/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") 2023-10-10 20:15:53 | 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') 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 mert_95M_4196_encode {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_95M_4196_encode overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 8%|▊ | 290/3515 [00:00<00:01, 2886.91it/s] word -> phonemes: 16%|█▋ | 579/3515 [00:00<00:01, 2677.38it/s] word -> phonemes: 25%|██▌ | 891/3515 [00:00<00:00, 2862.69it/s] word -> phonemes: 34%|███▎ | 1179/3515 [00:00<00:00, 2824.68it/s] word -> phonemes: 43%|████▎ | 1498/3515 [00:00<00:00, 2951.43it/s] word -> phonemes: 51%|█████ | 1794/3515 [00:00<00:00, 2906.77it/s] word -> phonemes: 60%|█████▉ | 2096/3515 [00:00<00:00, 2937.42it/s] word -> phonemes: 68%|██████▊ | 2391/3515 [00:00<00:00, 2815.05it/s] word -> phonemes: 77%|███████▋ | 2699/3515 [00:00<00:00, 2885.01it/s] word -> phonemes: 85%|████████▌ | 2989/3515 [00:01<00:00, 2718.22it/s] word -> phonemes: 93%|█████████▎| 3286/3515 [00:01<00:00, 2788.22it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2826.63it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 277/2703 [00:00<00:00, 2650.76it/s] word -> phonemes: 20%|██ | 543/2703 [00:00<00:00, 2589.80it/s] word -> phonemes: 32%|███▏ | 857/2703 [00:00<00:00, 2816.07it/s] word -> phonemes: 43%|████▎ | 1168/2703 [00:00<00:00, 2835.61it/s] word -> phonemes: 55%|█████▌ | 1499/2703 [00:00<00:00, 2999.33it/s] word -> phonemes: 68%|██████▊ | 1849/2703 [00:00<00:00, 3164.36it/s] word -> phonemes: 81%|████████ | 2191/2703 [00:00<00:00, 3233.95it/s] word -> phonemes: 93%|█████████▎| 2515/2703 [00:00<00:00, 2936.42it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2901.85it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 350/2703 [00:00<00:00, 3492.14it/s] word -> phonemes: 26%|██▌ | 700/2703 [00:00<00:00, 3023.85it/s] word -> phonemes: 39%|███▉ | 1061/2703 [00:00<00:00, 3268.57it/s] word -> phonemes: 52%|█████▏ | 1393/2703 [00:00<00:00, 3232.27it/s] word -> phonemes: 64%|██████▍ | 1741/2703 [00:00<00:00, 3315.64it/s] word -> phonemes: 77%|███████▋ | 2075/2703 [00:00<00:00, 3159.57it/s] word -> phonemes: 90%|████████▉ | 2425/2703 [00:00<00:00, 3244.38it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3174.40it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▊ | 234/2703 [00:00<00:01, 2248.16it/s] word -> phonemes: 18%|█▊ | 481/2703 [00:00<00:00, 2346.66it/s] word -> phonemes: 30%|███ | 812/2703 [00:00<00:00, 2776.33it/s] word -> phonemes: 42%|████▏ | 1127/2703 [00:00<00:00, 2922.18it/s] word -> phonemes: 53%|█████▎ | 1420/2703 [00:00<00:00, 2806.14it/s] word -> phonemes: 64%|██████▎ | 1717/2703 [00:00<00:00, 2859.28it/s] word -> phonemes: 74%|███████▍ | 2004/2703 [00:00<00:00, 2791.97it/s] word -> phonemes: 84%|████████▍ | 2284/2703 [00:00<00:00, 2681.57it/s] word -> phonemes: 94%|█████████▍| 2554/2703 [00:00<00:00, 2661.99it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2708.60it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 9%|▊ | 301/3515 [00:00<00:01, 3002.68it/s] word -> phonemes: 17%|█▋ | 602/3515 [00:00<00:00, 2991.91it/s] word -> phonemes: 26%|██▌ | 916/3515 [00:00<00:00, 3057.50it/s] word -> phonemes: 35%|███▌ | 1232/3515 [00:00<00:00, 3097.11it/s] word -> phonemes: 45%|████▍ | 1570/3515 [00:00<00:00, 3195.77it/s] word -> phonemes: 54%|█████▍ | 1890/3515 [00:00<00:00, 3183.48it/s] word -> phonemes: 63%|██████▎ | 2222/3515 [00:00<00:00, 3227.44it/s] word -> phonemes: 72%|███████▏ | 2545/3515 [00:00<00:00, 3095.38it/s] word -> phonemes: 81%|████████▏ | 2856/3515 [00:00<00:00, 2883.48it/s] word -> phonemes: 90%|████████▉ | 3148/3515 [00:01<00:00, 2664.47it/s] word -> phonemes: 97%|█████████▋| 3419/3515 [00:01<00:00, 2532.55it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2848.47it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 273/2703 [00:00<00:00, 2715.98it/s] word -> phonemes: 21%|██▏ | 575/2703 [00:00<00:00, 2892.01it/s] word -> phonemes: 32%|███▏ | 865/2703 [00:00<00:00, 2801.11it/s] word -> phonemes: 42%|████▏ | 1146/2703 [00:00<00:00, 2659.50it/s] word -> phonemes: 54%|█████▎ | 1450/2703 [00:00<00:00, 2788.09it/s] word -> phonemes: 64%|██████▍ | 1731/2703 [00:00<00:00, 2680.36it/s] word -> phonemes: 74%|███████▍ | 2001/2703 [00:00<00:00, 2654.23it/s] word -> phonemes: 84%|████████▍ | 2268/2703 [00:00<00:00, 2624.11it/s] word -> phonemes: 97%|█████████▋| 2611/2703 [00:00<00:00, 2863.43it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2782.51it/s] dev: 0%| | 0/2703 [00:00