Comments (7)
Sorry for the late reply! I think these results 53.04-27.85-49.71
are acceptable.
For more information
- I use
tesla_v100s-pcie-32gb
to train my model. - Different
seed
may also produce some differences.
from plm_annotator.
Hi,
I'm also having some problems with re-implement. The rouge score I got are only:
rouge-1: 42.80 53.80 45.06
rouge-2: 18.17 22.93 19.14
rouge-l: 40.59 49.03 42.67
ROUGE 1-2-L F: 45.06-19.14-42.67
I use tesla_v100-sxm2-32gb
to train the model. And I tested with the best checkpoint, which is probably the fifth one. However, there is a difference of about 10 points here. But can gpu and seed cause such a big gap? Can you give me some advice?
Thank you very much!
from plm_annotator.
@Aiah Have you checked with my released checkpoint? You can first test using it to make sure whether the difference is caused by different ROUGE versions.
from plm_annotator.
@Aiah Have you checked with my released checkpoint? You can first test using it to make sure whether the difference is caused by different ROUGE versions.
Yes, I have checked with your released checkpoint, and result is:
rouge-1: 54.52 57.37 53.11
rouge-2: 29.25 30.78 28.34
rouge-l: 51.02 53.16 50.18
ROUGE 1-2-L F: 53.11-28.34-50.18
from plm_annotator.
@Aiah You can add my WeChat, Id: xcfeng-hit.
from plm_annotator.
log for the first epoch
2021-11-20 12:07:05 | INFO | fairseq_cli.train | Namespace(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, batch_size=None, batch_size_valid=None, best_checkpoint_metric='loss', bf16=False, bpe=None, broadcast_buffers=False, bucket_cap_mb=25, checkpoint_suffix='', clip_norm=0.1, cpu=False, criterion='label_smoothed_cross_entropy', cross_self_attention=False, curriculum=0, data='data/bin', data_buffer_size=10, dataset_impl=None, ddp_backend='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_num_procs=1, distributed_port=-1, distributed_rank=0, distributed_world_size=1, distributed_wrapper='DDP', 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, finetune_from_model=None, 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, gen_subset='test', keep_best_checkpoints=-1, keep_interval_updates=-1, keep_last_epochs=-1, label_smoothing=0.1, layernorm_embedding=True, left_pad_source='True', left_pad_target='False', load_alignments=False, local_rank=0, localsgd_frequency=3, log_format=None, log_interval=100, lr=[3e-05], lr_scheduler='polynomial_decay', max_epoch=0, max_source_positions=1024, max_target_positions=1024, max_tokens=800, max_tokens_valid=1024, max_update=0, maximize_best_checkpoint_metric=False, memory_efficient_bf16=False, memory_efficient_fp16=False, min_loss_scale=0.0001, min_lr=-1.0, model_parallel_size=1, 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_seed_provided=False, no_token_positional_embeddings=False, nprocs_per_node=1, num_batch_buckets=0, num_shards=1, num_workers=1, optimizer='adam', optimizer_overrides='{}', patience=-1, pipeline_balance=None, pipeline_checkpoint='never', pipeline_chunks=0, pipeline_devices=None, pipeline_model_parallel=False, pooler_activation_fn='tanh', pooler_dropout=0.0, power=1.0, profile=False, quant_noise_pq=0, quant_noise_pq_block_size=8, quant_noise_scalar=0, quantization_config_path=None, relu_dropout=0.0, required_batch_size_multiple=1, required_seq_len_multiple=1, reset_dataloader=True, reset_lr_scheduler=False, reset_meters=True, reset_optimizer=True, restore_file='/users7/xiachongfeng/acl/acl21/fairseq090/bart/bart.large/model.pt', save_dir='ckpt/main', save_interval=1, save_interval_updates=0, scoring='bleu', seed=1, sent_ratio=0.0, sentence_avg=False, shard_id=0, share_all_embeddings=True, share_decoder_input_output_embed=True, skip_invalid_size_inputs_valid_test=True, slowmo_algorithm='LocalSGD', slowmo_momentum=None, source_lang='source', stop_time_hours=0, target_lang='target', task='translation', tensorboard_logdir=None, threshold_loss_scale=None, token_ratio=0.0, tokenizer=None, total_num_update=100000, tpu=False, 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_after_updates=0, validate_interval=1, validate_interval_updates=0, warmup_updates=400, weight_decay=0.01, zero_sharding='none')
2021-11-20 12:07:05 | INFO | fairseq.tasks.translation | [source] dictionary: 50264 types
2021-11-20 12:07:05 | INFO | fairseq.tasks.translation | [target] dictionary: 50264 types
2021-11-20 12:07:05 | INFO | fairseq.data.data_utils | loaded 818 examples from: data/bin/valid.source-target.source
2021-11-20 12:07:06 | INFO | fairseq.data.data_utils | loaded 818 examples from: data/bin/valid.source-target.target
2021-11-20 12:07:06 | INFO | fairseq.tasks.translation | data/bin valid source-target 818 examples
2021-11-20 12:07:17 | INFO | fairseq_cli.train | BARTModel(
(encoder): TransformerEncoder(
(dropout_module): FairseqDropout()
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(layers): ModuleList(
(0): TransformerEncoderLayer(
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(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)
(dropout_module): FairseqDropout()
(activation_dropout_module): FairseqDropout()
(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)
)
)
)
(decoder): TransformerDecoder(
(dropout_module): FairseqDropout()
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(layers): ModuleList(
(0): TransformerDecoderLayer(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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(
(dropout_module): FairseqDropout()
(self_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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)
)
(activation_dropout_module): FairseqDropout()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MultiheadAttention(
(dropout_module): FairseqDropout()
(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) [0/1676]
)
)
(output_projection): Linear(in_features=1024, out_features=50264, bias=False)
)
(classification_heads): ModuleDict()
)
2021-11-20 12:07:17 | INFO | fairseq_cli.train | task: translation (TranslationTask)
2021-11-20 12:07:17 | INFO | fairseq_cli.train | model: bart_large (BARTModel)
2021-11-20 12:07:17 | INFO | fairseq_cli.train | criterion: label_smoothed_cross_entropy (LabelSmoothedCrossEntropyCriterion)
2021-11-20 12:07:17 | INFO | fairseq_cli.train | num. model params: 406290432 (num. trained: 406290432)
2021-11-20 12:07:28 | INFO | fairseq.trainer | detected shared parameter: encoder.embed_tokens.weight <- decoder.embed_tokens.weight
2021-11-20 12:07:28 | INFO | fairseq.trainer | detected shared parameter: encoder.embed_tokens.weight <- decoder.output_projection.weight
2021-11-20 12:07:28 | INFO | fairseq.utils | ***********************CUDA enviroments for all 1 workers***********************
2021-11-20 12:07:28 | INFO | fairseq.utils | rank 0: capabilities = 7.0 ; total memory = 31.749 GB ; name = Tesla V100-PCIE-32GB
2021-11-20 12:07:28 | INFO | fairseq.utils | ***********************CUDA enviroments for all 1 workers***********************
2021-11-20 12:07:28 | INFO | fairseq_cli.train | training on 1 devices (GPUs/TPUs)
2021-11-20 12:07:28 | INFO | fairseq_cli.train | max tokens per GPU = 800 and max sentences per GPU = None
2021-11-20 12:08:11 | INFO | fairseq.trainer | loaded checkpoint /users7/xiachongfeng/acl/acl21/fairseq090/bart/bart.large/model.pt (epoch 41 @ 0 updates)
2021-11-20 12:08:11 | INFO | fairseq.trainer | NOTE: your device may support faster training with --fp16
2021-11-20 12:08:11 | INFO | fairseq.trainer | loading train data for epoch 1
2021-11-20 12:08:11 | INFO | fairseq.data.data_utils | loaded 14731 examples from: data/bin/train.source-target.source
2021-11-20 12:08:11 | INFO | fairseq.data.data_utils | loaded 14731 examples from: data/bin/train.source-target.target
2021-11-20 12:08:11 | INFO | fairseq.tasks.translation | data/bin train source-target 14731 examples
2021-11-20 12:08:11 | WARNING | fairseq.tasks.fairseq_task | 30 samples have invalid sizes and will be skipped, max_positions=(800, 800), first few sample ids=[4133, 4745, 14537, 13184, 11747, 8799, 12738, 13340, 1144, 8870]
epoch 001: 0%| | 0/124 [00:00<?, ?it/s]2021-11-20 12:08:11 | INFO | fairseq.trainer | begin training epoch 1
/users7/xiachongfeng/reacl/bart/fairseq/utils.py:341: UserWarning: amp_C fused kernels unavailable, disabling multi_tensor_l2norm; you may get better performance by installing NVIDIA's apex library
"amp_C fused kernels unavailable, disabling multi_tensor_l2norm; "
epoch 001: 99%|▉| 123/124 [09:04<00:04, 4.38s/it, loss=5.733, nll_loss=3.816, ppl=14.09, wps=712.8, ups=0.23, wpb=3117, bsz=119.4, num_updates=100, lr=7.5e
2021-11-20 12:17:18 | INFO | fairseq_cli.train | begin validation on "valid" subset
2021-11-20 12:17:27 | INFO | valid | epoch 001 | valid on 'valid' subset | loss 4.13 | nll_loss 2.225 | ppl 4.68 | wps 2361.1 | wpb 129.7 | bsz 5 | num_updates 124
2021-11-20 12:17:27 | INFO | fairseq_cli.train | begin save checkpoint
from plm_annotator.
log for the first epoch
2021-11-20 12:07:05 | INFO | fairseq_cli.train | Namespace(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, batch_size=None, batch_size_valid=None, best_checkpoint_metric='loss', bf16=False, bpe=None, broadcast_buffers=False, bucket_cap_mb=25, checkpoint_suffix='', clip_norm=0.1, cpu=False, criterion='label_smoothed_cross_entropy', cross_self_attention=False, curriculum=0, data='data/bin', data_buffer_size=10, dataset_impl=None, ddp_backend='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_num_procs=1, distributed_port=-1, distributed_rank=0, distributed_world_size=1, distributed_wrapper='DDP', 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, finetune_from_model=None, 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, gen_subset='test', keep_best_checkpoints=-1, keep_interval_updates=-1, keep_last_epochs=-1, label_smoothing=0.1, layernorm_embedding=True, left_pad_source='True', left_pad_target='False', load_alignments=False, local_rank=0, localsgd_frequency=3, log_format=None, log_interval=100, lr=[3e-05], lr_scheduler='polynomial_decay', max_epoch=0, max_source_positions=1024, max_target_positions=1024, max_tokens=800, max_tokens_valid=1024, max_update=0, maximize_best_checkpoint_metric=False, memory_efficient_bf16=False, memory_efficient_fp16=False, min_loss_scale=0.0001, min_lr=-1.0, model_parallel_size=1, 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_seed_provided=False, no_token_positional_embeddings=False, nprocs_per_node=1, num_batch_buckets=0, num_shards=1, num_workers=1, optimizer='adam', optimizer_overrides='{}', patience=-1, pipeline_balance=None, pipeline_checkpoint='never', pipeline_chunks=0, pipeline_devices=None, pipeline_model_parallel=False, pooler_activation_fn='tanh', pooler_dropout=0.0, power=1.0, profile=False, quant_noise_pq=0, quant_noise_pq_block_size=8, quant_noise_scalar=0, quantization_config_path=None, relu_dropout=0.0, required_batch_size_multiple=1, required_seq_len_multiple=1, reset_dataloader=True, reset_lr_scheduler=False, reset_meters=True, reset_optimizer=True, restore_file='/users7/xiachongfeng/acl/acl21/fairseq090/bart/bart.large/model.pt', save_dir='ckpt/main', save_interval=1, save_interval_updates=0, scoring='bleu', seed=1, sent_ratio=0.0, sentence_avg=False, shard_id=0, share_all_embeddings=True, share_decoder_input_output_embed=True, skip_invalid_size_inputs_valid_test=True, slowmo_algorithm='LocalSGD', slowmo_momentum=None, source_lang='source', stop_time_hours=0, target_lang='target', task='translation', tensorboard_logdir=None, threshold_loss_scale=None, token_ratio=0.0, tokenizer=None, total_num_update=100000, tpu=False, 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_after_updates=0, validate_interval=1, validate_interval_updates=0, warmup_updates=400, weight_decay=0.01, zero_sharding='none') 2021-11-20 12:07:05 | INFO | fairseq.tasks.translation | [source] dictionary: 50264 types 2021-11-20 12:07:05 | INFO | fairseq.tasks.translation | [target] dictionary: 50264 types 2021-11-20 12:07:05 | INFO | fairseq.data.data_utils | loaded 818 examples from: data/bin/valid.source-target.source 2021-11-20 12:07:06 | INFO | fairseq.data.data_utils | loaded 818 examples from: data/bin/valid.source-target.target 2021-11-20 12:07:06 | INFO | fairseq.tasks.translation | data/bin valid source-target 818 examples 2021-11-20 12:07:17 | INFO | fairseq_cli.train | BARTModel( (encoder): TransformerEncoder( (dropout_module): FairseqDropout() (embed_tokens): Embedding(50264, 1024, padding_idx=1) (embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1) (layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (layers): ModuleList( (0): TransformerEncoderLayer( (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (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) (dropout_module): FairseqDropout() (activation_dropout_module): FairseqDropout() (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) ) ) ) (decoder): TransformerDecoder( (dropout_module): FairseqDropout() (embed_tokens): Embedding(50264, 1024, padding_idx=1) (embed_positions): LearnedPositionalEmbedding(1026, 1024, padding_idx=1) (layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (layers): ModuleList( (0): TransformerDecoderLayer( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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( (dropout_module): FairseqDropout() (self_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) ) (activation_dropout_module): FairseqDropout() (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (encoder_attn): MultiheadAttention( (dropout_module): FairseqDropout() (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) [0/1676] ) ) (output_projection): Linear(in_features=1024, out_features=50264, bias=False) ) (classification_heads): ModuleDict() ) 2021-11-20 12:07:17 | INFO | fairseq_cli.train | task: translation (TranslationTask) 2021-11-20 12:07:17 | INFO | fairseq_cli.train | model: bart_large (BARTModel) 2021-11-20 12:07:17 | INFO | fairseq_cli.train | criterion: label_smoothed_cross_entropy (LabelSmoothedCrossEntropyCriterion) 2021-11-20 12:07:17 | INFO | fairseq_cli.train | num. model params: 406290432 (num. trained: 406290432) 2021-11-20 12:07:28 | INFO | fairseq.trainer | detected shared parameter: encoder.embed_tokens.weight <- decoder.embed_tokens.weight 2021-11-20 12:07:28 | INFO | fairseq.trainer | detected shared parameter: encoder.embed_tokens.weight <- decoder.output_projection.weight 2021-11-20 12:07:28 | INFO | fairseq.utils | ***********************CUDA enviroments for all 1 workers*********************** 2021-11-20 12:07:28 | INFO | fairseq.utils | rank 0: capabilities = 7.0 ; total memory = 31.749 GB ; name = Tesla V100-PCIE-32GB 2021-11-20 12:07:28 | INFO | fairseq.utils | ***********************CUDA enviroments for all 1 workers*********************** 2021-11-20 12:07:28 | INFO | fairseq_cli.train | training on 1 devices (GPUs/TPUs) 2021-11-20 12:07:28 | INFO | fairseq_cli.train | max tokens per GPU = 800 and max sentences per GPU = None 2021-11-20 12:08:11 | INFO | fairseq.trainer | loaded checkpoint /users7/xiachongfeng/acl/acl21/fairseq090/bart/bart.large/model.pt (epoch 41 @ 0 updates) 2021-11-20 12:08:11 | INFO | fairseq.trainer | NOTE: your device may support faster training with --fp16 2021-11-20 12:08:11 | INFO | fairseq.trainer | loading train data for epoch 1 2021-11-20 12:08:11 | INFO | fairseq.data.data_utils | loaded 14731 examples from: data/bin/train.source-target.source 2021-11-20 12:08:11 | INFO | fairseq.data.data_utils | loaded 14731 examples from: data/bin/train.source-target.target 2021-11-20 12:08:11 | INFO | fairseq.tasks.translation | data/bin train source-target 14731 examples 2021-11-20 12:08:11 | WARNING | fairseq.tasks.fairseq_task | 30 samples have invalid sizes and will be skipped, max_positions=(800, 800), first few sample ids=[4133, 4745, 14537, 13184, 11747, 8799, 12738, 13340, 1144, 8870] epoch 001: 0%| | 0/124 [00:00<?, ?it/s]2021-11-20 12:08:11 | INFO | fairseq.trainer | begin training epoch 1 /users7/xiachongfeng/reacl/bart/fairseq/utils.py:341: UserWarning: amp_C fused kernels unavailable, disabling multi_tensor_l2norm; you may get better performance by installing NVIDIA's apex library "amp_C fused kernels unavailable, disabling multi_tensor_l2norm; " epoch 001: 99%|▉| 123/124 [09:04<00:04, 4.38s/it, loss=5.733, nll_loss=3.816, ppl=14.09, wps=712.8, ups=0.23, wpb=3117, bsz=119.4, num_updates=100, lr=7.5e 2021-11-20 12:17:18 | INFO | fairseq_cli.train | begin validation on "valid" subset 2021-11-20 12:17:27 | INFO | valid | epoch 001 | valid on 'valid' subset | loss 4.13 | nll_loss 2.225 | ppl 4.68 | wps 2361.1 | wpb 129.7 | bsz 5 | num_updates 124 2021-11-20 12:17:27 | INFO | fairseq_cli.train | begin save checkpoint
Hi, may I know how much time it took to get the best checkpoint for both SamSUM and AMI datasets? Thanks.
from plm_annotator.
Related Issues (8)
- Code for Data Preprocessing HOT 5
- Rouge Score HOT 8
- 能分享一下源码吗 HOT 2
- 关于Topic Segmentation代码部分的问题 HOT 1
- Max sentence length shouldn't exceed 800 HOT 4
- 关于第一步get loss的问题 HOT 1
- Special Tokens Representation HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from plm_annotator.