/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") 2023-10-04 02:52:15 | 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_2nd_iter_varmask {'model_config': None, 'refresh': False} Loading model from Local mert_25hz_2nd_iter_varmask 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: 6%|▋ | 223/3515 [00:00<00:01, 2222.73it/s] word -> phonemes: 13%|█▎ | 466/3515 [00:00<00:01, 2341.87it/s] word -> phonemes: 20%|█▉ | 701/3515 [00:00<00:01, 2236.14it/s] word -> phonemes: 27%|██▋ | 951/3515 [00:00<00:01, 2332.19it/s] word -> phonemes: 34%|███▎ | 1185/3515 [00:00<00:01, 2320.41it/s] word -> phonemes: 40%|████ | 1418/3515 [00:00<00:00, 2312.38it/s] word -> phonemes: 47%|████▋ | 1665/3515 [00:00<00:00, 2361.37it/s] word -> phonemes: 55%|█████▌ | 1934/3515 [00:00<00:00, 2462.17it/s] word -> phonemes: 62%|██████▏ | 2181/3515 [00:00<00:00, 2248.79it/s] word -> phonemes: 69%|██████▊ | 2410/3515 [00:01<00:00, 2229.02it/s] word -> phonemes: 75%|███████▌ | 2653/3515 [00:01<00:00, 2285.73it/s] word -> phonemes: 82%|████████▏ | 2884/3515 [00:01<00:00, 2181.82it/s] word -> phonemes: 90%|████████▉ | 3152/3515 [00:01<00:00, 2321.16it/s] word -> phonemes: 97%|█████████▋| 3394/3515 [00:01<00:00, 2347.87it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2280.02it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▉ | 237/2703 [00:00<00:01, 2367.40it/s] word -> phonemes: 19%|█▉ | 521/2703 [00:00<00:00, 2641.99it/s] word -> phonemes: 29%|██▉ | 786/2703 [00:00<00:00, 2450.92it/s] word -> phonemes: 38%|███▊ | 1033/2703 [00:00<00:00, 2328.44it/s] word -> phonemes: 48%|████▊ | 1310/2703 [00:00<00:00, 2474.42it/s] word -> phonemes: 59%|█████▉ | 1600/2703 [00:00<00:00, 2610.29it/s] word -> phonemes: 69%|██████▉ | 1863/2703 [00:00<00:00, 2542.25it/s] word -> phonemes: 78%|███████▊ | 2119/2703 [00:00<00:00, 2536.12it/s] word -> phonemes: 89%|████████▊ | 2394/2703 [00:00<00:00, 2600.77it/s] word -> phonemes: 98%|█████████▊| 2655/2703 [00:01<00:00, 2471.37it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2495.07it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 283/2703 [00:00<00:00, 2828.20it/s] word -> phonemes: 21%|██ | 566/2703 [00:00<00:00, 2580.90it/s] word -> phonemes: 31%|███ | 836/2703 [00:00<00:00, 2631.69it/s] word -> phonemes: 41%|████ | 1104/2703 [00:00<00:00, 2649.58it/s] word -> phonemes: 51%|█████ | 1370/2703 [00:00<00:00, 2477.68it/s] word -> phonemes: 60%|█████▉ | 1620/2703 [00:00<00:00, 2467.86it/s] word -> phonemes: 69%|██████▉ | 1876/2703 [00:00<00:00, 2496.12it/s] word -> phonemes: 79%|███████▊ | 2127/2703 [00:00<00:00, 2462.00it/s] word -> phonemes: 88%|████████▊ | 2389/2703 [00:00<00:00, 2506.65it/s] word -> phonemes: 98%|█████████▊| 2641/2703 [00:01<00:00, 2446.70it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2505.23it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 228/2703 [00:00<00:01, 2274.94it/s] word -> phonemes: 17%|█▋ | 456/2703 [00:00<00:00, 2273.00it/s] word -> phonemes: 27%|██▋ | 717/2703 [00:00<00:00, 2423.81it/s] word -> phonemes: 36%|███▌ | 960/2703 [00:00<00:00, 2377.75it/s] word -> phonemes: 45%|████▍ | 1210/2703 [00:00<00:00, 2419.44it/s] word -> phonemes: 55%|█████▍ | 1486/2703 [00:00<00:00, 2533.83it/s] word -> phonemes: 64%|██████▍ | 1740/2703 [00:00<00:00, 2531.68it/s] word -> phonemes: 75%|███████▍ | 2016/2703 [00:00<00:00, 2602.33it/s] word -> phonemes: 84%|████████▍ | 2284/2703 [00:00<00:00, 2623.69it/s] word -> phonemes: 94%|█████████▍| 2547/2703 [00:01<00:00, 2618.94it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2520.90it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 7%|▋ | 255/3515 [00:00<00:01, 2548.91it/s] word -> phonemes: 15%|█▍ | 510/3515 [00:00<00:01, 2523.86it/s] word -> phonemes: 22%|██▏ | 783/3515 [00:00<00:01, 2615.50it/s] word -> phonemes: 30%|███ | 1055/3515 [00:00<00:00, 2655.76it/s] word -> phonemes: 38%|███▊ | 1321/3515 [00:00<00:00, 2655.23it/s] word -> phonemes: 45%|████▌ | 1597/3515 [00:00<00:00, 2688.00it/s] word -> phonemes: 53%|█████▎ | 1866/3515 [00:00<00:00, 2597.17it/s] word -> phonemes: 61%|██████ | 2147/3515 [00:00<00:00, 2662.99it/s] word -> phonemes: 69%|██████▊ | 2414/3515 [00:00<00:00, 2604.01it/s] word -> phonemes: 76%|███████▌ | 2675/3515 [00:01<00:00, 2602.62it/s] word -> phonemes: 84%|████████▎ | 2936/3515 [00:01<00:00, 2552.80it/s] word -> phonemes: 91%|█████████ | 3198/3515 [00:01<00:00, 2570.58it/s] word -> phonemes: 98%|█████████▊| 3456/3515 [00:01<00:00, 2531.64it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2592.37it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 270/2703 [00:00<00:00, 2691.42it/s] word -> phonemes: 20%|█▉ | 540/2703 [00:00<00:00, 2659.30it/s] word -> phonemes: 30%|██▉ | 806/2703 [00:00<00:00, 2579.10it/s] word -> phonemes: 40%|████ | 1090/2703 [00:00<00:00, 2678.43it/s] word -> phonemes: 50%|█████ | 1359/2703 [00:00<00:00, 2418.41it/s] word -> phonemes: 60%|█████▉ | 1614/2703 [00:00<00:00, 2459.43it/s] word -> phonemes: 70%|██████▉ | 1891/2703 [00:00<00:00, 2554.46it/s] word -> phonemes: 80%|████████ | 2172/2703 [00:00<00:00, 2631.93it/s] word -> phonemes: 90%|█████████ | 2438/2703 [00:00<00:00, 2570.80it/s] word -> phonemes: 100%|█████████▉| 2697/2703 [00:01<00:00, 2495.39it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2543.01it/s] dev: 0%| | 0/2703 [00:00