Dev gzf deepspeed (#1835)

zhifu gao

2024-06-20 8f5576c3eaf7ba89bfce269d2a4846004aee43db

 examples/industrial_data_pretraining/bicif_paraformer/finetune.sh

@@ -1,6 +1,8 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

workspace=`pwd`

# method1, finetune from model hub

# which gpu to train or finetune
@@ -45,21 +47,38 @@
mkdir -p ${output_dir}
echo "log_file: ${log_file}"

torchrun \
--nnodes 1 \
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
deepspeed_config=${workspace}../../ds_stage1.json

DISTRIBUTED_ARGS="
    --nnodes ${WORLD_SIZE:-1} \
    --nproc_per_node $gpu_num \
    --node_rank ${RANK:-0} \
    --master_addr ${MASTER_ADDR:-127.0.0.1} \
    --master_port ${MASTER_PORT: 26669}
"

echo $DISTRIBUTED_ARGS

torchrun $DISTRIBUTED_ARGS \
../../../funasr/bin/train_ds.py \
++model="${model_name_or_model_dir}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset_conf.batch_size=20000 \
++dataset="AudioDataset" \
++dataset_conf.index_ds="IndexDSJsonl" \
++dataset_conf.data_split_num=1 \
++dataset_conf.batch_sampler="BatchSampler" \
++dataset_conf.batch_size=6000  \
++dataset_conf.sort_size=1024 \
++dataset_conf.batch_type="token" \
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=50 \
++train_conf.log_interval=1 \
++train_conf.resume=false \
++train_conf.resume=true \
++train_conf.validate_interval=2000 \
++train_conf.save_checkpoint_interval=2000 \
++train_conf.keep_nbest_models=20 \
++train_conf.use_deepspeed=false \
++train_conf.deepspeed_config=${deepspeed_config} \
++optim_conf.lr=0.0002 \
++output_dir="${output_dir}" &> ${log_file}