I am trying to run the multilingual ASR recipe egs2/fleurs/asr1/run.sh with th

Thanks for the report. <a class="user-mention notranslate" data-hovercard-type="us

I am pasting the full log file here: <div class="snippet-clipboard-content notrans

Thanks! The LIDs should be read from the <a href="https://github.com/espnet/espnet/blo

Error while using auxiliary CTC objective for multilingual ASR,about espnet/espnet

Comments (5)

sw005320 commented on May 24, 2024

Thanks for the report.
@wanchichen, do you know what happens?

from espnet.

wanchichen commented on May 24, 2024

I am guessing the data for the aux objectives is either missing or not properly passed through the dataloader, but its hard to tell with just this info.
Can you paste the full logs and list the files in your train dump dir?

from espnet.

saurabhk0317 commented on May 24, 2024

I am pasting the full log file here:

# python3 -m espnet2.bin.asr_train --use_preprocessor true --bpemodel data/all_token_list/bpe_unigram6500/bpe.model --token_type bpe --token_list data/all_token_list/bpe_unigram6500/tokens.txt --non_linguistic_symbols none --cleaner none --g2p none --valid_data_path_and_name_and_type dump/raw/dev_all/wav.scp,speech,sound --valid_shape_file exp/asr_stats_raw_all_bpe6500_sp/valid/speech_shape --resume true --ignore_init_mismatch false --fold_length 80000 --output_dir exp/asr_train_asr_conformer_hier_lid_utt_raw_all_bpe6500_sp --config conf/tuning/train_asr_conformer_hier_lid_utt.yaml --frontend_conf fs=16k --train_data_path_and_name_and_type dump/raw/train_all_sp/wav.scp,speech,sound --train_shape_file exp/asr_stats_raw_all_bpe6500_sp/train/speech_shape --allow_variable_data_keys True --train_data_path_and_name_and_type dump/raw/train_all_sp/lid_utt,text,text --fold_length 150 --train_data_path_and_name_and_type dump/raw/train_all_sp/text,text,text --train_shape_file exp/asr_stats_raw_all_bpe6500_sp/train/text_shape.bpe --valid_data_path_and_name_and_type dump/raw/dev_all/text,text,text --valid_shape_file exp/asr_stats_raw_all_bpe6500_sp/valid/text_shape.bpe --ngpu 1 --multiprocessing_distributed True 
# Started at Thu Jan 18 06:06:28 IST 2024
#
/home1/Saurabh/exp/python/vitual_environments/venv_espnet/bin/python3 /home1/espnet/espnet2/bin/asr_train.py --use_preprocessor true --bpemodel data/all_token_list/bpe_unigram6500/bpe.model --token_type bpe --token_list data/all_token_list/bpe_unigram6500/tokens.txt --non_linguistic_symbols none --cleaner none --g2p none --valid_data_path_and_name_and_type dump/raw/dev_all/wav.scp,speech,sound --valid_shape_file exp/asr_stats_raw_all_bpe6500_sp/valid/speech_shape --resume true --ignore_init_mismatch false --fold_length 80000 --output_dir exp/asr_train_asr_conformer_hier_lid_utt_raw_all_bpe6500_sp --config conf/tuning/train_asr_conformer_hier_lid_utt.yaml --frontend_conf fs=16k --train_data_path_and_name_and_type dump/raw/train_all_sp/wav.scp,speech,sound --train_shape_file exp/asr_stats_raw_all_bpe6500_sp/train/speech_shape --allow_variable_data_keys True --train_data_path_and_name_and_type dump/raw/train_all_sp/lid_utt,text,text --fold_length 150 --train_data_path_and_name_and_type dump/raw/train_all_sp/text,text,text --train_shape_file exp/asr_stats_raw_all_bpe6500_sp/train/text_shape.bpe --valid_data_path_and_name_and_type dump/raw/dev_all/text,text,text --valid_shape_file exp/asr_stats_raw_all_bpe6500_sp/valid/text_shape.bpe --ngpu 1 --multiprocessing_distributed True
[wtc10-server] 2024-01-18 06:06:31,642 (asr:523) INFO: Vocabulary size: 6500
/home1/Saurabh/exp/python/vitual_environments/venv_espnet/lib/python3.10/site-packages/s3prl/upstream/byol_s/byol_a/common.py:20: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
  torchaudio.set_audio_backend("sox_io")
[wtc10-server] 2024-01-18 06:06:31,839 (download:170) INFO: Requesting URL: https://huggingface.co/s3prl/converted_ckpts/resolve/main/xlsr2_300m.pt
[wtc10-server] 2024-01-18 06:06:31,839 (download:181) INFO: Using URL's local file: hub/e44d93b23b084a8fe33772983fa5c5be6b0cf05e0b6b1743d0c2b397e3c6b999.xlsr2_300m.pt
/home1/Saurabh/exp/python/vitual_environments/venv_espnet/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
  warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
[wtc10-server] 2024-01-18 06:06:41,752 (conformer_encoder:144) WARNING: Using legacy_rel_pos and it will be deprecated in the future.
[wtc10-server] 2024-01-18 06:06:41,867 (conformer_encoder:251) WARNING: Using legacy_rel_selfattn and it will be deprecated in the future.
[wtc10-server] 2024-01-18 06:06:45,470 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.0.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.0.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.1.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.1.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.2.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.2.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.3.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.3.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.4.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.4.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.5.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.5.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.6.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.feature_extractor.conv_layers.6.2.1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.post_extract_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.quantizer.weight_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.project_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.pos_conv.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,471 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.0.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.1.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.2.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.3.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,472 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.4.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.5.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.6.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.7.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,473 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.8.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.9.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.10.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.11.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,474 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.12.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.13.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.14.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.15.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,475 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.16.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.17.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.18.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.19.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,476 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.20.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.21.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.22.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.self_attn.k_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.self_attn.v_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.self_attn.q_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.self_attn.out_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.self_attn_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.fc1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.fc2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layers.23.final_layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.encoder.layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.layer_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize frontend.upstream.upstream.model.final_proj.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize preencoder.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize encoder.embed.conv.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,477 (initialize:88) INFO: Initialize encoder.embed.conv.2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.embed.out.0.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.0.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,478 (initialize:88) INFO: Initialize encoder.encoders.1.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.1.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.1.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.1.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.2.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,479 (initialize:88) INFO: Initialize encoder.encoders.3.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.3.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.3.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.3.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.3.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.3.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.4.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,480 (initialize:88) INFO: Initialize encoder.encoders.5.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.5.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.6.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,481 (initialize:88) INFO: Initialize encoder.encoders.7.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.7.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.8.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,482 (initialize:88) INFO: Initialize encoder.encoders.9.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.9.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.10.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,483 (initialize:88) INFO: Initialize encoder.encoders.11.feed_forward_macaron.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.feed_forward_macaron.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.conv_module.pointwise_conv1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.conv_module.depthwise_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.conv_module.norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.conv_module.pointwise_conv2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.norm_ff.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.norm_mha.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.norm_ff_macaron.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.norm_conv.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.encoders.11.norm_final.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.after_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize encoder.conditioning_layer.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.after_norm.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.output_layer.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.0.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,484 (initialize:88) INFO: Initialize decoder.decoders.1.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.1.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.2.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.3.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,485 (initialize:88) INFO: Initialize decoder.decoders.4.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.4.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.self_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.self_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.self_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.self_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.src_attn.linear_q.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.src_attn.linear_k.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.src_attn.linear_v.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.src_attn.linear_out.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.feed_forward.w_1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.feed_forward.w_2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.norm1.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.norm2.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize decoder.decoders.5.norm3.bias to zeros
[wtc10-server] 2024-01-18 06:06:45,486 (initialize:88) INFO: Initialize ctc.ctc_lo.bias to zeros
[wtc10-server] 2024-01-18 06:06:46,413 (s3prl:117) INFO: Pretrained S3PRL frontend model parameters reloaded!
[wtc10-server] 2024-01-18 06:06:47,140 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.mask_emb.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.0.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.0.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.0.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.0.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.1.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.1.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.1.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.1.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.2.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.2.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.2.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.2.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.3.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.3.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.3.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.3.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.4.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.4.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.4.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.4.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.5.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.5.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.5.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.5.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.6.0.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.6.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.6.2.1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.feature_extractor.conv_layers.6.2.1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.post_extract_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.post_extract_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.quantizer.vars.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.quantizer.weight_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,141 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.quantizer.weight_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.project_q.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.project_q.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.pos_conv.0.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.pos_conv.0.weight_g.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.pos_conv.0.weight_v.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.0.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.1.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,142 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.2.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.3.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,143 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.4.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.5.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.6.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,144 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.7.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.8.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,145 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.9.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.10.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.11.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,146 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.12.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.13.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.14.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,147 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.15.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.16.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,148 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.17.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.18.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.19.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,149 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.20.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.21.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.22.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,150 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.k_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.k_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.v_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.v_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.q_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.q_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.out_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn.out_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.self_attn_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.fc1.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.fc1.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.fc2.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.fc2.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.final_layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layers.23.final_layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.encoder.layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.layer_norm.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.layer_norm.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.final_proj.weight.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,151 (abs_task:1242) INFO: Setting frontend.upstream.upstream.model.final_proj.bias.requires_grad = False
[wtc10-server] 2024-01-18 06:06:47,616 (abs_task:1270) INFO: pytorch.version=2.1.2+cu118, cuda.available=True, cudnn.version=8700, cudnn.benchmark=False, cudnn.deterministic=True
[wtc10-server] 2024-01-18 06:06:47,627 (abs_task:1271) INFO: Model structure:
ESPnetASRModel(
  (frontend): S3prlFrontend(
    (upstream): S3PRLUpstream(
      (upstream): UpstreamExpert(
        (model): Wav2Vec2Model(
          (feature_extractor): ConvFeatureExtractionModel(
            (conv_layers): ModuleList(
              (0): Sequential(
                (0): Conv1d(1, 512, kernel_size=(10,), stride=(5,))
                (1): Dropout(p=0.0, inplace=False)
                (2): Sequential(
                  (0): TransposeLast()
                  (1): Fp32LayerNorm((512,), eps=1e-05, elementwise_affine=True)
                  (2): TransposeLast()
                )
                (3): GELU(approximate='none')
              )
              (1-4): 4 x Sequential(
                (0): Conv1d(512, 512, kernel_size=(3,), stride=(2,))
                (1): Dropout(p=0.0, inplace=False)
                (2): Sequential(
                  (0): TransposeLast()
                  (1): Fp32LayerNorm((512,), eps=1e-05, elementwise_affine=True)
                  (2): TransposeLast()
                )
                (3): GELU(approximate='none')
              )
              (5-6): 2 x Sequential(
                (0): Conv1d(512, 512, kernel_size=(2,), stride=(2,))
                (1): Dropout(p=0.0, inplace=False)
                (2): Sequential(
                  (0): TransposeLast()
                  (1): Fp32LayerNorm((512,), eps=1e-05, elementwise_affine=True)
                  (2): TransposeLast()
                )
                (3): GELU(approximate='none')
              )
            )
          )
          (post_extract_proj): Linear(in_features=512, out_features=1024, bias=True)
          (dropout_input): Dropout(p=0.0, inplace=False)
          (dropout_features): Dropout(p=0.0, inplace=False)
          (quantizer): GumbelVectorQuantizer(
            (weight_proj): Linear(in_features=512, out_features=640, bias=True)
          )
          (project_q): Linear(in_features=768, out_features=768, bias=True)
          (encoder): TransformerEncoder(
            (pos_conv): Sequential(
              (0): Conv1d(1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16)
              (1): SamePad()
              (2): GELU(approximate='none')
            )
            (layers): ModuleList(
              (0-23): 24 x TransformerSentenceEncoderLayer(
                (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)
                )
                (dropout1): Dropout(p=0.0, inplace=False)
                (dropout2): Dropout(p=0.0, inplace=False)
                (dropout3): Dropout(p=0.0, inplace=False)
                (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (fc1): Linear(in_features=1024, out_features=4096, bias=True)
                (fc2): Linear(in_features=4096, out_features=1024, bias=True)
                (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              )
            )
            (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          )
          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
          (final_proj): Linear(in_features=1024, out_features=768, bias=True)
        )
      )
    )
    (featurizer): Featurizer()
  )
  (specaug): SpecAug(
    (time_warp): TimeWarp(window=5, mode=bicubic)
    (freq_mask): MaskAlongAxis(mask_width_range=[0, 30], num_mask=2, axis=freq)
    (time_mask): MaskAlongAxis(mask_width_range=[0, 40], num_mask=2, axis=time)
  )
  (normalize): UtteranceMVN(norm_means=True, norm_vars=False)
  (preencoder): LinearProjection(
    (linear_out): Linear(in_features=1024, out_features=80, bias=True)
    (dropout): Dropout(p=0.0, inplace=False)
  )
  (encoder): ConformerEncoder(
    (embed): Conv2dSubsampling2(
      (conv): Sequential(
        (0): Conv2d(1, 512, kernel_size=(3, 3), stride=(2, 2))
        (1): ReLU()
        (2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1))
        (3): ReLU()
      )
      (out): Sequential(
        (0): Linear(in_features=18944, out_features=512, bias=True)
        (1): LegacyRelPositionalEncoding(
          (dropout): Dropout(p=0.1, inplace=False)
        )
      )
    )
    (encoders): MultiSequential(
      (0): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (1): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (2): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (3): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (4): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (5): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (6): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (7): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (8): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (9): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (10): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (11): EncoderLayer(
        (self_attn): LegacyRelPositionMultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (linear_pos): Linear(in_features=512, out_features=512, bias=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (feed_forward_macaron): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): Swish()
        )
        (conv_module): ConvolutionModule(
          (pointwise_conv1): Conv1d(512, 1024, kernel_size=(1,), stride=(1,))
          (depthwise_conv): Conv1d(512, 512, kernel_size=(31,), stride=(1,), padding=(15,), groups=512)
          (norm): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (pointwise_conv2): Conv1d(512, 512, kernel_size=(1,), stride=(1,))
          (activation): Swish()
        )
        (norm_ff): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_mha): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_ff_macaron): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_conv): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm_final): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
    )
    (after_norm): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
    (conditioning_layer): Linear(in_features=6500, out_features=512, bias=True)
  )
  (decoder): TransformerDecoder(
    (embed): Sequential(
      (0): Embedding(6500, 512)
      (1): PositionalEncoding(
        (dropout): Dropout(p=0.1, inplace=False)
      )
    )
    (after_norm): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
    (output_layer): Linear(in_features=512, out_features=6500, bias=True)
    (decoders): MultiSequential(
      (0): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (1): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (2): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (3): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (4): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (5): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=512, out_features=512, bias=True)
          (linear_k): Linear(in_features=512, out_features=512, bias=True)
          (linear_v): Linear(in_features=512, out_features=512, bias=True)
          (linear_out): Linear(in_features=512, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w_1): Linear(in_features=512, out_features=2048, bias=True)
          (w_2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
          (activation): ReLU()
        )
        (norm1): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm2): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (norm3): LayerNorm((512,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
    )
  )
  (criterion_att): LabelSmoothingLoss(
    (criterion): KLDivLoss()
  )
  (ctc): CTC(
    (ctc_lo): Linear(in_features=512, out_features=6500, bias=True)
    (ctc_loss): CTCLoss()
  )
)

Model summary:
    Class Name: ESPnetASRModel
    Total Number of model parameters: 443.97 M
    Number of trainable parameters: 126.58 M (28.5%)
    Size: 506.33 MB
    Type: torch.float32
[wtc10-server] 2024-01-18 06:06:47,628 (abs_task:1274) INFO: Optimizer:
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    capturable: False
    differentiable: False
    eps: 1e-08
    foreach: None
    fused: None
    initial_lr: 0.0025
    lr: 3.125e-08
    maximize: False
    weight_decay: 0
)
[wtc10-server] 2024-01-18 06:06:47,628 (abs_task:1275) INFO: Scheduler: WarmupLR(warmup_steps=80000)
[wtc10-server] 2024-01-18 06:06:47,628 (abs_task:1284) INFO: Saving the configuration in exp/asr_train_asr_conformer_hier_lid_utt_raw_all_bpe6500_sp/config.yaml
[wtc10-server] 2024-01-18 06:06:48,538 (abs_task:1660) INFO: [train] dataset:
ESPnetDataset(
  speech: {"path": "dump/raw/train_all_sp/wav.scp", "type": "sound"}
  text: {"path": "dump/raw/train_all_sp/text", "type": "text"}
  preprocess: <espnet2.train.preprocessor.CommonPreprocessor object at 0x7f89514941f0>)
[wtc10-server] 2024-01-18 06:06:48,538 (abs_task:1661) INFO: [train] Batch sampler: NumElementsBatchSampler(N-batch=36062, batch_bins=160000, sort_in_batch=descending, sort_batch=descending)
[wtc10-server] 2024-01-18 06:06:48,545 (abs_task:1662) INFO: [train] mini-batch sizes summary: N-batch=36062, mean=1.0, min=1, max=2
[wtc10-server] 2024-01-18 06:06:48,670 (abs_task:1660) INFO: [valid] dataset:
ESPnetDataset(
  speech: {"path": "dump/raw/dev_all/wav.scp", "type": "sound"}
  text: {"path": "dump/raw/dev_all/text", "type": "text"}
  preprocess: <espnet2.train.preprocessor.CommonPreprocessor object at 0x7f893d760cd0>)
[wtc10-server] 2024-01-18 06:06:48,670 (abs_task:1661) INFO: [valid] Batch sampler: NumElementsBatchSampler(N-batch=1665, batch_bins=160000, sort_in_batch=descending, sort_batch=descending)
[wtc10-server] 2024-01-18 06:06:48,670 (abs_task:1662) INFO: [valid] mini-batch sizes summary: N-batch=1665, mean=1.0, min=1, max=1
[wtc10-server] 2024-01-18 06:06:48,710 (abs_task:1660) INFO: [plot_att] dataset:
ESPnetDataset(
  speech: {"path": "dump/raw/dev_all/wav.scp", "type": "sound"}
  text: {"path": "dump/raw/dev_all/text", "type": "text"}
  preprocess: <espnet2.train.preprocessor.CommonPreprocessor object at 0x7f8939b0c7c0>)
[wtc10-server] 2024-01-18 06:06:48,711 (abs_task:1661) INFO: [plot_att] Batch sampler: UnsortedBatchSampler(N-batch=1665, batch_size=1, key_file=exp/asr_stats_raw_all_bpe6500_sp/valid/speech_shape, 
[wtc10-server] 2024-01-18 06:06:48,711 (abs_task:1662) INFO: [plot_att] mini-batch sizes summary: N-batch=3, mean=1.0, min=1, max=1
[wtc10-server] 2024-01-18 06:06:48,798 (trainer:298) INFO: 1/20epoch started
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home1/espnet/espnet2/bin/asr_train.py", line 23, in <module>
    main()
  File "/home1/espnet/espnet2/bin/asr_train.py", line 19, in main
    ASRTask.main(cmd=cmd)
  File "/home1/espnet/espnet2/tasks/abs_task.py", line 1119, in main
    cls.main_worker(args)
  File "/home1/espnet/espnet2/tasks/abs_task.py", line 1432, in main_worker
    cls.trainer.run(
  File "/home1/espnet/espnet2/train/trainer.py", line 304, in run
    all_steps_are_invalid = cls.train_one_epoch(
  File "/home1/espnet/espnet2/train/trainer.py", line 588, in train_one_epoch
    retval = model(**batch)
  File "/home1/Saurabh/exp/python/vitual_environments/venv_espnet/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home1/Saurabh/exp/python/vitual_environments/venv_espnet/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home1/espnet/espnet2/asr/espnet_model.py", line 282, in forward
    raise Exception(
Exception: Aux. CTC tasks were specified but no data was found
# Accounting: time=23 threads=1
# Ended (code 1) at Thu Jan 18 06:06:51 IST 2024, elapsed time 23 seconds

Following files are present in dump/raw/train_all_sp directory:

feats_type  lid_tok  lid_utt  spk2utt  text  utt2num_samples  utt2spk  utt2uniq  wav.scp

I could not find which script is reading language IDs from 'lid_tok' and 'lid_utt'.

from espnet.

wanchichen commented on May 24, 2024

Thanks! The LIDs should be read from the preprocessor, assuming lid_utt isn't somehow empty.

I'll try to reproduce the error on my end, I can't tell why this happens. Just to make sure, did you make any changes to the config file? Its important that aux_ctc_tasks: ["lid_utt"] is there

from espnet.

saurabhk0317 commented on May 24, 2024

I found the issue in the code espnet/egs2/fleurs/asr1/asr.sh in line 1384

read -r -a aux_list <<< "$auxiliary_data_tags"
if [ ${#aux_list[@]} != 0 ]; then
    _opts+="--allow_variable_data_keys True "
    for aux_dset in "${aux_list[@]}"; do
         _opts+="--train_data_path_and_name_and_type ${_asr_train_dir}/${aux_dset},text,text "
    done
fi

${_asr_train_dir}/${aux_dset},text,text is supposed to be path, name and type I think. Because of this it was causing duplicate-key error in espnet/espnet2/train/dataset.py

changing ${_asr_train_dir}/${aux_dset},text,text to ${_asr_train_dir}/${aux_dset},${aux_dset},text resolved the issue.

Thanks for the quick response.

from espnet.

Error while using auxiliary CTC objective for multilingual ASR about espnet HOT 5 OPEN

Comments (5)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

Jobs