/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_v', 'encoder.pos_conv_embed.conv.weight_g'] - 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.original0', 'encoder.pos_conv_embed.conv.parametrizations.weight.original1'] 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 mert_330M_encode_norm2 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_330M_encode_norm2 overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 470/3515 [00:00<00:00, 4695.94it/s] word -> phonemes: 27%|██▋ | 940/3515 [00:00<00:00, 4242.04it/s] word -> phonemes: 39%|███▉ | 1374/3515 [00:00<00:00, 4281.88it/s] word -> phonemes: 52%|█████▏ | 1842/3515 [00:00<00:00, 4431.86it/s] word -> phonemes: 66%|██████▌ | 2312/3515 [00:00<00:00, 4522.81it/s] word -> phonemes: 79%|███████▊ | 2766/3515 [00:00<00:00, 4462.03it/s] word -> phonemes: 91%|█████████▏| 3214/3515 [00:00<00:00, 4443.42it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4406.85it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|█▉ | 535/2703 [00:00<00:00, 5343.34it/s] word -> phonemes: 41%|████ | 1106/2703 [00:00<00:00, 5557.70it/s] word -> phonemes: 62%|██████▏ | 1682/2703 [00:00<00:00, 5645.55it/s] word -> phonemes: 83%|████████▎ | 2249/2703 [00:00<00:00, 5652.65it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5439.17it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 23%|██▎ | 620/2703 [00:00<00:00, 6198.45it/s] word -> phonemes: 46%|████▌ | 1240/2703 [00:00<00:00, 6140.35it/s] word -> phonemes: 69%|██████▊ | 1855/2703 [00:00<00:00, 6013.82it/s] word -> phonemes: 91%|█████████ | 2457/2703 [00:00<00:00, 5993.55it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5966.25it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 23%|██▎ | 612/2703 [00:00<00:00, 6115.69it/s] word -> phonemes: 45%|████▌ | 1224/2703 [00:00<00:00, 5916.91it/s] word -> phonemes: 68%|██████▊ | 1842/2703 [00:00<00:00, 6033.89it/s] word -> phonemes: 90%|█████████ | 2446/2703 [00:00<00:00, 6029.19it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5969.85it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 467/3515 [00:00<00:00, 4666.86it/s] word -> phonemes: 27%|██▋ | 962/3515 [00:00<00:00, 4833.03it/s] word -> phonemes: 41%|████ | 1446/3515 [00:00<00:00, 4780.05it/s] word -> phonemes: 55%|█████▍ | 1926/3515 [00:00<00:00, 4785.53it/s] word -> phonemes: 68%|██████▊ | 2407/3515 [00:00<00:00, 4790.90it/s] word -> phonemes: 82%|████████▏ | 2892/3515 [00:00<00:00, 4808.92it/s] word -> phonemes: 96%|█████████▌| 3373/3515 [00:00<00:00, 4520.17it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4646.97it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 593/2703 [00:00<00:00, 5923.09it/s] word -> phonemes: 44%|████▍ | 1186/2703 [00:00<00:00, 5819.04it/s] word -> phonemes: 67%|██████▋ | 1798/2703 [00:00<00:00, 5954.96it/s] word -> phonemes: 89%|████████▊ | 2394/2703 [00:00<00:00, 5779.71it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5775.69it/s] dev: 0%| | 0/2703 [00:00