tmp.txt

FAIRSEQ_PATH=~/fairseq
CHECKPOINTS=checkpoints/levt
DATASET=data-bin/joint-bpe-37k

python3 train.py \
    --save-dir $CHECKPOINTS \
    --ddp-backend=no_c10d \
    --task translation_lev \
    --criterion nat_loss \
    --arch levenshtein_transformer \
    --noise random_delete \
    --share-all-embeddings \
    --optimizer adam --adam-betas '(0.9,0.98)' \
    --lr 0.0005 --lr-scheduler inverse_sqrt \
    --min-lr '1e-09' --warmup-updates 10000 \
    --warmup-init-lr '1e-07' --label-smoothing 0.1 \
    --dropout 0.3 --weight-decay 0.01 \
    --decoder-learned-pos \
    --encoder-learned-pos \
    --apply-bert-init \
    --log-format 'simple' --log-interval 100 \
    --fixed-validation-seed 7 \
    --max-tokens 500 \
    --save-interval-updates 5000 \
    --max-update 300000 \
    $DATASET

python3 train.py \
    $DATASET \
    --arch transformer --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 8182 --fp16



cat gec.src gec.trg | python subword-nmt/learn_bpe.py -s 8000 -o bpecodes

python subword-nmt/apply_bpe.py -c bpecodes  <gec.src> gec.src.bpe



python3 train.py \
    data-bin/gec \
    --arch transformer_vaswani_wmt_en_de_big --share-all-embeddings \
    --save-dir checkpoints/err_generator \
    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
    --lr 0.0005 --lr-scheduler inverse_sqrt --warmup-updates 4000 --warmup-init-lr 1e-07 \
    --dropout 0.3 --weight-decay 0.0 \
    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
    --max-update 100000 \
    --max-tokens 8000 \
    --fp16 \
    --keep-last-epochs 2