tensor([[-0.0185,  0.0170,  0.1999, -0.0860],
        [ 0.4003,  1.7137,  1.3981,  1.0497],
        [-0.1103, -0.1609,  0.0079, -0.2416],
        [ 0.0668,  0.3534,  0.2322,  0.1008],
        [ 0.1180,  0.6949,  0.3157,  0.2807],
        [-0.1827, -0.2060, -0.2393, -0.3167]], grad_fn=<CatBackward0>)
context_vecs.shape: torch.Size([6, 4])