It's been stuck for days!Already installed fairseq, but it’s still a problem:ModuleNotFoundError: No module named 'fairseq.logging' ,that is log!
thank you!!!
Traceback (most recent call last):
File "train.py", line 11, in
cli_main()
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq_cli/train.py", line 451, in cli_main
main(args)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq_cli/train.py", line 89, in main
extra_state, epoch_itr = checkpoint_utils.load_checkpoint(args, trainer)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/checkpoint_utils.py", line 133, in load_checkpoint
reset_meters=args.reset_meters,
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/trainer.py", line 269, in load_checkpoint
state = checkpoint_utils.load_checkpoint_to_cpu(filename)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/checkpoint_utils.py", line 165, in load_checkpoint_to_cpu
f, map_location=lambda s, l: default_restore_location(s, "cpu")
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 594, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'fairseq.logging'
2021-03-25 15:34:40 | INFO | fairseq_cli.train | Namespace(T=1.0, activation_fn='gelu', adam_betas='(0.9, 0.999)', adam_eps=1e-08, adaptive_softmax_cutoff=None, adaptive_softmax_dropout=0, all_gather_list_size=16384, arch='bart_large', attention_dropout=0.1, balance=True, best_checkpoint_metric='loss', bpe=None, broadcast_buffers=False, bucket_cap_mb=25, clip_norm=0.1, cpu=False, criterion='label_smoothed_cross_entropy', cross_self_attention=False, curriculum=0, data='cnn_dm-bin_2', dataset_impl=None, ddp_backend='no_c10d', decoder_attention_heads=16, decoder_embed_dim=1024, decoder_embed_path=None, decoder_ffn_embed_dim=4096, decoder_input_dim=1024, decoder_layerdrop=0, decoder_layers=12, decoder_layers_to_keep=None, decoder_learned_pos=True, decoder_normalize_before=False, decoder_output_dim=1024, device_id=0, disable_validation=False, distributed_backend='nccl', distributed_init_method=None, distributed_no_spawn=False, distributed_port=-1, distributed_rank=0, distributed_world_size=1, dropout=0.1, empty_cache_freq=0, encoder_attention_heads=16, encoder_embed_dim=1024, encoder_embed_path=None, encoder_ffn_embed_dim=4096, encoder_layerdrop=0, encoder_layers=12, encoder_layers_to_keep=None, encoder_learned_pos=True, encoder_normalize_before=False, end_learning_rate=0.0, eval_bleu=False, eval_bleu_args=None, eval_bleu_detok='space', eval_bleu_detok_args=None, eval_bleu_print_samples=False, eval_bleu_remove_bpe=None, eval_tokenized_bleu=False, fast_stat_sync=False, find_unused_parameters=True, fix_batches_to_gpus=False, fixed_validation_seed=None, force_anneal=None, fp16=False, fp16_init_scale=128, fp16_no_flatten_grads=False, fp16_scale_tolerance=0.0, fp16_scale_window=None, keep_best_checkpoints=-1, keep_interval_updates=-1, keep_last_epochs=-1, label_smoothing=0.1, layer_wise_attention=False, layernorm_embedding=True, left_pad_source='True', left_pad_target='False', load_alignments=False, log_format=None, log_interval=1000, lr=[3e-05], lr_scheduler='polynomial_decay', lr_weight=1000.0, max_epoch=0, max_sentences=None, max_sentences_valid=None, max_source_positions=1024, max_target_positions=1024, max_tokens=800, max_tokens_valid=800, max_update=0, maximize_best_checkpoint_metric=False, memory_efficient_fp16=False, min_loss_scale=0.0001, min_lr=-1, multi_views=True, no_cross_attention=False, no_epoch_checkpoints=True, no_last_checkpoints=False, no_progress_bar=False, no_save=False, no_save_optimizer_state=False, no_scale_embedding=True, no_token_positional_embeddings=False, num_workers=1, optimizer='adam', optimizer_overrides='{}', patience=-1, pooler_activation_fn='tanh', pooler_dropout=0.0, power=1.0, relu_dropout=0.0, required_batch_size_multiple=1, reset_dataloader=True, reset_lr_scheduler=False, reset_meters=True, reset_optimizer=True, restore_file='./bart.large/model.pt', save_dir='checkpoints', save_interval=1, save_interval_updates=0, seed=1, sentence_avg=False, share_all_embeddings=True, share_decoder_input_output_embed=True, skip_invalid_size_inputs_valid_test=True, source_lang='source', target_lang='target', task='translation', tensorboard_logdir='', threshold_loss_scale=None, tokenizer=None, total_num_update=5000, train_subset='train', truncate_source=True, update_freq=[32], upsample_primary=1, use_bmuf=False, use_old_adam=False, user_dir=None, valid_subset='valid', validate_interval=1, warmup_updates=200, weight_decay=0.01)
2021-03-25 15:34:41 | INFO | fairseq.tasks.translation | [source] dictionary: 50264 types
2021-03-25 15:34:41 | INFO | fairseq.tasks.translation | [target] dictionary: 50264 types
2021-03-25 15:34:41 | INFO | fairseq.data.data_utils | loaded 3685 examples from: cnn_dm-bin_2/valid.source-target.source
2021-03-25 15:34:41 | INFO | fairseq.data.data_utils | loaded 3685 examples from: cnn_dm-bin/valid.source-target.source
2021-03-25 15:34:41 | INFO | fairseq.data.data_utils | loaded 3685 examples from: cnn_dm-bin_2/valid.source-target.target
2021-03-25 15:34:41 | INFO | fairseq.tasks.translation | cnn_dm-bin_2 valid source-target 3685 examples
!!! 3685 3685
2021-03-25 15:34:53 | INFO | fairseq_cli.train | BARTModel(
(encoder): TransformerEncoder(
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1)
(layers): ModuleList(
(0): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(1): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(2): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(3): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(4): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(5): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(6): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(7): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(8): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(9): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(10): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(11): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(decoder): TransformerDecoder(
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1)
(layers): ModuleList(
(0): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(1): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(2): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(3): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(4): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(5): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(6): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(7): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(8): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(9): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(10): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(11): TransformerDecoderLayer(
(self_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(classification_heads): ModuleDict()
(section_positions): LearnedPositionalEmbedding(1025, 1024, padding_idx=0)
(section_layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(section): LSTM(1024, 1024)
(w_proj_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(w_proj): Linear(in_features=1024, out_features=1024, bias=True)
(w_context_vector): Linear(in_features=1024, out_features=1, bias=False)
(softmax): Softmax(dim=1)
)
2021-03-25 15:34:53 | INFO | fairseq_cli.train | model bart_large, criterion LabelSmoothedCrossEntropyCriterion
2021-03-25 15:34:53 | INFO | fairseq_cli.train | num. model params: 416791552 (num. trained: 416791552)
2021-03-25 15:34:58 | INFO | fairseq_cli.train | training on 1 GPUs
2021-03-25 15:34:58 | INFO | fairseq_cli.train | max tokens per GPU = 800 and max sentences per GPU = None
Namespace(T=1.0, activation_dropout=0.0, activation_fn='gelu', adam_betas='(0.9, 0.999)', adam_eps=1e-08, adaptive_input=False, adaptive_softmax_cutoff=None, adaptive_softmax_dropout=0, all_gather_list_size=16384, arch='bart_large', attention_dropout=0.1, balance=True, best_checkpoint_metric='loss', bpe=None, broadcast_buffers=False, bucket_cap_mb=25, clip_norm=0.1, cpu=False, criterion='label_smoothed_cross_entropy', cross_self_attention=False, curriculum=0, data='cnn_dm-bin_2', dataset_impl=None, ddp_backend='no_c10d', decoder_attention_heads=16, decoder_embed_dim=1024, decoder_embed_path=None, decoder_ffn_embed_dim=4096, decoder_input_dim=1024, decoder_layerdrop=0, decoder_layers=12, decoder_layers_to_keep=None, decoder_learned_pos=True, decoder_normalize_before=False, decoder_output_dim=1024, device_id=0, disable_validation=False, distributed_backend='nccl', distributed_init_method=None, distributed_no_spawn=False, distributed_port=-1, distributed_rank=0, distributed_world_size=1, dropout=0.1, empty_cache_freq=0, encoder_attention_heads=16, encoder_embed_dim=1024, encoder_embed_path=None, encoder_ffn_embed_dim=4096, encoder_layerdrop=0, encoder_layers=12, encoder_layers_to_keep=None, encoder_learned_pos=True, encoder_normalize_before=False, end_learning_rate=0.0, eval_bleu=False, eval_bleu_args=None, eval_bleu_detok='space', eval_bleu_detok_args=None, eval_bleu_print_samples=False, eval_bleu_remove_bpe=None, eval_tokenized_bleu=False, fast_stat_sync=False, find_unused_parameters=True, fix_batches_to_gpus=False, fixed_validation_seed=None, force_anneal=None, fp16=False, fp16_init_scale=128, fp16_no_flatten_grads=False, fp16_scale_tolerance=0.0, fp16_scale_window=None, keep_best_checkpoints=-1, keep_interval_updates=-1, keep_last_epochs=-1, label_smoothing=0.1, layer_wise_attention=False, layernorm_embedding=True, left_pad_source=True, left_pad_target=False, load_alignments=False, log_format=None, log_interval=1000, lr=[3e-05], lr_scheduler='polynomial_decay', lr_weight=1000.0, max_epoch=0, max_sentences=None, max_sentences_valid=None, max_source_positions=1024, max_target_positions=1024, max_tokens=800, max_tokens_valid=800, max_update=0, maximize_best_checkpoint_metric=False, memory_efficient_fp16=False, min_loss_scale=0.0001, min_lr=-1, multi_views=True, no_cross_attention=False, no_epoch_checkpoints=True, no_last_checkpoints=False, no_progress_bar=False, no_save=False, no_save_optimizer_state=False, no_scale_embedding=True, no_token_positional_embeddings=False, num_workers=1, optimizer='adam', optimizer_overrides='{}', patience=-1, pooler_activation_fn='tanh', pooler_dropout=0.0, power=1.0, relu_dropout=0.0, required_batch_size_multiple=1, reset_dataloader=True, reset_lr_scheduler=False, reset_meters=True, reset_optimizer=True, restore_file='./bart.large/model.pt', save_dir='checkpoints', save_interval=1, save_interval_updates=0, seed=1, sentence_avg=False, share_all_embeddings=True, share_decoder_input_output_embed=True, skip_invalid_size_inputs_valid_test=True, source_lang='source', target_lang='target', task='translation', tensorboard_logdir='', threshold_loss_scale=None, tokenizer=None, total_num_update=5000, train_subset='train', truncate_source=True, update_freq=[32], upsample_primary=1, use_bmuf=False, use_old_adam=False, user_dir=None, valid_subset='valid', validate_interval=1, warmup_updates=200, weight_decay=0.01) <fairseq.trainer.Trainer object at 0x7f8c143bccf8>
Traceback (most recent call last):
File "train.py", line 11, in
cli_main()
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq_cli/train.py", line 451, in cli_main
main(args)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq_cli/train.py", line 89, in main
extra_state, epoch_itr = checkpoint_utils.load_checkpoint(args, trainer)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/checkpoint_utils.py", line 133, in load_checkpoint
reset_meters=args.reset_meters,
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/trainer.py", line 269, in load_checkpoint
state = checkpoint_utils.load_checkpoint_to_cpu(filename)
File "/tf/pym/Multi-View-Seq2Seq-master/fairseq_multi_view/fairseq/checkpoint_utils.py", line 165, in load_checkpoint_to_cpu
f, map_location=lambda s, l: default_restore_location(s, "cpu")
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 594, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'fairseq.logging'