/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-v1-95M 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.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-v1-95M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 5%|▍ | 166/3515 [00:00<00:02, 1651.71it/s] word -> phonemes: 10%|▉ | 335/3515 [00:00<00:01, 1651.33it/s] word -> phonemes: 14%|█▍ | 501/3515 [00:00<00:01, 1585.09it/s] word -> phonemes: 19%|█▉ | 660/3515 [00:00<00:01, 1476.63it/s] word -> phonemes: 23%|██▎ | 809/3515 [00:00<00:01, 1379.51it/s] word -> phonemes: 28%|██▊ | 972/3515 [00:00<00:01, 1434.70it/s] word -> phonemes: 33%|███▎ | 1160/3515 [00:00<00:01, 1569.00it/s] word -> phonemes: 43%|████▎ | 1502/3515 [00:00<00:00, 2103.69it/s] word -> phonemes: 49%|████▉ | 1726/3515 [00:00<00:00, 2119.31it/s] word -> phonemes: 55%|█████▌ | 1940/3515 [00:01<00:00, 1843.95it/s] word -> phonemes: 63%|██████▎ | 2217/3515 [00:01<00:00, 2092.23it/s] word -> phonemes: 69%|██████▉ | 2435/3515 [00:01<00:00, 1955.08it/s] word -> phonemes: 75%|███████▌ | 2638/3515 [00:01<00:00, 1647.42it/s] word -> phonemes: 81%|████████ | 2843/3515 [00:01<00:00, 1730.20it/s] word -> phonemes: 86%|████████▌ | 3026/3515 [00:01<00:00, 1588.54it/s] word -> phonemes: 93%|█████████▎| 3278/3515 [00:01<00:00, 1801.51it/s] word -> phonemes: 99%|█████████▊| 3468/3515 [00:02<00:00, 1628.42it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:02<00:00, 1714.07it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 472/2703 [00:00<00:00, 4712.67it/s] word -> phonemes: 35%|███▍ | 944/2703 [00:00<00:00, 4436.98it/s] word -> phonemes: 52%|█████▏ | 1399/2703 [00:00<00:00, 4355.91it/s] word -> phonemes: 70%|██████▉ | 1880/2703 [00:00<00:00, 4527.97it/s] word -> phonemes: 88%|████████▊ | 2382/2703 [00:00<00:00, 4700.64it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4606.72it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 564/2703 [00:00<00:00, 5630.80it/s] word -> phonemes: 42%|████▏ | 1128/2703 [00:00<00:00, 5532.65it/s] word -> phonemes: 62%|██████▏ | 1682/2703 [00:00<00:00, 4790.87it/s] word -> phonemes: 81%|████████ | 2191/2703 [00:00<00:00, 4895.50it/s] word -> phonemes: 99%|█████████▉| 2688/2703 [00:00<00:00, 4830.09it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4946.15it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▌ | 416/2703 [00:00<00:00, 4157.34it/s] word -> phonemes: 33%|███▎ | 890/2703 [00:00<00:00, 4499.39it/s] word -> phonemes: 53%|█████▎ | 1422/2703 [00:00<00:00, 4873.07it/s] word -> phonemes: 71%|███████ | 1910/2703 [00:00<00:00, 4605.25it/s] word -> phonemes: 88%|████████▊ | 2373/2703 [00:00<00:00, 4241.71it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4405.38it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█▏ | 402/3515 [00:00<00:00, 4013.38it/s] word -> phonemes: 23%|██▎ | 808/3515 [00:00<00:00, 4040.41it/s] word -> phonemes: 36%|███▌ | 1254/3515 [00:00<00:00, 4228.73it/s] word -> phonemes: 49%|████▉ | 1723/3515 [00:00<00:00, 4408.22it/s] word -> phonemes: 62%|██████▏ | 2164/3515 [00:00<00:00, 4394.76it/s] word -> phonemes: 74%|███████▍ | 2606/3515 [00:00<00:00, 4400.94it/s] word -> phonemes: 87%|████████▋ | 3047/3515 [00:00<00:00, 4172.10it/s] word -> phonemes: 99%|█████████▉| 3497/3515 [00:00<00:00, 4269.72it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4272.07it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 326/2703 [00:00<00:00, 3234.95it/s] word -> phonemes: 28%|██▊ | 757/2703 [00:00<00:00, 3864.90it/s] word -> phonemes: 46%|████▌ | 1232/2703 [00:00<00:00, 4265.52it/s] word -> phonemes: 63%|██████▎ | 1698/2703 [00:00<00:00, 4418.66it/s] word -> phonemes: 81%|████████ | 2196/2703 [00:00<00:00, 4618.58it/s] word -> phonemes: 98%|█████████▊| 2658/2703 [00:00<00:00, 4213.54it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4228.66it/s] dev: 0%| | 0/2703 [00:00