|
|
|
save_data: cnndm/run/example |
|
|
|
overwrite: False |
|
|
|
|
|
src_seq_length: 10000 |
|
tgt_seq_length: 10000 |
|
src_seq_length_trunc: 400 |
|
tgt_seq_length_trunc: 100 |
|
|
|
|
|
share_vocab: True |
|
|
|
|
|
data: |
|
cnndm: |
|
path_src: cnndm/train.txt.src |
|
path_tgt: cnndm/train.txt.tgt.tagged |
|
transforms: [] |
|
weight: 1 |
|
valid: |
|
path_src: cnndm/val.txt.src |
|
path_tgt: cnndm/val.txt.tgt.tagged |
|
transforms: [] |
|
|
|
src_vocab_size: 50000 |
|
tgt_vocab_size: 50000 |
|
|
|
src_vocab: cnndm/run/example.vocab.src |
|
tgt_vocab: cnndm/run/example.vocab.tgt |
|
|
|
save_model: cnndm/run/model |
|
copy_attn: true |
|
global_attention: mlp |
|
word_vec_size: 128 |
|
rnn_size: 512 |
|
layers: 1 |
|
encoder_type: brnn |
|
train_steps: 200000 |
|
max_grad_norm: 2 |
|
dropout: 0 |
|
batch_size: 16 |
|
valid_batch_size: 16 |
|
optim: adagrad |
|
learning_rate: 0.15 |
|
adagrad_accumulator_init: 0.1 |
|
reuse_copy_attn: true |
|
copy_loss_by_seqlength: true |
|
bridge: true |
|
seed: 777 |
|
world_size: 2 |
|
gpu_ranks: [0, 1] |