/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") 2023-10-13 01:31:50 | WARNING | root | Pytorch pre-release version 2.1.0.dev20230831+cu118 - assuming intent to test it /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') [Featurizer] - Take a list of 13 features and weighted sum them. [Featurizer] - The selected feature hidden_states's downsample rate is 960 [Runner] - Start a new experiment mert_25hz_test_only_demuc_label2 {'model_config': None, 'refresh': False} Loading model from Local mert_25hz_test_only_demuc_label2 load local model succeed load local feat extractor Wav2Vec2FeatureExtractor { "do_normalize": false, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0, "return_attention_mask": true, "sampling_rate": 24000 } overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 9%|▉ | 311/3515 [00:00<00:01, 3106.92it/s] word -> phonemes: 22%|██▏ | 758/3515 [00:00<00:00, 3908.33it/s] word -> phonemes: 35%|███▍ | 1218/3515 [00:00<00:00, 4222.65it/s] word -> phonemes: 48%|████▊ | 1673/3515 [00:00<00:00, 4350.73it/s] word -> phonemes: 61%|██████ | 2142/3515 [00:00<00:00, 4470.78it/s] word -> phonemes: 74%|███████▎ | 2590/3515 [00:00<00:00, 4415.46it/s] word -> phonemes: 86%|████████▋ | 3032/3515 [00:00<00:00, 4241.67it/s] word -> phonemes: 98%|█████████▊| 3458/3515 [00:00<00:00, 4059.97it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4163.17it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|█▉ | 528/2703 [00:00<00:00, 5279.63it/s] word -> phonemes: 39%|███▉ | 1056/2703 [00:00<00:00, 5206.99it/s] word -> phonemes: 58%|█████▊ | 1577/2703 [00:00<00:00, 4842.33it/s] word -> phonemes: 76%|███████▋ | 2064/2703 [00:00<00:00, 4754.65it/s] word -> phonemes: 96%|█████████▌| 2596/2703 [00:00<00:00, 4947.27it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4965.82it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 507/2703 [00:00<00:00, 5062.18it/s] word -> phonemes: 40%|████ | 1082/2703 [00:00<00:00, 5462.42it/s] word -> phonemes: 60%|██████ | 1633/2703 [00:00<00:00, 5451.21it/s] word -> phonemes: 81%|████████ | 2179/2703 [00:00<00:00, 5425.47it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5426.49it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 452/2703 [00:00<00:00, 4513.67it/s] word -> phonemes: 37%|███▋ | 996/2703 [00:00<00:00, 5055.32it/s] word -> phonemes: 59%|█████▊ | 1582/2703 [00:00<00:00, 5420.21it/s] word -> phonemes: 79%|███████▊ | 2125/2703 [00:00<00:00, 5405.06it/s] word -> phonemes: 100%|█████████▉| 2701/2703 [00:00<00:00, 5532.14it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5387.09it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 451/3515 [00:00<00:00, 4508.65it/s] word -> phonemes: 26%|██▌ | 902/3515 [00:00<00:00, 4320.78it/s] word -> phonemes: 39%|███▉ | 1384/3515 [00:00<00:00, 4540.45it/s] word -> phonemes: 52%|█████▏ | 1839/3515 [00:00<00:00, 4239.69it/s] word -> phonemes: 64%|██████▍ | 2266/3515 [00:00<00:00, 4022.19it/s] word -> phonemes: 77%|███████▋ | 2706/3515 [00:00<00:00, 4140.82it/s] word -> phonemes: 90%|████████▉ | 3153/3515 [00:00<00:00, 4241.34it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4264.70it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 562/2703 [00:00<00:00, 5616.94it/s] word -> phonemes: 42%|████▏ | 1143/2703 [00:00<00:00, 5724.99it/s] word -> phonemes: 63%|██████▎ | 1716/2703 [00:00<00:00, 5332.84it/s] word -> phonemes: 85%|████████▌ | 2302/2703 [00:00<00:00, 5531.12it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5468.35it/s] dev: 0%| | 0/2703 [00:00