/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-v1-330M 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-v1-330M 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-v1-330M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 440/3515 [00:00<00:00, 4392.33it/s] word -> phonemes: 26%|██▌ | 921/3515 [00:00<00:00, 4636.23it/s] word -> phonemes: 40%|███▉ | 1396/3515 [00:00<00:00, 4686.09it/s] word -> phonemes: 53%|█████▎ | 1865/3515 [00:00<00:00, 4677.44it/s] word -> phonemes: 67%|██████▋ | 2338/3515 [00:00<00:00, 4693.24it/s] word -> phonemes: 80%|███████▉ | 2808/3515 [00:00<00:00, 4657.61it/s] word -> phonemes: 93%|█████████▎| 3274/3515 [00:00<00:00, 4562.61it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4516.47it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 480/2703 [00:00<00:00, 4798.79it/s] word -> phonemes: 39%|███▉ | 1063/2703 [00:00<00:00, 5402.56it/s] word -> phonemes: 61%|██████ | 1645/2703 [00:00<00:00, 5590.42it/s] word -> phonemes: 83%|████████▎ | 2231/2703 [00:00<00:00, 5695.09it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5556.25it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 471/2703 [00:00<00:00, 4707.60it/s] word -> phonemes: 35%|███▌ | 959/2703 [00:00<00:00, 4808.41it/s] word -> phonemes: 56%|█████▋ | 1522/2703 [00:00<00:00, 5178.99it/s] word -> phonemes: 78%|███████▊ | 2111/2703 [00:00<00:00, 5458.89it/s] word -> phonemes: 98%|█████████▊| 2657/2703 [00:00<00:00, 5422.95it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5287.44it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|██ | 545/2703 [00:00<00:00, 5442.58it/s] word -> phonemes: 42%|████▏ | 1131/2703 [00:00<00:00, 5685.88it/s] word -> phonemes: 63%|██████▎ | 1700/2703 [00:00<00:00, 5522.44it/s] word -> phonemes: 85%|████████▍ | 2294/2703 [00:00<00:00, 5683.69it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5649.74it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 453/3515 [00:00<00:00, 4521.49it/s] word -> phonemes: 27%|██▋ | 950/3515 [00:00<00:00, 4781.08it/s] word -> phonemes: 41%|████ | 1439/3515 [00:00<00:00, 4827.68it/s] word -> phonemes: 55%|█████▍ | 1922/3515 [00:00<00:00, 4546.94it/s] word -> phonemes: 68%|██████▊ | 2397/3515 [00:00<00:00, 4616.68it/s] word -> phonemes: 81%|████████▏ | 2861/3515 [00:00<00:00, 4462.26it/s] word -> phonemes: 94%|█████████▍| 3310/3515 [00:00<00:00, 4280.16it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4461.08it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|██ | 548/2703 [00:00<00:00, 5474.90it/s] word -> phonemes: 41%|████ | 1114/2703 [00:00<00:00, 5583.24it/s] word -> phonemes: 62%|██████▏ | 1673/2703 [00:00<00:00, 5513.18it/s] word -> phonemes: 82%|████████▏ | 2225/2703 [00:00<00:00, 5410.82it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5436.92it/s] dev: 0%| | 0/2703 [00:00