/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: 12%|█▏ | 430/3515 [00:00<00:00, 4298.05it/s] word -> phonemes: 24%|██▍ | 860/3515 [00:00<00:00, 4133.50it/s] word -> phonemes: 38%|███▊ | 1333/3515 [00:00<00:00, 4391.08it/s] word -> phonemes: 51%|█████ | 1793/3515 [00:00<00:00, 4471.06it/s] word -> phonemes: 64%|██████▍ | 2241/3515 [00:00<00:00, 4440.35it/s] word -> phonemes: 76%|███████▋ | 2686/3515 [00:00<00:00, 4379.37it/s] word -> phonemes: 89%|████████▉ | 3125/3515 [00:00<00:00, 4266.57it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4329.34it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 514/2703 [00:00<00:00, 5137.35it/s] word -> phonemes: 38%|███▊ | 1028/2703 [00:00<00:00, 4989.81it/s] word -> phonemes: 57%|█████▋ | 1536/2703 [00:00<00:00, 5027.89it/s] word -> phonemes: 77%|███████▋ | 2073/2703 [00:00<00:00, 5160.54it/s] word -> phonemes: 96%|█████████▌| 2590/2703 [00:00<00:00, 4952.75it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5008.81it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 568/2703 [00:00<00:00, 5677.84it/s] word -> phonemes: 42%|████▏ | 1136/2703 [00:00<00:00, 5205.90it/s] word -> phonemes: 64%|██████▎ | 1720/2703 [00:00<00:00, 5480.57it/s] word -> phonemes: 85%|████████▌ | 2298/2703 [00:00<00:00, 5593.78it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5510.01it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|██ | 554/2703 [00:00<00:00, 5535.45it/s] word -> phonemes: 42%|████▏ | 1129/2703 [00:00<00:00, 5656.36it/s] word -> phonemes: 63%|██████▎ | 1695/2703 [00:00<00:00, 5388.39it/s] word -> phonemes: 84%|████████▎ | 2261/2703 [00:00<00:00, 5488.86it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5328.46it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 447/3515 [00:00<00:00, 4468.82it/s] word -> phonemes: 27%|██▋ | 942/3515 [00:00<00:00, 4751.08it/s] word -> phonemes: 41%|████ | 1424/3515 [00:00<00:00, 4778.83it/s] word -> phonemes: 54%|█████▍ | 1909/3515 [00:00<00:00, 4805.00it/s] word -> phonemes: 68%|██████▊ | 2390/3515 [00:00<00:00, 3054.59it/s] word -> phonemes: 79%|███████▉ | 2783/3515 [00:00<00:00, 3269.09it/s] word -> phonemes: 91%|█████████▏| 3212/3515 [00:00<00:00, 3533.80it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3788.25it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 22%|██▏ | 594/2703 [00:00<00:00, 5936.54it/s] word -> phonemes: 44%|████▍ | 1188/2703 [00:00<00:00, 5603.32it/s] word -> phonemes: 65%|██████▍ | 1750/2703 [00:00<00:00, 5516.92it/s] word -> phonemes: 86%|████████▋ | 2334/2703 [00:00<00:00, 5637.56it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5614.69it/s] dev: 0%| | 0/2703 [00:00