add bert train configs

experiments.conf

@@ -60,6 +60,22 @@ bert_base = ${best}{
   init_checkpoint = ${best.log_root}/bert_base/model.max.ckpt
 }
 
+train_bert_base = ${best}{
+  num_docs = 2802
+  bert_learning_rate = 1e-05
+  task_learning_rate = 0.0002
+  max_segment_len = 128
+  ffnn_size = 1000
+  train_path = ${data_dir}/train.english.128.jsonlines
+  eval_path = ${data_dir}/dev.english.128.jsonlines
+  conll_eval_path = ${data_dir}/dev.english.v4_gold_conll
+  max_training_sentences = 11
+  bert_config_file = ${best.log_root}/cased_L-12_H-768_A-12/bert_config.json
+  vocab_file = ${best.log_root}/cased_L-12_H-768_A-12/vocab.txt
+  tf_checkpoint = ${best.log_root}/cased_L-12_H-768_A-12/bert_model.ckpt
+  init_checkpoint = ${best.log_root}/cased_L-12_H-768_A-12/bert_model.ckpt
+}
+
 bert_large = ${best}{
   num_docs = 2802
   bert_learning_rate = 1e-05
@@ -76,6 +92,22 @@ bert_large = ${best}{
   init_checkpoint = ${best.log_root}/bert_large/model.max.ckpt
 }
 
+train_bert_large = ${best}{
+  num_docs = 2802
+  bert_learning_rate = 1e-05
+  task_learning_rate = 0.0002
+  max_segment_len = 384
+  ffnn_size = 3000
+  train_path = ${data_dir}/train.english.384.jsonlines
+  eval_path = ${data_dir}/dev.english.384.jsonlines
+  conll_eval_path = ${data_dir}/dev.english.v4_gold_conll
+  max_training_sentences = 3
+  bert_config_file = ${best.log_root}/cased_L-24_H-1024_A-16/bert_config.json
+  vocab_file = ${best.log_root}/cased_L-24_H-1024_A-16/vocab.txt
+  tf_checkpoint = ${best.log_root}/cased_L-24_H-1024_A-16/bert_model.max.ckpt
+  init_checkpoint = ${best.log_root}/cased_L-24_H-1024_A-16/bert_model.max.ckpt
+}
+
 spanbert_base = ${best}{
   num_docs = 2802
   bert_learning_rate = 2e-05

setup_training.sh

@@ -10,6 +10,14 @@ dlx() {
   rm $data_dir/$2
 }
 
+download_bert(){
+  model=$1
+  wget -P $data_dir https://storage.googleapis.com/bert_models/2018_10_18/$model.zip
+  unzip $data_dir/$model.zip
+  rm $data_dir/$model.zip
+  mv $model $data_dir/
+}
+
 conll_url=http://conll.cemantix.org/2012/download
 dlx $conll_url conll-2012-train.v4.tar.gz
 dlx $conll_url conll-2012-development.v4.tar.gz
@@ -19,6 +27,8 @@ dlx $conll_url/test conll-2012-test-official.v9.tar.gz
 dlx $conll_url conll-2012-scripts.v3.tar.gz
 dlx http://conll.cemantix.org/download reference-coreference-scorers.v8.01.tar.gz
 
+download_bert cased_L-12_H-768_A-12
+download_bert cased_L-24_H-1024_A-16
 
 bash conll-2012/v3/scripts/skeleton2conll.sh -D $ontonotes_path/data/files/data $data_dir/conll-2012