/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") 2023-10-08 15:28:31 | 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-v1-330M 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-v1-330M 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] - Take a list of 25 features and weighted sum them. [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: 5%|▍ | 172/3515 [00:00<00:01, 1713.43it/s] word -> phonemes: 10%|▉ | 344/3515 [00:00<00:02, 1346.26it/s] word -> phonemes: 14%|█▍ | 484/3515 [00:00<00:02, 1335.21it/s] word -> phonemes: 18%|█▊ | 621/3515 [00:00<00:02, 1229.21it/s] word -> phonemes: 22%|██▏ | 759/3515 [00:00<00:02, 1274.75it/s] word -> phonemes: 25%|██▌ | 891/3515 [00:00<00:02, 1285.98it/s] word -> phonemes: 29%|██▉ | 1027/3515 [00:00<00:01, 1307.95it/s] word -> phonemes: 33%|███▎ | 1159/3515 [00:00<00:01, 1240.44it/s] word -> phonemes: 37%|███▋ | 1312/3515 [00:01<00:01, 1323.83it/s] word -> phonemes: 41%|████ | 1446/3515 [00:01<00:01, 1207.69it/s] word -> phonemes: 46%|████▌ | 1624/3515 [00:01<00:01, 1364.56it/s] word -> phonemes: 51%|█████ | 1782/3515 [00:01<00:01, 1410.21it/s] word -> phonemes: 55%|█████▍ | 1926/3515 [00:01<00:01, 1414.73it/s] word -> phonemes: 59%|█████▉ | 2070/3515 [00:01<00:01, 1375.77it/s] word -> phonemes: 63%|██████▎ | 2218/3515 [00:01<00:00, 1403.22it/s] word -> phonemes: 67%|██████▋ | 2360/3515 [00:01<00:00, 1242.06it/s] word -> phonemes: 71%|███████ | 2490/3515 [00:01<00:00, 1256.25it/s] word -> phonemes: 75%|███████▍ | 2628/3515 [00:02<00:00, 1263.63it/s] word -> phonemes: 78%|███████▊ | 2757/3515 [00:02<00:00, 1243.12it/s] word -> phonemes: 83%|████████▎ | 2917/3515 [00:02<00:00, 1334.60it/s] word -> phonemes: 87%|████████▋ | 3067/3515 [00:02<00:00, 1381.34it/s] word -> phonemes: 91%|█████████ | 3207/3515 [00:02<00:00, 1349.31it/s] word -> phonemes: 96%|█████████▌| 3381/3515 [00:02<00:00, 1461.15it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:02<00:00, 1346.39it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 5%|▌ | 136/2703 [00:00<00:01, 1359.46it/s] word -> phonemes: 11%|█ | 287/2703 [00:00<00:01, 1444.87it/s] word -> phonemes: 16%|█▌ | 432/2703 [00:00<00:01, 1354.80it/s] word -> phonemes: 22%|██▏ | 584/2703 [00:00<00:01, 1409.25it/s] word -> phonemes: 27%|██▋ | 726/2703 [00:00<00:01, 1368.83it/s] word -> phonemes: 32%|███▏ | 864/2703 [00:00<00:01, 1298.41it/s] word -> phonemes: 38%|███▊ | 1018/2703 [00:00<00:01, 1357.54it/s] word -> phonemes: 43%|████▎ | 1175/2703 [00:00<00:01, 1417.51it/s] word -> phonemes: 49%|████▉ | 1318/2703 [00:00<00:01, 1312.91it/s] word -> phonemes: 54%|█████▎ | 1452/2703 [00:01<00:00, 1261.81it/s] word -> phonemes: 59%|█████▉ | 1602/2703 [00:01<00:00, 1303.42it/s] word -> phonemes: 65%|██████▍ | 1753/2703 [00:01<00:00, 1361.40it/s] word -> phonemes: 70%|██████▉ | 1891/2703 [00:01<00:00, 1287.25it/s] word -> phonemes: 75%|███████▍ | 2022/2703 [00:01<00:00, 1279.33it/s] word -> phonemes: 80%|███████▉ | 2151/2703 [00:01<00:00, 1189.32it/s] word -> phonemes: 85%|████████▍ | 2295/2703 [00:01<00:00, 1256.56it/s] word -> phonemes: 90%|████████▉ | 2423/2703 [00:01<00:00, 1229.52it/s] word -> phonemes: 94%|█████████▍| 2550/2703 [00:01<00:00, 1227.48it/s] word -> phonemes: 100%|█████████▉| 2701/2703 [00:02<00:00, 1307.31it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:02<00:00, 1307.43it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 4%|▍ | 110/2703 [00:00<00:02, 1099.47it/s] word -> phonemes: 10%|▉ | 267/2703 [00:00<00:01, 1375.70it/s] word -> phonemes: 15%|█▍ | 405/2703 [00:00<00:01, 1334.92it/s] word -> phonemes: 20%|█▉ | 539/2703 [00:00<00:01, 1209.83it/s] word -> phonemes: 26%|██▌ | 693/2703 [00:00<00:01, 1318.75it/s] word -> phonemes: 31%|███ | 827/2703 [00:00<00:01, 1295.92it/s] word -> phonemes: 35%|███▌ | 958/2703 [00:00<00:01, 1242.74it/s] word -> phonemes: 41%|████ | 1100/2703 [00:00<00:01, 1288.89it/s] word -> phonemes: 46%|████▌ | 1230/2703 [00:00<00:01, 1256.30it/s] word -> phonemes: 51%|█████ | 1380/2703 [00:01<00:00, 1326.71it/s] word -> phonemes: 58%|█████▊ | 1574/2703 [00:01<00:00, 1505.84it/s] word -> phonemes: 64%|██████▍ | 1726/2703 [00:01<00:00, 1481.27it/s] word -> phonemes: 69%|██████▉ | 1876/2703 [00:01<00:00, 1482.50it/s] word -> phonemes: 76%|███████▌ | 2060/2703 [00:01<00:00, 1585.90it/s] word -> phonemes: 83%|████████▎ | 2232/2703 [00:01<00:00, 1624.37it/s] word -> phonemes: 89%|████████▊ | 2395/2703 [00:01<00:00, 1554.05it/s] word -> phonemes: 95%|█████████▌| 2571/2703 [00:01<00:00, 1583.04it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1430.04it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 5%|▌ | 138/2703 [00:00<00:01, 1379.74it/s] word -> phonemes: 10%|█ | 276/2703 [00:00<00:01, 1331.72it/s] word -> phonemes: 15%|█▌ | 410/2703 [00:00<00:01, 1309.64it/s] word -> phonemes: 20%|██ | 549/2703 [00:00<00:01, 1336.67it/s] word -> phonemes: 27%|██▋ | 729/2703 [00:00<00:01, 1498.86it/s] word -> phonemes: 33%|███▎ | 880/2703 [00:00<00:01, 1267.11it/s] word -> phonemes: 37%|███▋ | 1013/2703 [00:00<00:01, 1269.07it/s] word -> phonemes: 42%|████▏ | 1144/2703 [00:00<00:01, 1249.21it/s] word -> phonemes: 47%|████▋ | 1276/2703 [00:00<00:01, 1267.35it/s] word -> phonemes: 53%|█████▎ | 1434/2703 [00:01<00:00, 1351.56it/s] word -> phonemes: 59%|█████▉ | 1607/2703 [00:01<00:00, 1461.69it/s] word -> phonemes: 66%|██████▌ | 1784/2703 [00:01<00:00, 1550.96it/s] word -> phonemes: 72%|███████▏ | 1941/2703 [00:01<00:00, 1499.44it/s] word -> phonemes: 77%|███████▋ | 2093/2703 [00:01<00:00, 1499.31it/s] word -> phonemes: 83%|████████▎ | 2244/2703 [00:01<00:00, 1401.08it/s] word -> phonemes: 88%|████████▊ | 2386/2703 [00:01<00:00, 1358.02it/s] word -> phonemes: 93%|█████████▎| 2524/2703 [00:01<00:00, 1359.34it/s] word -> phonemes: 99%|█████████▉| 2687/2703 [00:01<00:00, 1423.94it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1377.80it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 4%|▍ | 138/3515 [00:00<00:02, 1375.07it/s] word -> phonemes: 8%|▊ | 284/3515 [00:00<00:02, 1422.84it/s] word -> phonemes: 12%|█▏ | 430/3515 [00:00<00:02, 1434.68it/s] word -> phonemes: 16%|█▋ | 574/3515 [00:00<00:02, 1370.13it/s] word -> phonemes: 21%|██ | 731/3515 [00:00<00:01, 1438.66it/s] word -> phonemes: 25%|██▍ | 876/3515 [00:00<00:01, 1327.20it/s] word -> phonemes: 29%|██▉ | 1032/3515 [00:00<00:01, 1396.99it/s] word -> phonemes: 34%|███▎ | 1180/3515 [00:00<00:01, 1421.84it/s] word -> phonemes: 38%|███▊ | 1336/3515 [00:00<00:01, 1457.45it/s] word -> phonemes: 42%|████▏ | 1483/3515 [00:01<00:01, 1387.70it/s] word -> phonemes: 47%|████▋ | 1636/3515 [00:01<00:01, 1428.14it/s] word -> phonemes: 51%|█████ | 1780/3515 [00:01<00:01, 1390.96it/s] word -> phonemes: 56%|█████▌ | 1954/3515 [00:01<00:01, 1491.29it/s] word -> phonemes: 60%|█████▉ | 2105/3515 [00:01<00:01, 1339.36it/s] word -> phonemes: 64%|██████▍ | 2257/3515 [00:01<00:00, 1387.77it/s] word -> phonemes: 68%|██████▊ | 2399/3515 [00:01<00:00, 1238.62it/s] word -> phonemes: 72%|███████▏ | 2535/3515 [00:01<00:00, 1257.03it/s] word -> phonemes: 76%|███████▌ | 2665/3515 [00:01<00:00, 1230.09it/s] word -> phonemes: 80%|████████ | 2817/3515 [00:02<00:00, 1306.97it/s] word -> phonemes: 84%|████████▍ | 2951/3515 [00:02<00:00, 1276.13it/s] word -> phonemes: 88%|████████▊ | 3096/3515 [00:02<00:00, 1305.93it/s] word -> phonemes: 92%|█████████▏| 3235/3515 [00:02<00:00, 1307.49it/s] word -> phonemes: 96%|█████████▌| 3367/3515 [00:02<00:00, 1264.12it/s] word -> phonemes: 99%|█████████▉| 3495/3515 [00:02<00:00, 1198.52it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:02<00:00, 1327.70it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 7%|▋ | 185/2703 [00:00<00:01, 1712.61it/s] word -> phonemes: 13%|█▎ | 357/2703 [00:00<00:01, 1665.38it/s] word -> phonemes: 19%|█▉ | 524/2703 [00:00<00:01, 1432.17it/s] word -> phonemes: 25%|██▍ | 671/2703 [00:00<00:01, 1411.50it/s] word -> phonemes: 30%|███ | 814/2703 [00:00<00:01, 1316.09it/s] word -> phonemes: 35%|███▌ | 950/2703 [00:00<00:01, 1328.95it/s] word -> phonemes: 40%|████ | 1089/2703 [00:00<00:01, 1346.85it/s] word -> phonemes: 47%|████▋ | 1283/2703 [00:00<00:00, 1524.26it/s] word -> phonemes: 53%|█████▎ | 1437/2703 [00:00<00:00, 1516.27it/s] word -> phonemes: 59%|█████▉ | 1590/2703 [00:01<00:00, 1493.46it/s] word -> phonemes: 64%|██████▍ | 1741/2703 [00:01<00:00, 1388.23it/s] word -> phonemes: 71%|███████▏ | 1927/2703 [00:01<00:00, 1519.43it/s] word -> phonemes: 77%|███████▋ | 2082/2703 [00:01<00:00, 1523.46it/s] word -> phonemes: 83%|████████▎ | 2236/2703 [00:01<00:00, 1441.18it/s] word -> phonemes: 88%|████████▊ | 2382/2703 [00:01<00:00, 1236.27it/s] word -> phonemes: 93%|█████████▎| 2514/2703 [00:01<00:00, 1255.87it/s] word -> phonemes: 99%|█████████▉| 2677/2703 [00:01<00:00, 1354.22it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1412.42it/s] dev: 0%| | 0/2703 [00:00