accelerate+deepspeed多机多卡训练的两种方法 - 知乎
单节点训练:
# Move into the first step of the pipeline cd training/step1_supervised_finetuning/
# Run the training script
bash training_scripts/single_gpu/ run_1.3b.sh
# Evaluate the model
bash evaluation_scripts/ run_prompt.sh
run_1.3b.sh脚本
# DeepSpeed Team
OUTPUT=$1
ZERO_STAGE=$2
if [ "$OUTPUT" == "" ]; then
OUTPUT=./output
fi
if [ "$ZERO_STAGE" == "" ]; then
ZERO_STAGE=2
fi
mkdir -p $OUTPUT
deepspeed main.py \
--data_path Dahoas/rm-static Dahoas/full-hh-rlhf Dahoas/synthetic-instruct-gptj-pairwise yitingxie/rlhf-reward-datasets \
--data_split 2,4,4 \
--model_name_or_path facebook/opt-1.3b \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 8 \
--max_seq_len 512 \
--learning_rate 9.65e-6 \
--weight_decay 0. \
--num_train_epochs 16 \
--gradient_accumulation_steps 1 \
--lr_scheduler_type cosine \
--num_warmup_steps 0 \
--seed 1234 \
--zero_stage $ZERO_STAGE \
--deepspeed \
--output_dir $OUTPUT \
&> $OUTPUT/training.log
~