mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-24 06:48:58 +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
19 lines
490 B
Bash
Executable File
19 lines
490 B
Bash
Executable File
export OUTPUT_DIR_NAME=bart_sum
|
|
export CURRENT_DIR=${PWD}
|
|
export OUTPUT_DIR=${CURRENT_DIR}/${OUTPUT_DIR_NAME}
|
|
|
|
# Make output directory if it doesn't exist
|
|
mkdir -p $OUTPUT_DIR
|
|
|
|
# Add parent directory to python path to access transformer_base.py
|
|
export PYTHONPATH="../../":"${PYTHONPATH}"
|
|
|
|
python finetune.py \
|
|
--data_dir=./cnn-dailymail/cnn_dm \
|
|
--model_name_or_path=bart-large \
|
|
--learning_rate=3e-5 \
|
|
--train_batch_size=4 \
|
|
--eval_batch_size=4 \
|
|
--output_dir=$OUTPUT_DIR \
|
|
--do_train $@
|