/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 m-a-p/MERT-v1-330M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█▏ | 400/3515 [00:00<00:00, 3781.06it/s] word -> phonemes: 24%|██▍ | 858/3515 [00:00<00:00, 4235.46it/s] word -> phonemes: 38%|███▊ | 1331/3515 [00:00<00:00, 4455.46it/s] word -> phonemes: 51%|█████ | 1778/3515 [00:00<00:00, 4163.43it/s] word -> phonemes: 63%|██████▎ | 2216/3515 [00:00<00:00, 4235.84it/s] word -> phonemes: 75%|███████▌ | 2642/3515 [00:00<00:00, 3815.28it/s] word -> phonemes: 88%|████████▊ | 3097/3515 [00:00<00:00, 4031.87it/s] word -> phonemes: 100%|█████████▉| 3508/3515 [00:00<00:00, 4048.03it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4042.41it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 605/2703 [00:00<00:00, 6043.45it/s] word -> phonemes: 45%|████▍ | 1210/2703 [00:00<00:00, 5531.92it/s] word -> phonemes: 68%|██████▊ | 1831/2703 [00:00<00:00, 5823.83it/s] word -> phonemes: 90%|████████▉ | 2429/2703 [00:00<00:00, 5882.68it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5776.04it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 588/2703 [00:00<00:00, 5879.09it/s] word -> phonemes: 44%|████▍ | 1184/2703 [00:00<00:00, 5921.33it/s] word -> phonemes: 66%|██████▌ | 1777/2703 [00:00<00:00, 5642.92it/s] word -> phonemes: 87%|████████▋ | 2353/2703 [00:00<00:00, 5687.64it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5734.44it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██▏ | 581/2703 [00:00<00:00, 5809.34it/s] word -> phonemes: 43%|████▎ | 1162/2703 [00:00<00:00, 5731.12it/s] word -> phonemes: 65%|██████▌ | 1767/2703 [00:00<00:00, 5872.65it/s] word -> phonemes: 87%|████████▋ | 2361/2703 [00:00<00:00, 5898.46it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5838.53it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 464/3515 [00:00<00:00, 4629.88it/s] word -> phonemes: 27%|██▋ | 942/3515 [00:00<00:00, 4716.83it/s] word -> phonemes: 41%|████▏ | 1452/3515 [00:00<00:00, 4889.75it/s] word -> phonemes: 55%|█████▌ | 1941/3515 [00:00<00:00, 4773.10it/s] word -> phonemes: 69%|██████▉ | 2419/3515 [00:00<00:00, 4753.35it/s] word -> phonemes: 83%|████████▎ | 2902/3515 [00:00<00:00, 4777.69it/s] word -> phonemes: 96%|█████████▌| 3380/3515 [00:00<00:00, 4625.60it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4710.59it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|█▉ | 539/2703 [00:00<00:00, 5386.72it/s] word -> phonemes: 41%|████ | 1107/2703 [00:00<00:00, 5558.64it/s] word -> phonemes: 62%|██████▏ | 1680/2703 [00:00<00:00, 5636.03it/s] word -> phonemes: 83%|████████▎ | 2244/2703 [00:00<00:00, 5569.86it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5550.08it/s] dev: 0%| | 0/2703 [00:00