/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.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%|█▎ | 466/3515 [00:00<00:00, 4656.93it/s] word -> phonemes: 27%|██▋ | 963/3515 [00:00<00:00, 4840.40it/s] word -> phonemes: 42%|████▏ | 1482/3515 [00:00<00:00, 4996.26it/s] word -> phonemes: 56%|█████▋ | 1982/3515 [00:00<00:00, 4794.40it/s] word -> phonemes: 70%|███████ | 2463/3515 [00:00<00:00, 4703.36it/s] word -> phonemes: 83%|████████▎ | 2935/3515 [00:00<00:00, 4658.87it/s] word -> phonemes: 97%|█████████▋| 3402/3515 [00:00<00:00, 4538.10it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4661.83it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██▏ | 580/2703 [00:00<00:00, 5796.05it/s] word -> phonemes: 44%|████▍ | 1193/2703 [00:00<00:00, 5990.89it/s] word -> phonemes: 67%|██████▋ | 1821/2703 [00:00<00:00, 6119.88it/s] word -> phonemes: 90%|█████████ | 2433/2703 [00:00<00:00, 5983.20it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5858.51it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 583/2703 [00:00<00:00, 5810.31it/s] word -> phonemes: 43%|████▎ | 1165/2703 [00:00<00:00, 5807.98it/s] word -> phonemes: 65%|██████▍ | 1746/2703 [00:00<00:00, 5353.12it/s] word -> phonemes: 86%|████████▌ | 2322/2703 [00:00<00:00, 5502.38it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5526.09it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 568/2703 [00:00<00:00, 5679.73it/s] word -> phonemes: 43%|████▎ | 1154/2703 [00:00<00:00, 5784.22it/s] word -> phonemes: 64%|██████▍ | 1741/2703 [00:00<00:00, 5821.68it/s] word -> phonemes: 86%|████████▌ | 2324/2703 [00:00<00:00, 5767.98it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5677.91it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█ | 371/3515 [00:00<00:00, 3707.17it/s] word -> phonemes: 21%|██ | 742/3515 [00:00<00:00, 3668.13it/s] word -> phonemes: 33%|███▎ | 1163/3515 [00:00<00:00, 3911.32it/s] word -> phonemes: 45%|████▍ | 1569/3515 [00:00<00:00, 3969.15it/s] word -> phonemes: 56%|█████▌ | 1967/3515 [00:00<00:00, 3845.98it/s] word -> phonemes: 67%|██████▋ | 2353/3515 [00:00<00:00, 3733.80it/s] word -> phonemes: 78%|███████▊ | 2735/3515 [00:00<00:00, 3749.89it/s] word -> phonemes: 89%|████████▊ | 3111/3515 [00:00<00:00, 3733.85it/s] word -> phonemes: 99%|█████████▉| 3485/3515 [00:00<00:00, 3498.80it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3690.89it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 555/2703 [00:00<00:00, 5542.37it/s] word -> phonemes: 42%|████▏ | 1126/2703 [00:00<00:00, 5636.55it/s] word -> phonemes: 63%|██████▎ | 1690/2703 [00:00<00:00, 5615.13it/s] word -> phonemes: 84%|████████▍ | 2274/2703 [00:00<00:00, 5702.95it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5553.11it/s] dev: 0%| | 0/2703 [00:00