/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 22:54:05 | 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_test_8x_400k {'model_config': None, 'refresh': False} Loading model from Local mert_test_8x_400k 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: 12%|█▏ | 414/3515 [00:00<00:00, 4137.24it/s] word -> phonemes: 24%|██▎ | 828/3515 [00:00<00:00, 4022.70it/s] word -> phonemes: 36%|███▋ | 1276/3515 [00:00<00:00, 4224.47it/s] word -> phonemes: 48%|████▊ | 1701/3515 [00:00<00:00, 4233.71it/s] word -> phonemes: 61%|██████ | 2141/3515 [00:00<00:00, 4291.93it/s] word -> phonemes: 73%|███████▎ | 2571/3515 [00:00<00:00, 4248.78it/s] word -> phonemes: 85%|████████▌ | 2997/3515 [00:00<00:00, 4247.60it/s] word -> phonemes: 97%|█████████▋| 3422/3515 [00:00<00:00, 4245.47it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4214.68it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 520/2703 [00:00<00:00, 5195.88it/s] word -> phonemes: 40%|████ | 1083/2703 [00:00<00:00, 5449.77it/s] word -> phonemes: 60%|██████ | 1628/2703 [00:00<00:00, 4847.78it/s] word -> phonemes: 80%|███████▉ | 2153/2703 [00:00<00:00, 4991.18it/s] word -> phonemes: 99%|█████████▊| 2663/2703 [00:00<00:00, 5026.77it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5044.60it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 21%|██ | 561/2703 [00:00<00:00, 5603.42it/s] word -> phonemes: 42%|████▏ | 1122/2703 [00:00<00:00, 5132.36it/s] word -> phonemes: 63%|██████▎ | 1704/2703 [00:00<00:00, 5430.32it/s] word -> phonemes: 83%|████████▎ | 2250/2703 [00:00<00:00, 5309.29it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5247.64it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▊ | 501/2703 [00:00<00:00, 5008.06it/s] word -> phonemes: 37%|███▋ | 1013/2703 [00:00<00:00, 5072.38it/s] word -> phonemes: 56%|█████▋ | 1521/2703 [00:00<00:00, 5005.42it/s] word -> phonemes: 75%|███████▍ | 2022/2703 [00:00<00:00, 4898.47it/s] word -> phonemes: 93%|█████████▎| 2513/2703 [00:00<00:00, 4693.25it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4788.39it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 442/3515 [00:00<00:00, 4411.36it/s] word -> phonemes: 26%|██▌ | 906/3515 [00:00<00:00, 4543.16it/s] word -> phonemes: 39%|███▊ | 1361/3515 [00:00<00:00, 4508.33it/s] word -> phonemes: 52%|█████▏ | 1821/3515 [00:00<00:00, 4543.92it/s] word -> phonemes: 65%|██████▍ | 2276/3515 [00:00<00:00, 4386.86it/s] word -> phonemes: 77%|███████▋ | 2716/3515 [00:00<00:00, 4374.43it/s] word -> phonemes: 90%|████████▉ | 3157/3515 [00:00<00:00, 4384.01it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4383.06it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▌ | 425/2703 [00:00<00:00, 4248.36it/s] word -> phonemes: 33%|███▎ | 880/2703 [00:00<00:00, 4424.60it/s] word -> phonemes: 49%|████▉ | 1323/2703 [00:00<00:00, 4301.90it/s] word -> phonemes: 66%|██████▋ | 1795/2703 [00:00<00:00, 4463.30it/s] word -> phonemes: 84%|████████▎ | 2258/2703 [00:00<00:00, 4393.50it/s] word -> phonemes: 100%|█████████▉| 2698/2703 [00:00<00:00, 4325.13it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4353.39it/s] dev: 0%| | 0/2703 [00:00