[Runner] - Start a new experiment 2023-08-11 02:23:47 | INFO | s3prl.upstream.hubert.hubconf | Converting a fairseq checkpoint: /home/victor/checkpoints/hubert_d2v2_800k.pt 2023-08-11 02:23:47 | INFO | s3prl.upstream.hubert.hubconf | To: /home/victor/checkpoints/hubert_d2v2_800k.converted.pt 2023-08-11 02:23:47 | INFO | fairseq.models.hubert.hubert | HubertModel Config: HubertConfig(_name='hubert', label_rate=50.0, extractor_mode='default', encoder_layers=12, encoder_embed_dim=768, encoder_ffn_embed_dim=3072, encoder_attention_heads=12, activation_fn='gelu', layer_type='transformer', dropout=0.1, attention_dropout=0.1, activation_dropout=0.0, encoder_layerdrop=0.05, dropout_input=0.1, dropout_features=0.1, final_dim=256, untie_final_proj=True, layer_norm_first=False, conv_feature_layers='[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 3', conv_bias=False, logit_temp=0.1, target_glu=False, feature_grad_mult=0.1, mask_length=10, mask_prob=0.8, mask_selection='static', mask_other=0.0, no_mask_overlap=False, mask_min_space=1, mask_channel_length=10, mask_channel_prob=0.0, mask_channel_selection='static', mask_channel_other=0.0, no_mask_channel_overlap=False, mask_channel_min_space=1, conv_pos=128, conv_pos_groups=16, latent_temp=[2.0, 0.5, 0.999995], skip_masked=False, skip_nomask=False, checkpoint_activations=False, required_seq_len_multiple=2, depthwise_conv_kernel_size=31, attn_type='', pos_enc_type='abs', fp16=False) [Featurizer] - Take a list of 13 features and weighted sum them. [(512, 10, 5), (512, 3, 2), (512, 3, 2), (512, 3, 2), (512, 3, 2), (512, 2, 2), (512, 2, 2), (512, 2, 2)] 640 [Featurizer] - The selected feature hidden_states's downsample rate is 640 overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 6%|▌ | 207/3515 [00:00<00:01, 2068.32it/s] word -> phonemes: 12%|█▏ | 414/3515 [00:00<00:01, 1844.85it/s] word -> phonemes: 17%|█▋ | 601/3515 [00:00<00:01, 1848.77it/s] word -> phonemes: 22%|██▏ | 787/3515 [00:00<00:01, 1850.64it/s] word -> phonemes: 28%|██▊ | 987/3515 [00:00<00:01, 1901.15it/s] word -> phonemes: 34%|███▍ | 1190/3515 [00:00<00:01, 1940.68it/s] word -> phonemes: 41%|████▏ | 1455/3515 [00:00<00:00, 2167.66it/s] word -> phonemes: 48%|████▊ | 1673/3515 [00:00<00:00, 2092.24it/s] word -> phonemes: 54%|█████▎ | 1887/3515 [00:00<00:00, 2105.99it/s] word -> phonemes: 62%|██████▏ | 2192/3515 [00:01<00:00, 2388.84it/s] word -> phonemes: 70%|███████ | 2469/3515 [00:01<00:00, 2503.08it/s] word -> phonemes: 79%|███████▊ | 2766/3515 [00:01<00:00, 2642.42it/s] word -> phonemes: 86%|████████▋ | 3032/3515 [00:01<00:00, 2616.96it/s] word -> phonemes: 94%|█████████▎| 3295/3515 [00:01<00:00, 2295.34it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2209.41it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 335/2703 [00:00<00:00, 3340.13it/s] word -> phonemes: 25%|██▍ | 670/2703 [00:00<00:00, 3147.07it/s] word -> phonemes: 37%|███▋ | 1004/2703 [00:00<00:00, 3228.01it/s] word -> phonemes: 49%|████▉ | 1336/2703 [00:00<00:00, 3262.68it/s] word -> phonemes: 62%|██████▏ | 1663/2703 [00:00<00:00, 3101.60it/s] word -> phonemes: 74%|███████▎ | 1993/2703 [00:00<00:00, 3166.07it/s] word -> phonemes: 86%|████████▌ | 2323/2703 [00:00<00:00, 3208.05it/s] word -> phonemes: 98%|█████████▊| 2645/2703 [00:00<00:00, 3189.01it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3188.09it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 311/2703 [00:00<00:00, 3102.41it/s] word -> phonemes: 23%|██▎ | 622/2703 [00:00<00:00, 3070.26it/s] word -> phonemes: 35%|███▌ | 955/2703 [00:00<00:00, 3187.45it/s] word -> phonemes: 47%|████▋ | 1274/2703 [00:00<00:00, 3084.10it/s] word -> phonemes: 60%|█████▉ | 1611/2703 [00:00<00:00, 3184.29it/s] word -> phonemes: 72%|███████▏ | 1933/2703 [00:00<00:00, 3194.30it/s] word -> phonemes: 83%|████████▎ | 2253/2703 [00:00<00:00, 3177.78it/s] word -> phonemes: 95%|█████████▌| 2577/2703 [00:00<00:00, 3195.43it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3164.36it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 343/2703 [00:00<00:00, 3428.59it/s] word -> phonemes: 25%|██▌ | 686/2703 [00:00<00:00, 3398.60it/s] word -> phonemes: 38%|███▊ | 1026/2703 [00:00<00:00, 3349.35it/s] word -> phonemes: 50%|█████ | 1362/2703 [00:00<00:00, 3216.34it/s] word -> phonemes: 62%|██████▏ | 1685/2703 [00:00<00:00, 3217.48it/s] word -> phonemes: 74%|███████▍ | 2008/2703 [00:00<00:00, 3174.40it/s] word -> phonemes: 87%|████████▋ | 2344/2703 [00:00<00:00, 3232.81it/s] word -> phonemes: 99%|█████████▉| 2671/2703 [00:00<00:00, 3243.48it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3218.45it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 8%|▊ | 277/3515 [00:00<00:01, 2768.26it/s] word -> phonemes: 16%|█▌ | 569/3515 [00:00<00:01, 2855.45it/s] word -> phonemes: 25%|██▍ | 875/3515 [00:00<00:00, 2946.19it/s] word -> phonemes: 33%|███▎ | 1170/3515 [00:00<00:00, 2917.59it/s] word -> phonemes: 42%|████▏ | 1477/3515 [00:00<00:00, 2968.79it/s] word -> phonemes: 50%|█████ | 1774/3515 [00:00<00:00, 2968.14it/s] word -> phonemes: 59%|█████▉ | 2071/3515 [00:00<00:00, 2883.01it/s] word -> phonemes: 67%|██████▋ | 2360/3515 [00:00<00:00, 2424.38it/s] word -> phonemes: 74%|███████▍ | 2614/3515 [00:01<00:00, 2272.60it/s] word -> phonemes: 81%|████████ | 2850/3515 [00:01<00:00, 2151.22it/s] word -> phonemes: 87%|████████▋ | 3072/3515 [00:01<00:00, 2055.89it/s] word -> phonemes: 93%|█████████▎| 3282/3515 [00:01<00:00, 2006.32it/s] word -> phonemes: 99%|█████████▉| 3486/3515 [00:01<00:00, 1923.66it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2343.62it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 345/2703 [00:00<00:00, 3440.24it/s] word -> phonemes: 26%|██▌ | 690/2703 [00:00<00:00, 3380.02it/s] word -> phonemes: 38%|███▊ | 1029/2703 [00:00<00:00, 3326.10it/s] word -> phonemes: 50%|█████ | 1362/2703 [00:00<00:00, 3318.06it/s] word -> phonemes: 63%|██████▎ | 1696/2703 [00:00<00:00, 3323.21it/s] word -> phonemes: 75%|███████▌ | 2029/2703 [00:00<00:00, 3234.59it/s] word -> phonemes: 87%|████████▋ | 2364/2703 [00:00<00:00, 3271.16it/s] word -> phonemes: 100%|█████████▉| 2692/2703 [00:00<00:00, 3191.92it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3257.60it/s] dev: 0%| | 0/2703 [00:00