export HSA_FORCE_FINE_GRAIN_PCIE=1 export MIOPEN_FIND_MODE=1 export HIP_VISIBLE_DEVICES=0 export TOKEN=2560 export DATA_PATH=~/data/wmt14_en_de_joined_dict python3 train.py \ $DATA_PATH \ --arch transformer_wmt_en_de \ --share-decoder-input-output-embed \ --optimizer adam \ --adam-betas '(0.9, 0.98)' \ --clip-norm 0.0 \ --lr 5e-4 \ --lr-scheduler inverse_sqrt \ --warmup-updates 4000 \ --dropout 0.3 \ --weight-decay 0.0001 \ --criterion label_smoothed_cross_entropy \ --label-smoothing 0.1 \ --max-tokens ${TOKEN} \ --eval-bleu \ --eval-bleu-args '{"beam": 5, "max_len_a": 1.2, "max_len_b": 10}' \ --eval-bleu-detok moses \ --eval-bleu-remove-bpe \ --eval-bleu-print-samples \ --best-checkpoint-metric bleu \ --maximize-best-checkpoint-metric \ --max-epoch 1 --fp16 --reset-optimizer