/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_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-v1-95M 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-v1-95M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 447/3515 [00:00<00:00, 4467.28it/s] word -> phonemes: 25%|██▌ | 894/3515 [00:00<00:00, 4338.26it/s] word -> phonemes: 39%|███▉ | 1381/3515 [00:00<00:00, 4574.80it/s] word -> phonemes: 52%|█████▏ | 1843/3515 [00:00<00:00, 4588.49it/s] word -> phonemes: 66%|██████▌ | 2303/3515 [00:00<00:00, 4315.86it/s] word -> phonemes: 78%|███████▊ | 2738/3515 [00:00<00:00, 4274.45it/s] word -> phonemes: 90%|█████████ | 3168/3515 [00:00<00:00, 4229.27it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4298.80it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▋ | 441/2703 [00:00<00:00, 4407.67it/s] word -> phonemes: 37%|███▋ | 1013/2703 [00:00<00:00, 5176.76it/s] word -> phonemes: 59%|█████▉ | 1593/2703 [00:00<00:00, 5461.16it/s] word -> phonemes: 81%|████████ | 2180/2703 [00:00<00:00, 5622.37it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5411.06it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 465/2703 [00:00<00:00, 4645.16it/s] word -> phonemes: 37%|███▋ | 1011/2703 [00:00<00:00, 5118.64it/s] word -> phonemes: 58%|█████▊ | 1563/2703 [00:00<00:00, 5297.60it/s] word -> phonemes: 77%|███████▋ | 2093/2703 [00:00<00:00, 5127.84it/s] word -> phonemes: 97%|█████████▋| 2627/2703 [00:00<00:00, 5200.47it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5150.65it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|█▉ | 532/2703 [00:00<00:00, 5311.77it/s] word -> phonemes: 39%|███▉ | 1064/2703 [00:00<00:00, 5257.53it/s] word -> phonemes: 59%|█████▉ | 1590/2703 [00:00<00:00, 5132.83it/s] word -> phonemes: 81%|████████ | 2183/2703 [00:00<00:00, 5438.86it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5414.56it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 415/3515 [00:00<00:00, 4149.38it/s] word -> phonemes: 25%|██▍ | 869/3515 [00:00<00:00, 4376.48it/s] word -> phonemes: 38%|███▊ | 1331/3515 [00:00<00:00, 4484.27it/s] word -> phonemes: 51%|█████ | 1780/3515 [00:00<00:00, 4202.46it/s] word -> phonemes: 64%|██████▎ | 2239/3515 [00:00<00:00, 4335.33it/s] word -> phonemes: 76%|███████▌ | 2676/3515 [00:00<00:00, 4344.21it/s] word -> phonemes: 89%|████████▊ | 3114/3515 [00:00<00:00, 4354.11it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4352.13it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▊ | 503/2703 [00:00<00:00, 5028.65it/s] word -> phonemes: 39%|███▉ | 1067/2703 [00:00<00:00, 5383.32it/s] word -> phonemes: 59%|█████▉ | 1606/2703 [00:00<00:00, 4937.02it/s] word -> phonemes: 80%|███████▉ | 2157/2703 [00:00<00:00, 5147.58it/s] word -> phonemes: 99%|█████████▉| 2680/2703 [00:00<00:00, 5175.08it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5144.64it/s] dev: 0%| | 0/2703 [00:00