Open xiang-xiang-zhu opened 2 years ago
when i run the dialogue code,it occurs i run the personachat code fairseq-train DATA-BIN -a transformer --optimizer adam --lr 0.0001 -s cxt -t res --label-smoothing 0.1 --dropout 0.3 --max-tokens 4000 --min-lr 1e-09 --criterion label_smoothed_cross_entropy --max-update 20000 --warmup-updates 3000 --warmup-init-lr 1e-07 --adam-betas '(0.9, 0.999)' --save-dir SAVE-DIR --share-all-embeddings --eval-bleu --eval-bleu-args '{"beam": 4, "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 --task translation --alpha 0.4 --temperature 4.5 --activation-dropout 0.1 --attention-dropout 0.1 --log-format json --log-interval 50
fairseq-train DATA-BIN -a transformer --optimizer adam --lr 0.0001 -s cxt -t res --label-smoothing 0.1 --dropout 0.3 --max-tokens 4000 --min-lr 1e-09 --criterion label_smoothed_cross_entropy --max-update 20000 --warmup-updates 3000 --warmup-init-lr 1e-07 --adam-betas '(0.9, 0.999)' --save-dir SAVE-DIR --share-all-embeddings --eval-bleu --eval-bleu-args '{"beam": 4, "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 --task translation --alpha 0.4 --temperature 4.5 --activation-dropout 0.1 --attention-dropout 0.1 --log-format json --log-interval 50
This is the Error fairseq-train: error: unrecognized arguments: --warmup-init-lr 1e-07 moses --alpha 0.4 --temperature 4.5
fairseq-train: error: unrecognized arguments: --warmup-init-lr 1e-07 moses --alpha 0.4 --temperature 4.5
Is there a solution yet?
LazyFyh
commented
1 year ago LazyFyh
commented
1 year ago
when i run the dialogue code,it occurs i run the personachat code
fairseq-train DATA-BIN -a transformer --optimizer adam --lr 0.0001 -s cxt -t res --label-smoothing 0.1 --dropout 0.3 --max-tokens 4000 --min-lr 1e-09 --criterion label_smoothed_cross_entropy --max-update 20000 --warmup-updates 3000 --warmup-init-lr 1e-07 --adam-betas '(0.9, 0.999)' --save-dir SAVE-DIR --share-all-embeddings --eval-bleu --eval-bleu-args '{"beam": 4, "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 --task translation --alpha 0.4 --temperature 4.5 --activation-dropout 0.1 --attention-dropout 0.1 --log-format json --log-interval 50This is the Error
fairseq-train: error: unrecognized arguments: --warmup-init-lr 1e-07 moses --alpha 0.4 --temperature 4.5