/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") 2023-10-10 05:35:23 | WARNING | root | Pytorch pre-release version 2.1.0.dev20230831+cu118 - assuming intent to test it /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-v1-95M 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-v1-95M 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_95M_encode_norm2 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_95M_encode_norm2 overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|▉ | 349/3515 [00:00<00:00, 3484.16it/s] word -> phonemes: 22%|██▏ | 769/3515 [00:00<00:00, 3902.26it/s] word -> phonemes: 34%|███▍ | 1199/3515 [00:00<00:00, 4081.46it/s] word -> phonemes: 47%|████▋ | 1636/3515 [00:00<00:00, 4193.42it/s] word -> phonemes: 58%|█████▊ | 2056/3515 [00:00<00:00, 3762.55it/s] word -> phonemes: 70%|███████ | 2470/3515 [00:00<00:00, 3880.96it/s] word -> phonemes: 83%|████████▎ | 2908/3515 [00:00<00:00, 4033.58it/s] word -> phonemes: 95%|█████████▍| 3328/3515 [00:00<00:00, 4082.86it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4003.18it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▍ | 401/2703 [00:00<00:00, 4008.40it/s] word -> phonemes: 30%|██▉ | 802/2703 [00:00<00:00, 3953.32it/s] word -> phonemes: 48%|████▊ | 1287/2703 [00:00<00:00, 4358.07it/s] word -> phonemes: 64%|██████▍ | 1724/2703 [00:00<00:00, 4249.72it/s] word -> phonemes: 80%|███████▉ | 2150/2703 [00:00<00:00, 4159.10it/s] word -> phonemes: 95%|█████████▍| 2567/2703 [00:00<00:00, 4011.96it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4058.43it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▌ | 438/2703 [00:00<00:00, 4370.63it/s] word -> phonemes: 32%|███▏ | 876/2703 [00:00<00:00, 4123.14it/s] word -> phonemes: 48%|████▊ | 1290/2703 [00:00<00:00, 4070.99it/s] word -> phonemes: 63%|██████▎ | 1698/2703 [00:00<00:00, 4063.07it/s] word -> phonemes: 80%|████████ | 2173/2703 [00:00<00:00, 4275.84it/s] word -> phonemes: 97%|█████████▋| 2621/2703 [00:00<00:00, 4342.05it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4259.31it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 483/2703 [00:00<00:00, 4821.29it/s] word -> phonemes: 36%|███▌ | 966/2703 [00:00<00:00, 4384.49it/s] word -> phonemes: 52%|█████▏ | 1408/2703 [00:00<00:00, 4276.94it/s] word -> phonemes: 68%|██████▊ | 1837/2703 [00:00<00:00, 4004.12it/s] word -> phonemes: 84%|████████▍ | 2271/2703 [00:00<00:00, 4114.52it/s] word -> phonemes: 99%|█████████▉| 2685/2703 [00:00<00:00, 3917.01it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4076.67it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█ | 385/3515 [00:00<00:00, 3849.62it/s] word -> phonemes: 23%|██▎ | 799/3515 [00:00<00:00, 4017.24it/s] word -> phonemes: 35%|███▍ | 1221/3515 [00:00<00:00, 4107.21it/s] word -> phonemes: 47%|████▋ | 1644/3515 [00:00<00:00, 4153.19it/s] word -> phonemes: 59%|█████▊ | 2060/3515 [00:00<00:00, 4127.57it/s] word -> phonemes: 70%|███████ | 2473/3515 [00:00<00:00, 4074.69it/s] word -> phonemes: 82%|████████▏ | 2886/3515 [00:00<00:00, 4089.28it/s] word -> phonemes: 94%|█████████▍| 3296/3515 [00:00<00:00, 4069.77it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4067.69it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▎ | 366/2703 [00:00<00:00, 3657.00it/s] word -> phonemes: 27%|██▋ | 732/2703 [00:00<00:00, 3230.08it/s] word -> phonemes: 40%|████ | 1091/2703 [00:00<00:00, 3382.72it/s] word -> phonemes: 56%|█████▌ | 1514/2703 [00:00<00:00, 3700.45it/s] word -> phonemes: 70%|███████ | 1905/2703 [00:00<00:00, 3773.63it/s] word -> phonemes: 85%|████████▍ | 2295/2703 [00:00<00:00, 3815.20it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3745.96it/s] dev: 0%| | 0/2703 [00:00