/home/tony/Work/glockenspiel/s3prl/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") /home/tony/Work/glockenspiel/s3prl/s3prl/run_downstream.py:157: 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') Some weights of the model checkpoint at m-a-p/MERT-v1-330M were not used when initializing MERTModel: ['encoder.pos_conv_embed.conv.weight_g', 'encoder.pos_conv_embed.conv.weight_v'] - This IS expected if you are initializing MERTModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing MERTModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). Some weights of MERTModel were not initialized from the model checkpoint at m-a-p/MERT-v1-330M and are newly initialized: ['encoder.pos_conv_embed.conv.parametrizations.weight.original1', 'encoder.pos_conv_embed.conv.parametrizations.weight.original0'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. [Featurizer] - The selected feature hidden_states's downsample rate is 320 [Runner] - Start a new experiment m-a-p/MERT-v1-330M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 453/3515 [00:00<00:00, 4521.69it/s] word -> phonemes: 27%|██▋ | 943/3515 [00:00<00:00, 4743.09it/s] word -> phonemes: 41%|████ | 1447/3515 [00:00<00:00, 4876.42it/s] word -> phonemes: 55%|█████▌ | 1935/3515 [00:00<00:00, 4846.42it/s] word -> phonemes: 69%|██████▉ | 2420/3515 [00:00<00:00, 4801.89it/s] word -> phonemes: 83%|████████▎ | 2901/3515 [00:00<00:00, 4785.93it/s] word -> phonemes: 96%|█████████▌| 3380/3515 [00:00<00:00, 4489.74it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4599.88it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 23%|██▎ | 627/2703 [00:00<00:00, 6268.56it/s] word -> phonemes: 46%|████▋ | 1254/2703 [00:00<00:00, 5951.19it/s] word -> phonemes: 68%|██████▊ | 1851/2703 [00:00<00:00, 5956.24it/s] word -> phonemes: 91%|█████████ | 2448/2703 [00:00<00:00, 5880.74it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5884.57it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 595/2703 [00:00<00:00, 5946.89it/s] word -> phonemes: 45%|████▍ | 1206/2703 [00:00<00:00, 6041.79it/s] word -> phonemes: 67%|██████▋ | 1824/2703 [00:00<00:00, 6102.02it/s] word -> phonemes: 90%|█████████ | 2435/2703 [00:00<00:00, 6041.31it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 6014.87it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 585/2703 [00:00<00:00, 5843.65it/s] word -> phonemes: 44%|████▍ | 1192/2703 [00:00<00:00, 5974.37it/s] word -> phonemes: 67%|██████▋ | 1812/2703 [00:00<00:00, 6075.12it/s] word -> phonemes: 90%|████████▉ | 2420/2703 [00:00<00:00, 6027.43it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5969.92it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 448/3515 [00:00<00:00, 4471.75it/s] word -> phonemes: 27%|██▋ | 938/3515 [00:00<00:00, 4723.28it/s] word -> phonemes: 41%|████ | 1435/3515 [00:00<00:00, 4832.65it/s] word -> phonemes: 55%|█████▍ | 1919/3515 [00:00<00:00, 4779.49it/s] word -> phonemes: 68%|██████▊ | 2398/3515 [00:00<00:00, 4762.72it/s] word -> phonemes: 82%|████████▏ | 2875/3515 [00:00<00:00, 4755.21it/s] word -> phonemes: 95%|█████████▌| 3351/3515 [00:00<00:00, 4665.07it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4711.76it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 586/2703 [00:00<00:00, 5855.29it/s] word -> phonemes: 44%|████▍ | 1193/2703 [00:00<00:00, 5981.29it/s] word -> phonemes: 67%|██████▋ | 1812/2703 [00:00<00:00, 6072.41it/s] word -> phonemes: 90%|████████▉ | 2420/2703 [00:00<00:00, 6003.17it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5958.38it/s] dev: 0%| | 0/2703 [00:00