/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: 13%|█▎ | 440/3515 [00:00<00:00, 4399.45it/s] word -> phonemes: 26%|██▌ | 912/3515 [00:00<00:00, 4587.60it/s] word -> phonemes: 39%|███▉ | 1371/3515 [00:00<00:00, 4493.49it/s] word -> phonemes: 52%|█████▏ | 1845/3515 [00:00<00:00, 4587.71it/s] word -> phonemes: 66%|██████▌ | 2305/3515 [00:00<00:00, 4438.56it/s] word -> phonemes: 78%|███████▊ | 2755/3515 [00:00<00:00, 4456.45it/s] word -> phonemes: 91%|█████████ | 3202/3515 [00:00<00:00, 4437.48it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4371.52it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 492/2703 [00:00<00:00, 4903.31it/s] word -> phonemes: 39%|███▊ | 1045/2703 [00:00<00:00, 5055.48it/s] word -> phonemes: 57%|█████▋ | 1551/2703 [00:00<00:00, 4900.03it/s] word -> phonemes: 76%|███████▌ | 2047/2703 [00:00<00:00, 4922.40it/s] word -> phonemes: 94%|█████████▍| 2552/2703 [00:00<00:00, 4964.58it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4972.43it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 20%|██ | 552/2703 [00:00<00:00, 5514.26it/s] word -> phonemes: 41%|████ | 1104/2703 [00:00<00:00, 5481.74it/s] word -> phonemes: 61%|██████ | 1653/2703 [00:00<00:00, 5311.70it/s] word -> phonemes: 81%|████████ | 2185/2703 [00:00<00:00, 5247.79it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5178.89it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 448/2703 [00:00<00:00, 4470.89it/s] word -> phonemes: 33%|███▎ | 905/2703 [00:00<00:00, 4528.01it/s] word -> phonemes: 51%|█████ | 1379/2703 [00:00<00:00, 4604.82it/s] word -> phonemes: 69%|██████▉ | 1860/2703 [00:00<00:00, 4661.95it/s] word -> phonemes: 88%|████████▊ | 2388/2703 [00:00<00:00, 4819.66it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4803.26it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|▉ | 348/3515 [00:00<00:00, 3478.71it/s] word -> phonemes: 23%|██▎ | 797/3515 [00:00<00:00, 4070.10it/s] word -> phonemes: 36%|███▌ | 1263/3515 [00:00<00:00, 4336.01it/s] word -> phonemes: 48%|████▊ | 1701/3515 [00:00<00:00, 4352.94it/s] word -> phonemes: 62%|██████▏ | 2166/3515 [00:00<00:00, 4412.94it/s] word -> phonemes: 74%|███████▍ | 2608/3515 [00:00<00:00, 4304.39it/s] word -> phonemes: 88%|████████▊ | 3076/3515 [00:00<00:00, 4422.21it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4309.56it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 517/2703 [00:00<00:00, 5162.37it/s] word -> phonemes: 39%|███▉ | 1054/2703 [00:00<00:00, 5281.47it/s] word -> phonemes: 59%|█████▊ | 1583/2703 [00:00<00:00, 4751.07it/s] word -> phonemes: 76%|███████▋ | 2064/2703 [00:00<00:00, 4735.19it/s] word -> phonemes: 94%|█████████▍| 2541/2703 [00:00<00:00, 4517.56it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4683.17it/s] dev: 0%| | 0/2703 [00:00