updates

.gitignore

@@ -0,0 +1,161 @@
+led / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

finetuning_categorisation_xl.gin

@@ -1,40 +0,0 @@
-from __gin__ import dynamic_registration
-import tasks
-
-import __main__ as train_script
-from t5.data import mixtures
-from t5x import models
-from t5x import partitioning
-from t5x import utils
-
-include "t5x/examples/t5/mt5/xl.gin"
-include "t5x/configs/runs/finetune.gin"
-
-MIXTURE_OR_TASK_NAME = "categorise"
-TASK_FEATURE_LENGTHS = {"inputs": 256, "targets": 256}
-TRAIN_STEPS = 1_010_000  # 1000000 pre-trained steps + 10000 fine-tuning steps.
-USE_CACHED_TASKS = False
-DROPOUT_RATE = 0.0
-RANDOM_SEED = 0
-
-
-# Pere: Only necessary if we load a t5 model. We can start with an t5x model here
-# `LOSS_NORMALIZING_FACTOR`: When fine-tuning a model that was pre-trained
-# using Mesh Tensorflow (e.g. the public T5 / mT5 / ByT5 models), this should be
-# set to `pretraining batch_size` * `target_token_length`. For T5 and T5.1.1:
-# `2048 * 114`. For mT5: `1024 * 229`. For ByT5: `1024 * 189`.
-#LOSS_NORMALIZING_FACTOR = 234496
-
-INITIAL_CHECKPOINT_PATH = "gs://t5-data/pretrained_models/t5x/mt5_xl/checkpoint_1000000"
-
-#train_script.train:
-#  eval_period = 500
-#  partitioner = @partitioning.ModelBasedPjitPartitioner()
-# partitioning.ModelBasedPjitPartitioner.num_partitions = 2
-
-# `num_decodes` is equivalent to a beam size in a beam search decoding.
-models.EncoderDecoderModel.predict_batch_with_aux.num_decodes = 4
-
-#mesh_transformer.learning_rate_schedules.constant_learning_rate.learning_rate = 0.0005
-#run.learning_rate_schedule = @learning_rate_schedules.constant_learning_rate
-

finetuning_categorisation_xxl.gin

@@ -1,40 +0,0 @@
-from __gin__ import dynamic_registration
-import tasks
-
-import __main__ as train_script
-from t5.data import mixtures
-from t5x import models
-from t5x import partitioning
-from t5x import utils
-
-include "t5x/examples/t5/mt5/xxl.gin"
-include "t5x/configs/runs/finetune.gin"
-
-MIXTURE_OR_TASK_NAME = "categorise"
-TASK_FEATURE_LENGTHS = {"inputs": 96, "targets": 4}
-TRAIN_STEPS = 1_010_000  # 1000000 pre-trained steps + 10000 fine-tuning steps.
-USE_CACHED_TASKS = False
-DROPOUT_RATE = 0.0
-RANDOM_SEED = 0
-BATCH_SIZE = 16
-
-# Pere: Only necessary if we load a t5 model. We can start with an t5x model here
-# `LOSS_NORMALIZING_FACTOR`: When fine-tuning a model that was pre-trained
-# using Mesh Tensorflow (e.g. the public T5 / mT5 / ByT5 models), this should be
-# set to `pretraining batch_size` * `target_token_length`. For T5 and T5.1.1:
-# `2048 * 114`. For mT5: `1024 * 229`. For ByT5: `1024 * 189`.
-#LOSS_NORMALIZING_FACTOR = 234496
-
-INITIAL_CHECKPOINT_PATH = "gs://t5-data/pretrained_models/t5x/mt5_xxl/checkpoint_1000000"
-
-#train_script.train:
-#  eval_period = 500
-#  partitioner = @partitioning.ModelBasedPjitPartitioner()
-partitioning.PjitPartitioner.num_partitions = 1
-
-# `num_decodes` is equivalent to a beam size in a beam search decoding.
-models.EncoderDecoderModel.predict_batch_with_aux.num_decodes = 4
-
-#mesh_transformer.learning_rate_schedules.constant_learning_rate.learning_rate = 0.0005
-#run.learning_rate_schedule = @learning_rate_schedules.constant_learning_rate
-

train_xl.sh

@@ -1,11 +0,0 @@
-PROJECT_DIR=${HOME}"/models/eu-jav-categorisation"
-T5X_DIR="../../t5x"  # directory where the t5x is cloned.
-#Needs to be updated when moving to tpu-v4  it should then be in another zone
-MODEL_DIR="gs://nb-t5x-us-central2/eujav_xl"
-export PYTHONPATH=${PROJECT_DIR}
-
-python3 ${T5X_DIR}/t5x/train.py \
-  --gin_search_paths=${PROJECT_DIR} \
-  --gin_file="finetuning_categorisation_xl.gin" \
-  --gin.MODEL_DIR="'${MODEL_DIR}'" 
-

train_xxl.sh

@@ -1,11 +0,0 @@
-PROJECT_DIR=${HOME}"/models/eu-jav-categorisation"
-T5X_DIR="../../t5x"  # directory where the t5x is cloned.
-#Needs to be updated when moving to tpu-v4  it should then be in another zone
-MODEL_DIR="gs://nb-t5x-us-central2/eujav_xxl"
-export PYTHONPATH=${PROJECT_DIR}
-
-python3 ${T5X_DIR}/t5x/train.py \
-  --gin_search_paths=${PROJECT_DIR} \
-  --gin_file="finetuning_categorisation_xxl.gin" \
-  --gin.MODEL_DIR="'${MODEL_DIR}'" 
-