data/test/trainable_data/de2en/preprocess.log

Namespace(no_progress_bar=False, log_interval=100, log_format=None, tensorboard_logdir=None, seed=30, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=False, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=128, fp16_scale_window=None, fp16_scale_tolerance=0.0, min_loss_scale=0.0001, threshold_loss_scale=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, checkpoint_suffix='', checkpoint_shard_count=1, quantization_config_path=None, profile=False, criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='de', target_lang='en', trainpref='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.train', validpref='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.valid', testpref='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test', align_suffix=None, destdir='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data', thresholdtgt=0, thresholdsrc=0, tgtdict=None, srcdict=None, nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='mmap', joined_dictionary=True, only_source=False, padding_factor=8, workers=32)
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.train.de: 46388489 sents, 1161403088 tokens, 0.0% replaced by <unk>
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.valid.de: 1997 sents, 58227 tokens, 0.00515% replaced by <unk>
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.de: 3545 sents, 116081 tokens, 0.00345% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.train.en: 46388489 sents, 1094684830 tokens, 0.0% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.valid.en: 1997 sents, 54062 tokens, 0.0% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.en: 3545 sents, 110575 tokens, 0.00181% replaced by <unk>
Wrote preprocessed data to /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data
Namespace(no_progress_bar=False, log_interval=100, log_format=None, tensorboard_logdir=None, seed=30, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=False, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=128, fp16_scale_window=None, fp16_scale_tolerance=0.0, min_loss_scale=0.0001, threshold_loss_scale=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, checkpoint_suffix='', checkpoint_shard_count=1, quantization_config_path=None, profile=False, criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='de', target_lang='en', trainpref=None, validpref=None, testpref='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.flores,/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt22,/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt23', align_suffix=None, destdir='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data', thresholdtgt=0, thresholdsrc=0, tgtdict=None, srcdict=None, nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='mmap', joined_dictionary=True, only_source=False, padding_factor=8, workers=32)
Namespace(no_progress_bar=False, log_interval=100, log_format=None, tensorboard_logdir=None, seed=30, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=False, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=128, fp16_scale_window=None, fp16_scale_tolerance=0.0, min_loss_scale=0.0001, threshold_loss_scale=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, checkpoint_suffix='', checkpoint_shard_count=1, quantization_config_path=None, profile=False, criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='de', target_lang='en', trainpref=None, validpref=None, testpref='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.flores,/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt22,/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt23', align_suffix=None, destdir='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data', thresholdtgt=0, thresholdsrc=0, tgtdict='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data/dict.en.txt', srcdict='/mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data/dict.de.txt', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='mmap', joined_dictionary=False, only_source=False, padding_factor=8, workers=32)
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.flores.de: 1012 sents, 34004 tokens, 0.00588% replaced by <unk>
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt22.de: 1984 sents, 45732 tokens, 0.00219% replaced by <unk>
[de] Dictionary: 47776 types
[de] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt23.de: 549 sents, 36345 tokens, 0.00275% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.flores.en: 1012 sents, 30385 tokens, 0.00658% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt22.en: 1984 sents, 45259 tokens, 0.0% replaced by <unk>
[en] Dictionary: 47776 types
[en] /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/bpe/bpe.test.wmt23.en: 549 sents, 34931 tokens, 0.0% replaced by <unk>
Wrote preprocessed data to /mnt/ouyangyx/trans_fairseq/nmt/data/de-en/wmt23-50M/trainable_data