Closed duyvuleo closed 3 years ago
Hi,
I followed the steps and trained a model with Spider dataset and experienced the following error:
./experiment-bridge.sh configs/bridge/spider-bridge-bert-large.sh --train 0 run CUDA_VISIBLE_DEVICES=0 python3 -m src.experiments --train --data_dir data/spider --db_dir data/spider/database --dataset_name spider --question_split --question_only --denormalize_sql --table_shuffling --use_lstm_encoder --use_meta_data_encoding --sql_consistency_check --use_picklist --anchor_text_match_threshold 0.85 --top_k_picklist_matches 2 --process_sql_in_execution_order --num_random_tables_added 0 --save_best_model_only --schema_augmentation_factor 1 --data_augmentation_factor 1 --vocab_min_freq 0 --text_vocab_min_freq 0 --program_vocab_min_freq 0 --num_values_per_field 0 --max_in_seq_len 512 --max_out_seq_len 60 --model bridge --num_steps 100000 --curriculum_interval 0 --num_peek_steps 1000 --num_accumulation_steps 2 --train_batch_size 16 --dev_batch_size 24 --encoder_input_dim 1024 --encoder_hidden_dim 400 --decoder_input_dim 400 --num_rnn_layers 1 --num_const_attn_layers 0 --emb_dropout_rate 0.3 --pretrained_lm_dropout_rate 0 --rnn_layer_dropout_rate 0 --rnn_weight_dropout_rate 0 --cross_attn_dropout_rate 0 --cross_attn_num_heads 8 --res_input_dropout_rate 0.2 --res_layer_dropout_rate 0 --ff_input_dropout_rate 0.4 --ff_hidden_dropout_rate 0.0 --pretrained_transformer bert-large-uncased --bert_finetune_rate 0.00006 --learning_rate 0.0005 --learning_rate_scheduler inverse-square --trans_learning_rate_scheduler inverse-square --warmup_init_lr 0.0005 --warmup_init_ft_lr 0.00003 --num_warmup_steps 4000 --grad_norm 0.3 --decoding_algorithm beam-search --beam_size 16 --bs_alpha 1.05 --gpu 0 ./experiment-bridge.sh: line 205: CUDA_VISIBLE_DEVICES=0: command not found (pyvenv37-oda-text2sql-tabular-semantic-parsing) [vchoang@oda2-vm-gpu3-4-ad3-03 TabularSemanticParsing]$ vim ./experiment-bridge.sh (pyvenv37-oda-text2sql-tabular-semantic-parsing) [vchoang@oda2-vm-gpu3-4-ad3-03 TabularSemanticParsing]$ ./experiment-bridge.sh configs/bridge/spider-bridge-bert-large.sh --train 0 run python3 -m src.experiments --train --data_dir data/spider --db_dir data/spider/database --dataset_name spider --question_split --question_only --denormalize_sql --table_shuffling --use_lstm_encoder --use_meta_data_encoding --sql_consistency_check --use_picklist --anchor_text_match_threshold 0.85 --top_k_picklist_matches 2 --process_sql_in_execution_order --num_random_tables_added 0 --save_best_model_only --schema_augmentation_factor 1 --data_augmentation_factor 1 --vocab_min_freq 0 --text_vocab_min_freq 0 --program_vocab_min_freq 0 --num_values_per_field 0 --max_in_seq_len 512 --max_out_seq_len 60 --model bridge --num_steps 100000 --curriculum_interval 0 --num_peek_steps 1000 --num_accumulation_steps 2 --train_batch_size 16 --dev_batch_size 24 --encoder_input_dim 1024 --encoder_hidden_dim 400 --decoder_input_dim 400 --num_rnn_layers 1 --num_const_attn_layers 0 --emb_dropout_rate 0.3 --pretrained_lm_dropout_rate 0 --rnn_layer_dropout_rate 0 --rnn_weight_dropout_rate 0 --cross_attn_dropout_rate 0 --cross_attn_num_heads 8 --res_input_dropout_rate 0.2 --res_layer_dropout_rate 0 --ff_input_dropout_rate 0.4 --ff_hidden_dropout_rate 0.0 --pretrained_transformer bert-large-uncased --bert_finetune_rate 0.00006 --learning_rate 0.0005 --learning_rate_scheduler inverse-square --trans_learning_rate_scheduler inverse-square --warmup_init_lr 0.0005 --warmup_init_ft_lr 0.00003 --num_warmup_steps 4000 --grad_norm 0.3 --decoding_algorithm beam-search --beam_size 16 --bs_alpha 1.05 --gpu 0 Model directory created: /mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/model/spider.bridge.lstm.meta.ts.ppl-0.85.2.dn.eo.feat.bert-large-uncased.xavier-1024-400-400-16-2-0.0005-inv-sqr-0.0005-4000-6e-05-inv-sqr-3e-05-4000-0.3-0.3-0.0-0.0-1-8-0.0-0.0-res-0.2-0.0-ff-0.4-0.0.210111-233401.kvzx Visualization directory created: /mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/viz/spider.bridge.lstm.meta.ts.ppl-0.85.2.dn.eo.feat.bert-large-uncased.xavier-1024-400-400-16-2-0.0005-inv-sqr-0.0005-4000-6e-05-inv-sqr-3e-05-4000-0.3-0.3-0.0-0.0-1-8-0.0-0.0-res-0.2-0.0-ff-0.4-0.0.210111-233401.kvzx * text vocab size = 30522 * program vocab size = 99 pretrained_transformer = bert-large-uncased fix_pretrained_transformer_parameters = False bridge module created execution order restoration cache copied source: data/spider/dev.eo.pred.restored.pkl dest: /mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/model/spider.bridge.lstm.meta.ts.ppl-0.85.2.dn.eo.feat.bert-large-uncased.xavier-1024-400-400-16-2-0.0005-inv-sqr-0.0005-4000-6e-05-inv-sqr-3e-05-4000-0.3-0.3-0.0-0.0-1-8-0.0-0.0-res-0.2-0.0-ff-0.4-0.0.210111-233401.kvzx/dev.eo.pred.restored.pkl loading preprocessed data: data/spider/spider.bridge.question-split.ppl-0.85.2.dn.eo.bert.pkl 8659 training examples loaded 1034 dev examples loaded Model initialization (xavier) -------------------------- encoder_embeddings.trans_parameters.embeddings.word_embeddings.weight (skipped) encoder_embeddings.trans_parameters.embeddings.position_embeddings.weight (skipped) encoder_embeddings.trans_parameters.embeddings.token_type_embeddings.weight (skipped) encoder_embeddings.trans_parameters.embeddings.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.embeddings.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.0.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.1.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.2.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.3.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.4.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.5.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.6.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.7.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.8.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.9.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.10.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.11.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.12.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.13.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.14.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.15.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.16.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.17.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.18.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.19.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.20.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.21.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.22.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.query.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.query.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.key.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.key.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.value.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.self.value.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.attention.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.intermediate.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.intermediate.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.output.dense.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.output.dense.bias (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.output.LayerNorm.weight (skipped) encoder_embeddings.trans_parameters.encoder.layer.23.output.LayerNorm.bias (skipped) encoder_embeddings.trans_parameters.pooler.dense.weight (skipped) encoder_embeddings.trans_parameters.pooler.dense.bias (skipped) decoder_embeddings.embeddings.weight done encoder.bilstm_encoder.rnn.rnn.rnn.weight_ih_l0 done encoder.bilstm_encoder.rnn.rnn.rnn.weight_hh_l0 done encoder.bilstm_encoder.rnn.rnn.rnn.bias_ih_l0 encoder.bilstm_encoder.rnn.rnn.rnn.bias_hh_l0 encoder.bilstm_encoder.rnn.rnn.rnn.weight_ih_l0_reverse done encoder.bilstm_encoder.rnn.rnn.rnn.weight_hh_l0_reverse done encoder.bilstm_encoder.rnn.rnn.rnn.bias_ih_l0_reverse encoder.bilstm_encoder.rnn.rnn.rnn.bias_hh_l0_reverse encoder.text_encoder.rnn.rnn.rnn.weight_ih_l0 done encoder.text_encoder.rnn.rnn.rnn.weight_hh_l0 done encoder.text_encoder.rnn.rnn.rnn.bias_ih_l0 encoder.text_encoder.rnn.rnn.rnn.bias_hh_l0 encoder.text_encoder.rnn.rnn.rnn.weight_ih_l0_reverse done encoder.text_encoder.rnn.rnn.rnn.weight_hh_l0_reverse done encoder.text_encoder.rnn.rnn.rnn.bias_ih_l0_reverse encoder.text_encoder.rnn.rnn.rnn.bias_hh_l0_reverse encoder.schema_encoder.primary_key_embeddings.embeddings.weight done encoder.schema_encoder.foreign_key_embeddings.embeddings.weight done encoder.schema_encoder.field_type_embeddings.embeddings.weight done encoder.schema_encoder.feature_fusion_layer.linear1.weight done encoder.schema_encoder.feature_fusion_layer.linear1.bias encoder.schema_encoder.feature_fusion_layer.linear2.weight done encoder.schema_encoder.feature_fusion_layer.linear2.bias encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear1.weight done encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear1.bias encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear2.weight done encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear2.bias decoder.out.linear.weight done decoder.out.linear.bias decoder.rnn.rnn.weight_ih_l0 done decoder.rnn.rnn.weight_hh_l0 done decoder.rnn.rnn.bias_ih_l0 decoder.rnn.rnn.bias_hh_l0 decoder.attn.wq.weight done decoder.attn.wk.weight done decoder.attn.wv.weight done decoder.attn.wo.weight done decoder.attn_combine.linear1.weight done decoder.attn_combine.linear1.bias decoder.pointer_switch.project.linear1.weight done decoder.pointer_switch.project.linear1.bias -------------------------- Model Parameters -------------------------- mdl.decoder_embeddings.embeddings.weight 39600 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.weight_ih_l0 819200 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.weight_hh_l0 160000 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.bias_ih_l0 800 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.bias_hh_l0 800 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.weight_ih_l0_reverse 819200 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.weight_hh_l0_reverse 160000 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.bias_ih_l0_reverse 800 requires_grad=True mdl.encoder.bilstm_encoder.rnn.rnn.rnn.bias_hh_l0_reverse 800 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.weight_ih_l0 320000 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.weight_hh_l0 160000 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.bias_ih_l0 800 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.bias_hh_l0 800 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.weight_ih_l0_reverse 320000 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.weight_hh_l0_reverse 160000 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.bias_ih_l0_reverse 800 requires_grad=True mdl.encoder.text_encoder.rnn.rnn.rnn.bias_hh_l0_reverse 800 requires_grad=True mdl.encoder.schema_encoder.primary_key_embeddings.embeddings.weight 800 requires_grad=True mdl.encoder.schema_encoder.foreign_key_embeddings.embeddings.weight 800 requires_grad=True mdl.encoder.schema_encoder.field_type_embeddings.embeddings.weight 2400 requires_grad=True mdl.encoder.schema_encoder.feature_fusion_layer.linear1.weight 640000 requires_grad=True mdl.encoder.schema_encoder.feature_fusion_layer.linear1.bias 400 requires_grad=True mdl.encoder.schema_encoder.feature_fusion_layer.linear2.weight 160000 requires_grad=True mdl.encoder.schema_encoder.feature_fusion_layer.linear2.bias 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.layer_norm.gamma 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.layer_norm.beta 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear1.weight 160000 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear1.bias 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear2.weight 160000 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.mdl_with_residual_connection.mdl.linear2.bias 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.layer_norm.gamma 400 requires_grad=True mdl.encoder.schema_encoder.field_table_fusion_layer.res_feed_forward.layer_norm.beta 400 requires_grad=True mdl.decoder.out.linear.weight 39600 requires_grad=True mdl.decoder.out.linear.bias 99 requires_grad=True mdl.decoder.rnn.rnn.weight_ih_l0 1280000 requires_grad=True mdl.decoder.rnn.rnn.weight_hh_l0 640000 requires_grad=True mdl.decoder.rnn.rnn.bias_ih_l0 1600 requires_grad=True mdl.decoder.rnn.rnn.bias_hh_l0 1600 requires_grad=True mdl.decoder.attn.wq.weight 160000 requires_grad=True mdl.decoder.attn.wk.weight 160000 requires_grad=True mdl.decoder.attn.wv.weight 160000 requires_grad=True mdl.decoder.attn.wo.weight 160000 requires_grad=True mdl.decoder.attn_combine.linear1.weight 320000 requires_grad=True mdl.decoder.attn_combine.linear1.bias 400 requires_grad=True mdl.decoder.pointer_switch.project.linear1.weight 800 requires_grad=True mdl.decoder.pointer_switch.project.linear1.bias 1 requires_grad=True Total # parameters = 342157588 -------------------------- wandb: Tracking run with wandb version 0.8.30 wandb: Wandb version 0.10.13 is available! To upgrade, please run: wandb: $ pip install wandb --upgrade wandb: Run data is saved locally in wandb/run-20210111_233422-17hmk4jb wandb: Syncing run spider.bridge.lstm.meta.ts.ppl-0.85.2.dn.eo.feat.bert-large-uncased.xavier-1024-400-400-16-2-0.0005-inv-sqr-0.0005-4000-6e-05-inv-sqr-3e-05-4000-0.3-0.3-0.0-0.0-1-8-0.0-0.0-res-0.2-0.0-ff-0.4-0.0.210111-233422.pomb wandb: ⭐️ View project at https://app.wandb.ai/duyvuleo/smore-spider-group--final wandb: 🚀 View run at https://app.wandb.ai/duyvuleo/smore-spider-group--final/runs/17hmk4jb wandb: Run `wandb off` to turn off syncing. 0%| | 1/2000 [00:01<45:32, 1.37s/it] Traceback (most recent call last): File "/usr/local/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/usr/local/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/experiments.py", line 407, in <module> run_experiment(args) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/experiments.py", line 392, in run_experiment train(sp) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/experiments.py", line 63, in train sp.run_train(train_data, dev_data) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/common/learn_framework.py", line 207, in run_train formatted_batch = self.format_batch(mini_batch) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/semantic_parser/learn_framework.py", line 430, in format_batch num_included_nodes=num_included_nodes) File "/mnt/shared_ad3_mt1/vchoang/works/projects/oda/text2sql/code/TabularSemanticParsing/src/data_processor/vectorizers.py", line 102, in vectorize_field_ptr_out if schema_pos < num_included_nodes: TypeError: '<' not supported between instances of 'NoneType' and 'int' wandb: Waiting for W&B process to finish, PID 21092 wandb: Program failed with code 1. Press ctrl-c to abort syncing. wandb: Run summary: wandb: learning_rate/spider 0.0005 wandb: _runtime 44.21112084388733 wandb: _timestamp 1610408083.642099 wandb: _step 1 wandb: fine_tuning_rate/spider 3.00075e-05 wandb: Syncing files in wandb/run-20210111_233422-17hmk4jb: wandb: code/src/experiments.py wandb: plus 7 W&B file(s) and 1 media file(s) wandb: wandb: Synced spider.bridge.lstm.meta.ts.ppl-0.85.2.dn.eo.feat.bert-large-uncased.xavier-1024-400-400-16-2-0.0005-inv-sqr-0.0005-4000-6e-05-inv-sqr-3e-05-4000-0.3-0.3-0.0-0.0-1-8-0.0-0.0-res-0.2-0.0-ff-0.4-0.0.210111-233422.pomb: https://app.wandb.ai/duyvuleo/smore-spider-group--final/runs/17hmk4jb
Do you know the reason for this error? Thanks!
Maybe same as #1 , please check if this helps.
@ #1
Hi,
I followed the steps and trained a model with Spider dataset and experienced the following error:
Do you know the reason for this error? Thanks!