minute ignored when running ETTm2 using provided code & script

[efg001]

Run config:

export CUDA_VISIBLE_DEVICES=0

#cd ..

for model in FEDformer
do

for preLen in 96
do

# ETTm2
python -u run.py \
  --is_training 1 \
  --root_path ./dataset/ETT-small/ \
  --data_path ETTm2.csv \
  --task_id ETTm2 \
  --model $model \
  --data ETTm2 \
  --features M \
  --seq_len 96 \
  --label_len 48 \
  --pred_len $preLen \
  --e_layers 2 \
  --d_layers 1 \
  --factor 3 \
  --enc_in 7 \
  --dec_in 7 \
  --c_out 7 \
  --des 'Exp' \
  --d_model 512 \
  --itr 3

done

done

Easiest way to verify it is to add a print statement here: https://github.com/MAZiqing/FEDformer/blob/c0f6b972def125691434d62be1ecadf710ae921a/layers/Embed.py#L132

class DataEmbedding_wo_pos(nn.Module):
    def __init__(self, c_in, d_model, embed_type='fixed', freq='h', dropout=0.1):
        super(DataEmbedding_wo_pos, self).__init__()
        print("DataEmbedding_wo_pos freq ", freq)

freq in run param is not set in run script(default to h) so there is no dimension mismatch

I could open a PR but I am pretty new to this repo so opening an issue first.