/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_g', 'encoder.pos_conv_embed.conv.weight_v'] - 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: 12%|█▏ | 408/3515 [00:00<00:00, 4063.35it/s] word -> phonemes: 26%|██▌ | 907/3515 [00:00<00:00, 4605.60it/s] word -> phonemes: 39%|███▉ | 1368/3515 [00:00<00:00, 4538.08it/s] word -> phonemes: 53%|█████▎ | 1847/3515 [00:00<00:00, 4632.68it/s] word -> phonemes: 66%|██████▌ | 2328/3515 [00:00<00:00, 4694.54it/s] word -> phonemes: 80%|███████▉ | 2798/3515 [00:00<00:00, 4693.70it/s] word -> phonemes: 93%|█████████▎| 3268/3515 [00:00<00:00, 4435.15it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4527.63it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 491/2703 [00:00<00:00, 4818.34it/s] word -> phonemes: 39%|███▉ | 1057/2703 [00:00<00:00, 5263.56it/s] word -> phonemes: 59%|█████▊ | 1584/2703 [00:00<00:00, 4978.16it/s] word -> phonemes: 79%|███████▉ | 2135/2703 [00:00<00:00, 5178.34it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5240.11it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 558/2703 [00:00<00:00, 5572.23it/s] word -> phonemes: 41%|████▏ | 1116/2703 [00:00<00:00, 5536.14it/s] word -> phonemes: 62%|██████▏ | 1670/2703 [00:00<00:00, 4972.63it/s] word -> phonemes: 81%|████████▏ | 2199/2703 [00:00<00:00, 4988.38it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5138.27it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▍ | 404/2703 [00:00<00:00, 3975.52it/s] word -> phonemes: 30%|██▉ | 804/2703 [00:00<00:00, 3847.32it/s] word -> phonemes: 47%|████▋ | 1274/2703 [00:00<00:00, 4226.50it/s] word -> phonemes: 65%|██████▍ | 1750/2703 [00:00<00:00, 4432.11it/s] word -> phonemes: 83%|████████▎ | 2236/2703 [00:00<00:00, 4582.24it/s] word -> phonemes: 100%|█████████▉| 2702/2703 [00:00<00:00, 4607.34it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4440.16it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|█ | 360/3515 [00:00<00:00, 3551.79it/s] word -> phonemes: 20%|██ | 716/3515 [00:00<00:00, 3375.41it/s] word -> phonemes: 32%|███▏ | 1123/3515 [00:00<00:00, 3681.81it/s] word -> phonemes: 42%|████▏ | 1493/3515 [00:00<00:00, 3310.23it/s] word -> phonemes: 52%|█████▏ | 1830/3515 [00:00<00:00, 3137.37it/s] word -> phonemes: 66%|██████▋ | 2332/3515 [00:00<00:00, 3717.40it/s] word -> phonemes: 77%|███████▋ | 2713/3515 [00:00<00:00, 3543.88it/s] word -> phonemes: 88%|████████▊ | 3101/3515 [00:00<00:00, 3639.84it/s] word -> phonemes: 99%|█████████▊| 3471/3515 [00:00<00:00, 3494.48it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 3507.47it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▊ | 505/2703 [00:00<00:00, 5042.30it/s] word -> phonemes: 41%|████ | 1113/2703 [00:00<00:00, 5652.19it/s] word -> phonemes: 62%|██████▏ | 1686/2703 [00:00<00:00, 5624.70it/s] word -> phonemes: 83%|████████▎ | 2249/2703 [00:00<00:00, 5548.66it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5559.62it/s] dev: 0%| | 0/2703 [00:00