Reproducing ZINC result with v2

Hi,
First, thanks for the code.
I tried to reproduce the result of ZINC subset with graphormer v2 code, but my best validation loss was 0.178 with parameters in the given script with test loss 0.164, and 0.186 with parameters in the paper with test loss 0.157.
The latter script's code is as follows:

CUDA_VISIBLE_DEVICES=0 fairseq-train \
--user-dir ../../graphormer \
--num-workers 16 \
--ddp-backend=legacy_ddp \
--dataset-name zinc \
--dataset-source pyg \
--task graph_prediction \
--criterion l1_loss \
--arch graphormer_slim \
--num-classes 1 \
--attention-dropout 0.1 --act-dropout 0.1 --dropout 0.0 \
--optimizer adam --adam-betas '(0.9, 0.999)' --adam-eps 1e-8 --clip-norm 5.0 --weight-decay 0.01 \
--lr-scheduler polynomial_decay --power 1 --warmup-updates 40000 --total-num-update 400000 \
--lr 2e-4 --end-learning-rate 1e-9 \
--batch-size 256 \
--fp16 \
--data-buffer-size 20 \
--encoder-layers 12 \
--encoder-embed-dim 80 \
--encoder-ffn-embed-dim 80 \
--encoder-attention-heads 8 \
--max-epoch 10000 \
--keep-best-checkpoints 1 \
--save-dir ./ckpts

Thanks in advance.

Start with the provided fairseq-train command and the Graphormer v2 ZINC training entry point. Compare the script and paper parameters against the reported validation and test losses, then document the cause of the reproduction gap or the settings needed to match the published result.