mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-28 16:52:24 +06:00
dd9d483d03
* doc
* [tests] Add sample files for a regression task
* [HUGE] Trainer
* Feedback from @sshleifer
* Feedback from @thomwolf + logging tweak
* [file_utils] when downloading concurrently, get_from_cache will use the cached file for subsequent processes
* [glue] Use default max_seq_length of 128 like before
* [glue] move DataTrainingArguments around
* [ner] Change interface of InputExample, and align run_{tf,pl}
* Re-align the pl scripts a little bit
* ner
* [ner] Add integration test
* Fix language_modeling with API tweak
* [ci] Tweak loss target
* Don't break console output
* amp.initialize: model must be on right device before
* [multiple-choice] update for Trainer
* Re-align to 827d6d6ef0
43 lines
1.7 KiB
Bash
Executable File
43 lines
1.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
# Install newest ptl.
|
|
pip install -U git+http://github.com/PyTorchLightning/pytorch-lightning/
|
|
# for seqeval metrics import
|
|
pip install -r ../requirements.txt
|
|
|
|
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-train.tsv?attredirects=0&d=1' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > train.txt.tmp
|
|
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-dev.tsv?attredirects=0&d=1' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > dev.txt.tmp
|
|
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-test.tsv?attredirects=0&d=1' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > test.txt.tmp
|
|
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
|
|
export MAX_LENGTH=128
|
|
export BERT_MODEL=bert-base-multilingual-cased
|
|
python3 preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt
|
|
python3 preprocess.py dev.txt.tmp $BERT_MODEL $MAX_LENGTH > dev.txt
|
|
python3 preprocess.py test.txt.tmp $BERT_MODEL $MAX_LENGTH > test.txt
|
|
cat train.txt dev.txt test.txt | cut -d " " -f 2 | grep -v "^$"| sort | uniq > labels.txt
|
|
export BATCH_SIZE=32
|
|
export NUM_EPOCHS=3
|
|
export SEED=1
|
|
|
|
export OUTPUT_DIR_NAME=germeval-model
|
|
export CURRENT_DIR=${PWD}
|
|
export OUTPUT_DIR=${CURRENT_DIR}/${OUTPUT_DIR_NAME}
|
|
mkdir -p $OUTPUT_DIR
|
|
|
|
# Add parent directory to python path to access transformer_base.py
|
|
export PYTHONPATH="../":"${PYTHONPATH}"
|
|
|
|
python3 run_pl_ner.py --data_dir ./ \
|
|
--model_type bert \
|
|
--labels ./labels.txt \
|
|
--model_name_or_path $BERT_MODEL \
|
|
--output_dir $OUTPUT_DIR \
|
|
--max_seq_length $MAX_LENGTH \
|
|
--num_train_epochs $NUM_EPOCHS \
|
|
--train_batch_size $BATCH_SIZE \
|
|
--seed $SEED \
|
|
--do_train \
|
|
--do_predict |