mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-29 17:22:25 +06:00
8062fa63c5
* replace init_ddp_connection for index init * style * add finetune test * add test data * move generate tensors to device * add test on EM metric * style * allow multi process test * keep gloo process group for retrieval * add multi-gpu test * use custom accelerator * clean test finetune * minor * style * style * typo * use python call instead of imported main fumction * return_dict fix in modeling_rag * use float32 in retrieval * store as float32 as well in the custom knowledge dataset example * style * rename to finetune_rag * style * update readme * rename utils and callbacks to utils_rag and callbacks_rag * fix test * patrick's comments * generate dummy data in the finetue test script * remove dummy data files * style
34 lines
1.0 KiB
Bash
Executable File
34 lines
1.0 KiB
Bash
Executable File
# Add parent directory to python path to access lightning_base.py
|
|
export PYTHONPATH="../":"${PYTHONPATH}"
|
|
|
|
# A sample finetuning run, you need to specify data_dir, output_dir and model_name_or_path
|
|
# run ./examples/rag/finetune.sh --help to see all the possible options
|
|
|
|
python examples/rag/finetune_rag.py \
|
|
--data_dir $DATA_DIR \
|
|
--output_dir $OUTPUT_DIR \
|
|
--model_name_or_path $MODEL_NAME_OR_PATH \
|
|
--model_type rag_sequence \
|
|
--fp16 \
|
|
--gpus 8 \
|
|
--do_train \
|
|
--do_predict \
|
|
--n_val -1 \
|
|
--val_check_interval 0.25 \
|
|
--train_batch_size 8 \
|
|
--eval_batch_size 1 \
|
|
--max_source_length 128 \
|
|
--max_target_length 25 \
|
|
--val_max_target_length 25 \
|
|
--test_max_target_length 25 \
|
|
--label_smoothing 0.1 \
|
|
--dropout 0.1 \
|
|
--attention_dropout 0.1 \
|
|
--weight_decay 0.001 \
|
|
--adam_epsilon 1e-08 \
|
|
--max_grad_norm 0.1 \
|
|
--lr_scheduler polynomial \
|
|
--learning_rate 3e-05 \
|
|
--num_train_epochs 100 \
|
|
--warmup_steps 500 \
|
|
--gradient_accumulation_steps 1 |