/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_g', 'encoder.pos_conv_embed.conv.weight_v'] - 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: 9%|▉ | 332/3515 [00:00<00:00, 3319.23it/s] word -> phonemes: 22%|██▏ | 787/3515 [00:00<00:00, 4002.92it/s] word -> phonemes: 34%|███▍ | 1187/3515 [00:00<00:00, 3184.36it/s] word -> phonemes: 45%|████▌ | 1589/3515 [00:00<00:00, 3468.34it/s] word -> phonemes: 55%|█████▌ | 1950/3515 [00:00<00:00, 3363.49it/s] word -> phonemes: 66%|██████▌ | 2314/3515 [00:00<00:00, 3448.87it/s] word -> phonemes: 76%|███████▌ | 2666/3515 [00:00<00:00, 3465.29it/s] word -> phonemes: 87%|████████▋ | 3067/3515 [00:00<00:00, 3629.01it/s] word -> phonemes: 99%|█████████▊| 3469/3515 [00:00<00:00, 3746.22it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3578.57it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 500/2703 [00:00<00:00, 4979.16it/s] word -> phonemes: 37%|███▋ | 998/2703 [00:00<00:00, 4672.55it/s] word -> phonemes: 54%|█████▍ | 1467/2703 [00:00<00:00, 4472.47it/s] word -> phonemes: 74%|███████▎ | 1988/2703 [00:00<00:00, 4747.44it/s] word -> phonemes: 93%|█████████▎| 2509/2703 [00:00<00:00, 4907.04it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4757.66it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 496/2703 [00:00<00:00, 4952.31it/s] word -> phonemes: 37%|███▋ | 999/2703 [00:00<00:00, 4994.81it/s] word -> phonemes: 55%|█████▌ | 1499/2703 [00:00<00:00, 4863.24it/s] word -> phonemes: 73%|███████▎ | 1986/2703 [00:00<00:00, 4522.01it/s] word -> phonemes: 93%|█████████▎| 2510/2703 [00:00<00:00, 4765.91it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4753.13it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 461/2703 [00:00<00:00, 4602.77it/s] word -> phonemes: 35%|███▌ | 957/2703 [00:00<00:00, 4811.00it/s] word -> phonemes: 53%|█████▎ | 1439/2703 [00:00<00:00, 4566.74it/s] word -> phonemes: 71%|███████ | 1914/2703 [00:00<00:00, 4633.63it/s] word -> phonemes: 88%|████████▊ | 2379/2703 [00:00<00:00, 4632.00it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4644.95it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 438/3515 [00:00<00:00, 4376.86it/s] word -> phonemes: 25%|██▍ | 876/3515 [00:00<00:00, 4284.95it/s] word -> phonemes: 37%|███▋ | 1307/3515 [00:00<00:00, 4294.68it/s] word -> phonemes: 50%|████▉ | 1751/3515 [00:00<00:00, 4347.47it/s] word -> phonemes: 63%|██████▎ | 2209/3515 [00:00<00:00, 4430.55it/s] word -> phonemes: 76%|███████▌ | 2654/3515 [00:00<00:00, 4435.79it/s] word -> phonemes: 88%|████████▊ | 3098/3515 [00:00<00:00, 4111.13it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4282.01it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 459/2703 [00:00<00:00, 4589.83it/s] word -> phonemes: 36%|███▋ | 980/2703 [00:00<00:00, 4950.38it/s] word -> phonemes: 55%|█████▍ | 1476/2703 [00:00<00:00, 4124.40it/s] word -> phonemes: 70%|███████ | 1903/2703 [00:00<00:00, 4106.30it/s] word -> phonemes: 87%|████████▋ | 2355/2703 [00:00<00:00, 4241.12it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4273.18it/s] dev: 0%| | 0/2703 [00:00