/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.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 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_330M_encode overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 467/3515 [00:00<00:00, 4666.86it/s] word -> phonemes: 27%|██▋ | 959/3515 [00:00<00:00, 4813.36it/s] word -> phonemes: 42%|████▏ | 1465/3515 [00:00<00:00, 4922.26it/s] word -> phonemes: 56%|█████▌ | 1958/3515 [00:00<00:00, 4877.09it/s] word -> phonemes: 70%|██████▉ | 2446/3515 [00:00<00:00, 4585.96it/s] word -> phonemes: 83%|████████▎ | 2908/3515 [00:00<00:00, 4331.58it/s] word -> phonemes: 95%|█████████▌| 3345/3515 [00:00<00:00, 4292.72it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4489.66it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 582/2703 [00:00<00:00, 5814.71it/s] word -> phonemes: 44%|████▍ | 1184/2703 [00:00<00:00, 5932.33it/s] word -> phonemes: 66%|██████▌ | 1781/2703 [00:00<00:00, 5946.40it/s] word -> phonemes: 88%|████████▊ | 2376/2703 [00:00<00:00, 5876.46it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5827.57it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 23%|██▎ | 611/2703 [00:00<00:00, 6103.66it/s] word -> phonemes: 45%|████▌ | 1222/2703 [00:00<00:00, 5839.91it/s] word -> phonemes: 68%|██████▊ | 1849/2703 [00:00<00:00, 6028.01it/s] word -> phonemes: 91%|█████████ | 2453/2703 [00:00<00:00, 5982.51it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5931.17it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 562/2703 [00:00<00:00, 5619.21it/s] word -> phonemes: 42%|████▏ | 1131/2703 [00:00<00:00, 5657.26it/s] word -> phonemes: 63%|██████▎ | 1700/2703 [00:00<00:00, 5668.23it/s] word -> phonemes: 84%|████████▍ | 2267/2703 [00:00<00:00, 5665.71it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5617.39it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 412/3515 [00:00<00:00, 4118.39it/s] word -> phonemes: 25%|██▌ | 893/3515 [00:00<00:00, 4522.49it/s] word -> phonemes: 39%|███▉ | 1386/3515 [00:00<00:00, 4704.03it/s] word -> phonemes: 53%|█████▎ | 1857/3515 [00:00<00:00, 4648.86it/s] word -> phonemes: 67%|██████▋ | 2351/3515 [00:00<00:00, 4750.31it/s] word -> phonemes: 81%|████████ | 2830/3515 [00:00<00:00, 4762.55it/s] word -> phonemes: 94%|█████████▍| 3307/3515 [00:00<00:00, 4724.18it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4669.77it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|██ | 547/2703 [00:00<00:00, 5467.18it/s] word -> phonemes: 42%|████▏ | 1124/2703 [00:00<00:00, 5639.45it/s] word -> phonemes: 63%|██████▎ | 1697/2703 [00:00<00:00, 5680.18it/s] word -> phonemes: 84%|████████▍ | 2276/2703 [00:00<00:00, 5720.70it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5623.17it/s] dev: 0%| | 0/2703 [00:00