File size: 68,741 Bytes
95a3ca6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='zh', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='zh', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='fr', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='zh', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='es', target_lang='en', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ar', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='zh', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='es', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='ru', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin
Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, 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, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', scoring='bleu', task='translation', source_lang='en', target_lang='fr', trainpref=None, validpref=None, testpref='input', align_suffix=None, destdir='data-bin', thresholdtgt=0, thresholdsrc=0, tgtdict='bpe_vocab', srcdict='bpe_vocab', nwordstgt=-1, nwordssrc=-1, alignfile=None, dataset_impl='raw', joined_dictionary=False, only_source=False, padding_factor=8, workers=1, dict_only=False)
Wrote preprocessed data to data-bin