + "Best match: chardet 4.0.0\n", + "Adding chardet 4.0.0 to easy-install.pth file\n", + "Installing chardetect script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for requests-oauthlib==1.3.1\n", + "Best match: requests-oauthlib 1.3.1\n", + "Adding requests-oauthlib 1.3.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for importlib-metadata==6.0.0\n", + "Best match: importlib-metadata 6.0.0\n", + "Adding importlib-metadata 6.0.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for cachetools==5.3.0\n", + "Best match: cachetools 5.3.0\n", + "Adding cachetools 5.3.0 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for rsa==4.9\n", + "Best match: rsa 4.9\n", + "Adding rsa 4.9 to easy-install.pth file\n", + "Installing pyrsa-decrypt script to /usr/local/bin\n", + "Installing pyrsa-encrypt script to /usr/local/bin\n", + "Installing pyrsa-keygen script to /usr/local/bin\n", + "Installing pyrsa-priv2pub script to /usr/local/bin\n", + "Installing pyrsa-sign script to /usr/local/bin\n", + "Installing pyrsa-verify script to /usr/local/bin\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for pyasn1-modules==0.2.8\n", + "Best match: pyasn1-modules 0.2.8\n", + "Adding pyasn1-modules 0.2.8 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for oauthlib==3.2.2\n", + "Best match: oauthlib 3.2.2\n", + "Adding oauthlib 3.2.2 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for zipp==3.12.1\n", + "Best match: zipp 3.12.1\n", + "Adding zipp 3.12.1 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Searching for pyasn1==0.4.8\n", + "Best match: pyasn1 0.4.8\n", + "Adding pyasn1 0.4.8 to easy-install.pth file\n", + "\n", + "Using /usr/local/lib/python3.8/dist-packages\n", + "Finished processing dependencies for cellbox==0.3.1\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Install CellBox" + ], + "metadata": { + "id": "F6n6c4I0vWx3" + } + }, + { + "cell_type": "code", + "source": [ + "!pip install -r /content/CellBox/requirements.txt" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "hhsecIDY2bTo", + "outputId": "6b035f42-1909-46e1-ac82-306a2222f71c" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", + "Requirement already satisfied: absl-py==1.4.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 1)) (1.4.0)\n", + "Requirement already satisfied: astor==0.8.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 2)) (0.8.1)\n", + "Requirement already satisfied: astunparse==1.6.3 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 3)) (1.6.3)\n", + "Requirement already satisfied: cachetools==5.3.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 4)) (5.3.0)\n", + "Requirement already satisfied: cellbox==0.3.1 in /usr/local/lib/python3.8/dist-packages/cellbox-0.3.1-py3.8.egg (from -r /content/CellBox/requirements.txt (line 5)) (0.3.1)\n", + "Collecting charset-normalizer==3.0.1\n", + " Downloading charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (195 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m195.4/195.4 KB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: flatbuffers==23.1.21 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 7)) (23.1.21)\n", + "Requirement already satisfied: gast==0.4.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 8)) (0.4.0)\n", + "Requirement already satisfied: google-auth==2.16.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 9)) (2.16.0)\n", + "Requirement already satisfied: google-auth-oauthlib==0.4.6 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 10)) (0.4.6)\n", + "Requirement already satisfied: google-pasta==0.2.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 11)) (0.2.0)\n", + "Requirement already satisfied: grpcio==1.51.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 12)) (1.51.1)\n", + "Collecting h5py==3.8.0\n", + " Downloading h5py-3.8.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.7/4.7 MB\u001b[0m \u001b[31m47.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting idna==3.4\n", + " Downloading idna-3.4-py3-none-any.whl (61 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.5/61.5 KB\u001b[0m \u001b[31m3.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: importlib-metadata==6.0.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 15)) (6.0.0)\n", + "Requirement already satisfied: keras==2.11.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 16)) (2.11.0)\n", + "Collecting Keras-Applications==1.0.8\n", + " Downloading Keras_Applications-1.0.8-py3-none-any.whl (50 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.7/50.7 KB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting Keras-Preprocessing==1.1.2\n", + " Downloading Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.6/42.6 KB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: libclang==15.0.6.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 19)) (15.0.6.1)\n", + "Requirement already satisfied: Markdown==3.4.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 20)) (3.4.1)\n", + "Collecting MarkupSafe==2.1.2\n", + " Downloading MarkupSafe-2.1.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n", + "Collecting numpy==1.24.1\n", + " Downloading numpy-1.24.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.3/17.3 MB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: oauthlib==3.2.2 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 23)) (3.2.2)\n", + "Requirement already satisfied: opt-einsum==3.3.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 24)) (3.3.0)\n", + "Requirement already satisfied: packaging==23.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 25)) (23.0)\n", + "Collecting pandas==1.5.3\n", + " Downloading pandas-1.5.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.2/12.2 MB\u001b[0m \u001b[31m38.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: protobuf==3.19.6 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 27)) (3.19.6)\n", + "Requirement already satisfied: pyasn1==0.4.8 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 28)) (0.4.8)\n", + "Requirement already satisfied: pyasn1-modules==0.2.8 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 29)) (0.2.8)\n", + "Requirement already satisfied: python-dateutil==2.8.2 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 30)) (2.8.2)\n", + "Requirement already satisfied: pytz==2022.7.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 31)) (2022.7.1)\n", + "Collecting requests==2.28.2\n", + " Downloading requests-2.28.2-py3-none-any.whl (62 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.8/62.8 KB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: requests-oauthlib==1.3.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 33)) (1.3.1)\n", + "Requirement already satisfied: rsa==4.9 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 34)) (4.9)\n", + "Collecting scipy==1.10.0\n", + " Downloading scipy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (34.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m34.5/34.5 MB\u001b[0m \u001b[31m12.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting six==1.16.0\n", + " Downloading six-1.16.0-py2.py3-none-any.whl (11 kB)\n", + "Requirement already satisfied: tensorboard==2.11.2 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 37)) (2.11.2)\n", + "Requirement already satisfied: tensorboard-data-server==0.6.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 38)) (0.6.1)\n", + "Requirement already satisfied: tensorboard-plugin-wit==1.8.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 39)) (1.8.1)\n", + "Requirement already satisfied: tensorflow==2.11.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 40)) (2.11.0)\n", + "Requirement already satisfied: tensorflow-estimator==2.11.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 41)) (2.11.0)\n", + "Requirement already satisfied: tensorflow-io-gcs-filesystem==0.30.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 42)) (0.30.0)\n", + "Requirement already satisfied: termcolor==2.2.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 43)) (2.2.0)\n", + "Requirement already satisfied: typing_extensions==4.4.0 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 44)) (4.4.0)\n", + "Collecting urllib3==1.26.14\n", + " Downloading urllib3-1.26.14-py2.py3-none-any.whl (140 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m140.6/140.6 KB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting Werkzeug==2.2.2\n", + " Downloading Werkzeug-2.2.2-py3-none-any.whl (232 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m232.7/232.7 KB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: wrapt==1.14.1 in /usr/local/lib/python3.8/dist-packages (from -r /content/CellBox/requirements.txt (line 47)) (1.14.1)\n", + "Collecting zipp==3.12.0\n", + " Downloading zipp-3.12.0-py3-none-any.whl (6.6 kB)\n", + "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.8/dist-packages (from astunparse==1.6.3->-r /content/CellBox/requirements.txt (line 3)) (0.38.4)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests==2.28.2->-r /content/CellBox/requirements.txt (line 32)) (2022.12.7)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.8/dist-packages (from tensorboard==2.11.2->-r /content/CellBox/requirements.txt (line 37)) (57.4.0)\n", + "Installing collected packages: charset-normalizer, zipp, urllib3, six, numpy, MarkupSafe, idna, Werkzeug, scipy, requests, Keras-Preprocessing, h5py, pandas, Keras-Applications\n", + " Attempting uninstall: charset-normalizer\n", + " Found existing installation: charset-normalizer 2.1.1\n", + " Uninstalling charset-normalizer-2.1.1:\n", + " Successfully uninstalled charset-normalizer-2.1.1\n", + " Attempting uninstall: zipp\n", + " Found existing installation: zipp 3.12.1\n", + " Uninstalling zipp-3.12.1:\n", + " Successfully uninstalled zipp-3.12.1\n", + " Attempting uninstall: urllib3\n", + " Found existing installation: urllib3 1.24.3\n", + " Uninstalling urllib3-1.24.3:\n", + " Successfully uninstalled urllib3-1.24.3\n", + " Attempting uninstall: six\n", + " Found existing installation: six 1.15.0\n", + " Uninstalling six-1.15.0:\n", + " Successfully uninstalled six-1.15.0\n", + " Attempting uninstall: numpy\n", + " Found existing installation: numpy 1.21.6\n", + " Uninstalling numpy-1.21.6:\n", + " Successfully uninstalled numpy-1.21.6\n", + " Attempting uninstall: MarkupSafe\n", + " Found existing installation: MarkupSafe 2.0.1\n", + " Uninstalling MarkupSafe-2.0.1:\n", + " Successfully uninstalled MarkupSafe-2.0.1\n", + " Attempting uninstall: idna\n", + " Found existing installation: idna 2.10\n", + " Uninstalling idna-2.10:\n", + " Successfully uninstalled idna-2.10\n", + " Attempting uninstall: Werkzeug\n", + " Found existing installation: Werkzeug 1.0.1\n", + " Uninstalling Werkzeug-1.0.1:\n", + " Successfully uninstalled Werkzeug-1.0.1\n", + " Attempting uninstall: scipy\n", + " Found existing installation: scipy 1.7.3\n", + " Uninstalling scipy-1.7.3:\n", + " Successfully uninstalled scipy-1.7.3\n", + " Attempting uninstall: requests\n", + " Found existing installation: requests 2.25.1\n", + " Uninstalling requests-2.25.1:\n", + " Successfully uninstalled requests-2.25.1\n", + " Attempting uninstall: h5py\n", + " Found existing installation: h5py 3.1.0\n", + " Uninstalling h5py-3.1.0:\n", + " Successfully uninstalled h5py-3.1.0\n", + " Attempting uninstall: pandas\n", + " Found existing installation: pandas 1.3.5\n", + " Uninstalling pandas-1.3.5:\n", + " Successfully uninstalled pandas-1.3.5\n", + "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "ipython 7.9.0 requires jedi>=0.10, which is not installed.\n", + "numba 0.56.4 requires numpy<1.24,>=1.18, but you have numpy 1.24.1 which is incompatible.\n", + "flask 1.1.4 requires Werkzeug<2.0,>=0.15, but you have werkzeug 2.2.2 which is incompatible.\n", + "aiohttp 3.8.3 requires charset-normalizer<3.0,>=2.0, but you have charset-normalizer 3.0.1 which is incompatible.\u001b[0m\u001b[31m\n", + "\u001b[0mSuccessfully installed Keras-Applications-1.0.8 Keras-Preprocessing-1.1.2 MarkupSafe-2.1.2 Werkzeug-2.2.2 charset-normalizer-3.0.1 h5py-3.8.0 idna-3.4 numpy-1.24.1 pandas-1.5.3 requests-2.28.2 scipy-1.10.0 six-1.16.0 urllib3-1.26.14 zipp-3.12.0\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Run Small Training Example\n", + "\n", + "## Data files: in ./data/ folder in GitHub repo used for example\n", + "* `node_index.txt`: names of each protein/phenotypic node.\n", + "* `expr_index.txt`: information each perturbation condition. This is one of the original data files we downloaded from [paper](https://elifesciences.org/articles/04640) and is only used here as a reference for the condition names. In other words the 2nd and 3rd columns are not being used in CellBox. See `loo_label.csv` for the actual indexing of perturbation targets.\n", + "* `expr.csv`: Protein expression data from RPPA for the protein nodes and phenotypic node values. Each row is a condition while each column is a node.\n", + "* `pert.csv`: Perturbation strength and target of all perturbation conditions. Used as input for differential equations.\n" + ], + "metadata": { + "id": "-D24Im3XvaDo" + } + }, + { + "cell_type": "code", + "source": [ + "!cd /content/CellBox; python ./scripts/main.py -config=./configs/Example.random_partition.json" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "O4rzhcdu3Cot", + "outputId": "7227f245-af2a-4ff0-cda3-298ac4dd738d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "2023-02-10 20:28:04.957319: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n", + "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", + "2023-02-10 20:28:07.013107: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n", + "2023-02-10 20:28:07.013279: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n", + "2023-02-10 20:28:07.013310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n", + "WARNING:tensorflow:From /usr/local/lib/python3.8/dist-packages/tensorflow/python/compat/v2_compat.py:107: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "non-resource variables are not supported in the long term\n", + "WARNING:tensorflow:From /usr/local/lib/python3.8/dist-packages/tensorflow/python/compat/v2_compat.py:107: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "non-resource variables are not supported in the long term\n", + "================================================================================\n", + " _____ _ _ ____ \n", + " / ____| | | | _ \\ \n", + " | | ___| | | |_) | _____ __ \n", + " | | / _ \\ | | _ < / _ \\ \\/ / \n", + " | |___| __/ | | |_) | (_) > < \n", + " \\_____\\___|_|_|____/ \\___/_/\\_\\ \n", + "Running CellBox scripts developed in Sander lab\n", + "Maintained by Bo Yuan, Judy Shen, and Augustin Luna\n", + "\n", + " version 0.3.1\n", + " -- Sept 25, 2020 --\n", + " * Release version for publication\n", + " * Add documentation \n", + " * Rename package to 'cellbox' \n", + " \n", + "Tutorials and documentations are available at https://github.com/dfci/CellBox\n", + "If you want to discuss the usage or to report a bug, please use the 'Issues' function at GitHub.\n", + "If you find CellBox useful for your research, please consider citing the corresponding publication.\n", + "For more information, please email us at boyuan@g.harvard.edu and c_shen@g.harvard.edu, augustin_luna@hms.harvard.edu\n", + " --------------------------------------------------------------------------------\n", + "{'experiment_id': 'Example_RP', 'model_prefix': 'seed', 'ckpt_name': 'model11.ckpt', 'export_verbose': 3, 'experiment_type': 'random partition', 'sparse_data': False, 'batchsize': 4, 'trainset_ratio': 0.7, 'validset_ratio': 0.8, 'n_batches_eval': None, 'add_noise_level': 0, 'dT': 0.1, 'ode_solver': 'heun', 'envelope_form': 'tanh', 'envelope': 0, 'pert_form': 'by u', 'ode_degree': 1, 'ode_last_steps': 2, 'n_iter_buffer': 50, 'n_iter_patience': 100, 'weight_loss': 'None', 'l1lambda': 0.0001, 'l2lambda': 0.0001, 'model': 'CellBox', 'pert_file': 'data/pert.csv', 'expr_file': 'data/expr.csv', 'node_index_file': 'data/node_Index.csv', 'n_protein_nodes': 82, 'n_activity_nodes': 87, 'n_x': 99, 'envelop_form': 'tanh', 'envelop': 0, 'n_epoch': 10000, 'n_iter': 10000, 'stages': [{'nT': 100, 'sub_stages': [{'lr_val': 0.1, 'l1lambda': 0.01, 'n_iter_patience': 1000}, {'lr_val': 0.01, 'l1lambda': 0.01}, {'lr_val': 0.01, 'l1lambda': 0.0001}, {'lr_val': 0.001, 'l1lambda': 1e-05}]}, {'nT': 200, 'sub_stages': [{'lr_val': 0.001, 'l1lambda': 0.0001}]}, {'nT': 400, 'sub_stages': [{'lr_val': 0.001, 'l1lambda': 0.0001}]}], 'ckpt_path_full': './model11.ckpt', 'drug_index': None, 'seed': 1000}\n", + "Working directory is ready at results/Example_RP_bac12a831ae7776664c46d28dd859b74.\n", + "############ Training on stage 1/3 ... --time elapsed: 0.08\n", + "\n", + "\n", + "\n", + "2023-02-10 20:28:28.989029: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:267] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected\n", + "Create new model at model11.ckpt...\n", + "######## --------- lr: 0.1\tl1: 0.01\tl2: 0.0001\t --time elapsed: 1.07\n", + "Substage:1\tEpoch:0/10000\tIteration: 0/10000\tloss (train):66.195328\tloss (buffer on valid):532.706963\tbest:1000.000000\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 1/10000\tloss (train):65.548164\tloss (buffer on valid):376.725960\tbest:532.706963\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 2/10000\tloss (train):64.884109\tloss (buffer on valid):298.656998\tbest:376.725960\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 3/10000\tloss (train):64.229202\tloss (buffer on valid):251.666650\tbest:298.656998\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 4/10000\tloss (train):63.769547\tloss (buffer on valid):220.260731\tbest:251.666650\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 5/10000\tloss (train):63.122292\tloss (buffer on valid):197.715772\tbest:220.260731\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 6/10000\tloss (train):62.567867\tloss (buffer on valid):180.739397\tbest:197.715772\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 7/10000\tloss (train):61.952888\tloss (buffer on valid):167.473828\tbest:180.739397\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 8/10000\tloss (train):61.229176\tloss (buffer on valid):156.793906\tbest:167.473828\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 9/10000\tloss (train):60.815094\tloss (buffer on valid):147.996100\tbest:156.793906\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 10/10000\tloss (train):59.960457\tloss (buffer on valid):140.606178\tbest:147.996100\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 11/10000\tloss (train):59.312214\tloss (buffer on valid):134.290765\tbest:140.606178\tTolerance: 0/1000\n", + "Substage:1\tEpoch:0/10000\tIteration: 12/10000\tloss (train):58.396896\tloss (buffer on valid):128.834800\tbest:134.290765\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 13/10000\tloss (train):57.820820\tloss (buffer on valid):124.058002\tbest:128.834800\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 14/10000\tloss (train):57.211941\tloss (buffer on valid):119.826024\tbest:124.058002\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 15/10000\tloss (train):56.537025\tloss (buffer on valid):116.046997\tbest:119.826024\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 16/10000\tloss (train):55.559864\tloss (buffer on valid):112.641683\tbest:116.046997\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 17/10000\tloss (train):54.858826\tloss (buffer on valid):109.556630\tbest:112.641683\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 18/10000\tloss (train):53.959389\tloss (buffer on valid):106.741653\tbest:109.556630\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 19/10000\tloss (train):53.184929\tloss (buffer on valid):104.153034\tbest:106.741653\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 20/10000\tloss (train):52.365181\tloss (buffer on valid):101.763100\tbest:104.153034\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 21/10000\tloss (train):51.423618\tloss (buffer on valid):99.538391\tbest:101.763100\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 22/10000\tloss (train):50.793457\tloss (buffer on valid):97.470886\tbest:99.538391\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 23/10000\tloss (train):49.813103\tloss (buffer on valid):95.539209\tbest:97.470886\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 24/10000\tloss (train):49.001381\tloss (buffer on valid):93.720672\tbest:95.539209\tTolerance: 0/1000\n", + "Substage:1\tEpoch:1/10000\tIteration: 25/10000\tloss (train):47.925350\tloss (buffer on valid):92.005293\tbest:93.720672\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 26/10000\tloss (train):47.203793\tloss (buffer on valid):90.381169\tbest:92.005293\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 27/10000\tloss (train):46.533741\tloss (buffer on valid):88.836285\tbest:90.381169\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 28/10000\tloss (train):45.647003\tloss (buffer on valid):87.361730\tbest:88.836285\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 29/10000\tloss (train):44.606533\tloss (buffer on valid):85.955924\tbest:87.361730\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 30/10000\tloss (train):43.812180\tloss (buffer on valid):84.613345\tbest:85.955924\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 31/10000\tloss (train):42.903740\tloss (buffer on valid):83.325269\tbest:84.613345\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 32/10000\tloss (train):42.086544\tloss (buffer on valid):82.095601\tbest:83.325269\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 33/10000\tloss (train):41.332882\tloss (buffer on valid):80.910123\tbest:82.095601\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 34/10000\tloss (train):40.458046\tloss (buffer on valid):79.767041\tbest:80.910123\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 35/10000\tloss (train):39.886242\tloss (buffer on valid):78.667791\tbest:79.767041\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 36/10000\tloss (train):38.924000\tloss (buffer on valid):77.600744\tbest:78.667791\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 37/10000\tloss (train):38.204937\tloss (buffer on valid):76.568574\tbest:77.600744\tTolerance: 0/1000\n", + "Substage:1\tEpoch:2/10000\tIteration: 38/10000\tloss (train):37.273209\tloss (buffer on valid):75.570642\tbest:76.568574\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 39/10000\tloss (train):36.657318\tloss (buffer on valid):74.603704\tbest:75.570642\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 40/10000\tloss (train):36.115387\tloss (buffer on valid):73.666663\tbest:74.603704\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 41/10000\tloss (train):35.427128\tloss (buffer on valid):72.757459\tbest:73.666663\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 42/10000\tloss (train):34.483204\tloss (buffer on valid):71.876566\tbest:72.757459\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 43/10000\tloss (train):33.884800\tloss (buffer on valid):71.017132\tbest:71.876566\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 44/10000\tloss (train):33.074776\tloss (buffer on valid):70.177622\tbest:71.017132\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 45/10000\tloss (train):32.434902\tloss (buffer on valid):69.361239\tbest:70.177622\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 46/10000\tloss (train):31.827263\tloss (buffer on valid):68.565098\tbest:69.361239\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 47/10000\tloss (train):31.093683\tloss (buffer on valid):67.791994\tbest:68.565098\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 48/10000\tloss (train):30.737379\tloss (buffer on valid):67.037012\tbest:67.791994\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 49/10000\tloss (train):29.923651\tloss (buffer on valid):47.625635\tbest:67.037012\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 50/10000\tloss (train):29.380671\tloss (buffer on valid):46.892628\tbest:47.625635\tTolerance: 0/1000\n", + "Substage:1\tEpoch:3/10000\tIteration: 51/10000\tloss (train):28.590248\tloss (buffer on valid):46.159669\tbest:46.892628\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 52/10000\tloss (train):28.101107\tloss (buffer on valid):45.423804\tbest:46.159669\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 53/10000\tloss (train):27.677851\tloss (buffer on valid):44.689722\tbest:45.423804\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 54/10000\tloss (train):27.163902\tloss (buffer on valid):43.956774\tbest:44.689722\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 55/10000\tloss (train):26.397127\tloss (buffer on valid):43.228403\tbest:43.956774\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 56/10000\tloss (train):25.979795\tloss (buffer on valid):42.500985\tbest:43.228403\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 57/10000\tloss (train):25.538074\tloss (buffer on valid):41.778067\tbest:42.500985\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 58/10000\tloss (train):25.156750\tloss (buffer on valid):41.059755\tbest:41.778067\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 59/10000\tloss (train):24.761581\tloss (buffer on valid):40.345491\tbest:41.059755\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 60/10000\tloss (train):24.264511\tloss (buffer on valid):39.638448\tbest:40.345491\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 61/10000\tloss (train):24.118887\tloss (buffer on valid):38.940635\tbest:39.638448\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 62/10000\tloss (train):23.453850\tloss (buffer on valid):38.245874\tbest:38.940635\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 63/10000\tloss (train):23.098637\tloss (buffer on valid):37.554821\tbest:38.245874\tTolerance: 0/1000\n", + "Substage:1\tEpoch:4/10000\tIteration: 64/10000\tloss (train):22.408163\tloss (buffer on valid):36.871610\tbest:37.554821\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 65/10000\tloss (train):22.023687\tloss (buffer on valid):36.193480\tbest:36.871610\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 66/10000\tloss (train):21.724516\tloss (buffer on valid):35.523936\tbest:36.193480\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 67/10000\tloss (train):21.337263\tloss (buffer on valid):34.863132\tbest:35.523936\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 68/10000\tloss (train):20.803207\tloss (buffer on valid):34.214583\tbest:34.863132\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 69/10000\tloss (train):20.608452\tloss (buffer on valid):33.574989\tbest:34.214583\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 70/10000\tloss (train):20.315472\tloss (buffer on valid):32.943742\tbest:33.574989\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 71/10000\tloss (train):19.989069\tloss (buffer on valid):32.326251\tbest:32.943742\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 72/10000\tloss (train):19.593422\tloss (buffer on valid):31.713893\tbest:32.326251\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 73/10000\tloss (train):19.185358\tloss (buffer on valid):31.106461\tbest:31.713893\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 74/10000\tloss (train):19.094606\tloss (buffer on valid):30.512152\tbest:31.106461\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 75/10000\tloss (train):18.525949\tloss (buffer on valid):29.926603\tbest:30.512152\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 76/10000\tloss (train):18.220657\tloss (buffer on valid):29.351673\tbest:29.926603\tTolerance: 0/1000\n", + "Substage:1\tEpoch:5/10000\tIteration: 77/10000\tloss (train):17.671745\tloss (buffer on valid):28.789303\tbest:29.351673\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 78/10000\tloss (train):17.481810\tloss (buffer on valid):28.243932\tbest:28.789303\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 79/10000\tloss (train):17.409664\tloss (buffer on valid):27.710114\tbest:28.243932\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 80/10000\tloss (train):17.114859\tloss (buffer on valid):27.180305\tbest:27.710114\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 81/10000\tloss (train):16.464136\tloss (buffer on valid):26.665127\tbest:27.180305\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 82/10000\tloss (train):16.206224\tloss (buffer on valid):26.153056\tbest:26.665127\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 83/10000\tloss (train):15.822009\tloss (buffer on valid):25.653159\tbest:26.153056\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 84/10000\tloss (train):15.553218\tloss (buffer on valid):25.165457\tbest:25.653159\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 85/10000\tloss (train):15.316573\tloss (buffer on valid):24.682776\tbest:25.165457\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 86/10000\tloss (train):14.882950\tloss (buffer on valid):24.214566\tbest:24.682776\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 87/10000\tloss (train):14.862023\tloss (buffer on valid):23.756602\tbest:24.214566\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 88/10000\tloss (train):14.390925\tloss (buffer on valid):23.307614\tbest:23.756602\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 89/10000\tloss (train):14.177221\tloss (buffer on valid):22.865473\tbest:23.307614\tTolerance: 0/1000\n", + "Substage:1\tEpoch:6/10000\tIteration: 90/10000\tloss (train):13.694977\tloss (buffer on valid):22.430120\tbest:22.865473\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 91/10000\tloss (train):13.512618\tloss (buffer on valid):22.004874\tbest:22.430120\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 92/10000\tloss (train):13.344428\tloss (buffer on valid):21.585862\tbest:22.004874\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 93/10000\tloss (train):13.075265\tloss (buffer on valid):21.181369\tbest:21.585862\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 94/10000\tloss (train):12.904845\tloss (buffer on valid):20.792160\tbest:21.181369\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 95/10000\tloss (train):12.954833\tloss (buffer on valid):20.415571\tbest:20.792160\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 96/10000\tloss (train):12.786301\tloss (buffer on valid):20.043647\tbest:20.415571\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 97/10000\tloss (train):12.604882\tloss (buffer on valid):19.679464\tbest:20.043647\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 98/10000\tloss (train):12.414972\tloss (buffer on valid):19.319832\tbest:19.679464\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 99/10000\tloss (train):12.107618\tloss (buffer on valid):18.968912\tbest:19.319832\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 100/10000\tloss (train):11.983366\tloss (buffer on valid):18.625694\tbest:18.968912\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 101/10000\tloss (train):11.622416\tloss (buffer on valid):18.291678\tbest:18.625694\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 102/10000\tloss (train):11.389812\tloss (buffer on valid):17.962448\tbest:18.291678\tTolerance: 0/1000\n", + "Substage:1\tEpoch:7/10000\tIteration: 103/10000\tloss (train):10.986670\tloss (buffer on valid):17.644201\tbest:17.962448\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 104/10000\tloss (train):11.015151\tloss (buffer on valid):17.332820\tbest:17.644201\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 105/10000\tloss (train):11.238377\tloss (buffer on valid):17.037840\tbest:17.332820\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 106/10000\tloss (train):11.239125\tloss (buffer on valid):16.749893\tbest:17.037840\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 107/10000\tloss (train):10.976730\tloss (buffer on valid):16.465976\tbest:16.749893\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 108/10000\tloss (train):10.976530\tloss (buffer on valid):16.186663\tbest:16.465976\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 109/10000\tloss (train):10.716442\tloss (buffer on valid):15.915836\tbest:16.186663\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 110/10000\tloss (train):10.542256\tloss (buffer on valid):15.647414\tbest:15.915836\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 111/10000\tloss (train):10.372369\tloss (buffer on valid):15.377349\tbest:15.647414\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 112/10000\tloss (train):10.076248\tloss (buffer on valid):15.113736\tbest:15.377349\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 113/10000\tloss (train):10.138377\tloss (buffer on valid):14.854607\tbest:15.113736\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 114/10000\tloss (train):9.729002\tloss (buffer on valid):14.599742\tbest:14.854607\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 115/10000\tloss (train):9.608597\tloss (buffer on valid):14.352510\tbest:14.599742\tTolerance: 0/1000\n", + "Substage:1\tEpoch:8/10000\tIteration: 116/10000\tloss (train):9.191604\tloss (buffer on valid):14.108525\tbest:14.352510\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 117/10000\tloss (train):9.104433\tloss (buffer on valid):13.871409\tbest:14.108525\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 118/10000\tloss (train):9.081492\tloss (buffer on valid):13.631970\tbest:13.871409\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 119/10000\tloss (train):8.935845\tloss (buffer on valid):13.399767\tbest:13.631970\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 120/10000\tloss (train):8.511114\tloss (buffer on valid):13.167399\tbest:13.399767\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 121/10000\tloss (train):8.426152\tloss (buffer on valid):12.938428\tbest:13.167399\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 122/10000\tloss (train):8.132801\tloss (buffer on valid):12.710547\tbest:12.938428\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 123/10000\tloss (train):7.965292\tloss (buffer on valid):12.489856\tbest:12.710547\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 124/10000\tloss (train):7.829467\tloss (buffer on valid):12.274211\tbest:12.489856\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 125/10000\tloss (train):7.547231\tloss (buffer on valid):12.062720\tbest:12.274211\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 126/10000\tloss (train):7.655627\tloss (buffer on valid):11.855723\tbest:12.062720\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 127/10000\tloss (train):7.272111\tloss (buffer on valid):11.651251\tbest:11.855723\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 128/10000\tloss (train):7.221316\tloss (buffer on valid):11.445401\tbest:11.651251\tTolerance: 0/1000\n", + "Substage:1\tEpoch:9/10000\tIteration: 129/10000\tloss (train):6.866951\tloss (buffer on valid):11.241417\tbest:11.445401\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 130/10000\tloss (train):6.857349\tloss (buffer on valid):11.049109\tbest:11.241417\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 131/10000\tloss (train):6.854261\tloss (buffer on valid):10.855813\tbest:11.049109\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 132/10000\tloss (train):6.743077\tloss (buffer on valid):10.668857\tbest:10.855813\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 133/10000\tloss (train):6.390191\tloss (buffer on valid):10.487852\tbest:10.668857\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 134/10000\tloss (train):6.369885\tloss (buffer on valid):10.305537\tbest:10.487852\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 135/10000\tloss (train):6.157838\tloss (buffer on valid):10.130139\tbest:10.305537\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 136/10000\tloss (train):6.060198\tloss (buffer on valid):9.957716\tbest:10.130139\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 137/10000\tloss (train):5.998085\tloss (buffer on valid):9.786447\tbest:9.957716\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 138/10000\tloss (train):5.784840\tloss (buffer on valid):9.617994\tbest:9.786447\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 139/10000\tloss (train):5.955758\tloss (buffer on valid):9.453017\tbest:9.617994\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 140/10000\tloss (train):5.629658\tloss (buffer on valid):9.292123\tbest:9.453017\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 141/10000\tloss (train):5.628050\tloss (buffer on valid):9.135854\tbest:9.292123\tTolerance: 0/1000\n", + "Substage:1\tEpoch:10/10000\tIteration: 142/10000\tloss (train):5.322620\tloss (buffer on valid):8.980931\tbest:9.135854\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 143/10000\tloss (train):5.323689\tloss (buffer on valid):8.826912\tbest:8.980931\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 144/10000\tloss (train):5.388566\tloss (buffer on valid):8.671939\tbest:8.826912\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 145/10000\tloss (train):5.301420\tloss (buffer on valid):8.515206\tbest:8.671939\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 146/10000\tloss (train):5.005972\tloss (buffer on valid):8.364687\tbest:8.515206\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 147/10000\tloss (train):5.032725\tloss (buffer on valid):8.214790\tbest:8.364687\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 148/10000\tloss (train):4.872200\tloss (buffer on valid):8.072642\tbest:8.214790\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 149/10000\tloss (train):4.810527\tloss (buffer on valid):7.929967\tbest:8.072642\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 150/10000\tloss (train):4.782670\tloss (buffer on valid):7.789690\tbest:7.929967\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 151/10000\tloss (train):4.601793\tloss (buffer on valid):7.652300\tbest:7.789690\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 152/10000\tloss (train):4.790531\tloss (buffer on valid):7.519039\tbest:7.652300\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 153/10000\tloss (train):4.504506\tloss (buffer on valid):7.389121\tbest:7.519039\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 154/10000\tloss (train):4.532470\tloss (buffer on valid):7.257533\tbest:7.389121\tTolerance: 0/1000\n", + "Substage:1\tEpoch:11/10000\tIteration: 155/10000\tloss (train):4.246585\tloss (buffer on valid):7.118641\tbest:7.257533\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 156/10000\tloss (train):4.275150\tloss (buffer on valid):6.982731\tbest:7.118641\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 157/10000\tloss (train):4.372032\tloss (buffer on valid):6.845031\tbest:6.982731\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 158/10000\tloss (train):4.324186\tloss (buffer on valid):6.712578\tbest:6.845031\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 159/10000\tloss (train):4.032744\tloss (buffer on valid):6.578808\tbest:6.712578\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 160/10000\tloss (train):4.079126\tloss (buffer on valid):6.450044\tbest:6.578808\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 161/10000\tloss (train):3.950741\tloss (buffer on valid):6.327691\tbest:6.450044\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 162/10000\tloss (train):3.915539\tloss (buffer on valid):6.205807\tbest:6.327691\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 163/10000\tloss (train):3.898254\tloss (buffer on valid):6.087981\tbest:6.205807\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 164/10000\tloss (train):3.736627\tloss (buffer on valid):5.977273\tbest:6.087981\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 165/10000\tloss (train):3.943091\tloss (buffer on valid):5.864660\tbest:5.977273\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 166/10000\tloss (train):3.695674\tloss (buffer on valid):5.756790\tbest:5.864660\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 167/10000\tloss (train):3.734315\tloss (buffer on valid):5.647842\tbest:5.756790\tTolerance: 0/1000\n", + "Substage:1\tEpoch:12/10000\tIteration: 168/10000\tloss (train):3.490244\tloss (buffer on valid):5.545846\tbest:5.647842\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 169/10000\tloss (train):3.636774\tloss (buffer on valid):5.443467\tbest:5.545846\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 170/10000\tloss (train):3.663302\tloss (buffer on valid):5.344548\tbest:5.443467\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 171/10000\tloss (train):3.660630\tloss (buffer on valid):5.250679\tbest:5.344548\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 172/10000\tloss (train):3.384295\tloss (buffer on valid):5.162556\tbest:5.250679\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 173/10000\tloss (train):3.463383\tloss (buffer on valid):5.074234\tbest:5.162556\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 174/10000\tloss (train):3.336624\tloss (buffer on valid):4.987882\tbest:5.074234\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 175/10000\tloss (train):3.313872\tloss (buffer on valid):4.904635\tbest:4.987882\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 176/10000\tloss (train):3.309334\tloss (buffer on valid):4.819661\tbest:4.904635\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 177/10000\tloss (train):3.163891\tloss (buffer on valid):4.739931\tbest:4.819661\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 178/10000\tloss (train):3.384671\tloss (buffer on valid):4.661858\tbest:4.739931\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 179/10000\tloss (train):3.142561\tloss (buffer on valid):4.586732\tbest:4.661858\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 180/10000\tloss (train):3.169508\tloss (buffer on valid):4.511487\tbest:4.586732\tTolerance: 0/1000\n", + "Substage:1\tEpoch:13/10000\tIteration: 181/10000\tloss (train):2.942857\tloss (buffer on valid):4.438792\tbest:4.511487\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 182/10000\tloss (train):2.974049\tloss (buffer on valid):4.367738\tbest:4.438792\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 183/10000\tloss (train):3.079057\tloss (buffer on valid):4.296677\tbest:4.367738\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 184/10000\tloss (train):3.045497\tloss (buffer on valid):4.228886\tbest:4.296677\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 185/10000\tloss (train):2.790090\tloss (buffer on valid):4.161107\tbest:4.228886\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 186/10000\tloss (train):2.865337\tloss (buffer on valid):4.093993\tbest:4.161107\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 187/10000\tloss (train):2.761194\tloss (buffer on valid):4.030898\tbest:4.093993\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 188/10000\tloss (train):2.744470\tloss (buffer on valid):3.971307\tbest:4.030898\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 189/10000\tloss (train):2.741966\tloss (buffer on valid):3.915136\tbest:3.971307\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 190/10000\tloss (train):2.614310\tloss (buffer on valid):3.862077\tbest:3.915136\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 191/10000\tloss (train):2.845611\tloss (buffer on valid):3.804897\tbest:3.862077\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 192/10000\tloss (train):2.618403\tloss (buffer on valid):3.755160\tbest:3.804897\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 193/10000\tloss (train):2.659709\tloss (buffer on valid):3.700564\tbest:3.755160\tTolerance: 0/1000\n", + "Substage:1\tEpoch:14/10000\tIteration: 194/10000\tloss (train):2.448907\tloss (buffer on valid):3.648612\tbest:3.700564\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 195/10000\tloss (train):2.492484\tloss (buffer on valid):3.600374\tbest:3.648612\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 196/10000\tloss (train):2.607187\tloss (buffer on valid):3.550854\tbest:3.600374\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 197/10000\tloss (train):2.575408\tloss (buffer on valid):3.497926\tbest:3.550854\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 198/10000\tloss (train):2.343739\tloss (buffer on valid):3.447699\tbest:3.497926\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 199/10000\tloss (train):2.427090\tloss (buffer on valid):3.399323\tbest:3.447699\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 200/10000\tloss (train):2.313155\tloss (buffer on valid):3.352767\tbest:3.399323\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 201/10000\tloss (train):2.304312\tloss (buffer on valid):3.308685\tbest:3.352767\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 202/10000\tloss (train):2.323652\tloss (buffer on valid):3.265386\tbest:3.308685\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 203/10000\tloss (train):2.206612\tloss (buffer on valid):3.218426\tbest:3.265386\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 204/10000\tloss (train):2.444259\tloss (buffer on valid):3.176338\tbest:3.218426\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 205/10000\tloss (train):2.211641\tloss (buffer on valid):3.136476\tbest:3.176338\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 206/10000\tloss (train):2.275888\tloss (buffer on valid):3.093720\tbest:3.136476\tTolerance: 0/1000\n", + "Substage:1\tEpoch:15/10000\tIteration: 207/10000\tloss (train):2.083600\tloss (buffer on valid):3.053464\tbest:3.093720\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 208/10000\tloss (train):2.137218\tloss (buffer on valid):3.016497\tbest:3.053464\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 209/10000\tloss (train):2.246913\tloss (buffer on valid):2.978199\tbest:3.016497\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 210/10000\tloss (train):2.234478\tloss (buffer on valid):2.939629\tbest:2.978199\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 211/10000\tloss (train):2.006401\tloss (buffer on valid):2.901850\tbest:2.939629\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 212/10000\tloss (train):2.088222\tloss (buffer on valid):2.865708\tbest:2.901850\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 213/10000\tloss (train):1.996620\tloss (buffer on valid):2.831248\tbest:2.865708\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 214/10000\tloss (train):1.993371\tloss (buffer on valid):2.794232\tbest:2.831248\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 215/10000\tloss (train):2.003556\tloss (buffer on valid):2.761482\tbest:2.794232\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 216/10000\tloss (train):1.901704\tloss (buffer on valid):2.727480\tbest:2.761482\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 217/10000\tloss (train):2.139387\tloss (buffer on valid):2.692999\tbest:2.727480\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 218/10000\tloss (train):1.924936\tloss (buffer on valid):2.656908\tbest:2.692999\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 219/10000\tloss (train):1.972983\tloss (buffer on valid):2.622719\tbest:2.656908\tTolerance: 0/1000\n", + "Substage:1\tEpoch:16/10000\tIteration: 220/10000\tloss (train):1.785825\tloss (buffer on valid):2.592214\tbest:2.622719\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 221/10000\tloss (train):1.845477\tloss (buffer on valid):2.556891\tbest:2.592214\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 222/10000\tloss (train):1.971159\tloss (buffer on valid):2.524184\tbest:2.556891\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 223/10000\tloss (train):1.953708\tloss (buffer on valid):2.491618\tbest:2.524184\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 224/10000\tloss (train):1.724468\tloss (buffer on valid):2.460029\tbest:2.491618\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 225/10000\tloss (train):1.822302\tloss (buffer on valid):2.430430\tbest:2.460029\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 226/10000\tloss (train):1.733537\tloss (buffer on valid):2.404496\tbest:2.430430\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 227/10000\tloss (train):1.731398\tloss (buffer on valid):2.376319\tbest:2.404496\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 228/10000\tloss (train):1.745365\tloss (buffer on valid):2.348697\tbest:2.376319\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 229/10000\tloss (train):1.646393\tloss (buffer on valid):2.320487\tbest:2.348697\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 230/10000\tloss (train):1.895564\tloss (buffer on valid):2.290175\tbest:2.320487\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 231/10000\tloss (train):1.687481\tloss (buffer on valid):2.262775\tbest:2.290175\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 232/10000\tloss (train):1.744613\tloss (buffer on valid):2.235886\tbest:2.262775\tTolerance: 0/1000\n", + "Substage:1\tEpoch:17/10000\tIteration: 233/10000\tloss (train):1.564033\tloss (buffer on valid):2.212045\tbest:2.235886\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 234/10000\tloss (train):1.623917\tloss (buffer on valid):2.186455\tbest:2.212045\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 235/10000\tloss (train):1.749624\tloss (buffer on valid):2.165204\tbest:2.186455\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 236/10000\tloss (train):1.741984\tloss (buffer on valid):2.144102\tbest:2.165204\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 237/10000\tloss (train):1.526412\tloss (buffer on valid):2.122153\tbest:2.144102\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 238/10000\tloss (train):1.628560\tloss (buffer on valid):2.099518\tbest:2.122153\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 239/10000\tloss (train):1.538861\tloss (buffer on valid):2.073785\tbest:2.099518\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 240/10000\tloss (train):1.548540\tloss (buffer on valid):2.051152\tbest:2.073785\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 241/10000\tloss (train):1.557547\tloss (buffer on valid):2.032161\tbest:2.051152\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 242/10000\tloss (train):1.465261\tloss (buffer on valid):2.007183\tbest:2.032161\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 243/10000\tloss (train):1.714628\tloss (buffer on valid):1.988364\tbest:2.007183\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 244/10000\tloss (train):1.505480\tloss (buffer on valid):1.968209\tbest:1.988364\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 245/10000\tloss (train):1.559810\tloss (buffer on valid):1.946350\tbest:1.968209\tTolerance: 0/1000\n", + "Substage:1\tEpoch:18/10000\tIteration: 246/10000\tloss (train):1.386039\tloss (buffer on valid):1.925897\tbest:1.946350\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 247/10000\tloss (train):1.455982\tloss (buffer on valid):1.910033\tbest:1.925897\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 248/10000\tloss (train):1.599125\tloss (buffer on valid):1.890431\tbest:1.910033\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 249/10000\tloss (train):1.574949\tloss (buffer on valid):1.874243\tbest:1.890431\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 250/10000\tloss (train):1.361772\tloss (buffer on valid):1.856382\tbest:1.874243\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 251/10000\tloss (train):1.471353\tloss (buffer on valid):1.840370\tbest:1.856382\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 252/10000\tloss (train):1.388103\tloss (buffer on valid):1.822889\tbest:1.840370\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 253/10000\tloss (train):1.402666\tloss (buffer on valid):1.806468\tbest:1.822889\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 254/10000\tloss (train):1.427020\tloss (buffer on valid):1.788230\tbest:1.806468\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 255/10000\tloss (train):1.331437\tloss (buffer on valid):1.769818\tbest:1.788230\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 256/10000\tloss (train):1.575106\tloss (buffer on valid):1.755101\tbest:1.769818\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 257/10000\tloss (train):1.374348\tloss (buffer on valid):1.742870\tbest:1.755101\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 258/10000\tloss (train):1.432966\tloss (buffer on valid):1.724243\tbest:1.742870\tTolerance: 0/1000\n", + "Substage:1\tEpoch:19/10000\tIteration: 259/10000\tloss (train):1.253621\tloss (buffer on valid):1.707298\tbest:1.724243\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 260/10000\tloss (train):1.315572\tloss (buffer on valid):1.693001\tbest:1.707298\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 261/10000\tloss (train):1.463028\tloss (buffer on valid):1.677564\tbest:1.693001\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 262/10000\tloss (train):1.463935\tloss (buffer on valid):1.663194\tbest:1.677564\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 263/10000\tloss (train):1.240105\tloss (buffer on valid):1.648320\tbest:1.663194\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 264/10000\tloss (train):1.339346\tloss (buffer on valid):1.634361\tbest:1.648320\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 265/10000\tloss (train):1.260828\tloss (buffer on valid):1.619524\tbest:1.634361\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 266/10000\tloss (train):1.282763\tloss (buffer on valid):1.604674\tbest:1.619524\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 267/10000\tloss (train):1.309564\tloss (buffer on valid):1.590495\tbest:1.604674\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 268/10000\tloss (train):1.200851\tloss (buffer on valid):1.577623\tbest:1.590495\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 269/10000\tloss (train):1.435875\tloss (buffer on valid):1.566359\tbest:1.577623\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 270/10000\tloss (train):1.259679\tloss (buffer on valid):1.552792\tbest:1.566359\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 271/10000\tloss (train):1.314943\tloss (buffer on valid):1.543217\tbest:1.552792\tTolerance: 0/1000\n", + "Substage:1\tEpoch:20/10000\tIteration: 272/10000\tloss (train):1.140280\tloss (buffer on valid):1.530492\tbest:1.543217\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 273/10000\tloss (train):1.191454\tloss (buffer on valid):1.521498\tbest:1.530492\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 274/10000\tloss (train):1.339642\tloss (buffer on valid):1.506992\tbest:1.521498\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 275/10000\tloss (train):1.328184\tloss (buffer on valid):1.493526\tbest:1.506992\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 276/10000\tloss (train):1.120343\tloss (buffer on valid):1.481793\tbest:1.493526\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 277/10000\tloss (train):1.217485\tloss (buffer on valid):1.470313\tbest:1.481793\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 278/10000\tloss (train):1.136568\tloss (buffer on valid):1.460144\tbest:1.470313\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 279/10000\tloss (train):1.157487\tloss (buffer on valid):1.447440\tbest:1.460144\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 280/10000\tloss (train):1.181993\tloss (buffer on valid):1.440010\tbest:1.447440\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 281/10000\tloss (train):1.080335\tloss (buffer on valid):1.428796\tbest:1.440010\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 282/10000\tloss (train):1.334117\tloss (buffer on valid):1.418752\tbest:1.428796\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 283/10000\tloss (train):1.137821\tloss (buffer on valid):1.403998\tbest:1.418752\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 284/10000\tloss (train):1.194293\tloss (buffer on valid):1.396561\tbest:1.403998\tTolerance: 0/1000\n", + "Substage:1\tEpoch:21/10000\tIteration: 285/10000\tloss (train):1.027228\tloss (buffer on valid):1.385122\tbest:1.396561\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 286/10000\tloss (train):1.093047\tloss (buffer on valid):1.372374\tbest:1.385122\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 287/10000\tloss (train):1.237302\tloss (buffer on valid):1.362741\tbest:1.372374\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 288/10000\tloss (train):1.220015\tloss (buffer on valid):1.351536\tbest:1.362741\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 289/10000\tloss (train):1.013746\tloss (buffer on valid):1.342838\tbest:1.351536\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 290/10000\tloss (train):1.130059\tloss (buffer on valid):1.333895\tbest:1.342838\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 291/10000\tloss (train):1.057190\tloss (buffer on valid):1.323020\tbest:1.333895\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 292/10000\tloss (train):1.066416\tloss (buffer on valid):1.313760\tbest:1.323020\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 293/10000\tloss (train):1.095777\tloss (buffer on valid):1.302866\tbest:1.313760\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 294/10000\tloss (train):0.997039\tloss (buffer on valid):1.293231\tbest:1.302866\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 295/10000\tloss (train):1.257136\tloss (buffer on valid):1.284094\tbest:1.293231\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 296/10000\tloss (train):1.064481\tloss (buffer on valid):1.273946\tbest:1.284094\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 297/10000\tloss (train):1.132888\tloss (buffer on valid):1.266407\tbest:1.273946\tTolerance: 0/1000\n", + "Substage:1\tEpoch:22/10000\tIteration: 298/10000\tloss (train):0.954557\tloss (buffer on valid):1.258252\tbest:1.266407\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 299/10000\tloss (train):1.017969\tloss (buffer on valid):1.252721\tbest:1.258252\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 300/10000\tloss (train):1.163467\tloss (buffer on valid):1.246447\tbest:1.252721\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 301/10000\tloss (train):1.160124\tloss (buffer on valid):1.236011\tbest:1.246447\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 302/10000\tloss (train):0.942251\tloss (buffer on valid):1.227883\tbest:1.236011\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 303/10000\tloss (train):1.055731\tloss (buffer on valid):1.222159\tbest:1.227883\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 304/10000\tloss (train):0.974747\tloss (buffer on valid):1.213072\tbest:1.222159\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 305/10000\tloss (train):0.987890\tloss (buffer on valid):1.209216\tbest:1.213072\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 306/10000\tloss (train):1.015682\tloss (buffer on valid):1.202424\tbest:1.209216\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 307/10000\tloss (train):0.925643\tloss (buffer on valid):1.191963\tbest:1.202424\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 308/10000\tloss (train):1.185325\tloss (buffer on valid):1.182730\tbest:1.191963\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 309/10000\tloss (train):0.975030\tloss (buffer on valid):1.176468\tbest:1.182730\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 310/10000\tloss (train):1.046011\tloss (buffer on valid):1.167663\tbest:1.176468\tTolerance: 0/1000\n", + "Substage:1\tEpoch:23/10000\tIteration: 311/10000\tloss (train):0.880116\tloss (buffer on valid):1.160688\tbest:1.167663\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 312/10000\tloss (train):0.944389\tloss (buffer on valid):1.153988\tbest:1.160688\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 313/10000\tloss (train):1.093863\tloss (buffer on valid):1.149880\tbest:1.153988\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 314/10000\tloss (train):1.084310\tloss (buffer on valid):1.144185\tbest:1.149880\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 315/10000\tloss (train):0.877482\tloss (buffer on valid):1.140299\tbest:1.144185\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 316/10000\tloss (train):0.987627\tloss (buffer on valid):1.136877\tbest:1.140299\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 317/10000\tloss (train):0.913093\tloss (buffer on valid):1.131396\tbest:1.136877\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 318/10000\tloss (train):0.945190\tloss (buffer on valid):1.124207\tbest:1.131396\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 319/10000\tloss (train):0.965973\tloss (buffer on valid):1.118287\tbest:1.124207\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 320/10000\tloss (train):0.875030\tloss (buffer on valid):1.111400\tbest:1.118287\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 321/10000\tloss (train):1.120988\tloss (buffer on valid):1.106742\tbest:1.111400\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 322/10000\tloss (train):0.941017\tloss (buffer on valid):1.104651\tbest:1.106742\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 323/10000\tloss (train):1.002733\tloss (buffer on valid):1.098710\tbest:1.104651\tTolerance: 0/1000\n", + "Substage:1\tEpoch:24/10000\tIteration: 324/10000\tloss (train):0.822457\tloss (buffer on valid):1.095981\tbest:1.098710\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 325/10000\tloss (train):0.881149\tloss (buffer on valid):1.091732\tbest:1.095981\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 326/10000\tloss (train):1.044665\tloss (buffer on valid):1.083610\tbest:1.091732\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 327/10000\tloss (train):1.033539\tloss (buffer on valid):1.075648\tbest:1.083610\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 328/10000\tloss (train):0.815493\tloss (buffer on valid):1.068840\tbest:1.075648\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 329/10000\tloss (train):0.925804\tloss (buffer on valid):1.066669\tbest:1.068840\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 330/10000\tloss (train):0.865672\tloss (buffer on valid):1.059456\tbest:1.066669\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 331/10000\tloss (train):0.889950\tloss (buffer on valid):1.058186\tbest:1.059456\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 332/10000\tloss (train):0.910135\tloss (buffer on valid):1.054660\tbest:1.058186\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 333/10000\tloss (train):0.820319\tloss (buffer on valid):1.051414\tbest:1.054660\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 334/10000\tloss (train):1.078736\tloss (buffer on valid):1.046543\tbest:1.051414\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 335/10000\tloss (train):0.888116\tloss (buffer on valid):1.039525\tbest:1.046543\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 336/10000\tloss (train):0.958405\tloss (buffer on valid):1.037022\tbest:1.039525\tTolerance: 0/1000\n", + "Substage:1\tEpoch:25/10000\tIteration: 337/10000\tloss (train):0.785026\tloss (buffer on valid):1.030469\tbest:1.037022\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 338/10000\tloss (train):0.849906\tloss (buffer on valid):1.027596\tbest:1.030469\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 339/10000\tloss (train):1.014043\tloss (buffer on valid):1.024320\tbest:1.027596\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 340/10000\tloss (train):0.993622\tloss (buffer on valid):1.021127\tbest:1.024320\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 341/10000\tloss (train):0.789776\tloss (buffer on valid):1.016819\tbest:1.021127\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 342/10000\tloss (train):0.901188\tloss (buffer on valid):1.012868\tbest:1.016819\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 343/10000\tloss (train):0.824657\tloss (buffer on valid):1.011339\tbest:1.012868\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 344/10000\tloss (train):0.849994\tloss (buffer on valid):1.007497\tbest:1.011339\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 345/10000\tloss (train):0.871055\tloss (buffer on valid):1.000557\tbest:1.007497\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 346/10000\tloss (train):0.787490\tloss (buffer on valid):0.998435\tbest:1.000557\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 347/10000\tloss (train):1.048088\tloss (buffer on valid):0.991971\tbest:0.998435\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 348/10000\tloss (train):0.856858\tloss (buffer on valid):0.989914\tbest:0.991971\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 349/10000\tloss (train):0.902803\tloss (buffer on valid):0.984087\tbest:0.989914\tTolerance: 0/1000\n", + "Substage:1\tEpoch:26/10000\tIteration: 350/10000\tloss (train):0.738064\tloss (buffer on valid):0.981689\tbest:0.984087\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 351/10000\tloss (train):0.818381\tloss (buffer on valid):0.982550\tbest:0.981689\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 352/10000\tloss (train):0.987927\tloss (buffer on valid):0.977656\tbest:0.981689\tTolerance: 1/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 353/10000\tloss (train):0.966094\tloss (buffer on valid):0.973996\tbest:0.977656\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 354/10000\tloss (train):0.756232\tloss (buffer on valid):0.974156\tbest:0.973996\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 355/10000\tloss (train):0.875393\tloss (buffer on valid):0.966703\tbest:0.973996\tTolerance: 1/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 356/10000\tloss (train):0.793267\tloss (buffer on valid):0.960339\tbest:0.966703\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 357/10000\tloss (train):0.821693\tloss (buffer on valid):0.956189\tbest:0.960339\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 358/10000\tloss (train):0.845907\tloss (buffer on valid):0.954034\tbest:0.956189\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 359/10000\tloss (train):0.764799\tloss (buffer on valid):0.948415\tbest:0.954034\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 360/10000\tloss (train):1.007122\tloss (buffer on valid):0.943933\tbest:0.948415\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 361/10000\tloss (train):0.822280\tloss (buffer on valid):0.939491\tbest:0.943933\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 362/10000\tloss (train):0.890154\tloss (buffer on valid):0.935226\tbest:0.939491\tTolerance: 0/1000\n", + "Substage:1\tEpoch:27/10000\tIteration: 363/10000\tloss (train):0.726534\tloss (buffer on valid):0.931102\tbest:0.935226\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 364/10000\tloss (train):0.784488\tloss (buffer on valid):0.928462\tbest:0.931102\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 365/10000\tloss (train):0.923255\tloss (buffer on valid):0.924460\tbest:0.928462\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 366/10000\tloss (train):0.927896\tloss (buffer on valid):0.922326\tbest:0.924460\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 367/10000\tloss (train):0.725156\tloss (buffer on valid):0.920299\tbest:0.922326\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 368/10000\tloss (train):0.842946\tloss (buffer on valid):0.916239\tbest:0.920299\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 369/10000\tloss (train):0.767688\tloss (buffer on valid):0.911882\tbest:0.916239\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 370/10000\tloss (train):0.793566\tloss (buffer on valid):0.910647\tbest:0.911882\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 371/10000\tloss (train):0.815394\tloss (buffer on valid):0.907119\tbest:0.910647\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 372/10000\tloss (train):0.740272\tloss (buffer on valid):0.900726\tbest:0.907119\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 373/10000\tloss (train):0.984286\tloss (buffer on valid):0.896596\tbest:0.900726\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 374/10000\tloss (train):0.793855\tloss (buffer on valid):0.893180\tbest:0.896596\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 375/10000\tloss (train):0.861247\tloss (buffer on valid):0.889331\tbest:0.893180\tTolerance: 0/1000\n", + "Substage:1\tEpoch:28/10000\tIteration: 376/10000\tloss (train):0.698306\tloss (buffer on valid):0.887846\tbest:0.889331\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 377/10000\tloss (train):0.767053\tloss (buffer on valid):0.884954\tbest:0.887846\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 378/10000\tloss (train):0.930411\tloss (buffer on valid):0.883961\tbest:0.884954\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 379/10000\tloss (train):0.925186\tloss (buffer on valid):0.881534\tbest:0.883961\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 380/10000\tloss (train):0.707005\tloss (buffer on valid):0.883181\tbest:0.881534\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 381/10000\tloss (train):0.833393\tloss (buffer on valid):0.879116\tbest:0.881534\tTolerance: 1/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 382/10000\tloss (train):0.761789\tloss (buffer on valid):0.876851\tbest:0.879116\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 383/10000\tloss (train):0.783006\tloss (buffer on valid):0.873847\tbest:0.876851\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 384/10000\tloss (train):0.815428\tloss (buffer on valid):0.869735\tbest:0.873847\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 385/10000\tloss (train):0.724320\tloss (buffer on valid):0.869601\tbest:0.869735\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 386/10000\tloss (train):0.974976\tloss (buffer on valid):0.866587\tbest:0.869601\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 387/10000\tloss (train):0.797211\tloss (buffer on valid):0.867489\tbest:0.866587\tTolerance: 0/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 388/10000\tloss (train):0.863069\tloss (buffer on valid):0.866828\tbest:0.866587\tTolerance: 1/1000\n", + "Substage:1\tEpoch:29/10000\tIteration: 389/10000\tloss (train):0.692826\tloss (buffer on valid):0.867964\tbest:0.866587\tTolerance: 2/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 390/10000\tloss (train):0.763509\tloss (buffer on valid):0.862791\tbest:0.866587\tTolerance: 3/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 391/10000\tloss (train):0.944243\tloss (buffer on valid):0.863293\tbest:0.862791\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 392/10000\tloss (train):0.926655\tloss (buffer on valid):0.860099\tbest:0.862791\tTolerance: 1/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 393/10000\tloss (train):0.701670\tloss (buffer on valid):0.859611\tbest:0.860099\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 394/10000\tloss (train):0.818269\tloss (buffer on valid):0.858759\tbest:0.859611\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 395/10000\tloss (train):0.764442\tloss (buffer on valid):0.858880\tbest:0.858759\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 396/10000\tloss (train):0.778470\tloss (buffer on valid):0.856505\tbest:0.858759\tTolerance: 1/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 397/10000\tloss (train):0.825473\tloss (buffer on valid):0.860059\tbest:0.856505\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 398/10000\tloss (train):0.722610\tloss (buffer on valid):0.856384\tbest:0.856505\tTolerance: 1/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 399/10000\tloss (train):0.977487\tloss (buffer on valid):0.853063\tbest:0.856384\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 400/10000\tloss (train):0.794123\tloss (buffer on valid):0.852059\tbest:0.853063\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 401/10000\tloss (train):0.867213\tloss (buffer on valid):0.852067\tbest:0.852059\tTolerance: 0/1000\n", + "Substage:1\tEpoch:30/10000\tIteration: 402/10000\tloss (train):0.689606\tloss (buffer on valid):0.850173\tbest:0.852059\tTolerance: 1/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 403/10000\tloss (train):0.756652\tloss (buffer on valid):0.846947\tbest:0.850173\tTolerance: 0/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 404/10000\tloss (train):0.911803\tloss (buffer on valid):0.841232\tbest:0.846947\tTolerance: 0/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 405/10000\tloss (train):0.906813\tloss (buffer on valid):0.839947\tbest:0.841232\tTolerance: 0/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 406/10000\tloss (train):0.715102\tloss (buffer on valid):0.841821\tbest:0.839947\tTolerance: 0/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 407/10000\tloss (train):0.826820\tloss (buffer on valid):0.841351\tbest:0.839947\tTolerance: 1/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 408/10000\tloss (train):0.740669\tloss (buffer on valid):0.840342\tbest:0.839947\tTolerance: 2/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 409/10000\tloss (train):0.767615\tloss (buffer on valid):0.843498\tbest:0.839947\tTolerance: 3/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 410/10000\tloss (train):0.791545\tloss (buffer on valid):0.845982\tbest:0.839947\tTolerance: 4/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 411/10000\tloss (train):0.714415\tloss (buffer on valid):0.846569\tbest:0.839947\tTolerance: 5/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 412/10000\tloss (train):0.962711\tloss (buffer on valid):0.846840\tbest:0.839947\tTolerance: 6/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 413/10000\tloss (train):0.772359\tloss (buffer on valid):0.842805\tbest:0.839947\tTolerance: 7/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 414/10000\tloss (train):0.831238\tloss (buffer on valid):0.842777\tbest:0.839947\tTolerance: 8/1000\n", + "Substage:1\tEpoch:31/10000\tIteration: 415/10000\tloss (train):0.673032\tloss (buffer on valid):0.838436\tbest:0.839947\tTolerance: 9/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 416/10000\tloss (train):0.744489\tloss (buffer on valid):0.839699\tbest:0.838436\tTolerance: 0/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 417/10000\tloss (train):0.897784\tloss (buffer on valid):0.837048\tbest:0.838436\tTolerance: 1/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 418/10000\tloss (train):0.896511\tloss (buffer on valid):0.840595\tbest:0.837048\tTolerance: 0/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 419/10000\tloss (train):0.687737\tloss (buffer on valid):0.838435\tbest:0.837048\tTolerance: 1/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 420/10000\tloss (train):0.809025\tloss (buffer on valid):0.837203\tbest:0.837048\tTolerance: 2/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 421/10000\tloss (train):0.718194\tloss (buffer on valid):0.837062\tbest:0.837048\tTolerance: 3/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 422/10000\tloss (train):0.755153\tloss (buffer on valid):0.837389\tbest:0.837048\tTolerance: 4/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 423/10000\tloss (train):0.783313\tloss (buffer on valid):0.837134\tbest:0.837048\tTolerance: 5/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 424/10000\tloss (train):0.700609\tloss (buffer on valid):0.835970\tbest:0.837048\tTolerance: 6/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 425/10000\tloss (train):0.945594\tloss (buffer on valid):0.836107\tbest:0.835970\tTolerance: 0/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 426/10000\tloss (train):0.757681\tloss (buffer on valid):0.834938\tbest:0.835970\tTolerance: 1/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 427/10000\tloss (train):0.833949\tloss (buffer on valid):0.835312\tbest:0.834938\tTolerance: 0/1000\n", + "Substage:1\tEpoch:32/10000\tIteration: 428/10000\tloss (train):0.662638\tloss (buffer on valid):0.834833\tbest:0.834938\tTolerance: 1/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 429/10000\tloss (train):0.735118\tloss (buffer on valid):0.833857\tbest:0.834833\tTolerance: 0/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 430/10000\tloss (train):0.884818\tloss (buffer on valid):0.829576\tbest:0.833857\tTolerance: 0/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 431/10000\tloss (train):0.890426\tloss (buffer on valid):0.829824\tbest:0.829576\tTolerance: 0/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 432/10000\tloss (train):0.685121\tloss (buffer on valid):0.825531\tbest:0.829576\tTolerance: 1/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 433/10000\tloss (train):0.788033\tloss (buffer on valid):0.826934\tbest:0.825531\tTolerance: 0/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 434/10000\tloss (train):0.718083\tloss (buffer on valid):0.830457\tbest:0.825531\tTolerance: 1/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 435/10000\tloss (train):0.751477\tloss (buffer on valid):0.832248\tbest:0.825531\tTolerance: 2/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 436/10000\tloss (train):0.780836\tloss (buffer on valid):0.836795\tbest:0.825531\tTolerance: 3/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 437/10000\tloss (train):0.684347\tloss (buffer on valid):0.834833\tbest:0.825531\tTolerance: 4/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 438/10000\tloss (train):0.946071\tloss (buffer on valid):0.831093\tbest:0.825531\tTolerance: 5/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 439/10000\tloss (train):0.757403\tloss (buffer on valid):0.830088\tbest:0.825531\tTolerance: 6/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 440/10000\tloss (train):0.820588\tloss (buffer on valid):0.833955\tbest:0.825531\tTolerance: 7/1000\n", + "Substage:1\tEpoch:33/10000\tIteration: 441/10000\tloss (train):0.653215\tloss (buffer on valid):0.830953\tbest:0.825531\tTolerance: 8/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 442/10000\tloss (train):0.736161\tloss (buffer on valid):0.832219\tbest:0.825531\tTolerance: 9/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 443/10000\tloss (train):0.901598\tloss (buffer on valid):0.828404\tbest:0.825531\tTolerance: 10/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 444/10000\tloss (train):0.892079\tloss (buffer on valid):0.825589\tbest:0.825531\tTolerance: 11/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 445/10000\tloss (train):0.671895\tloss (buffer on valid):0.823335\tbest:0.825531\tTolerance: 12/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 446/10000\tloss (train):0.779049\tloss (buffer on valid):0.823811\tbest:0.823335\tTolerance: 0/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 447/10000\tloss (train):0.748637\tloss (buffer on valid):0.818712\tbest:0.823335\tTolerance: 1/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 448/10000\tloss (train):0.761407\tloss (buffer on valid):0.819202\tbest:0.818712\tTolerance: 0/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 449/10000\tloss (train):0.773698\tloss (buffer on valid):0.818393\tbest:0.818712\tTolerance: 1/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 450/10000\tloss (train):0.697745\tloss (buffer on valid):0.817280\tbest:0.818393\tTolerance: 0/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 451/10000\tloss (train):0.944233\tloss (buffer on valid):0.812186\tbest:0.817280\tTolerance: 0/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 452/10000\tloss (train):0.758677\tloss (buffer on valid):0.814081\tbest:0.812186\tTolerance: 0/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 453/10000\tloss (train):0.826388\tloss (buffer on valid):0.815262\tbest:0.812186\tTolerance: 1/1000\n", + "Substage:1\tEpoch:34/10000\tIteration: 454/10000\tloss (train):0.653131\tloss (buffer on valid):0.817743\tbest:0.812186\tTolerance: 2/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 455/10000\tloss (train):0.728049\tloss (buffer on valid):0.817621\tbest:0.812186\tTolerance: 3/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 456/10000\tloss (train):0.912071\tloss (buffer on valid):0.814774\tbest:0.812186\tTolerance: 4/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 457/10000\tloss (train):0.899701\tloss (buffer on valid):0.818910\tbest:0.812186\tTolerance: 5/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 458/10000\tloss (train):0.684482\tloss (buffer on valid):0.819390\tbest:0.812186\tTolerance: 6/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 459/10000\tloss (train):0.795959\tloss (buffer on valid):0.817990\tbest:0.812186\tTolerance: 7/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 460/10000\tloss (train):0.752431\tloss (buffer on valid):0.813843\tbest:0.812186\tTolerance: 8/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 461/10000\tloss (train):0.740325\tloss (buffer on valid):0.813404\tbest:0.812186\tTolerance: 9/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 462/10000\tloss (train):0.778184\tloss (buffer on valid):0.811719\tbest:0.812186\tTolerance: 10/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 463/10000\tloss (train):0.700911\tloss (buffer on valid):0.811922\tbest:0.811719\tTolerance: 0/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 464/10000\tloss (train):0.960797\tloss (buffer on valid):0.809347\tbest:0.811719\tTolerance: 1/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 465/10000\tloss (train):0.757126\tloss (buffer on valid):0.814798\tbest:0.809347\tTolerance: 0/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 466/10000\tloss (train):0.846528\tloss (buffer on valid):0.810658\tbest:0.809347\tTolerance: 1/1000\n", + "Substage:1\tEpoch:35/10000\tIteration: 467/10000\tloss (train):0.648672\tloss (buffer on valid):0.811311\tbest:0.809347\tTolerance: 2/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 468/10000\tloss (train):0.727956\tloss (buffer on valid):0.807238\tbest:0.809347\tTolerance: 3/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 469/10000\tloss (train):0.883683\tloss (buffer on valid):0.808213\tbest:0.807238\tTolerance: 0/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 470/10000\tloss (train):0.871240\tloss (buffer on valid):0.809445\tbest:0.807238\tTolerance: 1/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 471/10000\tloss (train):0.665218\tloss (buffer on valid):0.805549\tbest:0.807238\tTolerance: 2/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 472/10000\tloss (train):0.780383\tloss (buffer on valid):0.807479\tbest:0.805549\tTolerance: 0/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 473/10000\tloss (train):0.713018\tloss (buffer on valid):0.806218\tbest:0.805549\tTolerance: 1/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 474/10000\tloss (train):0.724818\tloss (buffer on valid):0.808139\tbest:0.805549\tTolerance: 2/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 475/10000\tloss (train):0.767738\tloss (buffer on valid):0.806120\tbest:0.805549\tTolerance: 3/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 476/10000\tloss (train):0.677775\tloss (buffer on valid):0.806145\tbest:0.805549\tTolerance: 4/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 477/10000\tloss (train):0.951931\tloss (buffer on valid):0.806720\tbest:0.805549\tTolerance: 5/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 478/10000\tloss (train):0.751473\tloss (buffer on valid):0.804692\tbest:0.805549\tTolerance: 6/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 479/10000\tloss (train):0.812705\tloss (buffer on valid):0.802868\tbest:0.804692\tTolerance: 0/1000\n", + "Substage:1\tEpoch:36/10000\tIteration: 480/10000\tloss (train):0.643388\tloss (buffer on valid):0.806126\tbest:0.802868\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 481/10000\tloss (train):0.712160\tloss (buffer on valid):0.803128\tbest:0.802868\tTolerance: 1/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 482/10000\tloss (train):0.886074\tloss (buffer on valid):0.805721\tbest:0.802868\tTolerance: 2/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 483/10000\tloss (train):0.871383\tloss (buffer on valid):0.803177\tbest:0.802868\tTolerance: 3/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 484/10000\tloss (train):0.666282\tloss (buffer on valid):0.799708\tbest:0.802868\tTolerance: 4/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 485/10000\tloss (train):0.772821\tloss (buffer on valid):0.795752\tbest:0.799708\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 486/10000\tloss (train):0.699186\tloss (buffer on valid):0.791778\tbest:0.795752\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 487/10000\tloss (train):0.721481\tloss (buffer on valid):0.791606\tbest:0.791778\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 488/10000\tloss (train):0.757463\tloss (buffer on valid):0.790371\tbest:0.791606\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 489/10000\tloss (train):0.670249\tloss (buffer on valid):0.786385\tbest:0.790371\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 490/10000\tloss (train):0.950706\tloss (buffer on valid):0.784449\tbest:0.786385\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 491/10000\tloss (train):0.748604\tloss (buffer on valid):0.785435\tbest:0.784449\tTolerance: 0/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 492/10000\tloss (train):0.808632\tloss (buffer on valid):0.788738\tbest:0.784449\tTolerance: 1/1000\n", + "Substage:1\tEpoch:37/10000\tIteration: 493/10000\tloss (train):0.638786\tloss (buffer on valid):0.791606\tbest:0.784449\tTolerance: 2/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 494/10000\tloss (train):0.707096\tloss (buffer on valid):0.792421\tbest:0.784449\tTolerance: 3/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 495/10000\tloss (train):0.878573\tloss (buffer on valid):0.793795\tbest:0.784449\tTolerance: 4/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 496/10000\tloss (train):0.867273\tloss (buffer on valid):0.797194\tbest:0.784449\tTolerance: 5/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 497/10000\tloss (train):0.659131\tloss (buffer on valid):0.798810\tbest:0.784449\tTolerance: 6/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 498/10000\tloss (train):0.771789\tloss (buffer on valid):0.798615\tbest:0.784449\tTolerance: 7/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 499/10000\tloss (train):0.707505\tloss (buffer on valid):0.799992\tbest:0.784449\tTolerance: 8/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 500/10000\tloss (train):0.722096\tloss (buffer on valid):0.798016\tbest:0.784449\tTolerance: 9/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 501/10000\tloss (train):0.763032\tloss (buffer on valid):0.795481\tbest:0.784449\tTolerance: 10/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 502/10000\tloss (train):0.676838\tloss (buffer on valid):0.794582\tbest:0.784449\tTolerance: 11/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 503/10000\tloss (train):0.932833\tloss (buffer on valid):0.793003\tbest:0.784449\tTolerance: 12/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 504/10000\tloss (train):0.739800\tloss (buffer on valid):0.792417\tbest:0.784449\tTolerance: 13/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 505/10000\tloss (train):0.807761\tloss (buffer on valid):0.793657\tbest:0.784449\tTolerance: 14/1000\n", + "Substage:1\tEpoch:38/10000\tIteration: 506/10000\tloss (train):0.639552\tloss (buffer on valid):0.796787\tbest:0.784449\tTolerance: 15/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 507/10000\tloss (train):0.708938\tloss (buffer on valid):0.794333\tbest:0.784449\tTolerance: 16/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 508/10000\tloss (train):0.872287\tloss (buffer on valid):0.793117\tbest:0.784449\tTolerance: 17/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 509/10000\tloss (train):0.870569\tloss (buffer on valid):0.790754\tbest:0.784449\tTolerance: 18/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 510/10000\tloss (train):0.658976\tloss (buffer on valid):0.794113\tbest:0.784449\tTolerance: 19/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 511/10000\tloss (train):0.776964\tloss (buffer on valid):0.794865\tbest:0.784449\tTolerance: 20/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 512/10000\tloss (train):0.705373\tloss (buffer on valid):0.794944\tbest:0.784449\tTolerance: 21/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 513/10000\tloss (train):0.724110\tloss (buffer on valid):0.793515\tbest:0.784449\tTolerance: 22/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 514/10000\tloss (train):0.761393\tloss (buffer on valid):0.791835\tbest:0.784449\tTolerance: 23/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 515/10000\tloss (train):0.673976\tloss (buffer on valid):0.787075\tbest:0.784449\tTolerance: 24/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 516/10000\tloss (train):0.933500\tloss (buffer on valid):0.785580\tbest:0.784449\tTolerance: 25/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 517/10000\tloss (train):0.743232\tloss (buffer on valid):0.786730\tbest:0.784449\tTolerance: 26/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 518/10000\tloss (train):0.811308\tloss (buffer on valid):0.790007\tbest:0.784449\tTolerance: 27/1000\n", + "Substage:1\tEpoch:39/10000\tIteration: 519/10000\tloss (train):0.647305\tloss (buffer on valid):0.789286\tbest:0.784449\tTolerance: 28/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 520/10000\tloss (train):0.709677\tloss (buffer on valid):0.787096\tbest:0.784449\tTolerance: 29/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 521/10000\tloss (train):0.855438\tloss (buffer on valid):0.787878\tbest:0.784449\tTolerance: 30/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 522/10000\tloss (train):0.861046\tloss (buffer on valid):0.786803\tbest:0.784449\tTolerance: 31/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 523/10000\tloss (train):0.656056\tloss (buffer on valid):0.787825\tbest:0.784449\tTolerance: 32/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 524/10000\tloss (train):0.762243\tloss (buffer on valid):0.785272\tbest:0.784449\tTolerance: 33/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 525/10000\tloss (train):0.683930\tloss (buffer on valid):0.784611\tbest:0.784449\tTolerance: 34/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 526/10000\tloss (train):0.718295\tloss (buffer on valid):0.789590\tbest:0.784449\tTolerance: 35/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 527/10000\tloss (train):0.749861\tloss (buffer on valid):0.790320\tbest:0.784449\tTolerance: 36/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 528/10000\tloss (train):0.671018\tloss (buffer on valid):0.789841\tbest:0.784449\tTolerance: 37/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 529/10000\tloss (train):0.922397\tloss (buffer on valid):0.792096\tbest:0.784449\tTolerance: 38/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 530/10000\tloss (train):0.733059\tloss (buffer on valid):0.789312\tbest:0.784449\tTolerance: 39/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 531/10000\tloss (train):0.802360\tloss (buffer on valid):0.794416\tbest:0.784449\tTolerance: 40/1000\n", + "Substage:1\tEpoch:40/10000\tIteration: 532/10000\tloss (train):0.641292\tloss (buffer on valid):0.794930\tbest:0.784449\tTolerance: 41/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 533/10000\tloss (train):0.712396\tloss (buffer on valid):0.795554\tbest:0.784449\tTolerance: 42/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 534/10000\tloss (train):0.864921\tloss (buffer on valid):0.795535\tbest:0.784449\tTolerance: 43/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 535/10000\tloss (train):0.874212\tloss (buffer on valid):0.797145\tbest:0.784449\tTolerance: 44/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 536/10000\tloss (train):0.659808\tloss (buffer on valid):0.794181\tbest:0.784449\tTolerance: 45/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 537/10000\tloss (train):0.774180\tloss (buffer on valid):0.795562\tbest:0.784449\tTolerance: 46/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 538/10000\tloss (train):0.706870\tloss (buffer on valid):0.798553\tbest:0.784449\tTolerance: 47/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 539/10000\tloss (train):0.732060\tloss (buffer on valid):0.802496\tbest:0.784449\tTolerance: 48/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 540/10000\tloss (train):0.767867\tloss (buffer on valid):0.801532\tbest:0.784449\tTolerance: 49/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 541/10000\tloss (train):0.680854\tloss (buffer on valid):0.799150\tbest:0.784449\tTolerance: 50/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 542/10000\tloss (train):0.939507\tloss (buffer on valid):0.797780\tbest:0.784449\tTolerance: 51/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 543/10000\tloss (train):0.742555\tloss (buffer on valid):0.795294\tbest:0.784449\tTolerance: 52/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 544/10000\tloss (train):0.820378\tloss (buffer on valid):0.797249\tbest:0.784449\tTolerance: 53/1000\n", + "Substage:1\tEpoch:41/10000\tIteration: 545/10000\tloss (train):0.645916\tloss (buffer on valid):0.799534\tbest:0.784449\tTolerance: 54/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 546/10000\tloss (train):0.723434\tloss (buffer on valid):0.796011\tbest:0.784449\tTolerance: 55/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 547/10000\tloss (train):0.891943\tloss (buffer on valid):0.796207\tbest:0.784449\tTolerance: 56/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 548/10000\tloss (train):0.892989\tloss (buffer on valid):0.796955\tbest:0.784449\tTolerance: 57/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 549/10000\tloss (train):0.676601\tloss (buffer on valid):0.796423\tbest:0.784449\tTolerance: 58/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 550/10000\tloss (train):0.789835\tloss (buffer on valid):0.796549\tbest:0.784449\tTolerance: 59/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 551/10000\tloss (train):0.713425\tloss (buffer on valid):0.799185\tbest:0.784449\tTolerance: 60/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 552/10000\tloss (train):0.749946\tloss (buffer on valid):0.798561\tbest:0.784449\tTolerance: 61/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 553/10000\tloss (train):0.772120\tloss (buffer on valid):0.798166\tbest:0.784449\tTolerance: 62/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 554/10000\tloss (train):0.691055\tloss (buffer on valid):0.796687\tbest:0.784449\tTolerance: 63/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 555/10000\tloss (train):0.939605\tloss (buffer on valid):0.794475\tbest:0.784449\tTolerance: 64/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 556/10000\tloss (train):0.760554\tloss (buffer on valid):0.791911\tbest:0.784449\tTolerance: 65/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 557/10000\tloss (train):0.829351\tloss (buffer on valid):0.794628\tbest:0.784449\tTolerance: 66/1000\n", + "Substage:1\tEpoch:42/10000\tIteration: 558/10000\tloss (train):0.659405\tloss (buffer on valid):0.797520\tbest:0.784449\tTolerance: 67/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 559/10000\tloss (train):0.725777\tloss (buffer on valid):0.801267\tbest:0.784449\tTolerance: 68/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 560/10000\tloss (train):0.888793\tloss (buffer on valid):0.800094\tbest:0.784449\tTolerance: 69/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 561/10000\tloss (train):0.886136\tloss (buffer on valid):0.802607\tbest:0.784449\tTolerance: 70/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 562/10000\tloss (train):0.686959\tloss (buffer on valid):0.803230\tbest:0.784449\tTolerance: 71/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 563/10000\tloss (train):0.801520\tloss (buffer on valid):0.808608\tbest:0.784449\tTolerance: 72/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 564/10000\tloss (train):0.708415\tloss (buffer on valid):0.809064\tbest:0.784449\tTolerance: 73/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 565/10000\tloss (train):0.745957\tloss (buffer on valid):0.809343\tbest:0.784449\tTolerance: 74/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 566/10000\tloss (train):0.789940\tloss (buffer on valid):0.808872\tbest:0.784449\tTolerance: 75/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 567/10000\tloss (train):0.708035\tloss (buffer on valid):0.807840\tbest:0.784449\tTolerance: 76/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 568/10000\tloss (train):0.951827\tloss (buffer on valid):0.808259\tbest:0.784449\tTolerance: 77/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 569/10000\tloss (train):0.756589\tloss (buffer on valid):0.808876\tbest:0.784449\tTolerance: 78/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 570/10000\tloss (train):0.831002\tloss (buffer on valid):0.811001\tbest:0.784449\tTolerance: 79/1000\n", + "Substage:1\tEpoch:43/10000\tIteration: 571/10000\tloss (train):0.666357\tloss (buffer on valid):0.811507\tbest:0.784449\tTolerance: 80/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 572/10000\tloss (train):0.721980\tloss (buffer on valid):0.808784\tbest:0.784449\tTolerance: 81/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 573/10000\tloss (train):0.886119\tloss (buffer on valid):0.808963\tbest:0.784449\tTolerance: 82/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 574/10000\tloss (train):0.884715\tloss (buffer on valid):0.807537\tbest:0.784449\tTolerance: 83/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 575/10000\tloss (train):0.680887\tloss (buffer on valid):0.811025\tbest:0.784449\tTolerance: 84/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 576/10000\tloss (train):0.810721\tloss (buffer on valid):0.805685\tbest:0.784449\tTolerance: 85/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 577/10000\tloss (train):0.722308\tloss (buffer on valid):0.803817\tbest:0.784449\tTolerance: 86/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 578/10000\tloss (train):0.749863\tloss (buffer on valid):0.804579\tbest:0.784449\tTolerance: 87/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 579/10000\tloss (train):0.794391\tloss (buffer on valid):0.806075\tbest:0.784449\tTolerance: 88/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 580/10000\tloss (train):0.692918\tloss (buffer on valid):0.809435\tbest:0.784449\tTolerance: 89/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 581/10000\tloss (train):0.946894\tloss (buffer on valid):0.808392\tbest:0.784449\tTolerance: 90/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 582/10000\tloss (train):0.756482\tloss (buffer on valid):0.807281\tbest:0.784449\tTolerance: 91/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 583/10000\tloss (train):0.826622\tloss (buffer on valid):0.805832\tbest:0.784449\tTolerance: 92/1000\n", + "Substage:1\tEpoch:44/10000\tIteration: 584/10000\tloss (train):0.662878\tloss (buffer on valid):0.804964\tbest:0.784449\tTolerance: 93/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 585/10000\tloss (train):0.730386\tloss (buffer on valid):0.807699\tbest:0.784449\tTolerance: 94/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 586/10000\tloss (train):0.914690\tloss (buffer on valid):0.812194\tbest:0.784449\tTolerance: 95/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 587/10000\tloss (train):0.892772\tloss (buffer on valid):0.811915\tbest:0.784449\tTolerance: 96/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 588/10000\tloss (train):0.691600\tloss (buffer on valid):0.809438\tbest:0.784449\tTolerance: 97/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 589/10000\tloss (train):0.815786\tloss (buffer on valid):0.805707\tbest:0.784449\tTolerance: 98/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 590/10000\tloss (train):0.761877\tloss (buffer on valid):0.806983\tbest:0.784449\tTolerance: 99/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 591/10000\tloss (train):0.779983\tloss (buffer on valid):0.808763\tbest:0.784449\tTolerance: 100/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 592/10000\tloss (train):0.830399\tloss (buffer on valid):0.808313\tbest:0.784449\tTolerance: 101/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 593/10000\tloss (train):0.725133\tloss (buffer on valid):0.808337\tbest:0.784449\tTolerance: 102/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 594/10000\tloss (train):1.010142\tloss (buffer on valid):0.810790\tbest:0.784449\tTolerance: 103/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 595/10000\tloss (train):0.785372\tloss (buffer on valid):0.808753\tbest:0.784449\tTolerance: 104/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 596/10000\tloss (train):0.874024\tloss (buffer on valid):0.807497\tbest:0.784449\tTolerance: 105/1000\n", + "Substage:1\tEpoch:45/10000\tIteration: 597/10000\tloss (train):0.693337\tloss (buffer on valid):0.806857\tbest:0.784449\tTolerance: 106/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 598/10000\tloss (train):0.777432\tloss (buffer on valid):0.806582\tbest:0.784449\tTolerance: 107/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 599/10000\tloss (train):0.938949\tloss (buffer on valid):0.807316\tbest:0.784449\tTolerance: 108/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 600/10000\tloss (train):0.936691\tloss (buffer on valid):0.810415\tbest:0.784449\tTolerance: 109/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 601/10000\tloss (train):0.714031\tloss (buffer on valid):0.808663\tbest:0.784449\tTolerance: 110/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 602/10000\tloss (train):0.829959\tloss (buffer on valid):0.807904\tbest:0.784449\tTolerance: 111/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 603/10000\tloss (train):0.751807\tloss (buffer on valid):0.811767\tbest:0.784449\tTolerance: 112/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 604/10000\tloss (train):0.772370\tloss (buffer on valid):0.815498\tbest:0.784449\tTolerance: 113/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 605/10000\tloss (train):0.808611\tloss (buffer on valid):0.818624\tbest:0.784449\tTolerance: 114/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 606/10000\tloss (train):0.720774\tloss (buffer on valid):0.821276\tbest:0.784449\tTolerance: 115/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 607/10000\tloss (train):0.986143\tloss (buffer on valid):0.819235\tbest:0.784449\tTolerance: 116/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 608/10000\tloss (train):0.793340\tloss (buffer on valid):0.817062\tbest:0.784449\tTolerance: 117/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 609/10000\tloss (train):0.851922\tloss (buffer on valid):0.813688\tbest:0.784449\tTolerance: 118/1000\n", + "Substage:1\tEpoch:46/10000\tIteration: 610/10000\tloss (train):0.688283\tloss (buffer on valid):0.815754\tbest:0.784449\tTolerance: 119/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 611/10000\tloss (train):0.756362\tloss (buffer on valid):0.815295\tbest:0.784449\tTolerance: 120/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 612/10000\tloss (train):0.914460\tloss (buffer on valid):0.813280\tbest:0.784449\tTolerance: 121/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 613/10000\tloss (train):0.901568\tloss (buffer on valid):0.811540\tbest:0.784449\tTolerance: 122/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 614/10000\tloss (train):0.699557\tloss (buffer on valid):0.811057\tbest:0.784449\tTolerance: 123/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 615/10000\tloss (train):0.805236\tloss (buffer on valid):0.811522\tbest:0.784449\tTolerance: 124/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 616/10000\tloss (train):0.735517\tloss (buffer on valid):0.812545\tbest:0.784449\tTolerance: 125/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 617/10000\tloss (train):0.751048\tloss (buffer on valid):0.816828\tbest:0.784449\tTolerance: 126/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 618/10000\tloss (train):0.788931\tloss (buffer on valid):0.818202\tbest:0.784449\tTolerance: 127/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 619/10000\tloss (train):0.697983\tloss (buffer on valid):0.816490\tbest:0.784449\tTolerance: 128/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 620/10000\tloss (train):0.956353\tloss (buffer on valid):0.814730\tbest:0.784449\tTolerance: 129/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 621/10000\tloss (train):0.766266\tloss (buffer on valid):0.815452\tbest:0.784449\tTolerance: 130/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 622/10000\tloss (train):0.836999\tloss (buffer on valid):0.816438\tbest:0.784449\tTolerance: 131/1000\n", + "Substage:1\tEpoch:47/10000\tIteration: 623/10000\tloss (train):0.662879\tloss (buffer on valid):0.815341\tbest:0.784449\tTolerance: 132/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 624/10000\tloss (train):0.731630\tloss (buffer on valid):0.816708\tbest:0.784449\tTolerance: 133/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 625/10000\tloss (train):0.882008\tloss (buffer on valid):0.815418\tbest:0.784449\tTolerance: 134/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 626/10000\tloss (train):0.887557\tloss (buffer on valid):0.814570\tbest:0.784449\tTolerance: 135/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 627/10000\tloss (train):0.677884\tloss (buffer on valid):0.816118\tbest:0.784449\tTolerance: 136/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 628/10000\tloss (train):0.793307\tloss (buffer on valid):0.815578\tbest:0.784449\tTolerance: 137/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 629/10000\tloss (train):0.716079\tloss (buffer on valid):0.811737\tbest:0.784449\tTolerance: 138/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 630/10000\tloss (train):0.741469\tloss (buffer on valid):0.809103\tbest:0.784449\tTolerance: 139/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 631/10000\tloss (train):0.771231\tloss (buffer on valid):0.806756\tbest:0.784449\tTolerance: 140/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 632/10000\tloss (train):0.688954\tloss (buffer on valid):0.805761\tbest:0.784449\tTolerance: 141/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 633/10000\tloss (train):0.938236\tloss (buffer on valid):0.807263\tbest:0.784449\tTolerance: 142/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 634/10000\tloss (train):0.746855\tloss (buffer on valid):0.808056\tbest:0.784449\tTolerance: 143/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 635/10000\tloss (train):0.819919\tloss (buffer on valid):0.805652\tbest:0.784449\tTolerance: 144/1000\n", + "Substage:1\tEpoch:48/10000\tIteration: 636/10000\tloss (train):0.662229\tloss (buffer on valid):0.804745\tbest:0.784449\tTolerance: 145/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 637/10000\tloss (train):0.732512\tloss (buffer on valid):0.804830\tbest:0.784449\tTolerance: 146/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 638/10000\tloss (train):0.884220\tloss (buffer on valid):0.806354\tbest:0.784449\tTolerance: 147/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 639/10000\tloss (train):0.886369\tloss (buffer on valid):0.806976\tbest:0.784449\tTolerance: 148/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 640/10000\tloss (train):0.685967\tloss (buffer on valid):0.803252\tbest:0.784449\tTolerance: 149/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 641/10000\tloss (train):0.786862\tloss (buffer on valid):0.803979\tbest:0.784449\tTolerance: 150/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 642/10000\tloss (train):0.718256\tloss (buffer on valid):0.801609\tbest:0.784449\tTolerance: 151/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 643/10000\tloss (train):0.735659\tloss (buffer on valid):0.801016\tbest:0.784449\tTolerance: 152/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 644/10000\tloss (train):0.765475\tloss (buffer on valid):0.796613\tbest:0.784449\tTolerance: 153/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 645/10000\tloss (train):0.688122\tloss (buffer on valid):0.794319\tbest:0.784449\tTolerance: 154/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 646/10000\tloss (train):0.947126\tloss (buffer on valid):0.796942\tbest:0.784449\tTolerance: 155/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 647/10000\tloss (train):0.752906\tloss (buffer on valid):0.798604\tbest:0.784449\tTolerance: 156/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 648/10000\tloss (train):0.821063\tloss (buffer on valid):0.797384\tbest:0.784449\tTolerance: 157/1000\n", + "Substage:1\tEpoch:49/10000\tIteration: 649/10000\tloss (train):0.654375\tloss (buffer on valid):0.797190\tbest:0.784449\tTolerance: 158/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 650/10000\tloss (train):0.730694\tloss (buffer on valid):0.794956\tbest:0.784449\tTolerance: 159/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 651/10000\tloss (train):0.874424\tloss (buffer on valid):0.797486\tbest:0.784449\tTolerance: 160/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 652/10000\tloss (train):0.876262\tloss (buffer on valid):0.800204\tbest:0.784449\tTolerance: 161/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 653/10000\tloss (train):0.677557\tloss (buffer on valid):0.795916\tbest:0.784449\tTolerance: 162/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 654/10000\tloss (train):0.790425\tloss (buffer on valid):0.794528\tbest:0.784449\tTolerance: 163/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 655/10000\tloss (train):0.713257\tloss (buffer on valid):0.790514\tbest:0.784449\tTolerance: 164/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 656/10000\tloss (train):0.735699\tloss (buffer on valid):0.786888\tbest:0.784449\tTolerance: 165/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 657/10000\tloss (train):0.763522\tloss (buffer on valid):0.786523\tbest:0.784449\tTolerance: 166/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 658/10000\tloss (train):0.687352\tloss (buffer on valid):0.789417\tbest:0.784449\tTolerance: 167/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 659/10000\tloss (train):0.955362\tloss (buffer on valid):0.791640\tbest:0.784449\tTolerance: 168/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 660/10000\tloss (train):0.754710\tloss (buffer on valid):0.788362\tbest:0.784449\tTolerance: 169/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 661/10000\tloss (train):0.817757\tloss (buffer on valid):0.789055\tbest:0.784449\tTolerance: 170/1000\n", + "Substage:1\tEpoch:50/10000\tIteration: 662/10000\tloss (train):0.649666\tloss (buffer on valid):0.789039\tbest:0.784449\tTolerance: 171/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 663/10000\tloss (train):0.717381\tloss (buffer on valid):0.791220\tbest:0.784449\tTolerance: 172/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 664/10000\tloss (train):0.877199\tloss (buffer on valid):0.791425\tbest:0.784449\tTolerance: 173/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 665/10000\tloss (train):0.868510\tloss (buffer on valid):0.792159\tbest:0.784449\tTolerance: 174/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 666/10000\tloss (train):0.671858\tloss (buffer on valid):0.793374\tbest:0.784449\tTolerance: 175/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 667/10000\tloss (train):0.794130\tloss (buffer on valid):0.789931\tbest:0.784449\tTolerance: 176/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 668/10000\tloss (train):0.722344\tloss (buffer on valid):0.788617\tbest:0.784449\tTolerance: 177/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 669/10000\tloss (train):0.748954\tloss (buffer on valid):0.791242\tbest:0.784449\tTolerance: 178/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 670/10000\tloss (train):0.785448\tloss (buffer on valid):0.793961\tbest:0.784449\tTolerance: 179/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 671/10000\tloss (train):0.699910\tloss (buffer on valid):0.794113\tbest:0.784449\tTolerance: 180/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 672/10000\tloss (train):0.960058\tloss (buffer on valid):0.797908\tbest:0.784449\tTolerance: 181/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 673/10000\tloss (train):0.768849\tloss (buffer on valid):0.800304\tbest:0.784449\tTolerance: 182/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 674/10000\tloss (train):0.833673\tloss (buffer on valid):0.801414\tbest:0.784449\tTolerance: 183/1000\n", + "Substage:1\tEpoch:51/10000\tIteration: 675/10000\tloss (train):0.681895\tloss (buffer on valid):0.799752\tbest:0.784449\tTolerance: 184/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 676/10000\tloss (train):0.741718\tloss (buffer on valid):0.803826\tbest:0.784449\tTolerance: 185/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 677/10000\tloss (train):0.884912\tloss (buffer on valid):0.804248\tbest:0.784449\tTolerance: 186/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 678/10000\tloss (train):0.894297\tloss (buffer on valid):0.805221\tbest:0.784449\tTolerance: 187/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 679/10000\tloss (train):0.696055\tloss (buffer on valid):0.806602\tbest:0.784449\tTolerance: 188/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 680/10000\tloss (train):0.807422\tloss (buffer on valid):0.806309\tbest:0.784449\tTolerance: 189/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 681/10000\tloss (train):0.728626\tloss (buffer on valid):0.806032\tbest:0.784449\tTolerance: 190/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 682/10000\tloss (train):0.752430\tloss (buffer on valid):0.806352\tbest:0.784449\tTolerance: 191/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 683/10000\tloss (train):0.778709\tloss (buffer on valid):0.806124\tbest:0.784449\tTolerance: 192/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 684/10000\tloss (train):0.699498\tloss (buffer on valid):0.808409\tbest:0.784449\tTolerance: 193/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 685/10000\tloss (train):0.934836\tloss (buffer on valid):0.808375\tbest:0.784449\tTolerance: 194/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 686/10000\tloss (train):0.763255\tloss (buffer on valid):0.809918\tbest:0.784449\tTolerance: 195/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 687/10000\tloss (train):0.833659\tloss (buffer on valid):0.809660\tbest:0.784449\tTolerance: 196/1000\n", + "Substage:1\tEpoch:52/10000\tIteration: 688/10000\tloss (train):0.671890\tloss (buffer on valid):0.809498\tbest:0.784449\tTolerance: 197/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 689/10000\tloss (train):0.742974\tloss (buffer on valid):0.810265\tbest:0.784449\tTolerance: 198/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 690/10000\tloss (train):0.879204\tloss (buffer on valid):0.815567\tbest:0.784449\tTolerance: 199/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 691/10000\tloss (train):0.889672\tloss (buffer on valid):0.813283\tbest:0.784449\tTolerance: 200/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 692/10000\tloss (train):0.690908\tloss (buffer on valid):0.814555\tbest:0.784449\tTolerance: 201/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 693/10000\tloss (train):0.798446\tloss (buffer on valid):0.817868\tbest:0.784449\tTolerance: 202/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 694/10000\tloss (train):0.740686\tloss (buffer on valid):0.820476\tbest:0.784449\tTolerance: 203/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 695/10000\tloss (train):0.756808\tloss (buffer on valid):0.825079\tbest:0.784449\tTolerance: 204/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 696/10000\tloss (train):0.785135\tloss (buffer on valid):0.822923\tbest:0.784449\tTolerance: 205/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 697/10000\tloss (train):0.698672\tloss (buffer on valid):0.818963\tbest:0.784449\tTolerance: 206/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 698/10000\tloss (train):0.961189\tloss (buffer on valid):0.819915\tbest:0.784449\tTolerance: 207/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 699/10000\tloss (train):0.764762\tloss (buffer on valid):0.818712\tbest:0.784449\tTolerance: 208/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 700/10000\tloss (train):0.864103\tloss (buffer on valid):0.822976\tbest:0.784449\tTolerance: 209/1000\n", + "Substage:1\tEpoch:53/10000\tIteration: 701/10000\tloss (train):0.668808\tloss (buffer on valid):0.824787\tbest:0.784449\tTolerance: 210/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 702/10000\tloss (train):0.735032\tloss (buffer on valid):0.823441\tbest:0.784449\tTolerance: 211/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 703/10000\tloss (train):0.892917\tloss (buffer on valid):0.825588\tbest:0.784449\tTolerance: 212/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 704/10000\tloss (train):0.891003\tloss (buffer on valid):0.824664\tbest:0.784449\tTolerance: 213/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 705/10000\tloss (train):0.688069\tloss (buffer on valid):0.828467\tbest:0.784449\tTolerance: 214/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 706/10000\tloss (train):0.800554\tloss (buffer on valid):0.829169\tbest:0.784449\tTolerance: 215/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 707/10000\tloss (train):0.735443\tloss (buffer on valid):0.830635\tbest:0.784449\tTolerance: 216/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 708/10000\tloss (train):0.769330\tloss (buffer on valid):0.827541\tbest:0.784449\tTolerance: 217/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 709/10000\tloss (train):0.791482\tloss (buffer on valid):0.827847\tbest:0.784449\tTolerance: 218/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 710/10000\tloss (train):0.711778\tloss (buffer on valid):0.830020\tbest:0.784449\tTolerance: 219/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 711/10000\tloss (train):0.985290\tloss (buffer on valid):0.829938\tbest:0.784449\tTolerance: 220/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 712/10000\tloss (train):0.775226\tloss (buffer on valid):0.832559\tbest:0.784449\tTolerance: 221/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 713/10000\tloss (train):0.844127\tloss (buffer on valid):0.829633\tbest:0.784449\tTolerance: 222/1000\n", + "Substage:1\tEpoch:54/10000\tIteration: 714/10000\tloss (train):0.682949\tloss (buffer on valid):0.833328\tbest:0.784449\tTolerance: 223/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 715/10000\tloss (train):0.759105\tloss (buffer on valid):0.833394\tbest:0.784449\tTolerance: 224/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 716/10000\tloss (train):0.895942\tloss (buffer on valid):0.834659\tbest:0.784449\tTolerance: 225/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 717/10000\tloss (train):0.904031\tloss (buffer on valid):0.832775\tbest:0.784449\tTolerance: 226/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 718/10000\tloss (train):0.708489\tloss (buffer on valid):0.831927\tbest:0.784449\tTolerance: 227/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 719/10000\tloss (train):0.834743\tloss (buffer on valid):0.832884\tbest:0.784449\tTolerance: 228/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 720/10000\tloss (train):0.748778\tloss (buffer on valid):0.832231\tbest:0.784449\tTolerance: 229/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 721/10000\tloss (train):0.762296\tloss (buffer on valid):0.830048\tbest:0.784449\tTolerance: 230/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 722/10000\tloss (train):0.786554\tloss (buffer on valid):0.826268\tbest:0.784449\tTolerance: 231/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 723/10000\tloss (train):0.724238\tloss (buffer on valid):0.826181\tbest:0.784449\tTolerance: 232/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 724/10000\tloss (train):0.953285\tloss (buffer on valid):0.826498\tbest:0.784449\tTolerance: 233/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 725/10000\tloss (train):0.768836\tloss (buffer on valid):0.827357\tbest:0.784449\tTolerance: 234/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 726/10000\tloss (train):0.835651\tloss (buffer on valid):0.826390\tbest:0.784449\tTolerance: 235/1000\n", + "Substage:1\tEpoch:55/10000\tIteration: 727/10000\tloss (train):0.683770\tloss (buffer on valid):0.828022\tbest:0.784449\tTolerance: 236/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 728/10000\tloss (train):0.758613\tloss (buffer on valid):0.828460\tbest:0.784449\tTolerance: 237/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 729/10000\tloss (train):0.888598\tloss (buffer on valid):0.829951\tbest:0.784449\tTolerance: 238/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 730/10000\tloss (train):0.900109\tloss (buffer on valid):0.830098\tbest:0.784449\tTolerance: 239/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 731/10000\tloss (train):0.697566\tloss (buffer on valid):0.829291\tbest:0.784449\tTolerance: 240/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 732/10000\tloss (train):0.804962\tloss (buffer on valid):0.832383\tbest:0.784449\tTolerance: 241/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 733/10000\tloss (train):0.737112\tloss (buffer on valid):0.832504\tbest:0.784449\tTolerance: 242/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 734/10000\tloss (train):0.754466\tloss (buffer on valid):0.831442\tbest:0.784449\tTolerance: 243/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 735/10000\tloss (train):0.777873\tloss (buffer on valid):0.831570\tbest:0.784449\tTolerance: 244/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 736/10000\tloss (train):0.712714\tloss (buffer on valid):0.828775\tbest:0.784449\tTolerance: 245/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 737/10000\tloss (train):0.961299\tloss (buffer on valid):0.828661\tbest:0.784449\tTolerance: 246/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 738/10000\tloss (train):0.771694\tloss (buffer on valid):0.828739\tbest:0.784449\tTolerance: 247/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 739/10000\tloss (train):0.825482\tloss (buffer on valid):0.832830\tbest:0.784449\tTolerance: 248/1000\n", + "Substage:1\tEpoch:56/10000\tIteration: 740/10000\tloss (train):0.674671\tloss (buffer on valid):0.829398\tbest:0.784449\tTolerance: 249/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 741/10000\tloss (train):0.740774\tloss (buffer on valid):0.831091\tbest:0.784449\tTolerance: 250/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 742/10000\tloss (train):0.898608\tloss (buffer on valid):0.828926\tbest:0.784449\tTolerance: 251/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 743/10000\tloss (train):0.902672\tloss (buffer on valid):0.827212\tbest:0.784449\tTolerance: 252/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 744/10000\tloss (train):0.702529\tloss (buffer on valid):0.825404\tbest:0.784449\tTolerance: 253/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 745/10000\tloss (train):0.806910\tloss (buffer on valid):0.824264\tbest:0.784449\tTolerance: 254/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 746/10000\tloss (train):0.733723\tloss (buffer on valid):0.826356\tbest:0.784449\tTolerance: 255/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 747/10000\tloss (train):0.765334\tloss (buffer on valid):0.831634\tbest:0.784449\tTolerance: 256/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 748/10000\tloss (train):0.798090\tloss (buffer on valid):0.833503\tbest:0.784449\tTolerance: 257/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 749/10000\tloss (train):0.708104\tloss (buffer on valid):0.832503\tbest:0.784449\tTolerance: 258/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 750/10000\tloss (train):0.956182\tloss (buffer on valid):0.829001\tbest:0.784449\tTolerance: 259/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 751/10000\tloss (train):0.786886\tloss (buffer on valid):0.825750\tbest:0.784449\tTolerance: 260/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 752/10000\tloss (train):0.841724\tloss (buffer on valid):0.827242\tbest:0.784449\tTolerance: 261/1000\n", + "Substage:1\tEpoch:57/10000\tIteration: 753/10000\tloss (train):0.683998\tloss (buffer on valid):0.827279\tbest:0.784449\tTolerance: 262/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 754/10000\tloss (train):0.761331\tloss (buffer on valid):0.827235\tbest:0.784449\tTolerance: 263/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 755/10000\tloss (train):0.933927\tloss (buffer on valid):0.827510\tbest:0.784449\tTolerance: 264/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 756/10000\tloss (train):0.892872\tloss (buffer on valid):0.829066\tbest:0.784449\tTolerance: 265/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 757/10000\tloss (train):0.710113\tloss (buffer on valid):0.825027\tbest:0.784449\tTolerance: 266/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 758/10000\tloss (train):0.837226\tloss (buffer on valid):0.826789\tbest:0.784449\tTolerance: 267/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 759/10000\tloss (train):0.747137\tloss (buffer on valid):0.826500\tbest:0.784449\tTolerance: 268/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 760/10000\tloss (train):0.758883\tloss (buffer on valid):0.826041\tbest:0.784449\tTolerance: 269/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 761/10000\tloss (train):0.794358\tloss (buffer on valid):0.823262\tbest:0.784449\tTolerance: 270/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 762/10000\tloss (train):0.728968\tloss (buffer on valid):0.826197\tbest:0.784449\tTolerance: 271/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 763/10000\tloss (train):0.971589\tloss (buffer on valid):0.827697\tbest:0.784449\tTolerance: 272/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 764/10000\tloss (train):0.767915\tloss (buffer on valid):0.824959\tbest:0.784449\tTolerance: 273/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 765/10000\tloss (train):0.843352\tloss (buffer on valid):0.825693\tbest:0.784449\tTolerance: 274/1000\n", + "Substage:1\tEpoch:58/10000\tIteration: 766/10000\tloss (train):0.694383\tloss (buffer on valid):0.824237\tbest:0.784449\tTolerance: 275/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 767/10000\tloss (train):0.766548\tloss (buffer on valid):0.826034\tbest:0.784449\tTolerance: 276/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 768/10000\tloss (train):0.884773\tloss (buffer on valid):0.824677\tbest:0.784449\tTolerance: 277/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 769/10000\tloss (train):0.886002\tloss (buffer on valid):0.823848\tbest:0.784449\tTolerance: 278/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 770/10000\tloss (train):0.724316\tloss (buffer on valid):0.824423\tbest:0.784449\tTolerance: 279/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 771/10000\tloss (train):0.834486\tloss (buffer on valid):0.825522\tbest:0.784449\tTolerance: 280/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 772/10000\tloss (train):0.766777\tloss (buffer on valid):0.826445\tbest:0.784449\tTolerance: 281/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 773/10000\tloss (train):0.772342\tloss (buffer on valid):0.826895\tbest:0.784449\tTolerance: 282/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 774/10000\tloss (train):0.799335\tloss (buffer on valid):0.828185\tbest:0.784449\tTolerance: 283/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 775/10000\tloss (train):0.733101\tloss (buffer on valid):0.829438\tbest:0.784449\tTolerance: 284/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 776/10000\tloss (train):0.930832\tloss (buffer on valid):0.827480\tbest:0.784449\tTolerance: 285/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 777/10000\tloss (train):0.769659\tloss (buffer on valid):0.825803\tbest:0.784449\tTolerance: 286/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 778/10000\tloss (train):0.838889\tloss (buffer on valid):0.826656\tbest:0.784449\tTolerance: 287/1000\n", + "Substage:1\tEpoch:59/10000\tIteration: 779/10000\tloss (train):0.706447\tloss (buffer on valid):0.826100\tbest:0.784449\tTolerance: 288/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 780/10000\tloss (train):0.773467\tloss (buffer on valid):0.825745\tbest:0.784449\tTolerance: 289/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 781/10000\tloss (train):0.861876\tloss (buffer on valid):0.828063\tbest:0.784449\tTolerance: 290/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 782/10000\tloss (train):0.901662\tloss (buffer on valid):0.827614\tbest:0.784449\tTolerance: 291/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 783/10000\tloss (train):0.727295\tloss (buffer on valid):0.831285\tbest:0.784449\tTolerance: 292/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 784/10000\tloss (train):0.818311\tloss (buffer on valid):0.831559\tbest:0.784449\tTolerance: 293/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 785/10000\tloss (train):0.762030\tloss (buffer on valid):0.833256\tbest:0.784449\tTolerance: 294/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 786/10000\tloss (train):0.755275\tloss (buffer on valid):0.834442\tbest:0.784449\tTolerance: 295/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 787/10000\tloss (train):0.783273\tloss (buffer on valid):0.835213\tbest:0.784449\tTolerance: 296/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 788/10000\tloss (train):0.724324\tloss (buffer on valid):0.834697\tbest:0.784449\tTolerance: 297/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 789/10000\tloss (train):0.943478\tloss (buffer on valid):0.830932\tbest:0.784449\tTolerance: 298/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 790/10000\tloss (train):0.772880\tloss (buffer on valid):0.832083\tbest:0.784449\tTolerance: 299/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 791/10000\tloss (train):0.829911\tloss (buffer on valid):0.830509\tbest:0.784449\tTolerance: 300/1000\n", + "Substage:1\tEpoch:60/10000\tIteration: 792/10000\tloss (train):0.703270\tloss (buffer on valid):0.832157\tbest:0.784449\tTolerance: 301/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 793/10000\tloss (train):0.766938\tloss (buffer on valid):0.833099\tbest:0.784449\tTolerance: 302/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 794/10000\tloss (train):0.872431\tloss (buffer on valid):0.832519\tbest:0.784449\tTolerance: 303/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 795/10000\tloss (train):0.886161\tloss (buffer on valid):0.833142\tbest:0.784449\tTolerance: 304/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 796/10000\tloss (train):0.719607\tloss (buffer on valid):0.831182\tbest:0.784449\tTolerance: 305/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 797/10000\tloss (train):0.820534\tloss (buffer on valid):0.829178\tbest:0.784449\tTolerance: 306/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 798/10000\tloss (train):0.748352\tloss (buffer on valid):0.827742\tbest:0.784449\tTolerance: 307/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 799/10000\tloss (train):0.757637\tloss (buffer on valid):0.829394\tbest:0.784449\tTolerance: 308/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 800/10000\tloss (train):0.813747\tloss (buffer on valid):0.830061\tbest:0.784449\tTolerance: 309/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 801/10000\tloss (train):0.727261\tloss (buffer on valid):0.831364\tbest:0.784449\tTolerance: 310/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 802/10000\tloss (train):0.959951\tloss (buffer on valid):0.829382\tbest:0.784449\tTolerance: 311/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 803/10000\tloss (train):0.775013\tloss (buffer on valid):0.829820\tbest:0.784449\tTolerance: 312/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 804/10000\tloss (train):0.840936\tloss (buffer on valid):0.831050\tbest:0.784449\tTolerance: 313/1000\n", + "Substage:1\tEpoch:61/10000\tIteration: 805/10000\tloss (train):0.703825\tloss (buffer on valid):0.828760\tbest:0.784449\tTolerance: 314/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 806/10000\tloss (train):0.770650\tloss (buffer on valid):0.827806\tbest:0.784449\tTolerance: 315/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 807/10000\tloss (train):0.898814\tloss (buffer on valid):0.830014\tbest:0.784449\tTolerance: 316/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 808/10000\tloss (train):0.902572\tloss (buffer on valid):0.830707\tbest:0.784449\tTolerance: 317/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 809/10000\tloss (train):0.738578\tloss (buffer on valid):0.829277\tbest:0.784449\tTolerance: 318/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 810/10000\tloss (train):0.827517\tloss (buffer on valid):0.828231\tbest:0.784449\tTolerance: 319/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 811/10000\tloss (train):0.754074\tloss (buffer on valid):0.827396\tbest:0.784449\tTolerance: 320/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 812/10000\tloss (train):0.765396\tloss (buffer on valid):0.824220\tbest:0.784449\tTolerance: 321/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 813/10000\tloss (train):0.797683\tloss (buffer on valid):0.823713\tbest:0.784449\tTolerance: 322/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 814/10000\tloss (train):0.746991\tloss (buffer on valid):0.822045\tbest:0.784449\tTolerance: 323/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 815/10000\tloss (train):0.954115\tloss (buffer on valid):0.822075\tbest:0.784449\tTolerance: 324/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 816/10000\tloss (train):0.769539\tloss (buffer on valid):0.821214\tbest:0.784449\tTolerance: 325/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 817/10000\tloss (train):0.834576\tloss (buffer on valid):0.821966\tbest:0.784449\tTolerance: 326/1000\n", + "Substage:1\tEpoch:62/10000\tIteration: 818/10000\tloss (train):0.716828\tloss (buffer on valid):0.821494\tbest:0.784449\tTolerance: 327/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 819/10000\tloss (train):0.782283\tloss (buffer on valid):0.821432\tbest:0.784449\tTolerance: 328/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 820/10000\tloss (train):0.869483\tloss (buffer on valid):0.820379\tbest:0.784449\tTolerance: 329/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 821/10000\tloss (train):0.915705\tloss (buffer on valid):0.820930\tbest:0.784449\tTolerance: 330/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 822/10000\tloss (train):0.740213\tloss (buffer on valid):0.821467\tbest:0.784449\tTolerance: 331/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 823/10000\tloss (train):0.835481\tloss (buffer on valid):0.821520\tbest:0.784449\tTolerance: 332/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 824/10000\tloss (train):0.771963\tloss (buffer on valid):0.819898\tbest:0.784449\tTolerance: 333/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 825/10000\tloss (train):0.762859\tloss (buffer on valid):0.819462\tbest:0.784449\tTolerance: 334/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 826/10000\tloss (train):0.829943\tloss (buffer on valid):0.820592\tbest:0.784449\tTolerance: 335/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 827/10000\tloss (train):0.749997\tloss (buffer on valid):0.819552\tbest:0.784449\tTolerance: 336/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 828/10000\tloss (train):0.970072\tloss (buffer on valid):0.818032\tbest:0.784449\tTolerance: 337/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 829/10000\tloss (train):0.781527\tloss (buffer on valid):0.816508\tbest:0.784449\tTolerance: 338/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 830/10000\tloss (train):0.854321\tloss (buffer on valid):0.818420\tbest:0.784449\tTolerance: 339/1000\n", + "Substage:1\tEpoch:63/10000\tIteration: 831/10000\tloss (train):0.719246\tloss (buffer on valid):0.817276\tbest:0.784449\tTolerance: 340/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 832/10000\tloss (train):0.789229\tloss (buffer on valid):0.815835\tbest:0.784449\tTolerance: 341/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 833/10000\tloss (train):0.881342\tloss (buffer on valid):0.813176\tbest:0.784449\tTolerance: 342/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 834/10000\tloss (train):0.898939\tloss (buffer on valid):0.813881\tbest:0.784449\tTolerance: 343/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 835/10000\tloss (train):0.737336\tloss (buffer on valid):0.812916\tbest:0.784449\tTolerance: 344/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 836/10000\tloss (train):0.854868\tloss (buffer on valid):0.814353\tbest:0.784449\tTolerance: 345/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 837/10000\tloss (train):0.759695\tloss (buffer on valid):0.812224\tbest:0.784449\tTolerance: 346/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 838/10000\tloss (train):0.763029\tloss (buffer on valid):0.812481\tbest:0.784449\tTolerance: 347/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 839/10000\tloss (train):0.797090\tloss (buffer on valid):0.813305\tbest:0.784449\tTolerance: 348/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 840/10000\tloss (train):0.747553\tloss (buffer on valid):0.812649\tbest:0.784449\tTolerance: 349/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 841/10000\tloss (train):0.989772\tloss (buffer on valid):0.815428\tbest:0.784449\tTolerance: 350/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 842/10000\tloss (train):0.785616\tloss (buffer on valid):0.816370\tbest:0.784449\tTolerance: 351/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 843/10000\tloss (train):0.847817\tloss (buffer on valid):0.815128\tbest:0.784449\tTolerance: 352/1000\n", + "Substage:1\tEpoch:64/10000\tIteration: 844/10000\tloss (train):0.718022\tloss (buffer on valid):0.815738\tbest:0.784449\tTolerance: 353/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 845/10000\tloss (train):0.785183\tloss (buffer on valid):0.813932\tbest:0.784449\tTolerance: 354/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 846/10000\tloss (train):0.892455\tloss (buffer on valid):0.814517\tbest:0.784449\tTolerance: 355/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 847/10000\tloss (train):0.889889\tloss (buffer on valid):0.814146\tbest:0.784449\tTolerance: 356/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 848/10000\tloss (train):0.736143\tloss (buffer on valid):0.812521\tbest:0.784449\tTolerance: 357/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 849/10000\tloss (train):0.831870\tloss (buffer on valid):0.814190\tbest:0.784449\tTolerance: 358/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 850/10000\tloss (train):0.758364\tloss (buffer on valid):0.812837\tbest:0.784449\tTolerance: 359/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 851/10000\tloss (train):0.768113\tloss (buffer on valid):0.812265\tbest:0.784449\tTolerance: 360/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 852/10000\tloss (train):0.790520\tloss (buffer on valid):0.813996\tbest:0.784449\tTolerance: 361/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 853/10000\tloss (train):0.731693\tloss (buffer on valid):0.812654\tbest:0.784449\tTolerance: 362/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 854/10000\tloss (train):0.928373\tloss (buffer on valid):0.811187\tbest:0.784449\tTolerance: 363/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 855/10000\tloss (train):0.782150\tloss (buffer on valid):0.812142\tbest:0.784449\tTolerance: 364/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 856/10000\tloss (train):0.840828\tloss (buffer on valid):0.811423\tbest:0.784449\tTolerance: 365/1000\n", + "Substage:1\tEpoch:65/10000\tIteration: 857/10000\tloss (train):0.708218\tloss (buffer on valid):0.810234\tbest:0.784449\tTolerance: 366/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 858/10000\tloss (train):0.781579\tloss (buffer on valid):0.809608\tbest:0.784449\tTolerance: 367/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 859/10000\tloss (train):0.859633\tloss (buffer on valid):0.811085\tbest:0.784449\tTolerance: 368/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 860/10000\tloss (train):0.897094\tloss (buffer on valid):0.810247\tbest:0.784449\tTolerance: 369/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 861/10000\tloss (train):0.754092\tloss (buffer on valid):0.812936\tbest:0.784449\tTolerance: 370/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 862/10000\tloss (train):0.823203\tloss (buffer on valid):0.812205\tbest:0.784449\tTolerance: 371/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 863/10000\tloss (train):0.751685\tloss (buffer on valid):0.810664\tbest:0.784449\tTolerance: 372/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 864/10000\tloss (train):0.762769\tloss (buffer on valid):0.814054\tbest:0.784449\tTolerance: 373/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 865/10000\tloss (train):0.798370\tloss (buffer on valid):0.813887\tbest:0.784449\tTolerance: 374/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 866/10000\tloss (train):0.750648\tloss (buffer on valid):0.815812\tbest:0.784449\tTolerance: 375/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 867/10000\tloss (train):0.940675\tloss (buffer on valid):0.816642\tbest:0.784449\tTolerance: 376/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 868/10000\tloss (train):0.780766\tloss (buffer on valid):0.817985\tbest:0.784449\tTolerance: 377/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 869/10000\tloss (train):0.886957\tloss (buffer on valid):0.816870\tbest:0.784449\tTolerance: 378/1000\n", + "Substage:1\tEpoch:66/10000\tIteration: 870/10000\tloss (train):0.734640\tloss (buffer on valid):0.816427\tbest:0.784449\tTolerance: 379/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 871/10000\tloss (train):0.799514\tloss (buffer on valid):0.817477\tbest:0.784449\tTolerance: 380/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 872/10000\tloss (train):0.890929\tloss (buffer on valid):0.820659\tbest:0.784449\tTolerance: 381/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 873/10000\tloss (train):0.965179\tloss (buffer on valid):0.818624\tbest:0.784449\tTolerance: 382/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 874/10000\tloss (train):0.745524\tloss (buffer on valid):0.821866\tbest:0.784449\tTolerance: 383/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 875/10000\tloss (train):0.862947\tloss (buffer on valid):0.824274\tbest:0.784449\tTolerance: 384/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 876/10000\tloss (train):0.776866\tloss (buffer on valid):0.823925\tbest:0.784449\tTolerance: 385/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 877/10000\tloss (train):0.793842\tloss (buffer on valid):0.826747\tbest:0.784449\tTolerance: 386/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 878/10000\tloss (train):0.837728\tloss (buffer on valid):0.828973\tbest:0.784449\tTolerance: 387/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 879/10000\tloss (train):0.763246\tloss (buffer on valid):0.829832\tbest:0.784449\tTolerance: 388/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 880/10000\tloss (train):0.955649\tloss (buffer on valid):0.828789\tbest:0.784449\tTolerance: 389/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 881/10000\tloss (train):0.791590\tloss (buffer on valid):0.827513\tbest:0.784449\tTolerance: 390/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 882/10000\tloss (train):0.872620\tloss (buffer on valid):0.829042\tbest:0.784449\tTolerance: 391/1000\n", + "Substage:1\tEpoch:67/10000\tIteration: 883/10000\tloss (train):0.730230\tloss (buffer on valid):0.830617\tbest:0.784449\tTolerance: 392/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 884/10000\tloss (train):0.819144\tloss (buffer on valid):0.831070\tbest:0.784449\tTolerance: 393/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 885/10000\tloss (train):0.908379\tloss (buffer on valid):0.831847\tbest:0.784449\tTolerance: 394/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 886/10000\tloss (train):0.892976\tloss (buffer on valid):0.830106\tbest:0.784449\tTolerance: 395/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 887/10000\tloss (train):0.767975\tloss (buffer on valid):0.832255\tbest:0.784449\tTolerance: 396/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 888/10000\tloss (train):0.866653\tloss (buffer on valid):0.833420\tbest:0.784449\tTolerance: 397/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 889/10000\tloss (train):0.784113\tloss (buffer on valid):0.833958\tbest:0.784449\tTolerance: 398/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 890/10000\tloss (train):0.785891\tloss (buffer on valid):0.834416\tbest:0.784449\tTolerance: 399/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 891/10000\tloss (train):0.809322\tloss (buffer on valid):0.836089\tbest:0.784449\tTolerance: 400/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 892/10000\tloss (train):0.778210\tloss (buffer on valid):0.835764\tbest:0.784449\tTolerance: 401/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 893/10000\tloss (train):0.959625\tloss (buffer on valid):0.836201\tbest:0.784449\tTolerance: 402/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 894/10000\tloss (train):0.809939\tloss (buffer on valid):0.835787\tbest:0.784449\tTolerance: 403/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 895/10000\tloss (train):0.835367\tloss (buffer on valid):0.834979\tbest:0.784449\tTolerance: 404/1000\n", + "Substage:1\tEpoch:68/10000\tIteration: 896/10000\tloss (train):0.733804\tloss (buffer on valid):0.835285\tbest:0.784449\tTolerance: 405/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 897/10000\tloss (train):0.817449\tloss (buffer on valid):0.834028\tbest:0.784449\tTolerance: 406/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 898/10000\tloss (train):0.868949\tloss (buffer on valid):0.836095\tbest:0.784449\tTolerance: 407/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 899/10000\tloss (train):0.894232\tloss (buffer on valid):0.835513\tbest:0.784449\tTolerance: 408/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 900/10000\tloss (train):0.755019\tloss (buffer on valid):0.837348\tbest:0.784449\tTolerance: 409/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 901/10000\tloss (train):0.841152\tloss (buffer on valid):0.838107\tbest:0.784449\tTolerance: 410/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 902/10000\tloss (train):0.780146\tloss (buffer on valid):0.836426\tbest:0.784449\tTolerance: 411/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 903/10000\tloss (train):0.769896\tloss (buffer on valid):0.837695\tbest:0.784449\tTolerance: 412/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 904/10000\tloss (train):0.788502\tloss (buffer on valid):0.838801\tbest:0.784449\tTolerance: 413/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 905/10000\tloss (train):0.763627\tloss (buffer on valid):0.839051\tbest:0.784449\tTolerance: 414/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 906/10000\tloss (train):0.920397\tloss (buffer on valid):0.838691\tbest:0.784449\tTolerance: 415/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 907/10000\tloss (train):0.792150\tloss (buffer on valid):0.840014\tbest:0.784449\tTolerance: 416/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 908/10000\tloss (train):0.825812\tloss (buffer on valid):0.838417\tbest:0.784449\tTolerance: 417/1000\n", + "Substage:1\tEpoch:69/10000\tIteration: 909/10000\tloss (train):0.735436\tloss (buffer on valid):0.838676\tbest:0.784449\tTolerance: 418/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 910/10000\tloss (train):0.809548\tloss (buffer on valid):0.839864\tbest:0.784449\tTolerance: 419/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 911/10000\tloss (train):0.847384\tloss (buffer on valid):0.838184\tbest:0.784449\tTolerance: 420/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 912/10000\tloss (train):0.876785\tloss (buffer on valid):0.839424\tbest:0.784449\tTolerance: 421/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 913/10000\tloss (train):0.758609\tloss (buffer on valid):0.840387\tbest:0.784449\tTolerance: 422/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 914/10000\tloss (train):0.833895\tloss (buffer on valid):0.840009\tbest:0.784449\tTolerance: 423/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 915/10000\tloss (train):0.770652\tloss (buffer on valid):0.839448\tbest:0.784449\tTolerance: 424/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 916/10000\tloss (train):0.787317\tloss (buffer on valid):0.836898\tbest:0.784449\tTolerance: 425/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 917/10000\tloss (train):0.804867\tloss (buffer on valid):0.834992\tbest:0.784449\tTolerance: 426/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 918/10000\tloss (train):0.749862\tloss (buffer on valid):0.833504\tbest:0.784449\tTolerance: 427/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 919/10000\tloss (train):0.945893\tloss (buffer on valid):0.834283\tbest:0.784449\tTolerance: 428/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 920/10000\tloss (train):0.798591\tloss (buffer on valid):0.836201\tbest:0.784449\tTolerance: 429/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 921/10000\tloss (train):0.880793\tloss (buffer on valid):0.834910\tbest:0.784449\tTolerance: 430/1000\n", + "Substage:1\tEpoch:70/10000\tIteration: 922/10000\tloss (train):0.756658\tloss (buffer on valid):0.830154\tbest:0.784449\tTolerance: 431/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 923/10000\tloss (train):0.834777\tloss (buffer on valid):0.832744\tbest:0.784449\tTolerance: 432/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 924/10000\tloss (train):0.872548\tloss (buffer on valid):0.829878\tbest:0.784449\tTolerance: 433/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 925/10000\tloss (train):0.926993\tloss (buffer on valid):0.828671\tbest:0.784449\tTolerance: 434/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 926/10000\tloss (train):0.797157\tloss (buffer on valid):0.829705\tbest:0.784449\tTolerance: 435/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 927/10000\tloss (train):0.874517\tloss (buffer on valid):0.828693\tbest:0.784449\tTolerance: 436/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 928/10000\tloss (train):0.798385\tloss (buffer on valid):0.827855\tbest:0.784449\tTolerance: 437/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 929/10000\tloss (train):0.795403\tloss (buffer on valid):0.826976\tbest:0.784449\tTolerance: 438/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 930/10000\tloss (train):0.827887\tloss (buffer on valid):0.828709\tbest:0.784449\tTolerance: 439/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 931/10000\tloss (train):0.781813\tloss (buffer on valid):0.829904\tbest:0.784449\tTolerance: 440/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 932/10000\tloss (train):0.949899\tloss (buffer on valid):0.829609\tbest:0.784449\tTolerance: 441/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 933/10000\tloss (train):0.806745\tloss (buffer on valid):0.828809\tbest:0.784449\tTolerance: 442/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 934/10000\tloss (train):0.843772\tloss (buffer on valid):0.827611\tbest:0.784449\tTolerance: 443/1000\n", + "Substage:1\tEpoch:71/10000\tIteration: 935/10000\tloss (train):0.758541\tloss (buffer on valid):0.826108\tbest:0.784449\tTolerance: 444/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 936/10000\tloss (train):0.834408\tloss (buffer on valid):0.826220\tbest:0.784449\tTolerance: 445/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 937/10000\tloss (train):0.861610\tloss (buffer on valid):0.825147\tbest:0.784449\tTolerance: 446/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 938/10000\tloss (train):0.900061\tloss (buffer on valid):0.825973\tbest:0.784449\tTolerance: 447/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 939/10000\tloss (train):0.789419\tloss (buffer on valid):0.825386\tbest:0.784449\tTolerance: 448/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 940/10000\tloss (train):0.877310\tloss (buffer on valid):0.826320\tbest:0.784449\tTolerance: 449/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 941/10000\tloss (train):0.784351\tloss (buffer on valid):0.823036\tbest:0.784449\tTolerance: 450/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 942/10000\tloss (train):0.803908\tloss (buffer on valid):0.823585\tbest:0.784449\tTolerance: 451/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 943/10000\tloss (train):0.824086\tloss (buffer on valid):0.824481\tbest:0.784449\tTolerance: 452/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 944/10000\tloss (train):0.785466\tloss (buffer on valid):0.824884\tbest:0.784449\tTolerance: 453/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 945/10000\tloss (train):0.967067\tloss (buffer on valid):0.826204\tbest:0.784449\tTolerance: 454/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 946/10000\tloss (train):0.807146\tloss (buffer on valid):0.827127\tbest:0.784449\tTolerance: 455/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 947/10000\tloss (train):0.857747\tloss (buffer on valid):0.828229\tbest:0.784449\tTolerance: 456/1000\n", + "Substage:1\tEpoch:72/10000\tIteration: 948/10000\tloss (train):0.757620\tloss (buffer on valid):0.829090\tbest:0.784449\tTolerance: 457/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 949/10000\tloss (train):0.830642\tloss (buffer on valid):0.829320\tbest:0.784449\tTolerance: 458/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 950/10000\tloss (train):0.869677\tloss (buffer on valid):0.829151\tbest:0.784449\tTolerance: 459/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 951/10000\tloss (train):0.893127\tloss (buffer on valid):0.830112\tbest:0.784449\tTolerance: 460/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 952/10000\tloss (train):0.801700\tloss (buffer on valid):0.830546\tbest:0.784449\tTolerance: 461/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 953/10000\tloss (train):0.852721\tloss (buffer on valid):0.829411\tbest:0.784449\tTolerance: 462/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 954/10000\tloss (train):0.784137\tloss (buffer on valid):0.830250\tbest:0.784449\tTolerance: 463/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 955/10000\tloss (train):0.794980\tloss (buffer on valid):0.829903\tbest:0.784449\tTolerance: 464/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 956/10000\tloss (train):0.836432\tloss (buffer on valid):0.831077\tbest:0.784449\tTolerance: 465/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 957/10000\tloss (train):0.767445\tloss (buffer on valid):0.831132\tbest:0.784449\tTolerance: 466/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 958/10000\tloss (train):1.002346\tloss (buffer on valid):0.831969\tbest:0.784449\tTolerance: 467/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 959/10000\tloss (train):0.809773\tloss (buffer on valid):0.831963\tbest:0.784449\tTolerance: 468/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 960/10000\tloss (train):0.871575\tloss (buffer on valid):0.831673\tbest:0.784449\tTolerance: 469/1000\n", + "Substage:1\tEpoch:73/10000\tIteration: 961/10000\tloss (train):0.751265\tloss (buffer on valid):0.832035\tbest:0.784449\tTolerance: 470/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 962/10000\tloss (train):0.833098\tloss (buffer on valid):0.832324\tbest:0.784449\tTolerance: 471/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 963/10000\tloss (train):0.870307\tloss (buffer on valid):0.833455\tbest:0.784449\tTolerance: 472/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 964/10000\tloss (train):0.901487\tloss (buffer on valid):0.833079\tbest:0.784449\tTolerance: 473/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 965/10000\tloss (train):0.807106\tloss (buffer on valid):0.834795\tbest:0.784449\tTolerance: 474/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 966/10000\tloss (train):0.874560\tloss (buffer on valid):0.836514\tbest:0.784449\tTolerance: 475/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 967/10000\tloss (train):0.785924\tloss (buffer on valid):0.837723\tbest:0.784449\tTolerance: 476/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 968/10000\tloss (train):0.804693\tloss (buffer on valid):0.838874\tbest:0.784449\tTolerance: 477/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 969/10000\tloss (train):0.842606\tloss (buffer on valid):0.837892\tbest:0.784449\tTolerance: 478/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 970/10000\tloss (train):0.795961\tloss (buffer on valid):0.837054\tbest:0.784449\tTolerance: 479/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 971/10000\tloss (train):0.927603\tloss (buffer on valid):0.838187\tbest:0.784449\tTolerance: 480/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 972/10000\tloss (train):0.816581\tloss (buffer on valid):0.838744\tbest:0.784449\tTolerance: 481/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 973/10000\tloss (train):0.876827\tloss (buffer on valid):0.838120\tbest:0.784449\tTolerance: 482/1000\n", + "Substage:1\tEpoch:74/10000\tIteration: 974/10000\tloss (train):0.786446\tloss (buffer on valid):0.839213\tbest:0.784449\tTolerance: 483/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 975/10000\tloss (train):0.852948\tloss (buffer on valid):0.838889\tbest:0.784449\tTolerance: 484/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 976/10000\tloss (train):0.896091\tloss (buffer on valid):0.839820\tbest:0.784449\tTolerance: 485/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 977/10000\tloss (train):0.940886\tloss (buffer on valid):0.840248\tbest:0.784449\tTolerance: 486/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 978/10000\tloss (train):0.796505\tloss (buffer on valid):0.840546\tbest:0.784449\tTolerance: 487/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 979/10000\tloss (train):0.865244\tloss (buffer on valid):0.842184\tbest:0.784449\tTolerance: 488/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 980/10000\tloss (train):0.805273\tloss (buffer on valid):0.840681\tbest:0.784449\tTolerance: 489/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 981/10000\tloss (train):0.798970\tloss (buffer on valid):0.841475\tbest:0.784449\tTolerance: 490/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 982/10000\tloss (train):0.823366\tloss (buffer on valid):0.842044\tbest:0.784449\tTolerance: 491/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 983/10000\tloss (train):0.788689\tloss (buffer on valid):0.843060\tbest:0.784449\tTolerance: 492/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 984/10000\tloss (train):0.945858\tloss (buffer on valid):0.843355\tbest:0.784449\tTolerance: 493/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 985/10000\tloss (train):0.823817\tloss (buffer on valid):0.843782\tbest:0.784449\tTolerance: 494/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 986/10000\tloss (train):0.859304\tloss (buffer on valid):0.845355\tbest:0.784449\tTolerance: 495/1000\n", + "Substage:1\tEpoch:75/10000\tIteration: 987/10000\tloss (train):0.760794\tloss (buffer on valid):0.845810\tbest:0.784449\tTolerance: 496/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 988/10000\tloss (train):0.826421\tloss (buffer on valid):0.846218\tbest:0.784449\tTolerance: 497/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 989/10000\tloss (train):0.906484\tloss (buffer on valid):0.846700\tbest:0.784449\tTolerance: 498/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 990/10000\tloss (train):0.914605\tloss (buffer on valid):0.844352\tbest:0.784449\tTolerance: 499/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 991/10000\tloss (train):0.806695\tloss (buffer on valid):0.843712\tbest:0.784449\tTolerance: 500/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 992/10000\tloss (train):0.868418\tloss (buffer on valid):0.843124\tbest:0.784449\tTolerance: 501/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 993/10000\tloss (train):0.787025\tloss (buffer on valid):0.841421\tbest:0.784449\tTolerance: 502/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 994/10000\tloss (train):0.791108\tloss (buffer on valid):0.841681\tbest:0.784449\tTolerance: 503/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 995/10000\tloss (train):0.809831\tloss (buffer on valid):0.841396\tbest:0.784449\tTolerance: 504/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 996/10000\tloss (train):0.776458\tloss (buffer on valid):0.840645\tbest:0.784449\tTolerance: 505/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 997/10000\tloss (train):0.986382\tloss (buffer on valid):0.840798\tbest:0.784449\tTolerance: 506/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 998/10000\tloss (train):0.825304\tloss (buffer on valid):0.840870\tbest:0.784449\tTolerance: 507/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 999/10000\tloss (train):0.889316\tloss (buffer on valid):0.840388\tbest:0.784449\tTolerance: 508/1000\n", + "Substage:1\tEpoch:76/10000\tIteration: 1000/10000\tloss (train):0.766671\tloss (buffer on valid):0.839326\tbest:0.784449\tTolerance: 509/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1001/10000\tloss (train):0.843201\tloss (buffer on valid):0.839165\tbest:0.784449\tTolerance: 510/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1002/10000\tloss (train):0.875091\tloss (buffer on valid):0.841130\tbest:0.784449\tTolerance: 511/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1003/10000\tloss (train):0.923379\tloss (buffer on valid):0.841340\tbest:0.784449\tTolerance: 512/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1004/10000\tloss (train):0.790559\tloss (buffer on valid):0.841167\tbest:0.784449\tTolerance: 513/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1005/10000\tloss (train):0.877509\tloss (buffer on valid):0.841459\tbest:0.784449\tTolerance: 514/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1006/10000\tloss (train):0.799938\tloss (buffer on valid):0.842214\tbest:0.784449\tTolerance: 515/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1007/10000\tloss (train):0.801713\tloss (buffer on valid):0.842405\tbest:0.784449\tTolerance: 516/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1008/10000\tloss (train):0.823664\tloss (buffer on valid):0.842278\tbest:0.784449\tTolerance: 517/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1009/10000\tloss (train):0.777001\tloss (buffer on valid):0.842879\tbest:0.784449\tTolerance: 518/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1010/10000\tloss (train):0.940134\tloss (buffer on valid):0.843951\tbest:0.784449\tTolerance: 519/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1011/10000\tloss (train):0.797522\tloss (buffer on valid):0.844029\tbest:0.784449\tTolerance: 520/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1012/10000\tloss (train):0.847808\tloss (buffer on valid):0.843443\tbest:0.784449\tTolerance: 521/1000\n", + "Substage:1\tEpoch:77/10000\tIteration: 1013/10000\tloss (train):0.767241\tloss (buffer on valid):0.842658\tbest:0.784449\tTolerance: 522/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1014/10000\tloss (train):0.822871\tloss (buffer on valid):0.842473\tbest:0.784449\tTolerance: 523/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1015/10000\tloss (train):0.852676\tloss (buffer on valid):0.841115\tbest:0.784449\tTolerance: 524/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1016/10000\tloss (train):0.895221\tloss (buffer on valid):0.840919\tbest:0.784449\tTolerance: 525/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1017/10000\tloss (train):0.803173\tloss (buffer on valid):0.840997\tbest:0.784449\tTolerance: 526/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1018/10000\tloss (train):0.858670\tloss (buffer on valid):0.841041\tbest:0.784449\tTolerance: 527/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1019/10000\tloss (train):0.780928\tloss (buffer on valid):0.840846\tbest:0.784449\tTolerance: 528/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1020/10000\tloss (train):0.775972\tloss (buffer on valid):0.840754\tbest:0.784449\tTolerance: 529/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1021/10000\tloss (train):0.813078\tloss (buffer on valid):0.840509\tbest:0.784449\tTolerance: 530/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1022/10000\tloss (train):0.775077\tloss (buffer on valid):0.840448\tbest:0.784449\tTolerance: 531/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1023/10000\tloss (train):0.960916\tloss (buffer on valid):0.839426\tbest:0.784449\tTolerance: 532/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1024/10000\tloss (train):0.799410\tloss (buffer on valid):0.838925\tbest:0.784449\tTolerance: 533/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1025/10000\tloss (train):0.877661\tloss (buffer on valid):0.837809\tbest:0.784449\tTolerance: 534/1000\n", + "Substage:1\tEpoch:78/10000\tIteration: 1026/10000\tloss (train):0.758303\tloss (buffer on valid):0.837350\tbest:0.784449\tTolerance: 535/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1027/10000\tloss (train):0.826352\tloss (buffer on valid):0.838170\tbest:0.784449\tTolerance: 536/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1028/10000\tloss (train):0.894338\tloss (buffer on valid):0.837470\tbest:0.784449\tTolerance: 537/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1029/10000\tloss (train):0.948207\tloss (buffer on valid):0.837564\tbest:0.784449\tTolerance: 538/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1030/10000\tloss (train):0.808792\tloss (buffer on valid):0.838755\tbest:0.784449\tTolerance: 539/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1031/10000\tloss (train):0.867410\tloss (buffer on valid):0.839102\tbest:0.784449\tTolerance: 540/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1032/10000\tloss (train):0.797724\tloss (buffer on valid):0.839784\tbest:0.784449\tTolerance: 541/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1033/10000\tloss (train):0.816517\tloss (buffer on valid):0.839722\tbest:0.784449\tTolerance: 542/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1034/10000\tloss (train):0.853550\tloss (buffer on valid):0.839282\tbest:0.784449\tTolerance: 543/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1035/10000\tloss (train):0.795384\tloss (buffer on valid):0.839007\tbest:0.784449\tTolerance: 544/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1036/10000\tloss (train):0.945698\tloss (buffer on valid):0.837756\tbest:0.784449\tTolerance: 545/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1037/10000\tloss (train):0.835256\tloss (buffer on valid):0.838223\tbest:0.784449\tTolerance: 546/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1038/10000\tloss (train):0.897039\tloss (buffer on valid):0.837969\tbest:0.784449\tTolerance: 547/1000\n", + "Substage:1\tEpoch:79/10000\tIteration: 1039/10000\tloss (train):0.785335\tloss (buffer on valid):0.838050\tbest:0.784449\tTolerance: 548/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1040/10000\tloss (train):0.846864\tloss (buffer on valid):0.840091\tbest:0.784449\tTolerance: 549/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1041/10000\tloss (train):0.901650\tloss (buffer on valid):0.841742\tbest:0.784449\tTolerance: 550/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1042/10000\tloss (train):0.922254\tloss (buffer on valid):0.841685\tbest:0.784449\tTolerance: 551/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1043/10000\tloss (train):0.809089\tloss (buffer on valid):0.842423\tbest:0.784449\tTolerance: 552/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1044/10000\tloss (train):0.879556\tloss (buffer on valid):0.842581\tbest:0.784449\tTolerance: 553/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1045/10000\tloss (train):0.820700\tloss (buffer on valid):0.843970\tbest:0.784449\tTolerance: 554/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1046/10000\tloss (train):0.818211\tloss (buffer on valid):0.844560\tbest:0.784449\tTolerance: 555/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1047/10000\tloss (train):0.869689\tloss (buffer on valid):0.844760\tbest:0.784449\tTolerance: 556/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1048/10000\tloss (train):0.799769\tloss (buffer on valid):0.844001\tbest:0.784449\tTolerance: 557/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1049/10000\tloss (train):0.994054\tloss (buffer on valid):0.844887\tbest:0.784449\tTolerance: 558/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1050/10000\tloss (train):0.832993\tloss (buffer on valid):0.845936\tbest:0.784449\tTolerance: 559/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1051/10000\tloss (train):0.882117\tloss (buffer on valid):0.844183\tbest:0.784449\tTolerance: 560/1000\n", + "Substage:1\tEpoch:80/10000\tIteration: 1052/10000\tloss (train):0.784619\tloss (buffer on valid):0.844609\tbest:0.784449\tTolerance: 561/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1053/10000\tloss (train):0.861199\tloss (buffer on valid):0.844909\tbest:0.784449\tTolerance: 562/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1054/10000\tloss (train):0.907030\tloss (buffer on valid):0.844335\tbest:0.784449\tTolerance: 563/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1055/10000\tloss (train):0.963913\tloss (buffer on valid):0.844709\tbest:0.784449\tTolerance: 564/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1056/10000\tloss (train):0.819894\tloss (buffer on valid):0.845214\tbest:0.784449\tTolerance: 565/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1057/10000\tloss (train):0.909668\tloss (buffer on valid):0.845678\tbest:0.784449\tTolerance: 566/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1058/10000\tloss (train):0.825269\tloss (buffer on valid):0.846760\tbest:0.784449\tTolerance: 567/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1059/10000\tloss (train):0.815433\tloss (buffer on valid):0.847054\tbest:0.784449\tTolerance: 568/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1060/10000\tloss (train):0.846725\tloss (buffer on valid):0.846174\tbest:0.784449\tTolerance: 569/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1061/10000\tloss (train):0.804113\tloss (buffer on valid):0.846608\tbest:0.784449\tTolerance: 570/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1062/10000\tloss (train):0.974722\tloss (buffer on valid):0.847910\tbest:0.784449\tTolerance: 571/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1063/10000\tloss (train):0.831498\tloss (buffer on valid):0.848185\tbest:0.784449\tTolerance: 572/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1064/10000\tloss (train):0.872962\tloss (buffer on valid):0.848613\tbest:0.784449\tTolerance: 573/1000\n", + "Substage:1\tEpoch:81/10000\tIteration: 1065/10000\tloss (train):0.787181\tloss (buffer on valid):0.849300\tbest:0.784449\tTolerance: 574/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1066/10000\tloss (train):0.847044\tloss (buffer on valid):0.849972\tbest:0.784449\tTolerance: 575/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1067/10000\tloss (train):0.881360\tloss (buffer on valid):0.849287\tbest:0.784449\tTolerance: 576/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1068/10000\tloss (train):0.933309\tloss (buffer on valid):0.850800\tbest:0.784449\tTolerance: 577/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1069/10000\tloss (train):0.819100\tloss (buffer on valid):0.850927\tbest:0.784449\tTolerance: 578/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1070/10000\tloss (train):0.867462\tloss (buffer on valid):0.851518\tbest:0.784449\tTolerance: 579/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1071/10000\tloss (train):0.836690\tloss (buffer on valid):0.852446\tbest:0.784449\tTolerance: 580/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1072/10000\tloss (train):0.830460\tloss (buffer on valid):0.854183\tbest:0.784449\tTolerance: 581/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1073/10000\tloss (train):0.872324\tloss (buffer on valid):0.856366\tbest:0.784449\tTolerance: 582/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1074/10000\tloss (train):0.807945\tloss (buffer on valid):0.856910\tbest:0.784449\tTolerance: 583/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1075/10000\tloss (train):0.981411\tloss (buffer on valid):0.858861\tbest:0.784449\tTolerance: 584/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1076/10000\tloss (train):0.838323\tloss (buffer on valid):0.858282\tbest:0.784449\tTolerance: 585/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1077/10000\tloss (train):0.907520\tloss (buffer on valid):0.857237\tbest:0.784449\tTolerance: 586/1000\n", + "Substage:1\tEpoch:82/10000\tIteration: 1078/10000\tloss (train):0.806474\tloss (buffer on valid):0.859311\tbest:0.784449\tTolerance: 587/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1079/10000\tloss (train):0.873654\tloss (buffer on valid):0.859996\tbest:0.784449\tTolerance: 588/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1080/10000\tloss (train):0.909726\tloss (buffer on valid):0.860656\tbest:0.784449\tTolerance: 589/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1081/10000\tloss (train):0.939602\tloss (buffer on valid):0.861255\tbest:0.784449\tTolerance: 590/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1082/10000\tloss (train):0.833500\tloss (buffer on valid):0.861041\tbest:0.784449\tTolerance: 591/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1083/10000\tloss (train):0.910071\tloss (buffer on valid):0.859704\tbest:0.784449\tTolerance: 592/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1084/10000\tloss (train):0.829377\tloss (buffer on valid):0.861258\tbest:0.784449\tTolerance: 593/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1085/10000\tloss (train):0.818526\tloss (buffer on valid):0.861930\tbest:0.784449\tTolerance: 594/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1086/10000\tloss (train):0.866519\tloss (buffer on valid):0.863608\tbest:0.784449\tTolerance: 595/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1087/10000\tloss (train):0.824804\tloss (buffer on valid):0.864411\tbest:0.784449\tTolerance: 596/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1088/10000\tloss (train):0.987793\tloss (buffer on valid):0.863609\tbest:0.784449\tTolerance: 597/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1089/10000\tloss (train):0.842406\tloss (buffer on valid):0.864241\tbest:0.784449\tTolerance: 598/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1090/10000\tloss (train):0.899109\tloss (buffer on valid):0.863675\tbest:0.784449\tTolerance: 599/1000\n", + "Substage:1\tEpoch:83/10000\tIteration: 1091/10000\tloss (train):0.797777\tloss (buffer on valid):0.864254\tbest:0.784449\tTolerance: 600/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1092/10000\tloss (train):0.872917\tloss (buffer on valid):0.863736\tbest:0.784449\tTolerance: 601/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1093/10000\tloss (train):0.904197\tloss (buffer on valid):0.865123\tbest:0.784449\tTolerance: 602/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1094/10000\tloss (train):0.940810\tloss (buffer on valid):0.866169\tbest:0.784449\tTolerance: 603/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1095/10000\tloss (train):0.813150\tloss (buffer on valid):0.867159\tbest:0.784449\tTolerance: 604/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1096/10000\tloss (train):0.877982\tloss (buffer on valid):0.866781\tbest:0.784449\tTolerance: 605/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1097/10000\tloss (train):0.827193\tloss (buffer on valid):0.865860\tbest:0.784449\tTolerance: 606/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1098/10000\tloss (train):0.826213\tloss (buffer on valid):0.866326\tbest:0.784449\tTolerance: 607/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1099/10000\tloss (train):0.858245\tloss (buffer on valid):0.865611\tbest:0.784449\tTolerance: 608/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1100/10000\tloss (train):0.815867\tloss (buffer on valid):0.864646\tbest:0.784449\tTolerance: 609/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1101/10000\tloss (train):0.951684\tloss (buffer on valid):0.865540\tbest:0.784449\tTolerance: 610/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1102/10000\tloss (train):0.842427\tloss (buffer on valid):0.863432\tbest:0.784449\tTolerance: 611/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1103/10000\tloss (train):0.890134\tloss (buffer on valid):0.862925\tbest:0.784449\tTolerance: 612/1000\n", + "Substage:1\tEpoch:84/10000\tIteration: 1104/10000\tloss (train):0.787951\tloss (buffer on valid):0.865826\tbest:0.784449\tTolerance: 613/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1105/10000\tloss (train):0.867686\tloss (buffer on valid):0.864557\tbest:0.784449\tTolerance: 614/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1106/10000\tloss (train):0.962515\tloss (buffer on valid):0.865107\tbest:0.784449\tTolerance: 615/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1107/10000\tloss (train):0.996777\tloss (buffer on valid):0.866293\tbest:0.784449\tTolerance: 616/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1108/10000\tloss (train):0.821311\tloss (buffer on valid):0.867094\tbest:0.784449\tTolerance: 617/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1109/10000\tloss (train):0.926100\tloss (buffer on valid):0.867124\tbest:0.784449\tTolerance: 618/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1110/10000\tloss (train):0.864529\tloss (buffer on valid):0.867055\tbest:0.784449\tTolerance: 619/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1111/10000\tloss (train):0.817974\tloss (buffer on valid):0.867320\tbest:0.784449\tTolerance: 620/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1112/10000\tloss (train):0.863558\tloss (buffer on valid):0.866620\tbest:0.784449\tTolerance: 621/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1113/10000\tloss (train):0.828568\tloss (buffer on valid):0.866581\tbest:0.784449\tTolerance: 622/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1114/10000\tloss (train):0.981467\tloss (buffer on valid):0.867798\tbest:0.784449\tTolerance: 623/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1115/10000\tloss (train):0.847521\tloss (buffer on valid):0.868078\tbest:0.784449\tTolerance: 624/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1116/10000\tloss (train):0.907313\tloss (buffer on valid):0.868176\tbest:0.784449\tTolerance: 625/1000\n", + "Substage:1\tEpoch:85/10000\tIteration: 1117/10000\tloss (train):0.826034\tloss (buffer on valid):0.869187\tbest:0.784449\tTolerance: 626/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1118/10000\tloss (train):0.884223\tloss (buffer on valid):0.868756\tbest:0.784449\tTolerance: 627/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1119/10000\tloss (train):0.919018\tloss (buffer on valid):0.871036\tbest:0.784449\tTolerance: 628/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1120/10000\tloss (train):0.970328\tloss (buffer on valid):0.870866\tbest:0.784449\tTolerance: 629/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1121/10000\tloss (train):0.859279\tloss (buffer on valid):0.872041\tbest:0.784449\tTolerance: 630/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1122/10000\tloss (train):0.914268\tloss (buffer on valid):0.871973\tbest:0.784449\tTolerance: 631/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1123/10000\tloss (train):0.857733\tloss (buffer on valid):0.871796\tbest:0.784449\tTolerance: 632/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1124/10000\tloss (train):0.851371\tloss (buffer on valid):0.872384\tbest:0.784449\tTolerance: 633/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1125/10000\tloss (train):0.887637\tloss (buffer on valid):0.872807\tbest:0.784449\tTolerance: 634/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1126/10000\tloss (train):0.837719\tloss (buffer on valid):0.873719\tbest:0.784449\tTolerance: 635/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1127/10000\tloss (train):1.019802\tloss (buffer on valid):0.873393\tbest:0.784449\tTolerance: 636/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1128/10000\tloss (train):0.860400\tloss (buffer on valid):0.873137\tbest:0.784449\tTolerance: 637/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1129/10000\tloss (train):0.904070\tloss (buffer on valid):0.873503\tbest:0.784449\tTolerance: 638/1000\n", + "Substage:1\tEpoch:86/10000\tIteration: 1130/10000\tloss (train):0.830611\tloss (buffer on valid):0.872535\tbest:0.784449\tTolerance: 639/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1131/10000\tloss (train):0.883306\tloss (buffer on valid):0.873690\tbest:0.784449\tTolerance: 640/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1132/10000\tloss (train):0.913981\tloss (buffer on valid):0.873507\tbest:0.784449\tTolerance: 641/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1133/10000\tloss (train):0.956977\tloss (buffer on valid):0.874534\tbest:0.784449\tTolerance: 642/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1134/10000\tloss (train):0.837535\tloss (buffer on valid):0.873916\tbest:0.784449\tTolerance: 643/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1135/10000\tloss (train):0.904214\tloss (buffer on valid):0.875187\tbest:0.784449\tTolerance: 644/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1136/10000\tloss (train):0.865588\tloss (buffer on valid):0.875045\tbest:0.784449\tTolerance: 645/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1137/10000\tloss (train):0.838501\tloss (buffer on valid):0.875765\tbest:0.784449\tTolerance: 646/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1138/10000\tloss (train):0.876736\tloss (buffer on valid):0.876685\tbest:0.784449\tTolerance: 647/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1139/10000\tloss (train):0.847116\tloss (buffer on valid):0.877102\tbest:0.784449\tTolerance: 648/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1140/10000\tloss (train):0.978605\tloss (buffer on valid):0.877406\tbest:0.784449\tTolerance: 649/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1141/10000\tloss (train):0.832564\tloss (buffer on valid):0.877796\tbest:0.784449\tTolerance: 650/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1142/10000\tloss (train):0.865116\tloss (buffer on valid):0.878200\tbest:0.784449\tTolerance: 651/1000\n", + "Substage:1\tEpoch:87/10000\tIteration: 1143/10000\tloss (train):0.807815\tloss (buffer on valid):0.877089\tbest:0.784449\tTolerance: 652/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1144/10000\tloss (train):0.887980\tloss (buffer on valid):0.876928\tbest:0.784449\tTolerance: 653/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1145/10000\tloss (train):0.908662\tloss (buffer on valid):0.874546\tbest:0.784449\tTolerance: 654/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1146/10000\tloss (train):0.935601\tloss (buffer on valid):0.875562\tbest:0.784449\tTolerance: 655/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1147/10000\tloss (train):0.819387\tloss (buffer on valid):0.877444\tbest:0.784449\tTolerance: 656/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1148/10000\tloss (train):0.894482\tloss (buffer on valid):0.877094\tbest:0.784449\tTolerance: 657/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1149/10000\tloss (train):0.816981\tloss (buffer on valid):0.876659\tbest:0.784449\tTolerance: 658/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1150/10000\tloss (train):0.809541\tloss (buffer on valid):0.878183\tbest:0.784449\tTolerance: 659/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1151/10000\tloss (train):0.842349\tloss (buffer on valid):0.878151\tbest:0.784449\tTolerance: 660/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1152/10000\tloss (train):0.807525\tloss (buffer on valid):0.878240\tbest:0.784449\tTolerance: 661/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1153/10000\tloss (train):0.968675\tloss (buffer on valid):0.879617\tbest:0.784449\tTolerance: 662/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1154/10000\tloss (train):0.850567\tloss (buffer on valid):0.877456\tbest:0.784449\tTolerance: 663/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1155/10000\tloss (train):0.878888\tloss (buffer on valid):0.879671\tbest:0.784449\tTolerance: 664/1000\n", + "Substage:1\tEpoch:88/10000\tIteration: 1156/10000\tloss (train):0.803290\tloss (buffer on valid):0.880981\tbest:0.784449\tTolerance: 665/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1157/10000\tloss (train):0.870839\tloss (buffer on valid):0.883514\tbest:0.784449\tTolerance: 666/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1158/10000\tloss (train):0.903598\tloss (buffer on valid):0.883039\tbest:0.784449\tTolerance: 667/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1159/10000\tloss (train):1.086986\tloss (buffer on valid):0.883995\tbest:0.784449\tTolerance: 668/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1160/10000\tloss (train):0.886715\tloss (buffer on valid):0.887561\tbest:0.784449\tTolerance: 669/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1161/10000\tloss (train):0.915326\tloss (buffer on valid):0.889210\tbest:0.784449\tTolerance: 670/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1162/10000\tloss (train):0.937443\tloss (buffer on valid):0.890960\tbest:0.784449\tTolerance: 671/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1163/10000\tloss (train):0.951947\tloss (buffer on valid):0.892721\tbest:0.784449\tTolerance: 672/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1164/10000\tloss (train):1.008300\tloss (buffer on valid):0.893685\tbest:0.784449\tTolerance: 673/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1165/10000\tloss (train):0.895822\tloss (buffer on valid):0.894783\tbest:0.784449\tTolerance: 674/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1166/10000\tloss (train):1.109288\tloss (buffer on valid):0.897157\tbest:0.784449\tTolerance: 675/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1167/10000\tloss (train):0.975490\tloss (buffer on valid):0.899620\tbest:0.784449\tTolerance: 676/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1168/10000\tloss (train):1.048725\tloss (buffer on valid):0.901975\tbest:0.784449\tTolerance: 677/1000\n", + "Substage:1\tEpoch:89/10000\tIteration: 1169/10000\tloss (train):0.895579\tloss (buffer on valid):0.903454\tbest:0.784449\tTolerance: 678/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1170/10000\tloss (train):0.975317\tloss (buffer on valid):0.905816\tbest:0.784449\tTolerance: 679/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1171/10000\tloss (train):1.036638\tloss (buffer on valid):0.906886\tbest:0.784449\tTolerance: 680/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1172/10000\tloss (train):1.060367\tloss (buffer on valid):0.909021\tbest:0.784449\tTolerance: 681/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1173/10000\tloss (train):0.906437\tloss (buffer on valid):0.912003\tbest:0.784449\tTolerance: 682/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1174/10000\tloss (train):0.994409\tloss (buffer on valid):0.912928\tbest:0.784449\tTolerance: 683/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1175/10000\tloss (train):0.906977\tloss (buffer on valid):0.913037\tbest:0.784449\tTolerance: 684/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1176/10000\tloss (train):0.905285\tloss (buffer on valid):0.913520\tbest:0.784449\tTolerance: 685/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1177/10000\tloss (train):0.926942\tloss (buffer on valid):0.916404\tbest:0.784449\tTolerance: 686/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1178/10000\tloss (train):0.888806\tloss (buffer on valid):0.916852\tbest:0.784449\tTolerance: 687/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1179/10000\tloss (train):1.027866\tloss (buffer on valid):0.916915\tbest:0.784449\tTolerance: 688/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1180/10000\tloss (train):0.908600\tloss (buffer on valid):0.918566\tbest:0.784449\tTolerance: 689/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1181/10000\tloss (train):0.952069\tloss (buffer on valid):0.918362\tbest:0.784449\tTolerance: 690/1000\n", + "Substage:1\tEpoch:90/10000\tIteration: 1182/10000\tloss (train):0.865296\tloss (buffer on valid):0.918332\tbest:0.784449\tTolerance: 691/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1183/10000\tloss (train):0.928870\tloss (buffer on valid):0.919042\tbest:0.784449\tTolerance: 692/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1184/10000\tloss (train):0.943811\tloss (buffer on valid):0.919048\tbest:0.784449\tTolerance: 693/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1185/10000\tloss (train):0.968495\tloss (buffer on valid):0.918515\tbest:0.784449\tTolerance: 694/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1186/10000\tloss (train):0.865644\tloss (buffer on valid):0.919172\tbest:0.784449\tTolerance: 695/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1187/10000\tloss (train):0.945703\tloss (buffer on valid):0.919415\tbest:0.784449\tTolerance: 696/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1188/10000\tloss (train):0.868286\tloss (buffer on valid):0.919822\tbest:0.784449\tTolerance: 697/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1189/10000\tloss (train):0.858255\tloss (buffer on valid):0.919236\tbest:0.784449\tTolerance: 698/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1190/10000\tloss (train):0.890849\tloss (buffer on valid):0.920020\tbest:0.784449\tTolerance: 699/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1191/10000\tloss (train):0.855915\tloss (buffer on valid):0.919779\tbest:0.784449\tTolerance: 700/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1192/10000\tloss (train):0.993798\tloss (buffer on valid):0.921288\tbest:0.784449\tTolerance: 701/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1193/10000\tloss (train):0.874601\tloss (buffer on valid):0.921768\tbest:0.784449\tTolerance: 702/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1194/10000\tloss (train):0.916417\tloss (buffer on valid):0.922282\tbest:0.784449\tTolerance: 703/1000\n", + "Substage:1\tEpoch:91/10000\tIteration: 1195/10000\tloss (train):0.833926\tloss (buffer on valid):0.924060\tbest:0.784449\tTolerance: 704/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1196/10000\tloss (train):0.905107\tloss (buffer on valid):0.924907\tbest:0.784449\tTolerance: 705/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1197/10000\tloss (train):0.946856\tloss (buffer on valid):0.924094\tbest:0.784449\tTolerance: 706/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1198/10000\tloss (train):0.959024\tloss (buffer on valid):0.924989\tbest:0.784449\tTolerance: 707/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1199/10000\tloss (train):0.839737\tloss (buffer on valid):0.926228\tbest:0.784449\tTolerance: 708/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1200/10000\tloss (train):0.908299\tloss (buffer on valid):0.926284\tbest:0.784449\tTolerance: 709/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1201/10000\tloss (train):0.855663\tloss (buffer on valid):0.926624\tbest:0.784449\tTolerance: 710/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1202/10000\tloss (train):0.853530\tloss (buffer on valid):0.928710\tbest:0.784449\tTolerance: 711/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1203/10000\tloss (train):0.866023\tloss (buffer on valid):0.928140\tbest:0.784449\tTolerance: 712/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1204/10000\tloss (train):0.840259\tloss (buffer on valid):0.927946\tbest:0.784449\tTolerance: 713/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1205/10000\tloss (train):1.027728\tloss (buffer on valid):0.927545\tbest:0.784449\tTolerance: 714/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1206/10000\tloss (train):0.847900\tloss (buffer on valid):0.926728\tbest:0.784449\tTolerance: 715/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1207/10000\tloss (train):0.903914\tloss (buffer on valid):0.922770\tbest:0.784449\tTolerance: 716/1000\n", + "Substage:1\tEpoch:92/10000\tIteration: 1208/10000\tloss (train):0.815219\tloss (buffer on valid):0.923251\tbest:0.784449\tTolerance: 717/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1209/10000\tloss (train):0.882330\tloss (buffer on valid):0.922646\tbest:0.784449\tTolerance: 718/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1210/10000\tloss (train):0.927018\tloss (buffer on valid):0.919951\tbest:0.784449\tTolerance: 719/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1211/10000\tloss (train):0.940138\tloss (buffer on valid):0.918141\tbest:0.784449\tTolerance: 720/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1212/10000\tloss (train):0.824831\tloss (buffer on valid):0.916688\tbest:0.784449\tTolerance: 721/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1213/10000\tloss (train):0.909474\tloss (buffer on valid):0.916964\tbest:0.784449\tTolerance: 722/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1214/10000\tloss (train):0.883461\tloss (buffer on valid):0.915736\tbest:0.784449\tTolerance: 723/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1215/10000\tloss (train):0.830479\tloss (buffer on valid):0.914912\tbest:0.784449\tTolerance: 724/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1216/10000\tloss (train):0.858407\tloss (buffer on valid):0.913692\tbest:0.784449\tTolerance: 725/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1217/10000\tloss (train):0.824805\tloss (buffer on valid):0.910320\tbest:0.784449\tTolerance: 726/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1218/10000\tloss (train):0.979461\tloss (buffer on valid):0.907976\tbest:0.784449\tTolerance: 727/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1219/10000\tloss (train):0.854275\tloss (buffer on valid):0.906017\tbest:0.784449\tTolerance: 728/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1220/10000\tloss (train):0.891672\tloss (buffer on valid):0.904066\tbest:0.784449\tTolerance: 729/1000\n", + "Substage:1\tEpoch:93/10000\tIteration: 1221/10000\tloss (train):0.803495\tloss (buffer on valid):0.901829\tbest:0.784449\tTolerance: 730/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1222/10000\tloss (train):0.877822\tloss (buffer on valid):0.899685\tbest:0.784449\tTolerance: 731/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1223/10000\tloss (train):0.906712\tloss (buffer on valid):0.896302\tbest:0.784449\tTolerance: 732/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1224/10000\tloss (train):0.929779\tloss (buffer on valid):0.895752\tbest:0.784449\tTolerance: 733/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1225/10000\tloss (train):0.850646\tloss (buffer on valid):0.893972\tbest:0.784449\tTolerance: 734/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1226/10000\tloss (train):0.900377\tloss (buffer on valid):0.893149\tbest:0.784449\tTolerance: 735/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1227/10000\tloss (train):0.859282\tloss (buffer on valid):0.890796\tbest:0.784449\tTolerance: 736/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1228/10000\tloss (train):0.844663\tloss (buffer on valid):0.890346\tbest:0.784449\tTolerance: 737/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1229/10000\tloss (train):0.855152\tloss (buffer on valid):0.891046\tbest:0.784449\tTolerance: 738/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1230/10000\tloss (train):0.832748\tloss (buffer on valid):0.889381\tbest:0.784449\tTolerance: 739/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1231/10000\tloss (train):1.031108\tloss (buffer on valid):0.888679\tbest:0.784449\tTolerance: 740/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1232/10000\tloss (train):0.853740\tloss (buffer on valid):0.888028\tbest:0.784449\tTolerance: 741/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1233/10000\tloss (train):0.909604\tloss (buffer on valid):0.888916\tbest:0.784449\tTolerance: 742/1000\n", + "Substage:1\tEpoch:94/10000\tIteration: 1234/10000\tloss (train):0.811863\tloss (buffer on valid):0.888846\tbest:0.784449\tTolerance: 743/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1235/10000\tloss (train):0.890810\tloss (buffer on valid):0.889256\tbest:0.784449\tTolerance: 744/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1236/10000\tloss (train):0.917847\tloss (buffer on valid):0.887819\tbest:0.784449\tTolerance: 745/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1237/10000\tloss (train):0.952521\tloss (buffer on valid):0.887547\tbest:0.784449\tTolerance: 746/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1238/10000\tloss (train):0.831649\tloss (buffer on valid):0.886932\tbest:0.784449\tTolerance: 747/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1239/10000\tloss (train):0.911442\tloss (buffer on valid):0.887028\tbest:0.784449\tTolerance: 748/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1240/10000\tloss (train):0.838211\tloss (buffer on valid):0.886282\tbest:0.784449\tTolerance: 749/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1241/10000\tloss (train):0.838224\tloss (buffer on valid):0.887001\tbest:0.784449\tTolerance: 750/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1242/10000\tloss (train):0.869288\tloss (buffer on valid):0.886454\tbest:0.784449\tTolerance: 751/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1243/10000\tloss (train):0.829717\tloss (buffer on valid):0.886162\tbest:0.784449\tTolerance: 752/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1244/10000\tloss (train):0.969535\tloss (buffer on valid):0.885926\tbest:0.784449\tTolerance: 753/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1245/10000\tloss (train):0.854525\tloss (buffer on valid):0.885117\tbest:0.784449\tTolerance: 754/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1246/10000\tloss (train):0.892302\tloss (buffer on valid):0.883908\tbest:0.784449\tTolerance: 755/1000\n", + "Substage:1\tEpoch:95/10000\tIteration: 1247/10000\tloss (train):0.808951\tloss (buffer on valid):0.884546\tbest:0.784449\tTolerance: 756/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1248/10000\tloss (train):0.879175\tloss (buffer on valid):0.886026\tbest:0.784449\tTolerance: 757/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1249/10000\tloss (train):0.977684\tloss (buffer on valid):0.886829\tbest:0.784449\tTolerance: 758/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1250/10000\tloss (train):0.979574\tloss (buffer on valid):0.886380\tbest:0.784449\tTolerance: 759/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1251/10000\tloss (train):0.826092\tloss (buffer on valid):0.887478\tbest:0.784449\tTolerance: 760/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1252/10000\tloss (train):0.946189\tloss (buffer on valid):0.886255\tbest:0.784449\tTolerance: 761/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1253/10000\tloss (train):0.839934\tloss (buffer on valid):0.887118\tbest:0.784449\tTolerance: 762/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1254/10000\tloss (train):0.850482\tloss (buffer on valid):0.886687\tbest:0.784449\tTolerance: 763/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1255/10000\tloss (train):0.867726\tloss (buffer on valid):0.886362\tbest:0.784449\tTolerance: 764/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1256/10000\tloss (train):0.837259\tloss (buffer on valid):0.885020\tbest:0.784449\tTolerance: 765/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1257/10000\tloss (train):0.992973\tloss (buffer on valid):0.885311\tbest:0.784449\tTolerance: 766/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1258/10000\tloss (train):0.866939\tloss (buffer on valid):0.884588\tbest:0.784449\tTolerance: 767/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1259/10000\tloss (train):0.904138\tloss (buffer on valid):0.884716\tbest:0.784449\tTolerance: 768/1000\n", + "Substage:1\tEpoch:96/10000\tIteration: 1260/10000\tloss (train):0.815018\tloss (buffer on valid):0.885802\tbest:0.784449\tTolerance: 769/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1261/10000\tloss (train):0.873996\tloss (buffer on valid):0.885859\tbest:0.784449\tTolerance: 770/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1262/10000\tloss (train):0.958251\tloss (buffer on valid):0.888215\tbest:0.784449\tTolerance: 771/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1263/10000\tloss (train):0.966779\tloss (buffer on valid):0.887871\tbest:0.784449\tTolerance: 772/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1264/10000\tloss (train):0.866670\tloss (buffer on valid):0.887352\tbest:0.784449\tTolerance: 773/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1265/10000\tloss (train):0.918075\tloss (buffer on valid):0.886925\tbest:0.784449\tTolerance: 774/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1266/10000\tloss (train):0.832660\tloss (buffer on valid):0.885734\tbest:0.784449\tTolerance: 775/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1267/10000\tloss (train):0.849299\tloss (buffer on valid):0.887199\tbest:0.784449\tTolerance: 776/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1268/10000\tloss (train):0.865631\tloss (buffer on valid):0.888647\tbest:0.784449\tTolerance: 777/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1269/10000\tloss (train):0.837504\tloss (buffer on valid):0.888431\tbest:0.784449\tTolerance: 778/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1270/10000\tloss (train):1.022436\tloss (buffer on valid):0.887155\tbest:0.784449\tTolerance: 779/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1271/10000\tloss (train):0.860665\tloss (buffer on valid):0.887261\tbest:0.784449\tTolerance: 780/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1272/10000\tloss (train):0.935828\tloss (buffer on valid):0.887391\tbest:0.784449\tTolerance: 781/1000\n", + "Substage:1\tEpoch:97/10000\tIteration: 1273/10000\tloss (train):0.817241\tloss (buffer on valid):0.887525\tbest:0.784449\tTolerance: 782/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1274/10000\tloss (train):0.895098\tloss (buffer on valid):0.887158\tbest:0.784449\tTolerance: 783/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1275/10000\tloss (train):0.910645\tloss (buffer on valid):0.888261\tbest:0.784449\tTolerance: 784/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1276/10000\tloss (train):0.952032\tloss (buffer on valid):0.889520\tbest:0.784449\tTolerance: 785/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1277/10000\tloss (train):0.857022\tloss (buffer on valid):0.889941\tbest:0.784449\tTolerance: 786/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1278/10000\tloss (train):0.926105\tloss (buffer on valid):0.890461\tbest:0.784449\tTolerance: 787/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1279/10000\tloss (train):0.851966\tloss (buffer on valid):0.890616\tbest:0.784449\tTolerance: 788/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1280/10000\tloss (train):0.854059\tloss (buffer on valid):0.890565\tbest:0.784449\tTolerance: 789/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1281/10000\tloss (train):0.899506\tloss (buffer on valid):0.890445\tbest:0.784449\tTolerance: 790/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1282/10000\tloss (train):0.853633\tloss (buffer on valid):0.892055\tbest:0.784449\tTolerance: 791/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1283/10000\tloss (train):1.068571\tloss (buffer on valid):0.891326\tbest:0.784449\tTolerance: 792/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1284/10000\tloss (train):0.888073\tloss (buffer on valid):0.892058\tbest:0.784449\tTolerance: 793/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1285/10000\tloss (train):0.943308\tloss (buffer on valid):0.892725\tbest:0.784449\tTolerance: 794/1000\n", + "Substage:1\tEpoch:98/10000\tIteration: 1286/10000\tloss (train):0.823065\tloss (buffer on valid):0.892573\tbest:0.784449\tTolerance: 795/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1287/10000\tloss (train):0.904624\tloss (buffer on valid):0.892786\tbest:0.784449\tTolerance: 796/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1288/10000\tloss (train):0.937532\tloss (buffer on valid):0.892961\tbest:0.784449\tTolerance: 797/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1289/10000\tloss (train):0.968110\tloss (buffer on valid):0.893352\tbest:0.784449\tTolerance: 798/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1290/10000\tloss (train):0.851894\tloss (buffer on valid):0.894363\tbest:0.784449\tTolerance: 799/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1291/10000\tloss (train):0.922003\tloss (buffer on valid):0.893696\tbest:0.784449\tTolerance: 800/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1292/10000\tloss (train):0.874356\tloss (buffer on valid):0.895413\tbest:0.784449\tTolerance: 801/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1293/10000\tloss (train):0.848627\tloss (buffer on valid):0.896592\tbest:0.784449\tTolerance: 802/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1294/10000\tloss (train):0.877806\tloss (buffer on valid):0.896155\tbest:0.784449\tTolerance: 803/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1295/10000\tloss (train):0.841168\tloss (buffer on valid):0.896392\tbest:0.784449\tTolerance: 804/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1296/10000\tloss (train):1.026965\tloss (buffer on valid):0.896113\tbest:0.784449\tTolerance: 805/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1297/10000\tloss (train):0.864039\tloss (buffer on valid):0.895070\tbest:0.784449\tTolerance: 806/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1298/10000\tloss (train):0.935305\tloss (buffer on valid):0.893144\tbest:0.784449\tTolerance: 807/1000\n", + "Substage:1\tEpoch:99/10000\tIteration: 1299/10000\tloss (train):0.816382\tloss (buffer on valid):0.892489\tbest:0.784449\tTolerance: 808/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1300/10000\tloss (train):0.870293\tloss (buffer on valid):0.892555\tbest:0.784449\tTolerance: 809/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1301/10000\tloss (train):0.902757\tloss (buffer on valid):0.892728\tbest:0.784449\tTolerance: 810/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1302/10000\tloss (train):0.965335\tloss (buffer on valid):0.893502\tbest:0.784449\tTolerance: 811/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1303/10000\tloss (train):0.874944\tloss (buffer on valid):0.893336\tbest:0.784449\tTolerance: 812/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1304/10000\tloss (train):0.928396\tloss (buffer on valid):0.894610\tbest:0.784449\tTolerance: 813/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1305/10000\tloss (train):0.851601\tloss (buffer on valid):0.894952\tbest:0.784449\tTolerance: 814/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1306/10000\tloss (train):0.866461\tloss (buffer on valid):0.894865\tbest:0.784449\tTolerance: 815/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1307/10000\tloss (train):0.888306\tloss (buffer on valid):0.895667\tbest:0.784449\tTolerance: 816/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1308/10000\tloss (train):0.842950\tloss (buffer on valid):0.895272\tbest:0.784449\tTolerance: 817/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1309/10000\tloss (train):0.990680\tloss (buffer on valid):0.895156\tbest:0.784449\tTolerance: 818/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1310/10000\tloss (train):0.880669\tloss (buffer on valid):0.895989\tbest:0.784449\tTolerance: 819/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1311/10000\tloss (train):0.921732\tloss (buffer on valid):0.897323\tbest:0.784449\tTolerance: 820/1000\n", + "Substage:1\tEpoch:100/10000\tIteration: 1312/10000\tloss (train):0.821844\tloss (buffer on valid):0.895687\tbest:0.784449\tTolerance: 821/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1313/10000\tloss (train):0.884534\tloss (buffer on valid):0.895331\tbest:0.784449\tTolerance: 822/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1314/10000\tloss (train):0.930167\tloss (buffer on valid):0.897260\tbest:0.784449\tTolerance: 823/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1315/10000\tloss (train):0.973902\tloss (buffer on valid):0.898212\tbest:0.784449\tTolerance: 824/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1316/10000\tloss (train):0.863823\tloss (buffer on valid):0.898512\tbest:0.784449\tTolerance: 825/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1317/10000\tloss (train):0.917279\tloss (buffer on valid):0.898420\tbest:0.784449\tTolerance: 826/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1318/10000\tloss (train):0.870005\tloss (buffer on valid):0.897488\tbest:0.784449\tTolerance: 827/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1319/10000\tloss (train):0.847954\tloss (buffer on valid):0.897542\tbest:0.784449\tTolerance: 828/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1320/10000\tloss (train):0.891584\tloss (buffer on valid):0.898340\tbest:0.784449\tTolerance: 829/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1321/10000\tloss (train):0.854259\tloss (buffer on valid):0.898682\tbest:0.784449\tTolerance: 830/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1322/10000\tloss (train):1.028626\tloss (buffer on valid):0.899201\tbest:0.784449\tTolerance: 831/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1323/10000\tloss (train):0.867465\tloss (buffer on valid):0.899297\tbest:0.784449\tTolerance: 832/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1324/10000\tloss (train):0.916968\tloss (buffer on valid):0.899315\tbest:0.784449\tTolerance: 833/1000\n", + "Substage:1\tEpoch:101/10000\tIteration: 1325/10000\tloss (train):0.843183\tloss (buffer on valid):0.898669\tbest:0.784449\tTolerance: 834/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1326/10000\tloss (train):0.898901\tloss (buffer on valid):0.898273\tbest:0.784449\tTolerance: 835/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1327/10000\tloss (train):0.929366\tloss (buffer on valid):0.898655\tbest:0.784449\tTolerance: 836/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1328/10000\tloss (train):0.965003\tloss (buffer on valid):0.897640\tbest:0.784449\tTolerance: 837/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1329/10000\tloss (train):0.862415\tloss (buffer on valid):0.896821\tbest:0.784449\tTolerance: 838/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1330/10000\tloss (train):0.921624\tloss (buffer on valid):0.896517\tbest:0.784449\tTolerance: 839/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1331/10000\tloss (train):0.860723\tloss (buffer on valid):0.896191\tbest:0.784449\tTolerance: 840/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1332/10000\tloss (train):0.850998\tloss (buffer on valid):0.894680\tbest:0.784449\tTolerance: 841/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1333/10000\tloss (train):0.889032\tloss (buffer on valid):0.895557\tbest:0.784449\tTolerance: 842/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1334/10000\tloss (train):0.846693\tloss (buffer on valid):0.896234\tbest:0.784449\tTolerance: 843/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1335/10000\tloss (train):0.966991\tloss (buffer on valid):0.894985\tbest:0.784449\tTolerance: 844/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1336/10000\tloss (train):0.855049\tloss (buffer on valid):0.896287\tbest:0.784449\tTolerance: 845/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1337/10000\tloss (train):0.907457\tloss (buffer on valid):0.896561\tbest:0.784449\tTolerance: 846/1000\n", + "Substage:1\tEpoch:102/10000\tIteration: 1338/10000\tloss (train):0.829136\tloss (buffer on valid):0.896090\tbest:0.784449\tTolerance: 847/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1339/10000\tloss (train):0.904426\tloss (buffer on valid):0.897387\tbest:0.784449\tTolerance: 848/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1340/10000\tloss (train):0.955493\tloss (buffer on valid):0.896203\tbest:0.784449\tTolerance: 849/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1341/10000\tloss (train):0.963734\tloss (buffer on valid):0.896853\tbest:0.784449\tTolerance: 850/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1342/10000\tloss (train):0.859111\tloss (buffer on valid):0.896188\tbest:0.784449\tTolerance: 851/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1343/10000\tloss (train):0.945254\tloss (buffer on valid):0.896200\tbest:0.784449\tTolerance: 852/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1344/10000\tloss (train):0.886233\tloss (buffer on valid):0.896825\tbest:0.784449\tTolerance: 853/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1345/10000\tloss (train):0.856068\tloss (buffer on valid):0.896744\tbest:0.784449\tTolerance: 854/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1346/10000\tloss (train):0.881456\tloss (buffer on valid):0.898076\tbest:0.784449\tTolerance: 855/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1347/10000\tloss (train):0.859492\tloss (buffer on valid):0.900817\tbest:0.784449\tTolerance: 856/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1348/10000\tloss (train):1.012633\tloss (buffer on valid):0.902071\tbest:0.784449\tTolerance: 857/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1349/10000\tloss (train):0.902041\tloss (buffer on valid):0.902576\tbest:0.784449\tTolerance: 858/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1350/10000\tloss (train):0.934087\tloss (buffer on valid):0.903740\tbest:0.784449\tTolerance: 859/1000\n", + "Substage:1\tEpoch:103/10000\tIteration: 1351/10000\tloss (train):0.840670\tloss (buffer on valid):0.903919\tbest:0.784449\tTolerance: 860/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1352/10000\tloss (train):0.921626\tloss (buffer on valid):0.906066\tbest:0.784449\tTolerance: 861/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1353/10000\tloss (train):1.027798\tloss (buffer on valid):0.907282\tbest:0.784449\tTolerance: 862/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1354/10000\tloss (train):1.036257\tloss (buffer on valid):0.908802\tbest:0.784449\tTolerance: 863/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1355/10000\tloss (train):0.856211\tloss (buffer on valid):0.909353\tbest:0.784449\tTolerance: 864/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1356/10000\tloss (train):0.908987\tloss (buffer on valid):0.910728\tbest:0.784449\tTolerance: 865/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1357/10000\tloss (train):0.880656\tloss (buffer on valid):0.910963\tbest:0.784449\tTolerance: 866/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1358/10000\tloss (train):0.897720\tloss (buffer on valid):0.913667\tbest:0.784449\tTolerance: 867/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1359/10000\tloss (train):0.941141\tloss (buffer on valid):0.914723\tbest:0.784449\tTolerance: 868/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1360/10000\tloss (train):0.877745\tloss (buffer on valid):0.914061\tbest:0.784449\tTolerance: 869/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1361/10000\tloss (train):1.008658\tloss (buffer on valid):0.915056\tbest:0.784449\tTolerance: 870/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1362/10000\tloss (train):0.907330\tloss (buffer on valid):0.917533\tbest:0.784449\tTolerance: 871/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1363/10000\tloss (train):0.961706\tloss (buffer on valid):0.919047\tbest:0.784449\tTolerance: 872/1000\n", + "Substage:1\tEpoch:104/10000\tIteration: 1364/10000\tloss (train):0.869844\tloss (buffer on valid):0.917855\tbest:0.784449\tTolerance: 873/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1365/10000\tloss (train):0.939243\tloss (buffer on valid):0.918847\tbest:0.784449\tTolerance: 874/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1366/10000\tloss (train):0.943617\tloss (buffer on valid):0.919505\tbest:0.784449\tTolerance: 875/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1367/10000\tloss (train):0.989362\tloss (buffer on valid):0.919359\tbest:0.784449\tTolerance: 876/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1368/10000\tloss (train):0.888986\tloss (buffer on valid):0.919140\tbest:0.784449\tTolerance: 877/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1369/10000\tloss (train):0.918665\tloss (buffer on valid):0.919279\tbest:0.784449\tTolerance: 878/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1370/10000\tloss (train):0.869818\tloss (buffer on valid):0.919562\tbest:0.784449\tTolerance: 879/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1371/10000\tloss (train):0.867507\tloss (buffer on valid):0.919883\tbest:0.784449\tTolerance: 880/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1372/10000\tloss (train):0.899310\tloss (buffer on valid):0.920314\tbest:0.784449\tTolerance: 881/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1373/10000\tloss (train):0.857430\tloss (buffer on valid):0.919775\tbest:0.784449\tTolerance: 882/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1374/10000\tloss (train):1.020163\tloss (buffer on valid):0.919274\tbest:0.784449\tTolerance: 883/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1375/10000\tloss (train):0.873398\tloss (buffer on valid):0.920721\tbest:0.784449\tTolerance: 884/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1376/10000\tloss (train):0.932892\tloss (buffer on valid):0.920751\tbest:0.784449\tTolerance: 885/1000\n", + "Substage:1\tEpoch:105/10000\tIteration: 1377/10000\tloss (train):0.853002\tloss (buffer on valid):0.919987\tbest:0.784449\tTolerance: 886/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1378/10000\tloss (train):0.913050\tloss (buffer on valid):0.920788\tbest:0.784449\tTolerance: 887/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1379/10000\tloss (train):0.931802\tloss (buffer on valid):0.920598\tbest:0.784449\tTolerance: 888/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1380/10000\tloss (train):0.973768\tloss (buffer on valid):0.920602\tbest:0.784449\tTolerance: 889/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1381/10000\tloss (train):0.867548\tloss (buffer on valid):0.920787\tbest:0.784449\tTolerance: 890/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1382/10000\tloss (train):0.930510\tloss (buffer on valid):0.922067\tbest:0.784449\tTolerance: 891/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1383/10000\tloss (train):0.887313\tloss (buffer on valid):0.921472\tbest:0.784449\tTolerance: 892/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1384/10000\tloss (train):0.893709\tloss (buffer on valid):0.922080\tbest:0.784449\tTolerance: 893/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1385/10000\tloss (train):0.929423\tloss (buffer on valid):0.923379\tbest:0.784449\tTolerance: 894/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1386/10000\tloss (train):0.861941\tloss (buffer on valid):0.924192\tbest:0.784449\tTolerance: 895/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1387/10000\tloss (train):0.995397\tloss (buffer on valid):0.925381\tbest:0.784449\tTolerance: 896/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1388/10000\tloss (train):0.893250\tloss (buffer on valid):0.926292\tbest:0.784449\tTolerance: 897/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1389/10000\tloss (train):0.912825\tloss (buffer on valid):0.926349\tbest:0.784449\tTolerance: 898/1000\n", + "Substage:1\tEpoch:106/10000\tIteration: 1390/10000\tloss (train):0.836570\tloss (buffer on valid):0.927824\tbest:0.784449\tTolerance: 899/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1391/10000\tloss (train):0.909806\tloss (buffer on valid):0.928159\tbest:0.784449\tTolerance: 900/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1392/10000\tloss (train):0.963878\tloss (buffer on valid):0.927117\tbest:0.784449\tTolerance: 901/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1393/10000\tloss (train):1.004037\tloss (buffer on valid):0.928885\tbest:0.784449\tTolerance: 902/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1394/10000\tloss (train):0.882470\tloss (buffer on valid):0.930128\tbest:0.784449\tTolerance: 903/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1395/10000\tloss (train):0.937263\tloss (buffer on valid):0.932710\tbest:0.784449\tTolerance: 904/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1396/10000\tloss (train):0.920776\tloss (buffer on valid):0.932799\tbest:0.784449\tTolerance: 905/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1397/10000\tloss (train):0.876703\tloss (buffer on valid):0.931077\tbest:0.784449\tTolerance: 906/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1398/10000\tloss (train):0.909584\tloss (buffer on valid):0.929929\tbest:0.784449\tTolerance: 907/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1399/10000\tloss (train):0.877216\tloss (buffer on valid):0.930131\tbest:0.784449\tTolerance: 908/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1400/10000\tloss (train):1.143808\tloss (buffer on valid):0.929711\tbest:0.784449\tTolerance: 909/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1401/10000\tloss (train):0.892692\tloss (buffer on valid):0.929549\tbest:0.784449\tTolerance: 910/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1402/10000\tloss (train):0.951684\tloss (buffer on valid):0.927926\tbest:0.784449\tTolerance: 911/1000\n", + "Substage:1\tEpoch:107/10000\tIteration: 1403/10000\tloss (train):0.884765\tloss (buffer on valid):0.927805\tbest:0.784449\tTolerance: 912/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1404/10000\tloss (train):0.970407\tloss (buffer on valid):0.927951\tbest:0.784449\tTolerance: 913/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1405/10000\tloss (train):0.994401\tloss (buffer on valid):0.930305\tbest:0.784449\tTolerance: 914/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1406/10000\tloss (train):1.050746\tloss (buffer on valid):0.932121\tbest:0.784449\tTolerance: 915/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1407/10000\tloss (train):0.936146\tloss (buffer on valid):0.933458\tbest:0.784449\tTolerance: 916/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1408/10000\tloss (train):1.007525\tloss (buffer on valid):0.934499\tbest:0.784449\tTolerance: 917/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1409/10000\tloss (train):0.949491\tloss (buffer on valid):0.933865\tbest:0.784449\tTolerance: 918/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1410/10000\tloss (train):0.936309\tloss (buffer on valid):0.935387\tbest:0.784449\tTolerance: 919/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1411/10000\tloss (train):0.953632\tloss (buffer on valid):0.934634\tbest:0.784449\tTolerance: 920/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1412/10000\tloss (train):0.921666\tloss (buffer on valid):0.934392\tbest:0.784449\tTolerance: 921/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1413/10000\tloss (train):1.034309\tloss (buffer on valid):0.933438\tbest:0.784449\tTolerance: 922/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1414/10000\tloss (train):0.932565\tloss (buffer on valid):0.934521\tbest:0.784449\tTolerance: 923/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1415/10000\tloss (train):0.956904\tloss (buffer on valid):0.934272\tbest:0.784449\tTolerance: 924/1000\n", + "Substage:1\tEpoch:108/10000\tIteration: 1416/10000\tloss (train):0.877003\tloss (buffer on valid):0.936299\tbest:0.784449\tTolerance: 925/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1417/10000\tloss (train):0.929489\tloss (buffer on valid):0.938594\tbest:0.784449\tTolerance: 926/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1418/10000\tloss (train):0.940057\tloss (buffer on valid):0.940704\tbest:0.784449\tTolerance: 927/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1419/10000\tloss (train):1.015728\tloss (buffer on valid):0.940818\tbest:0.784449\tTolerance: 928/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1420/10000\tloss (train):0.896813\tloss (buffer on valid):0.942404\tbest:0.784449\tTolerance: 929/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1421/10000\tloss (train):0.938456\tloss (buffer on valid):0.943259\tbest:0.784449\tTolerance: 930/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1422/10000\tloss (train):0.887128\tloss (buffer on valid):0.945110\tbest:0.784449\tTolerance: 931/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1423/10000\tloss (train):0.902578\tloss (buffer on valid):0.948625\tbest:0.784449\tTolerance: 932/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1424/10000\tloss (train):0.926471\tloss (buffer on valid):0.950866\tbest:0.784449\tTolerance: 933/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1425/10000\tloss (train):0.877922\tloss (buffer on valid):0.950825\tbest:0.784449\tTolerance: 934/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1426/10000\tloss (train):1.012727\tloss (buffer on valid):0.952287\tbest:0.784449\tTolerance: 935/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1427/10000\tloss (train):0.903799\tloss (buffer on valid):0.953297\tbest:0.784449\tTolerance: 936/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1428/10000\tloss (train):0.934303\tloss (buffer on valid):0.953826\tbest:0.784449\tTolerance: 937/1000\n", + "Substage:1\tEpoch:109/10000\tIteration: 1429/10000\tloss (train):0.860160\tloss (buffer on valid):0.953747\tbest:0.784449\tTolerance: 938/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1430/10000\tloss (train):0.930488\tloss (buffer on valid):0.954963\tbest:0.784449\tTolerance: 939/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1431/10000\tloss (train):0.933398\tloss (buffer on valid):0.955142\tbest:0.784449\tTolerance: 940/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1432/10000\tloss (train):0.982320\tloss (buffer on valid):0.955095\tbest:0.784449\tTolerance: 941/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1433/10000\tloss (train):0.879369\tloss (buffer on valid):0.954439\tbest:0.784449\tTolerance: 942/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1434/10000\tloss (train):0.925880\tloss (buffer on valid):0.953680\tbest:0.784449\tTolerance: 943/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1435/10000\tloss (train):0.865553\tloss (buffer on valid):0.952088\tbest:0.784449\tTolerance: 944/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1436/10000\tloss (train):0.869018\tloss (buffer on valid):0.951031\tbest:0.784449\tTolerance: 945/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1437/10000\tloss (train):0.895324\tloss (buffer on valid):0.949180\tbest:0.784449\tTolerance: 946/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1438/10000\tloss (train):0.848672\tloss (buffer on valid):0.949190\tbest:0.784449\tTolerance: 947/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1439/10000\tloss (train):0.982346\tloss (buffer on valid):0.948168\tbest:0.784449\tTolerance: 948/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1440/10000\tloss (train):0.883015\tloss (buffer on valid):0.947634\tbest:0.784449\tTolerance: 949/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1441/10000\tloss (train):0.928444\tloss (buffer on valid):0.947793\tbest:0.784449\tTolerance: 950/1000\n", + "Substage:1\tEpoch:110/10000\tIteration: 1442/10000\tloss (train):0.826755\tloss (buffer on valid):0.949140\tbest:0.784449\tTolerance: 951/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1443/10000\tloss (train):0.897214\tloss (buffer on valid):0.947566\tbest:0.784449\tTolerance: 952/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1444/10000\tloss (train):0.949331\tloss (buffer on valid):0.948188\tbest:0.784449\tTolerance: 953/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1445/10000\tloss (train):1.017401\tloss (buffer on valid):0.946042\tbest:0.784449\tTolerance: 954/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1446/10000\tloss (train):0.887432\tloss (buffer on valid):0.945317\tbest:0.784449\tTolerance: 955/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1447/10000\tloss (train):0.943664\tloss (buffer on valid):0.946111\tbest:0.784449\tTolerance: 956/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1448/10000\tloss (train):0.916380\tloss (buffer on valid):0.947146\tbest:0.784449\tTolerance: 957/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1449/10000\tloss (train):0.899709\tloss (buffer on valid):0.946607\tbest:0.784449\tTolerance: 958/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1450/10000\tloss (train):0.906341\tloss (buffer on valid):0.945461\tbest:0.784449\tTolerance: 959/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1451/10000\tloss (train):0.864987\tloss (buffer on valid):0.945870\tbest:0.784449\tTolerance: 960/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1452/10000\tloss (train):1.008166\tloss (buffer on valid):0.946228\tbest:0.784449\tTolerance: 961/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1453/10000\tloss (train):0.908071\tloss (buffer on valid):0.946004\tbest:0.784449\tTolerance: 962/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1454/10000\tloss (train):0.964278\tloss (buffer on valid):0.944815\tbest:0.784449\tTolerance: 963/1000\n", + "Substage:1\tEpoch:111/10000\tIteration: 1455/10000\tloss (train):0.856141\tloss (buffer on valid):0.943038\tbest:0.784449\tTolerance: 964/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1456/10000\tloss (train):0.933373\tloss (buffer on valid):0.941792\tbest:0.784449\tTolerance: 965/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1457/10000\tloss (train):0.973247\tloss (buffer on valid):0.939997\tbest:0.784449\tTolerance: 966/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1458/10000\tloss (train):0.974762\tloss (buffer on valid):0.936971\tbest:0.784449\tTolerance: 967/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1459/10000\tloss (train):0.869077\tloss (buffer on valid):0.936534\tbest:0.784449\tTolerance: 968/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1460/10000\tloss (train):0.950901\tloss (buffer on valid):0.934721\tbest:0.784449\tTolerance: 969/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1461/10000\tloss (train):0.871438\tloss (buffer on valid):0.934427\tbest:0.784449\tTolerance: 970/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1462/10000\tloss (train):0.873200\tloss (buffer on valid):0.932412\tbest:0.784449\tTolerance: 971/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1463/10000\tloss (train):0.906869\tloss (buffer on valid):0.932265\tbest:0.784449\tTolerance: 972/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1464/10000\tloss (train):0.870918\tloss (buffer on valid):0.931101\tbest:0.784449\tTolerance: 973/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1465/10000\tloss (train):1.010347\tloss (buffer on valid):0.930205\tbest:0.784449\tTolerance: 974/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1466/10000\tloss (train):0.895783\tloss (buffer on valid):0.928991\tbest:0.784449\tTolerance: 975/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1467/10000\tloss (train):0.913795\tloss (buffer on valid):0.927333\tbest:0.784449\tTolerance: 976/1000\n", + "Substage:1\tEpoch:112/10000\tIteration: 1468/10000\tloss (train):0.846502\tloss (buffer on valid):0.925580\tbest:0.784449\tTolerance: 977/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1469/10000\tloss (train):0.916617\tloss (buffer on valid):0.926086\tbest:0.784449\tTolerance: 978/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1470/10000\tloss (train):0.968717\tloss (buffer on valid):0.925650\tbest:0.784449\tTolerance: 979/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1471/10000\tloss (train):0.993658\tloss (buffer on valid):0.924689\tbest:0.784449\tTolerance: 980/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1472/10000\tloss (train):0.868994\tloss (buffer on valid):0.922478\tbest:0.784449\tTolerance: 981/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1473/10000\tloss (train):0.918494\tloss (buffer on valid):0.920174\tbest:0.784449\tTolerance: 982/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1474/10000\tloss (train):0.880827\tloss (buffer on valid):0.919500\tbest:0.784449\tTolerance: 983/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1475/10000\tloss (train):0.881802\tloss (buffer on valid):0.920338\tbest:0.784449\tTolerance: 984/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1476/10000\tloss (train):0.912758\tloss (buffer on valid):0.919401\tbest:0.784449\tTolerance: 985/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1477/10000\tloss (train):0.887435\tloss (buffer on valid):0.919391\tbest:0.784449\tTolerance: 986/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1478/10000\tloss (train):1.094504\tloss (buffer on valid):0.918102\tbest:0.784449\tTolerance: 987/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1479/10000\tloss (train):0.897989\tloss (buffer on valid):0.920197\tbest:0.784449\tTolerance: 988/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1480/10000\tloss (train):0.991395\tloss (buffer on valid):0.920222\tbest:0.784449\tTolerance: 989/1000\n", + "Substage:1\tEpoch:113/10000\tIteration: 1481/10000\tloss (train):0.887031\tloss (buffer on valid):0.920489\tbest:0.784449\tTolerance: 990/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1482/10000\tloss (train):0.965120\tloss (buffer on valid):0.922936\tbest:0.784449\tTolerance: 991/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1483/10000\tloss (train):0.980561\tloss (buffer on valid):0.923525\tbest:0.784449\tTolerance: 992/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1484/10000\tloss (train):1.030397\tloss (buffer on valid):0.923626\tbest:0.784449\tTolerance: 993/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1485/10000\tloss (train):0.931636\tloss (buffer on valid):0.924495\tbest:0.784449\tTolerance: 994/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1486/10000\tloss (train):0.985210\tloss (buffer on valid):0.926269\tbest:0.784449\tTolerance: 995/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1487/10000\tloss (train):0.926198\tloss (buffer on valid):0.927542\tbest:0.784449\tTolerance: 996/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1488/10000\tloss (train):0.925764\tloss (buffer on valid):0.928060\tbest:0.784449\tTolerance: 997/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1489/10000\tloss (train):0.945437\tloss (buffer on valid):0.928587\tbest:0.784449\tTolerance: 998/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1490/10000\tloss (train):0.914792\tloss (buffer on valid):0.930397\tbest:0.784449\tTolerance: 999/1000\n", + "Substage:1\tEpoch:114/10000\tIteration: 1491/10000\tloss (train):1.051824\tloss (buffer on valid):0.931468\tbest:0.784449\tTolerance: 1000/1000\n", + "######## ------------------ Substage 1 finished!------------------- --time elapsed: 165.34\n", + "Model saved in path: ./model11.ckpt\n", + "######## --------- lr: 0.01\tl1: 0.01\tl2: 0.0001\t --time elapsed: 1.43\n", + "Substage:2\tEpoch:0/10000\tIteration: 0/10000\tloss (train):0.935321\tloss (buffer on valid):500.459241\tbest:1000.000000\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 1/10000\tloss (train):0.923305\tloss (buffer on valid):333.916359\tbest:500.459241\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 2/10000\tloss (train):0.916194\tloss (buffer on valid):250.627815\tbest:333.916359\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 3/10000\tloss (train):0.678334\tloss (buffer on valid):200.625096\tbest:250.627815\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 4/10000\tloss (train):0.633786\tloss (buffer on valid):167.289602\tbest:200.625096\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 5/10000\tloss (train):0.506245\tloss (buffer on valid):143.454140\tbest:167.289602\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 6/10000\tloss (train):0.455666\tloss (buffer on valid):125.576325\tbest:143.454140\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 7/10000\tloss (train):0.448408\tloss (buffer on valid):111.680116\tbest:125.576325\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 8/10000\tloss (train):0.429053\tloss (buffer on valid):100.564737\tbest:111.680116\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 9/10000\tloss (train):0.541954\tloss (buffer on valid):91.466188\tbest:100.564737\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 10/10000\tloss (train):0.464731\tloss (buffer on valid):83.886482\tbest:91.466188\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 11/10000\tloss (train):0.483849\tloss (buffer on valid):77.465469\tbest:83.886482\tTolerance: 0/100\n", + "Substage:2\tEpoch:0/10000\tIteration: 12/10000\tloss (train):0.381917\tloss (buffer on valid):71.966020\tbest:77.465469\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 13/10000\tloss (train):0.429963\tloss (buffer on valid):67.198593\tbest:71.966020\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 14/10000\tloss (train):0.425070\tloss (buffer on valid):63.022101\tbest:67.198593\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 15/10000\tloss (train):0.476232\tloss (buffer on valid):59.337615\tbest:63.022101\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 16/10000\tloss (train):0.332147\tloss (buffer on valid):56.059990\tbest:59.337615\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 17/10000\tloss (train):0.386093\tloss (buffer on valid):53.129256\tbest:56.059990\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 18/10000\tloss (train):0.316945\tloss (buffer on valid):50.492244\tbest:53.129256\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 19/10000\tloss (train):0.312247\tloss (buffer on valid):48.103705\tbest:50.492244\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 20/10000\tloss (train):0.319703\tloss (buffer on valid):45.931149\tbest:48.103705\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 21/10000\tloss (train):0.290210\tloss (buffer on valid):43.946438\tbest:45.931149\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 22/10000\tloss (train):0.398796\tloss (buffer on valid):42.129766\tbest:43.946438\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 23/10000\tloss (train):0.309495\tloss (buffer on valid):40.457833\tbest:42.129766\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 24/10000\tloss (train):0.316547\tloss (buffer on valid):38.915021\tbest:40.457833\tTolerance: 0/100\n", + "Substage:2\tEpoch:1/10000\tIteration: 25/10000\tloss (train):0.239930\tloss (buffer on valid):37.485009\tbest:38.915021\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 26/10000\tloss (train):0.294880\tloss (buffer on valid):36.159118\tbest:37.485009\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 27/10000\tloss (train):0.302525\tloss (buffer on valid):34.922937\tbest:36.159118\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 28/10000\tloss (train):0.369972\tloss (buffer on valid):33.766544\tbest:34.922937\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 29/10000\tloss (train):0.240577\tloss (buffer on valid):32.685934\tbest:33.766544\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 30/10000\tloss (train):0.299155\tloss (buffer on valid):31.673829\tbest:32.685934\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 31/10000\tloss (train):0.232449\tloss (buffer on valid):30.721549\tbest:31.673829\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 32/10000\tloss (train):0.232176\tloss (buffer on valid):29.827011\tbest:30.721549\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 33/10000\tloss (train):0.252068\tloss (buffer on valid):28.981894\tbest:29.827011\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 34/10000\tloss (train):0.232482\tloss (buffer on valid):28.185097\tbest:28.981894\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 35/10000\tloss (train):0.344355\tloss (buffer on valid):27.432106\tbest:28.185097\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 36/10000\tloss (train):0.254976\tloss (buffer on valid):26.716817\tbest:27.432106\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 37/10000\tloss (train):0.265796\tloss (buffer on valid):26.037667\tbest:26.716817\tTolerance: 0/100\n", + "Substage:2\tEpoch:2/10000\tIteration: 38/10000\tloss (train):0.193669\tloss (buffer on valid):25.392739\tbest:26.037667\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 39/10000\tloss (train):0.253560\tloss (buffer on valid):24.779773\tbest:25.392739\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 40/10000\tloss (train):0.265454\tloss (buffer on valid):24.195915\tbest:24.779773\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 41/10000\tloss (train):0.333806\tloss (buffer on valid):23.640394\tbest:24.195915\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 42/10000\tloss (train):0.210944\tloss (buffer on valid):23.108981\tbest:23.640394\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 43/10000\tloss (train):0.276226\tloss (buffer on valid):22.601096\tbest:23.108981\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 44/10000\tloss (train):0.207260\tloss (buffer on valid):22.114183\tbest:22.601096\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 45/10000\tloss (train):0.207059\tloss (buffer on valid):21.648306\tbest:22.114183\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 46/10000\tloss (train):0.226151\tloss (buffer on valid):21.201577\tbest:21.648306\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 47/10000\tloss (train):0.207223\tloss (buffer on valid):20.773959\tbest:21.201577\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 48/10000\tloss (train):0.318451\tloss (buffer on valid):20.364258\tbest:20.773959\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 49/10000\tloss (train):0.231930\tloss (buffer on valid):0.369647\tbest:20.364258\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 50/10000\tloss (train):0.245922\tloss (buffer on valid):0.356776\tbest:0.369647\tTolerance: 0/100\n", + "Substage:2\tEpoch:3/10000\tIteration: 51/10000\tloss (train):0.177739\tloss (buffer on valid):0.344851\tbest:0.356776\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 52/10000\tloss (train):0.243312\tloss (buffer on valid):0.334985\tbest:0.344851\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 53/10000\tloss (train):0.254791\tloss (buffer on valid):0.327437\tbest:0.334985\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 54/10000\tloss (train):0.320348\tloss (buffer on valid):0.320675\tbest:0.327437\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 55/10000\tloss (train):0.197684\tloss (buffer on valid):0.316475\tbest:0.320675\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 56/10000\tloss (train):0.262538\tloss (buffer on valid):0.311801\tbest:0.316475\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 57/10000\tloss (train):0.193316\tloss (buffer on valid):0.306381\tbest:0.311801\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 58/10000\tloss (train):0.193592\tloss (buffer on valid):0.300664\tbest:0.306381\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 59/10000\tloss (train):0.214547\tloss (buffer on valid):0.295579\tbest:0.300664\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 60/10000\tloss (train):0.198292\tloss (buffer on valid):0.290828\tbest:0.295579\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 61/10000\tloss (train):0.311391\tloss (buffer on valid):0.287279\tbest:0.290828\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 62/10000\tloss (train):0.223518\tloss (buffer on valid):0.283397\tbest:0.287279\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 63/10000\tloss (train):0.236544\tloss (buffer on valid):0.280353\tbest:0.283397\tTolerance: 0/100\n", + "Substage:2\tEpoch:4/10000\tIteration: 64/10000\tloss (train):0.169082\tloss (buffer on valid):0.278743\tbest:0.280353\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 65/10000\tloss (train):0.234887\tloss (buffer on valid):0.275915\tbest:0.278743\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 66/10000\tloss (train):0.246866\tloss (buffer on valid):0.274498\tbest:0.275915\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 67/10000\tloss (train):0.311522\tloss (buffer on valid):0.271859\tbest:0.274498\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 68/10000\tloss (train):0.190861\tloss (buffer on valid):0.270441\tbest:0.271859\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 69/10000\tloss (train):0.256072\tloss (buffer on valid):0.268977\tbest:0.270441\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 70/10000\tloss (train):0.193111\tloss (buffer on valid):0.267796\tbest:0.268977\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 71/10000\tloss (train):0.193043\tloss (buffer on valid):0.267598\tbest:0.267796\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 72/10000\tloss (train):0.212272\tloss (buffer on valid):0.264930\tbest:0.267598\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 73/10000\tloss (train):0.194479\tloss (buffer on valid):0.262563\tbest:0.264930\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 74/10000\tloss (train):0.306102\tloss (buffer on valid):0.260019\tbest:0.262563\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 75/10000\tloss (train):0.220190\tloss (buffer on valid):0.258842\tbest:0.260019\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 76/10000\tloss (train):0.234899\tloss (buffer on valid):0.255401\tbest:0.258842\tTolerance: 0/100\n", + "Substage:2\tEpoch:5/10000\tIteration: 77/10000\tloss (train):0.164823\tloss (buffer on valid):0.252954\tbest:0.255401\tTolerance: 0/100\n", + "Substage:2\tEpoch:6/10000\tIteration: 78/10000\tloss (train):0.230520\tloss (buffer on valid):0.253062\tbest:0.252954\tTolerance: 0/100\n", + "Substage:2\tEpoch:6/10000\tIteration: 79/10000\tloss (train):0.244577\tloss (buffer on valid):0.252263\tbest:0.252954\tTolerance: 1/100\n", + "Traceback (most recent call last):\n", + " File \"./scripts/main.py\", line 86, in \n", + " cellbox.train.train_model(model, args)\n", + " File \"/usr/local/lib/python3.8/dist-packages/cellbox-0.3.1-py3.8.egg/cellbox/train.py\", line 170, in train_model\n", + " File \"/usr/local/lib/python3.8/dist-packages/cellbox-0.3.1-py3.8.egg/cellbox/train.py\", line 71, in train_substage\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 968, in run\n", + " result = self._run(None, fetches, feed_dict, options_ptr,\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 1191, in _run\n", + " results = self._do_run(handle, final_targets, final_fetches,\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 1371, in _do_run\n", + " return self._do_call(_run_fn, feeds, fetches, targets, options,\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 1378, in _do_call\n", + " return fn(*args)\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 1361, in _run_fn\n", + " return self._call_tf_sessionrun(options, feed_dict, fetch_list,\n", + " File \"/usr/local/lib/python3.8/dist-packages/tensorflow/python/client/session.py\", line 1454, in _call_tf_sessionrun\n", + " return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,\n", + "KeyboardInterrupt\n", + "^C\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "Jsq9U7ev3laD" + }, + "execution_count": null, + "outputs": [] + } + ] +} \ No newline at end of file diff --git a/requirements.txt b/requirements.txt index 69b3636..18fb3e4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,25 +1,48 @@ -absl-py==0.9.0 +absl-py==1.4.0 astor==0.8.1 -gast==0.2.2 +astunparse==1.6.3 +cachetools==5.3.0 +cellbox==0.3.1 +charset-normalizer==3.0.1 +flatbuffers==23.1.21 +gast==0.4.0 +google-auth==2.16.0 +google-auth-oauthlib==0.4.6 google-pasta==0.2.0 -grpcio==1.30.0 -h5py==2.10.0 -importlib-metadata==1.7.0 +grpcio==1.51.1 +h5py==3.8.0 +idna==3.4 +importlib-metadata==6.0.0 +keras==2.11.0 Keras-Applications==1.0.8 Keras-Preprocessing==1.1.2 -Markdown==3.2.2 -numpy==1.16.0 -opt-einsum==3.2.1 -pandas==0.24.2 -protobuf==3.12.2 -python-dateutil==2.8.1 -pytz==2020.1 -six==1.15.0 -tensorboard==1.15.0 -tensorflow==1.15.0 -tensorflow-estimator==1.15.1 -termcolor==1.1.0 -Werkzeug==1.0.1 -wrapt==1.12.1 -zipp==3.1.0 -scipy==1.3.0 +libclang==15.0.6.1 +Markdown==3.4.1 +MarkupSafe==2.1.2 +numpy==1.24.1 +oauthlib==3.2.2 +opt-einsum==3.3.0 +packaging==23.0 +pandas==1.5.3 +protobuf==3.19.6 +pyasn1==0.4.8 +pyasn1-modules==0.2.8 +python-dateutil==2.8.2 +pytz==2022.7.1 +requests==2.28.2 +requests-oauthlib==1.3.1 +rsa==4.9 +scipy==1.10.0 +six==1.16.0 +tensorboard==2.11.2 +tensorboard-data-server==0.6.1 +tensorboard-plugin-wit==1.8.1 +tensorflow==2.11.0 +tensorflow-estimator==2.11.0 +tensorflow-io-gcs-filesystem==0.30.0 +termcolor==2.2.0 +typing_extensions==4.4.0 +urllib3==1.26.14 +Werkzeug==2.2.2 +wrapt==1.14.1 +zipp==3.12.0 diff --git a/requirements_old.txt b/requirements_old.txt new file mode 100644 index 0000000..d56b75c --- /dev/null +++ b/requirements_old.txt @@ -0,0 +1,25 @@ +absl-py==0.9.0 +astor==0.8.1 +gast==0.2.2 +google-pasta==0.2.0 +grpcio==1.30.0 +h5py==2.10.0 +importlib-metadata==1.7.0 +Keras-Applications==1.0.8 +Keras-Preprocessing==1.1.2 +Markdown==3.2.2 +numpy==1.19.5 +opt-einsum==3.2.1 +pandas==0.24.2 +protobuf==3.12.2 +python-dateutil==2.8.1 +pytz==2020.1 +six==1.15.0 +tensorboard==2.6.0 +tensorflow==2.6.2 +tensorflow-estimator==2.6.0 +termcolor==1.1.0 +Werkzeug==1.0.1 +wrapt==1.12.1 +zipp==3.1.0 +scipy==1.3.0 diff --git a/scripts/main.py b/scripts/main.py index 4bf3dce..57177de 100644 --- a/scripts/main.py +++ b/scripts/main.py @@ -5,11 +5,11 @@ import os import numpy as np import pandas as pd -import tensorflow as tf +import tensorflow.compat.v1 as tf import shutil import argparse import json - +tf.disable_v2_behavior() parser = argparse.ArgumentParser(description='CellBox main script') parser.add_argument('-config', '--experiment_config_path', required=True, type=str, help="Path of experiment config") parser.add_argument('-i', '--working_index', default=0, type=int)