AI-EnabledSoftwareEngineering-AISE
commented
2 years ago Also, this is my setup to just test your training.
export MASTER_PORT=1051
log_dir=./stage1_logs
save_dir=./stage1_checkpoints
mkdir -p $log_dir $save_dir
bpe_dir=../../utils/BPE
user_dir=../../ofa_module
# data_dir=../../dataset/caption_data
data_dir=/raid/AISSEL/YYYY/datasets/caption_data
data=${data_dir}/caption_stage1_train.tsv,${data_dir}/caption_val.tsv
restore_file=../../checkpoints/ofa_large.pt
selected_cols=0,4,2
task=caption
arch=ofa_large
criterion=adjust_label_smoothed_cross_entropy
label_smoothing=0.1
lr=1e-5
max_epoch=2
warmup_ratio=0.06
batch_size=8
update_freq=4
resnet_drop_path_rate=0.0
encoder_drop_path_rate=0.1
decoder_drop_path_rate=0.1
dropout=0.1
attention_dropout=0.0
max_src_length=80
max_tgt_length=20
num_bins=1000
drop_worst_after=2500
patch_image_size=480
eval_cider_cached=${data_dir}/cider_cached_tokens/coco-valid-words.p
drop_worst_ratio=0.2
CUDA_VISIBLE_DEVICES=0,1 ~/.conda/envs/ofa/bin/python -m torch.distributed.launch --nproc_per_node=4 --master_port=${MASTER_PORT} ../../train.py \
$data \
--selected-cols=${selected_cols} \
--bpe-dir=${bpe_dir} \
--user-dir=${user_dir} \
--restore-file=${restore_file} \
--reset-optimizer --reset-dataloader --reset-meters \
--save-dir=${save_path} \
--task=${task} \
--arch=${arch} \
--criterion=${criterion} \
--label-smoothing=${label_smoothing} \
--batch-size=${batch_size} \
--update-freq=${update_freq} \
--encoder-normalize-before \
--decoder-normalize-before \
--share-decoder-input-output-embed \
--share-all-embeddings \
--layernorm-embedding \
--patch-layernorm-embedding \
--code-layernorm-embedding \
--resnet-drop-path-rate=${resnet_drop_path_rate} \
--encoder-drop-path-rate=${encoder_drop_path_rate} \
--decoder-drop-path-rate=${decoder_drop_path_rate} \
--dropout=${dropout} \
--attention-dropout=${attention_dropout} \
--weight-decay=0.01 --optimizer=adam --adam-betas="(0.9,0.999)" --adam-eps=1e-08 --clip-norm=1.0 \
--lr-scheduler=polynomial_decay --lr=${lr} \
--max-epoch=${max_epoch} --warmup-ratio=${warmup_ratio} \
--log-format=simple --log-interval=10 \
--fixed-validation-seed=7 \
--no-epoch-checkpoints --keep-best-checkpoints=1 \
--save-interval=1 --validate-interval=1 \
--save-interval-updates=500 --validate-interval-updates=500 \
--eval-cider \
--eval-cider-cached-tokens=${eval_cider_cached} \
--eval-args='{"beam":5,"max_len_b":16,"no_repeat_ngram_size":3}' \
--best-checkpoint-metric=cider --maximize-best-checkpoint-metric \
--max-src-length=${max_src_length} \
--max-tgt-length=${max_tgt_length} \
--find-unused-parameters \
--freeze-encoder-embedding \
--freeze-decoder-embedding \
--add-type-embedding \
--scale-attn \
--scale-fc \
--scale-heads \
--disable-entangle \
--num-bins=${num_bins} \
--patch-image-size=${patch_image_size} \
--drop-worst-ratio=${drop_worst_ratio} \
--drop-worst-after=${drop_worst_after} \
--fp16 \
--fp16-scale-window=512 \
--num-workers=0 #> ${log_file} 2>&1
logicwong
zh-zhang1984
Hi, I am trying to train your model for the caption task, to do that I clone your last updated repository, and then I have followed your instruction. first of all, I faced a max_epoch error that was because of the shell version. After that I tried to train the model it gives me
unrecognized arguments: --warmup-ratio=0.06. I go to your train code and I could not find the warmup-ratio variable, did you remove it? How should I solve this issue?