cfgDefault.txt

FairseqConfig(_name=None, common=CommonConfig(_name=None, 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'), common_eval=CommonEvalConfig(_name=None, path=None, post_process=None, quiet=False, model_overrides='{}', results_path=None), distributed_training=DistributedTrainingConfig(_name=None, distributed_world_size=8, distributed_num_procs=8, distributed_rank=0, distributed_backend='nccl', distributed_init_method=None, distributed_port=-1, device_id=0, distributed_no_spawn=False, ddp_backend='pytorch_ddp', ddp_comm_hook='none', bucket_cap_mb=25, fix_batches_to_gpus=False, find_unused_parameters=False, gradient_as_bucket_view=False, fast_stat_sync=False, heartbeat_timeout=-1, broadcast_buffers=False, slowmo_momentum=None, slowmo_base_algorithm='localsgd', localsgd_frequency=3, nprocs_per_node=8, pipeline_model_parallel=False, pipeline_balance=None, pipeline_devices=None, pipeline_chunks=0, pipeline_encoder_balance=None, pipeline_encoder_devices=None, pipeline_decoder_balance=None, pipeline_decoder_devices=None, pipeline_checkpoint='never', zero_sharding='none', fp16='${common.fp16}', memory_efficient_fp16='${common.memory_efficient_fp16}', tpu='${common.tpu}', no_reshard_after_forward=False, fp32_reduce_scatter=False, cpu_offload=False, use_sharded_state=False, not_fsdp_flatten_parameters=False), dataset=DatasetConfig(_name=None, num_workers=1, skip_invalid_size_inputs_valid_test=False, max_tokens=None, batch_size=None, required_batch_size_multiple=8, required_seq_len_multiple=1, dataset_impl=None, data_buffer_size=10, train_subset='train', valid_subset='valid', combine_valid_subsets=None, ignore_unused_valid_subsets=False, validate_interval=1, validate_interval_updates=0, validate_after_updates=0, fixed_validation_seed=None, disable_validation=False, max_tokens_valid='${dataset.max_tokens}', batch_size_valid='${dataset.batch_size}', max_valid_steps=None, curriculum=0, gen_subset='test', num_shards=1, shard_id=0, grouped_shuffling=False, update_epoch_batch_itr='${dataset.grouped_shuffling}', update_ordered_indices_seed=False), optimization=OptimizationConfig(_name=None, max_epoch=0, max_update=0, stop_time_hours=0, clip_norm=0.0, sentence_avg=False, update_freq=[1], lr=[0.25], stop_min_lr=-1.0, use_bmuf=False, skip_remainder_batch=False, debug_param_names=False), checkpoint=CheckpointConfig(_name=None, save_dir='checkpoints', restore_file='checkpoint_last.pt', continue_once=None, finetune_from_model=None, reset_dataloader=False, reset_lr_scheduler=False, reset_meters=False, reset_optimizer=False, optimizer_overrides='{}', save_interval=1, save_interval_updates=0, keep_interval_updates=-1, keep_interval_updates_pattern=-1, keep_last_epochs=-1, keep_best_checkpoints=-1, no_save=False, no_epoch_checkpoints=False, no_last_checkpoints=False, no_save_optimizer_state=False, best_checkpoint_metric='loss', maximize_best_checkpoint_metric=False, patience=-1, checkpoint_suffix='', checkpoint_shard_count=1, load_checkpoint_on_all_dp_ranks=False, write_checkpoints_asynchronously=False, model_parallel_size='${common.model_parallel_size}'), bmuf=FairseqBMUFConfig(_name=None, block_lr=1, block_momentum=0.875, global_sync_iter=50, warmup_iterations=500, use_nbm=False, average_sync=False, distributed_world_size='${distributed_training.distributed_world_size}'), generation=GenerationConfig(_name=None, beam=5, beam_mt=0, nbest=1, max_len_a=0, max_len_b=200, max_len_a_mt=0, max_len_b_mt=200, min_len=1, match_source_len=False, unnormalized=False, no_early_stop=False, no_beamable_mm=False, lenpen=1, lenpen_mt=1, unkpen=0, replace_unk=None, sacrebleu=False, score_reference=False, prefix_size=0, no_repeat_ngram_size=0, sampling=False, sampling_topk=-1, sampling_topp=-1.0, constraints=None, temperature=1.0, diverse_beam_groups=-1, diverse_beam_strength=0.5, diversity_rate=-1.0, print_alignment=None, print_step=False, lm_path=None, lm_weight=0.0, iter_decode_eos_penalty=0.0, iter_decode_max_iter=10, iter_decode_force_max_iter=False, iter_decode_with_beam=1, iter_decode_with_external_reranker=False, retain_iter_history=False, retain_dropout=False, retain_dropout_modules=None, decoding_format=None, no_seed_provided=False, eos_token=None), eval_lm=EvalLMConfig(_name=None, output_word_probs=False, output_word_stats=False, context_window=0, softmax_batch=9223372036854775807), interactive=InteractiveConfig(_name=None, buffer_size=0, input='-'), model='???', task=None, criterion=None, optimizer=None, lr_scheduler=None, scoring=None, bpe=None, tokenizer=None, ema=EMAConfig(_name=None, store_ema=False, ema_decay=0.9999, ema_start_update=0, ema_seed_model=None, ema_update_freq=1, ema_fp32=False))