/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: 10%|▉ | 339/3515 [00:00<00:00, 3337.31it/s] word -> phonemes: 19%|█▉ | 673/3515 [00:00<00:00, 2880.76it/s] word -> phonemes: 29%|██▉ | 1024/3515 [00:00<00:00, 3143.97it/s] word -> phonemes: 40%|████ | 1412/3515 [00:00<00:00, 3417.38it/s] word -> phonemes: 50%|█████ | 1775/3515 [00:00<00:00, 3490.04it/s] word -> phonemes: 62%|██████▏ | 2192/3515 [00:00<00:00, 3714.28it/s] word -> phonemes: 73%|███████▎ | 2566/3515 [00:00<00:00, 3697.28it/s] word -> phonemes: 84%|████████▎ | 2938/3515 [00:00<00:00, 3626.50it/s] word -> phonemes: 94%|█████████▍| 3302/3515 [00:00<00:00, 3408.39it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 3471.85it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 598/2703 [00:00<00:00, 5979.81it/s] word -> phonemes: 44%|████▍ | 1196/2703 [00:00<00:00, 5299.55it/s] word -> phonemes: 66%|██████▌ | 1790/2703 [00:00<00:00, 5571.16it/s] word -> phonemes: 87%|████████▋ | 2360/2703 [00:00<00:00, 5617.35it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5570.98it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 23%|██▎ | 613/2703 [00:00<00:00, 6119.65it/s] word -> phonemes: 46%|████▌ | 1245/2703 [00:00<00:00, 6234.72it/s] word -> phonemes: 70%|██████▉ | 1884/2703 [00:00<00:00, 6304.30it/s] word -> phonemes: 93%|█████████▎| 2515/2703 [00:00<00:00, 6041.79it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5933.71it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 586/2703 [00:00<00:00, 5854.66it/s] word -> phonemes: 44%|████▍ | 1184/2703 [00:00<00:00, 5926.40it/s] word -> phonemes: 66%|██████▋ | 1794/2703 [00:00<00:00, 6003.52it/s] word -> phonemes: 89%|████████▊ | 2395/2703 [00:00<00:00, 5945.17it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5896.82it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 424/3515 [00:00<00:00, 4233.02it/s] word -> phonemes: 25%|██▍ | 868/3515 [00:00<00:00, 4353.25it/s] word -> phonemes: 38%|███▊ | 1326/3515 [00:00<00:00, 4454.98it/s] word -> phonemes: 51%|█████ | 1798/3515 [00:00<00:00, 4493.33it/s] word -> phonemes: 64%|██████▍ | 2248/3515 [00:00<00:00, 4479.26it/s] word -> phonemes: 77%|███████▋ | 2696/3515 [00:00<00:00, 4260.40it/s] word -> phonemes: 89%|████████▉ | 3140/3515 [00:00<00:00, 4314.85it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4381.19it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 562/2703 [00:00<00:00, 5617.54it/s] word -> phonemes: 42%|████▏ | 1142/2703 [00:00<00:00, 5722.16it/s] word -> phonemes: 64%|██████▍ | 1733/2703 [00:00<00:00, 5803.90it/s] word -> phonemes: 86%|████████▌ | 2314/2703 [00:00<00:00, 5779.42it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5722.21it/s] dev: 0%| | 0/2703 [00:00