37 lines
1.5 KiB
Bash
Executable File
37 lines
1.5 KiB
Bash
Executable File
## The relevant files are currently on a shared Google
|
|
## drive at https://drive.google.com/drive/folders/1kC0I2UGl2ltrluI9NqDjaQJGw5iliw_J
|
|
## Monitor for changes and eventually migrate to use the `datasets` library
|
|
curl -L 'https://drive.google.com/uc?export=download&id=1Jjhbal535VVz2ap4v4r_rN1UEHTdLK5P' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > train.txt.tmp
|
|
curl -L 'https://drive.google.com/uc?export=download&id=1ZfRcQThdtAR5PPRjIDtrVP7BtXSCUBbm' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > dev.txt.tmp
|
|
curl -L 'https://drive.google.com/uc?export=download&id=1u9mb7kNJHWQCWyweMDRMuTFoOHOfeBTH' \
|
|
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > test.txt.tmp
|
|
|
|
export MAX_LENGTH=128
|
|
export BERT_MODEL=bert-base-multilingual-cased
|
|
python3 scripts/preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt
|
|
python3 scripts/preprocess.py dev.txt.tmp $BERT_MODEL $MAX_LENGTH > dev.txt
|
|
python3 scripts/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 OUTPUT_DIR=germeval-model
|
|
export BATCH_SIZE=32
|
|
export NUM_EPOCHS=3
|
|
export SAVE_STEPS=750
|
|
export SEED=1
|
|
|
|
python3 run_ner.py \
|
|
--task_type NER \
|
|
--data_dir . \
|
|
--labels ./labels.txt \
|
|
--model_name_or_path $BERT_MODEL \
|
|
--output_dir $OUTPUT_DIR \
|
|
--max_seq_length $MAX_LENGTH \
|
|
--num_train_epochs $NUM_EPOCHS \
|
|
--per_gpu_train_batch_size $BATCH_SIZE \
|
|
--save_steps $SAVE_STEPS \
|
|
--seed $SEED \
|
|
--do_train \
|
|
--do_eval \
|
|
--do_predict
|