[Runner] - Start a new experiment 2023-08-10 22:33:01 | INFO | s3prl.upstream.hubert.hubconf | Converting a fairseq checkpoint: /home/victor/checkpoints/hubert_d2v2_800k.pt 2023-08-10 22:33:01 | INFO | s3prl.upstream.hubert.hubconf | To: /home/victor/checkpoints/hubert_d2v2_800k.converted.pt 2023-08-10 22:33:01 | 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