/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_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-v1-95M 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-v1-95M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 455/3515 [00:00<00:00, 4543.42it/s] word -> phonemes: 26%|██▌ | 910/3515 [00:00<00:00, 4494.27it/s] word -> phonemes: 40%|███▉ | 1396/3515 [00:00<00:00, 4658.59it/s] word -> phonemes: 53%|█████▎ | 1869/3515 [00:00<00:00, 4682.78it/s] word -> phonemes: 67%|██████▋ | 2338/3515 [00:00<00:00, 4524.95it/s] word -> phonemes: 79%|███████▉ | 2792/3515 [00:00<00:00, 4450.44it/s] word -> phonemes: 92%|█████████▏| 3238/3515 [00:00<00:00, 4142.99it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4304.25it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 7%|▋ | 190/2703 [00:00<00:01, 1846.42it/s] word -> phonemes: 14%|█▍ | 375/2703 [00:00<00:01, 1315.90it/s] word -> phonemes: 22%|██▏ | 596/2703 [00:00<00:01, 1632.70it/s] word -> phonemes: 33%|███▎ | 883/2703 [00:00<00:00, 2057.96it/s] word -> phonemes: 41%|████ | 1102/2703 [00:00<00:00, 1962.94it/s] word -> phonemes: 54%|█████▍ | 1463/2703 [00:00<00:00, 2465.57it/s] word -> phonemes: 64%|██████▍ | 1728/2703 [00:00<00:00, 2512.38it/s] word -> phonemes: 76%|███████▋ | 2067/2703 [00:00<00:00, 2776.84it/s] word -> phonemes: 87%|████████▋ | 2361/2703 [00:00<00:00, 2825.95it/s] word -> phonemes: 98%|█████████▊| 2649/2703 [00:01<00:00, 2577.70it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2365.32it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 260/2703 [00:00<00:00, 2502.34it/s] word -> phonemes: 19%|█▉ | 511/2703 [00:00<00:00, 2351.58it/s] word -> phonemes: 28%|██▊ | 747/2703 [00:00<00:00, 2276.93it/s] word -> phonemes: 36%|███▌ | 975/2703 [00:00<00:00, 2022.94it/s] word -> phonemes: 44%|████▎ | 1181/2703 [00:00<00:00, 1938.66it/s] word -> phonemes: 51%|█████ | 1383/2703 [00:00<00:00, 1963.01it/s] word -> phonemes: 61%|██████ | 1649/2703 [00:00<00:00, 2170.77it/s] word -> phonemes: 72%|███████▏ | 1942/2703 [00:00<00:00, 2346.21it/s] word -> phonemes: 82%|████████▏ | 2213/2703 [00:00<00:00, 2453.24it/s] word -> phonemes: 93%|█████████▎| 2527/2703 [00:01<00:00, 2648.83it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2410.56it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▌ | 409/2703 [00:00<00:00, 4087.51it/s] word -> phonemes: 30%|███ | 818/2703 [00:00<00:00, 3009.29it/s] word -> phonemes: 42%|████▏ | 1136/2703 [00:00<00:00, 2908.98it/s] word -> phonemes: 53%|█████▎ | 1436/2703 [00:00<00:00, 2662.90it/s] word -> phonemes: 64%|██████▎ | 1718/2703 [00:00<00:00, 2708.84it/s] word -> phonemes: 74%|███████▍ | 1994/2703 [00:00<00:00, 2620.85it/s] word -> phonemes: 84%|████████▎ | 2259/2703 [00:00<00:00, 2387.81it/s] word -> phonemes: 93%|█████████▎| 2521/2703 [00:00<00:00, 2447.95it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2539.52it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█▏ | 398/3515 [00:00<00:00, 3977.75it/s] word -> phonemes: 25%|██▍ | 870/3515 [00:00<00:00, 4411.12it/s] word -> phonemes: 37%|███▋ | 1312/3515 [00:00<00:00, 4002.47it/s] word -> phonemes: 51%|█████ | 1796/3515 [00:00<00:00, 4311.74it/s] word -> phonemes: 63%|██████▎ | 2232/3515 [00:00<00:00, 2543.86it/s] word -> phonemes: 74%|███████▎ | 2584/3515 [00:00<00:00, 2762.55it/s] word -> phonemes: 87%|████████▋ | 3055/3515 [00:00<00:00, 3236.62it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 3432.58it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 312/2703 [00:00<00:00, 2929.88it/s] word -> phonemes: 26%|██▌ | 702/2703 [00:00<00:00, 3483.73it/s] word -> phonemes: 39%|███▉ | 1052/2703 [00:00<00:00, 3021.72it/s] word -> phonemes: 50%|█████ | 1361/2703 [00:00<00:00, 2911.63it/s] word -> phonemes: 61%|██████▏ | 1656/2703 [00:00<00:00, 2378.11it/s] word -> phonemes: 71%|███████ | 1908/2703 [00:00<00:00, 2402.16it/s] word -> phonemes: 81%|████████▏ | 2198/2703 [00:00<00:00, 2461.97it/s] word -> phonemes: 95%|█████████▍| 2556/2703 [00:00<00:00, 2774.53it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2579.16it/s] dev: 0%| | 0/2703 [00:00