{ "mode": "dense", "variant": "pilot_residual_mlp_d256", "transition": "residual", "decoder_type": "mlp", "args": { "variant_name": "pilot_residual_mlp_d256", "mode": "dense", "supervision": "teacher_belief", "seed": 53, "modulus": 11, "observe_mod": 4, "observe_prob": 0.3, "op_family": "full", "query_family": "all", "train_min_len": 1, "train_max_len": 6, "eval_lengths": "3,6,9,12", "eval_k": "0,1,2,3,6,9,12", "eval_query_types": "all", "state_dim": 256, "instr_dim": 128, "transition": "residual", "decoder_type": "mlp", "decoder_rank": 16, "heads": 4, "compiler_layers": 2, "dropout": 0.0, "train_steps": 800, "batch_size": 256, "eval_batch_size": 256, "eval_examples": 256, "lr": 0.001, "weight_decay": 0.0001, "query_loss_weight": 0.0, "belief_loss_weight": 1.0, "decoder_query_loss_weight": 0.0, "belief_distill_prob": 1.0, "probe_steps": 400, "probe_batch_size": 256, "probe_lr": 0.001, "probe_weight_decay": 0.0001, "probe_dropout": 0.0, "max_grad_norm": 1.0, "log_every": 100, "probe_log_every": 100, "output_dir": "experiments/dense_teacher_distillation/runs/pilot_residual_mlp_d256", "checkpoint_dir": "large_artifacts/dense_teacher_distillation/checkpoints/pilot_residual_mlp_d256" }, "env": { "python": "3.12.3", "torch": "2.8.0+cu128", "device": "cuda", "cuda_name": "NVIDIA RTX 6000 Ada Generation" }, "train": [ { "step": 1, "loss": 4.8134331703186035, "grad_norm": 0.39247697591781616, "query_loss": 0.0, "belief_loss": 4.8134331703186035, "decoder_query_loss": 0.0, "query_target_mass": 0.4250399172306061, "query_target_nll": 2.4017109870910645, "query_top1_on_support": 0.44140625, "mean_query_support_size": 4.65625, "decoder_belief_target_mass": 0.05102561414241791, "decoder_belief_target_nll": 4.665122032165527, "decoder_belief_top1_on_support": 0.109375, "mean_decoder_belief_support_size": 5.6953125, "decoder_query_target_mass": 0.42693769931793213, "decoder_query_target_nll": 2.3752942085266113, "decoder_query_top1_on_support": 0.51953125, "mean_decoder_query_support_size": 4.65625 }, { "step": 100, "loss": 3.3411190509796143, "grad_norm": 0.3460848927497864, "query_loss": 0.0, "belief_loss": 3.3411190509796143, "decoder_query_loss": 0.0, "query_target_mass": 0.42870986461639404, "query_target_nll": 2.423711061477661, "query_top1_on_support": 0.421875, "mean_query_support_size": 4.73046875, "decoder_belief_target_mass": 0.22560833394527435, "decoder_belief_target_nll": 3.8220157623291016, "decoder_belief_top1_on_support": 0.27734375, "mean_decoder_belief_support_size": 5.9453125, "decoder_query_target_mass": 0.5657342076301575, "decoder_query_target_nll": 2.0647435188293457, "decoder_query_top1_on_support": 0.63671875, "mean_decoder_query_support_size": 4.73046875 }, { "step": 200, "loss": 2.991176128387451, "grad_norm": 0.4864928424358368, "query_loss": 0.0, "belief_loss": 2.991176128387451, "decoder_query_loss": 0.0, "query_target_mass": 0.47393783926963806, "query_target_nll": 2.4106574058532715, "query_top1_on_support": 0.47265625, "mean_query_support_size": 5.20703125, "decoder_belief_target_mass": 0.3225463330745697, "decoder_belief_target_nll": 3.2551770210266113, "decoder_belief_top1_on_support": 0.40625, "mean_decoder_belief_support_size": 5.75390625, "decoder_query_target_mass": 0.66986083984375, "decoder_query_target_nll": 1.9392848014831543, "decoder_query_top1_on_support": 0.7421875, "mean_decoder_query_support_size": 5.20703125 }, { "step": 300, "loss": 2.478471040725708, "grad_norm": 0.6540323495864868, "query_loss": 0.0, "belief_loss": 2.478471040725708, "decoder_query_loss": 0.0, "query_target_mass": 0.44867223501205444, "query_target_nll": 2.42356014251709, "query_top1_on_support": 0.4296875, "mean_query_support_size": 4.94921875, "decoder_belief_target_mass": 0.5387719869613647, "decoder_belief_target_nll": 2.6003222465515137, "decoder_belief_top1_on_support": 0.6640625, "mean_decoder_belief_support_size": 5.81640625, "decoder_query_target_mass": 0.7663012146949768, "decoder_query_target_nll": 1.661423683166504, "decoder_query_top1_on_support": 0.83984375, "mean_decoder_query_support_size": 4.94921875 }, { "step": 400, "loss": 2.2790703773498535, "grad_norm": 0.5292051434516907, "query_loss": 0.0, "belief_loss": 2.2790703773498535, "decoder_query_loss": 0.0, "query_target_mass": 0.429808646440506, "query_target_nll": 2.4127538204193115, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.734375, "decoder_belief_target_mass": 0.6318562626838684, "decoder_belief_target_nll": 2.338371992111206, "decoder_belief_top1_on_support": 0.74609375, "mean_decoder_belief_support_size": 5.515625, "decoder_query_target_mass": 0.8041597604751587, "decoder_query_target_nll": 1.5466084480285645, "decoder_query_top1_on_support": 0.84765625, "mean_decoder_query_support_size": 4.734375 }, { "step": 500, "loss": 2.1762397289276123, "grad_norm": 0.47107237577438354, "query_loss": 0.0, "belief_loss": 2.1762397289276123, "decoder_query_loss": 0.0, "query_target_mass": 0.43121081590652466, "query_target_nll": 2.4130992889404297, "query_top1_on_support": 0.41796875, "mean_query_support_size": 4.73828125, "decoder_belief_target_mass": 0.6868423819541931, "decoder_belief_target_nll": 2.1604361534118652, "decoder_belief_top1_on_support": 0.796875, "mean_decoder_belief_support_size": 5.671875, "decoder_query_target_mass": 0.850180983543396, "decoder_query_target_nll": 1.4354162216186523, "decoder_query_top1_on_support": 0.91015625, "mean_decoder_query_support_size": 4.73828125 }, { "step": 600, "loss": 2.159940719604492, "grad_norm": 0.3697603940963745, "query_loss": 0.0, "belief_loss": 2.159940719604492, "decoder_query_loss": 0.0, "query_target_mass": 0.4422745406627655, "query_target_nll": 2.407832384109497, "query_top1_on_support": 0.44921875, "mean_query_support_size": 4.85546875, "decoder_belief_target_mass": 0.7414703369140625, "decoder_belief_target_nll": 2.080458641052246, "decoder_belief_top1_on_support": 0.86328125, "mean_decoder_belief_support_size": 6.046875, "decoder_query_target_mass": 0.8866012096405029, "decoder_query_target_nll": 1.3750454187393188, "decoder_query_top1_on_support": 0.94140625, "mean_decoder_query_support_size": 4.85546875 }, { "step": 700, "loss": 2.1328907012939453, "grad_norm": 0.4287487268447876, "query_loss": 0.0, "belief_loss": 2.1328907012939453, "decoder_query_loss": 0.0, "query_target_mass": 0.46159350872039795, "query_target_nll": 2.4096226692199707, "query_top1_on_support": 0.49609375, "mean_query_support_size": 5.0625, "decoder_belief_target_mass": 0.7651711106300354, "decoder_belief_target_nll": 1.991736650466919, "decoder_belief_top1_on_support": 0.859375, "mean_decoder_belief_support_size": 5.8671875, "decoder_query_target_mass": 0.8900718688964844, "decoder_query_target_nll": 1.4173674583435059, "decoder_query_top1_on_support": 0.9296875, "mean_decoder_query_support_size": 5.0625 }, { "step": 800, "loss": 2.0254695415496826, "grad_norm": 0.398582398891449, "query_loss": 0.0, "belief_loss": 2.0254695415496826, "decoder_query_loss": 0.0, "query_target_mass": 0.46793073415756226, "query_target_nll": 2.3978915214538574, "query_top1_on_support": 0.48046875, "mean_query_support_size": 5.1171875, "decoder_belief_target_mass": 0.8026813864707947, "decoder_belief_target_nll": 1.9471936225891113, "decoder_belief_top1_on_support": 0.890625, "mean_decoder_belief_support_size": 5.98046875, "decoder_query_target_mass": 0.9109006524085999, "decoder_query_target_nll": 1.4033942222595215, "decoder_query_top1_on_support": 0.9453125, "mean_decoder_query_support_size": 5.1171875 } ], "probe_train": [ { "step": 1, "loss": 4.811487197875977, "grad_norm": 0.4650287926197052, "probe_belief_target_mass": 0.060396336019039154, "probe_belief_target_nll": 4.811487197875977, "probe_belief_top1_on_support": 0.0736607164144516, "mean_belief_support_size": 7.3058037757873535 }, { "step": 100, "loss": 2.2776858806610107, "grad_norm": 0.34436213970184326, "probe_belief_target_mass": 0.7774102687835693, "probe_belief_target_nll": 2.2776858806610107, "probe_belief_top1_on_support": 0.863839328289032, "mean_belief_support_size": 7.245535850524902 }, { "step": 200, "loss": 2.1482503414154053, "grad_norm": 0.31964704394340515, "probe_belief_target_mass": 0.8419898748397827, "probe_belief_target_nll": 2.1482503414154053, "probe_belief_top1_on_support": 0.9123884439468384, "mean_belief_support_size": 7.470424652099609 }, { "step": 300, "loss": 2.0249876976013184, "grad_norm": 0.3169151842594147, "probe_belief_target_mass": 0.882841169834137, "probe_belief_target_nll": 2.0249876976013184, "probe_belief_top1_on_support": 0.9453125596046448, "mean_belief_support_size": 7.313058376312256 }, { "step": 400, "loss": 2.0488297939300537, "grad_norm": 0.4490543603897095, "probe_belief_target_mass": 0.8594762682914734, "probe_belief_target_nll": 2.0488297939300537, "probe_belief_top1_on_support": 0.9084821939468384, "mean_belief_support_size": 7.136160850524902 } ], "eval": [ { "step": 800, "rows": [ { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.47061049938201904, "query_target_nll": 2.421949863433838, "query_top1_on_support": 0.44921875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.06349872052669525, "probe_belief_target_nll": 18.46678924560547, "probe_belief_top1_on_support": 0.0703125, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.06292125582695007, "decoder_belief_target_nll": 23.34846305847168, "decoder_belief_top1_on_support": 0.0546875, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.47140592336654663, "decoder_query_target_nll": 2.400887966156006, "decoder_query_top1_on_support": 0.44140625, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.47080209851264954, "query_target_nll": 2.422612190246582, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.12227785587310791, "probe_belief_target_nll": 13.314199447631836, "probe_belief_top1_on_support": 0.12109375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.11915528774261475, "decoder_belief_target_nll": 15.553043365478516, "decoder_belief_top1_on_support": 0.10546875, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.5565239787101746, "decoder_query_target_nll": 4.331748962402344, "decoder_query_top1_on_support": 0.5859375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.4703376889228821, "query_target_nll": 2.423281192779541, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.2518092095851898, "probe_belief_target_nll": 8.289321899414062, "probe_belief_top1_on_support": 0.25, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.2561163306236267, "decoder_belief_target_nll": 9.387136459350586, "decoder_belief_top1_on_support": 0.265625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.70142662525177, "decoder_query_target_nll": 3.37837553024292, "decoder_query_top1_on_support": 0.71875, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.4720696210861206, "query_target_nll": 2.412106513977051, "query_top1_on_support": 0.45703125, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7610410451889038, "probe_belief_target_nll": 2.0451602935791016, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7762807011604309, "decoder_belief_target_nll": 2.023420810699463, "decoder_belief_top1_on_support": 0.859375, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591490030288696, "decoder_query_target_nll": 1.3899049758911133, "decoder_query_top1_on_support": 0.984375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.4720696210861206, "query_target_nll": 2.412106513977051, "query_top1_on_support": 0.45703125, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7610410451889038, "probe_belief_target_nll": 2.0451602935791016, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7762807011604309, "decoder_belief_target_nll": 2.023420810699463, "decoder_belief_top1_on_support": 0.859375, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591490030288696, "decoder_query_target_nll": 1.3899049758911133, "decoder_query_top1_on_support": 0.984375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.4720696210861206, "query_target_nll": 2.412106513977051, "query_top1_on_support": 0.45703125, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7610410451889038, "probe_belief_target_nll": 2.0451602935791016, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7762807011604309, "decoder_belief_target_nll": 2.023420810699463, "decoder_belief_top1_on_support": 0.859375, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591490030288696, "decoder_query_target_nll": 1.3899049758911133, "decoder_query_top1_on_support": 0.984375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.4720696210861206, "query_target_nll": 2.412106513977051, "query_top1_on_support": 0.45703125, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7610410451889038, "probe_belief_target_nll": 2.0451602935791016, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7762807011604309, "decoder_belief_target_nll": 2.023420810699463, "decoder_belief_top1_on_support": 0.859375, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591490030288696, "decoder_query_target_nll": 1.3899049758911133, "decoder_query_top1_on_support": 0.984375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.466585636138916, "query_target_nll": 2.418590784072876, "query_top1_on_support": 0.484375, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.053532060235738754, "probe_belief_target_nll": 18.61171531677246, "probe_belief_top1_on_support": 0.06640625, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.05328281968832016, "decoder_belief_target_nll": 23.477245330810547, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.4670911133289337, "decoder_query_target_nll": 2.4141364097595215, "decoder_query_top1_on_support": 0.48828125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.46602246165275574, "query_target_nll": 2.4231820106506348, "query_top1_on_support": 0.4375, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.13598349690437317, "probe_belief_target_nll": 12.646707534790039, "probe_belief_top1_on_support": 0.1328125, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.13275328278541565, "decoder_belief_target_nll": 14.670604705810547, "decoder_belief_top1_on_support": 0.13671875, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.5366594791412354, "decoder_query_target_nll": 4.53201150894165, "decoder_query_top1_on_support": 0.52734375, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.46569812297821045, "query_target_nll": 2.430530071258545, "query_top1_on_support": 0.43359375, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.27021950483322144, "probe_belief_target_nll": 8.348033905029297, "probe_belief_top1_on_support": 0.2578125, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.26836806535720825, "decoder_belief_target_nll": 9.273866653442383, "decoder_belief_top1_on_support": 0.265625, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.6880897879600525, "decoder_query_target_nll": 3.635714292526245, "decoder_query_top1_on_support": 0.69921875, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.4658002257347107, "query_target_nll": 2.427919387817383, "query_top1_on_support": 0.4453125, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.7904666662216187, "probe_belief_target_nll": 1.9663417339324951, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8104264140129089, "decoder_belief_target_nll": 1.932316780090332, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9584445953369141, "decoder_query_target_nll": 1.3669521808624268, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.4658002257347107, "query_target_nll": 2.427919387817383, "query_top1_on_support": 0.4453125, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.7904666662216187, "probe_belief_target_nll": 1.9663417339324951, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8104264140129089, "decoder_belief_target_nll": 1.932316780090332, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9584445953369141, "decoder_query_target_nll": 1.3669521808624268, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.4658002257347107, "query_target_nll": 2.427919387817383, "query_top1_on_support": 0.4453125, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.7904666662216187, "probe_belief_target_nll": 1.9663417339324951, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8104264140129089, "decoder_belief_target_nll": 1.932316780090332, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9584445953369141, "decoder_query_target_nll": 1.3669521808624268, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.4658002257347107, "query_target_nll": 2.427919387817383, "query_top1_on_support": 0.4453125, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.7904666662216187, "probe_belief_target_nll": 1.9663417339324951, "probe_belief_top1_on_support": 0.859375, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8104264140129089, "decoder_belief_target_nll": 1.932316780090332, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9584445953369141, "decoder_query_target_nll": 1.3669521808624268, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 0, "n": 256, "query_target_mass": 0.48778554797172546, "query_target_nll": 2.4171628952026367, "query_top1_on_support": 0.5234375, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.06544677913188934, "probe_belief_target_nll": 18.037166595458984, "probe_belief_top1_on_support": 0.078125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.06551246345043182, "decoder_belief_target_nll": 22.796350479125977, "decoder_belief_top1_on_support": 0.07421875, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.48801788687705994, "decoder_query_target_nll": 2.404860019683838, "decoder_query_top1_on_support": 0.49609375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 1, "n": 256, "query_target_mass": 0.4882776141166687, "query_target_nll": 2.4212188720703125, "query_top1_on_support": 0.51953125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.15588213503360748, "probe_belief_target_nll": 13.378474235534668, "probe_belief_top1_on_support": 0.15625, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.15466776490211487, "decoder_belief_target_nll": 15.672307968139648, "decoder_belief_top1_on_support": 0.1640625, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.49062037467956543, "decoder_query_target_nll": 5.006906986236572, "decoder_query_top1_on_support": 0.50390625, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 2, "n": 256, "query_target_mass": 0.4885297417640686, "query_target_nll": 2.4173736572265625, "query_top1_on_support": 0.52734375, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.24473020434379578, "probe_belief_target_nll": 9.454981803894043, "probe_belief_top1_on_support": 0.234375, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.2455655038356781, "decoder_belief_target_nll": 10.556427001953125, "decoder_belief_top1_on_support": 0.24609375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.5460927486419678, "decoder_query_target_nll": 4.705493927001953, "decoder_query_top1_on_support": 0.546875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 3, "n": 256, "query_target_mass": 0.48929038643836975, "query_target_nll": 2.4139509201049805, "query_top1_on_support": 0.53515625, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8222470283508301, "probe_belief_target_nll": 1.81166410446167, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8428096771240234, "decoder_belief_target_nll": 1.7768566608428955, "decoder_belief_top1_on_support": 0.9375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9233784079551697, "decoder_query_target_nll": 1.5479832887649536, "decoder_query_top1_on_support": 0.96484375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 6, "n": 256, "query_target_mass": 0.48929038643836975, "query_target_nll": 2.4139509201049805, "query_top1_on_support": 0.53515625, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8222470283508301, "probe_belief_target_nll": 1.81166410446167, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8428096771240234, "decoder_belief_target_nll": 1.7768566608428955, "decoder_belief_top1_on_support": 0.9375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9233784079551697, "decoder_query_target_nll": 1.5479832887649536, "decoder_query_top1_on_support": 0.96484375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 9, "n": 256, "query_target_mass": 0.48929038643836975, "query_target_nll": 2.4139509201049805, "query_top1_on_support": 0.53515625, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8222470283508301, "probe_belief_target_nll": 1.81166410446167, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8428096771240234, "decoder_belief_target_nll": 1.7768566608428955, "decoder_belief_top1_on_support": 0.9375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9233784079551697, "decoder_query_target_nll": 1.5479832887649536, "decoder_query_top1_on_support": 0.96484375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_PLUS_B", "k": 12, "n": 256, "query_target_mass": 0.48929038643836975, "query_target_nll": 2.4139509201049805, "query_top1_on_support": 0.53515625, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8222470283508301, "probe_belief_target_nll": 1.81166410446167, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8428096771240234, "decoder_belief_target_nll": 1.7768566608428955, "decoder_belief_top1_on_support": 0.9375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9233784079551697, "decoder_query_target_nll": 1.5479832887649536, "decoder_query_top1_on_support": 0.96484375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 0, "n": 256, "query_target_mass": 0.4256283640861511, "query_target_nll": 2.4222049713134766, "query_top1_on_support": 0.4296875, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.058006152510643005, "probe_belief_target_nll": 18.154373168945312, "probe_belief_top1_on_support": 0.0546875, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.05843270942568779, "decoder_belief_target_nll": 22.742874145507812, "decoder_belief_top1_on_support": 0.08203125, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.47265625, "decoder_query_target_nll": 16.30625343322754, "decoder_query_top1_on_support": 0.47265625, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 1, "n": 256, "query_target_mass": 0.42466968297958374, "query_target_nll": 2.4253900051116943, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.15780870616436005, "probe_belief_target_nll": 12.502660751342773, "probe_belief_top1_on_support": 0.171875, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.15385262668132782, "decoder_belief_target_nll": 14.61492919921875, "decoder_belief_top1_on_support": 0.11328125, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.528844952583313, "decoder_query_target_nll": 8.899767875671387, "decoder_query_top1_on_support": 0.50390625, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 2, "n": 256, "query_target_mass": 0.4258915185928345, "query_target_nll": 2.4131503105163574, "query_top1_on_support": 0.42578125, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.29308393597602844, "probe_belief_target_nll": 8.116654396057129, "probe_belief_top1_on_support": 0.30859375, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.2887963652610779, "decoder_belief_target_nll": 9.086322784423828, "decoder_belief_top1_on_support": 0.29296875, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.5860241651535034, "decoder_query_target_nll": 5.7317070960998535, "decoder_query_top1_on_support": 0.57421875, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 3, "n": 256, "query_target_mass": 0.4257308840751648, "query_target_nll": 2.411794900894165, "query_top1_on_support": 0.421875, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.7935657501220703, "probe_belief_target_nll": 1.9083234071731567, "probe_belief_top1_on_support": 0.90234375, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8108798265457153, "decoder_belief_target_nll": 1.8693079948425293, "decoder_belief_top1_on_support": 0.90625, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.9519676566123962, "decoder_query_target_nll": 1.187961459159851, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 6, "n": 256, "query_target_mass": 0.4257308840751648, "query_target_nll": 2.411794900894165, "query_top1_on_support": 0.421875, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.7935657501220703, "probe_belief_target_nll": 1.9083234071731567, "probe_belief_top1_on_support": 0.90234375, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8108798265457153, "decoder_belief_target_nll": 1.8693079948425293, "decoder_belief_top1_on_support": 0.90625, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.951967716217041, "decoder_query_target_nll": 1.187961459159851, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 9, "n": 256, "query_target_mass": 0.4257308840751648, "query_target_nll": 2.411794900894165, "query_top1_on_support": 0.421875, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.7935657501220703, "probe_belief_target_nll": 1.9083234071731567, "probe_belief_top1_on_support": 0.90234375, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8108798265457153, "decoder_belief_target_nll": 1.8693079948425293, "decoder_belief_top1_on_support": 0.90625, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.951967716217041, "decoder_query_target_nll": 1.187961459159851, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A_MINUS_B", "k": 12, "n": 256, "query_target_mass": 0.4257308840751648, "query_target_nll": 2.411794900894165, "query_top1_on_support": 0.421875, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.7935657501220703, "probe_belief_target_nll": 1.9083234071731567, "probe_belief_top1_on_support": 0.90234375, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8108798265457153, "decoder_belief_target_nll": 1.8693079948425293, "decoder_belief_top1_on_support": 0.90625, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.951967716217041, "decoder_query_target_nll": 1.187961459159851, "decoder_query_top1_on_support": 0.98828125, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.2532777190208435, "query_target_nll": 2.4119648933410645, "query_top1_on_support": 0.25390625, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.028538847342133522, "probe_belief_target_nll": 18.940135955810547, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.03083837404847145, "decoder_belief_target_nll": 23.862855911254883, "decoder_belief_top1_on_support": 0.0546875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.25366389751434326, "decoder_query_target_nll": 2.397902250289917, "decoder_query_top1_on_support": 0.29296875, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.25352969765663147, "query_target_nll": 2.4146792888641357, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.0713176503777504, "probe_belief_target_nll": 14.621966361999512, "probe_belief_top1_on_support": 0.07421875, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.07035735249519348, "decoder_belief_target_nll": 16.964679718017578, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.28154876828193665, "decoder_query_target_nll": 5.487313270568848, "decoder_query_top1_on_support": 0.27734375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.25306183099746704, "query_target_nll": 2.4161176681518555, "query_top1_on_support": 0.25390625, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.085465207695961, "probe_belief_target_nll": 12.611672401428223, "probe_belief_top1_on_support": 0.078125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.08486250042915344, "decoder_belief_target_nll": 14.30154800415039, "decoder_belief_top1_on_support": 0.0859375, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.34753739833831787, "decoder_query_target_nll": 5.132897853851318, "decoder_query_top1_on_support": 0.3203125, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.25300630927085876, "query_target_nll": 2.411608934402466, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.10856367647647858, "probe_belief_target_nll": 11.444894790649414, "probe_belief_top1_on_support": 0.11328125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.11002512276172638, "decoder_belief_target_nll": 12.677862167358398, "decoder_belief_top1_on_support": 0.1171875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.4104686975479126, "decoder_query_target_nll": 4.931557655334473, "decoder_query_top1_on_support": 0.39453125, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.25606369972229004, "query_target_nll": 2.3925070762634277, "query_top1_on_support": 0.29296875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5372854471206665, "probe_belief_target_nll": 2.037883758544922, "probe_belief_top1_on_support": 0.6953125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5476378202438354, "decoder_belief_target_nll": 2.0116934776306152, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.7385406494140625, "decoder_query_target_nll": 1.2223037481307983, "decoder_query_top1_on_support": 0.80078125, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.25606369972229004, "query_target_nll": 2.3925070762634277, "query_top1_on_support": 0.29296875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5372854471206665, "probe_belief_target_nll": 2.037883758544922, "probe_belief_top1_on_support": 0.6953125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5476378202438354, "decoder_belief_target_nll": 2.0116934776306152, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.7385406494140625, "decoder_query_target_nll": 1.2223037481307983, "decoder_query_top1_on_support": 0.80078125, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.25606369972229004, "query_target_nll": 2.3925070762634277, "query_top1_on_support": 0.29296875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5372854471206665, "probe_belief_target_nll": 2.037883758544922, "probe_belief_top1_on_support": 0.6953125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5476378202438354, "decoder_belief_target_nll": 2.0116934776306152, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.7385406494140625, "decoder_query_target_nll": 1.2223037481307983, "decoder_query_top1_on_support": 0.80078125, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.3106520175933838, "query_target_nll": 2.414126396179199, "query_top1_on_support": 0.3359375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.03468844294548035, "probe_belief_target_nll": 19.585968017578125, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.03474937751889229, "decoder_belief_target_nll": 24.877363204956055, "decoder_belief_top1_on_support": 0.0546875, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.31095027923583984, "decoder_query_target_nll": 2.4017181396484375, "decoder_query_top1_on_support": 0.33203125, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.3108137547969818, "query_target_nll": 2.4088001251220703, "query_top1_on_support": 0.31640625, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.044223710894584656, "probe_belief_target_nll": 16.187320709228516, "probe_belief_top1_on_support": 0.04296875, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.04382854700088501, "decoder_belief_target_nll": 18.961652755737305, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.34161922335624695, "decoder_query_target_nll": 6.0675458908081055, "decoder_query_top1_on_support": 0.33984375, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.3104948103427887, "query_target_nll": 2.40792179107666, "query_top1_on_support": 0.27734375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.07373784482479095, "probe_belief_target_nll": 13.167787551879883, "probe_belief_top1_on_support": 0.0859375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.0710226371884346, "decoder_belief_target_nll": 15.057942390441895, "decoder_belief_top1_on_support": 0.0703125, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.3885459899902344, "decoder_query_target_nll": 5.480961322784424, "decoder_query_top1_on_support": 0.36328125, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.309997022151947, "query_target_nll": 2.4121508598327637, "query_top1_on_support": 0.2890625, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.1016782820224762, "probe_belief_target_nll": 11.48840618133545, "probe_belief_top1_on_support": 0.12109375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.10008521378040314, "decoder_belief_target_nll": 12.863410949707031, "decoder_belief_top1_on_support": 0.10546875, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.4398377537727356, "decoder_query_target_nll": 5.280394554138184, "decoder_query_top1_on_support": 0.453125, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.3091319799423218, "query_target_nll": 2.42512845993042, "query_top1_on_support": 0.2734375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5302584767341614, "probe_belief_target_nll": 2.2576351165771484, "probe_belief_top1_on_support": 0.671875, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.539268970489502, "decoder_belief_target_nll": 2.213139533996582, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7655318975448608, "decoder_query_target_nll": 1.3333899974822998, "decoder_query_top1_on_support": 0.8359375, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.3091319799423218, "query_target_nll": 2.42512845993042, "query_top1_on_support": 0.2734375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5302584767341614, "probe_belief_target_nll": 2.2576351165771484, "probe_belief_top1_on_support": 0.671875, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.539268970489502, "decoder_belief_target_nll": 2.213139533996582, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7655318975448608, "decoder_query_target_nll": 1.3333899974822998, "decoder_query_top1_on_support": 0.8359375, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.3091319799423218, "query_target_nll": 2.42512845993042, "query_top1_on_support": 0.2734375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5302584767341614, "probe_belief_target_nll": 2.2576351165771484, "probe_belief_top1_on_support": 0.671875, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.539268970489502, "decoder_belief_target_nll": 2.213139533996582, "decoder_belief_top1_on_support": 0.66796875, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7655318975448608, "decoder_query_target_nll": 1.3333899974822998, "decoder_query_top1_on_support": 0.8359375, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 0, "n": 256, "query_target_mass": 0.330803781747818, "query_target_nll": 2.41317081451416, "query_top1_on_support": 0.34375, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.032926127314567566, "probe_belief_target_nll": 19.17205810546875, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.03330511599779129, "decoder_belief_target_nll": 24.08324432373047, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.328589528799057, "decoder_query_target_nll": 2.4053092002868652, "decoder_query_top1_on_support": 0.35546875, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 1, "n": 256, "query_target_mass": 0.331953227519989, "query_target_nll": 2.4133849143981934, "query_top1_on_support": 0.3984375, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.05097595229744911, "probe_belief_target_nll": 15.16079330444336, "probe_belief_top1_on_support": 0.0546875, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.05205869302153587, "decoder_belief_target_nll": 17.703174591064453, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.3383503556251526, "decoder_query_target_nll": 4.317008018493652, "decoder_query_top1_on_support": 0.3671875, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 2, "n": 256, "query_target_mass": 0.3308049440383911, "query_target_nll": 2.4135589599609375, "query_top1_on_support": 0.3828125, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.07535520195960999, "probe_belief_target_nll": 12.751383781433105, "probe_belief_top1_on_support": 0.10546875, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.07130339741706848, "decoder_belief_target_nll": 14.4487886428833, "decoder_belief_top1_on_support": 0.07421875, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.33290332555770874, "decoder_query_target_nll": 4.903316020965576, "decoder_query_top1_on_support": 0.3359375, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 3, "n": 256, "query_target_mass": 0.33031630516052246, "query_target_nll": 2.4136581420898438, "query_top1_on_support": 0.34375, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.09929528087377548, "probe_belief_target_nll": 10.833488464355469, "probe_belief_top1_on_support": 0.1015625, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.09891723096370697, "decoder_belief_target_nll": 12.054027557373047, "decoder_belief_top1_on_support": 0.1171875, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.3199068307876587, "decoder_query_target_nll": 4.817712783813477, "decoder_query_top1_on_support": 0.32421875, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 6, "n": 256, "query_target_mass": 0.33056163787841797, "query_target_nll": 2.417269229888916, "query_top1_on_support": 0.40625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5004197955131531, "probe_belief_target_nll": 2.2605841159820557, "probe_belief_top1_on_support": 0.66015625, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5071732997894287, "decoder_belief_target_nll": 2.2274532318115234, "decoder_belief_top1_on_support": 0.640625, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6549732685089111, "decoder_query_target_nll": 1.6050338745117188, "decoder_query_top1_on_support": 0.73828125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 9, "n": 256, "query_target_mass": 0.33056163787841797, "query_target_nll": 2.417269229888916, "query_top1_on_support": 0.40625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5004197955131531, "probe_belief_target_nll": 2.2605841159820557, "probe_belief_top1_on_support": 0.66015625, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5071732997894287, "decoder_belief_target_nll": 2.2274532318115234, "decoder_belief_top1_on_support": 0.640625, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6549732685089111, "decoder_query_target_nll": 1.6050338745117188, "decoder_query_top1_on_support": 0.73828125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_PLUS_B", "k": 12, "n": 256, "query_target_mass": 0.33056163787841797, "query_target_nll": 2.417269229888916, "query_top1_on_support": 0.40625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5004197955131531, "probe_belief_target_nll": 2.2605841159820557, "probe_belief_top1_on_support": 0.66015625, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5071732997894287, "decoder_belief_target_nll": 2.2274532318115234, "decoder_belief_top1_on_support": 0.640625, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6549732685089111, "decoder_query_target_nll": 1.6050338745117188, "decoder_query_top1_on_support": 0.73828125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 0, "n": 256, "query_target_mass": 0.2934335470199585, "query_target_nll": 2.423219680786133, "query_top1_on_support": 0.32421875, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.030943164601922035, "probe_belief_target_nll": 18.903457641601562, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.03137341886758804, "decoder_belief_target_nll": 23.920169830322266, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.31250008940696716, "decoder_query_target_nll": 17.042470932006836, "decoder_query_top1_on_support": 0.3125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 1, "n": 256, "query_target_mass": 0.2925398349761963, "query_target_nll": 2.4230008125305176, "query_top1_on_support": 0.27734375, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.04381237551569939, "probe_belief_target_nll": 15.311500549316406, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.04372347518801689, "decoder_belief_target_nll": 17.96269989013672, "decoder_belief_top1_on_support": 0.046875, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.3013046979904175, "decoder_query_target_nll": 10.187450408935547, "decoder_query_top1_on_support": 0.3125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 2, "n": 256, "query_target_mass": 0.29182708263397217, "query_target_nll": 2.424746513366699, "query_top1_on_support": 0.26171875, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.0708789974451065, "probe_belief_target_nll": 12.978483200073242, "probe_belief_top1_on_support": 0.0859375, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.07282352447509766, "decoder_belief_target_nll": 14.712188720703125, "decoder_belief_top1_on_support": 0.08203125, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.3327594995498657, "decoder_query_target_nll": 7.7900004386901855, "decoder_query_top1_on_support": 0.3203125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 3, "n": 256, "query_target_mass": 0.29160988330841064, "query_target_nll": 2.4234437942504883, "query_top1_on_support": 0.26171875, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.07776902616024017, "probe_belief_target_nll": 11.223306655883789, "probe_belief_top1_on_support": 0.08203125, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.07797668129205704, "decoder_belief_target_nll": 12.668453216552734, "decoder_belief_top1_on_support": 0.0703125, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.313946396112442, "decoder_query_target_nll": 6.738012313842773, "decoder_query_top1_on_support": 0.3125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 6, "n": 256, "query_target_mass": 0.29220426082611084, "query_target_nll": 2.417506217956543, "query_top1_on_support": 0.28515625, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.509953498840332, "probe_belief_target_nll": 2.2115001678466797, "probe_belief_top1_on_support": 0.66796875, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5188002586364746, "decoder_belief_target_nll": 2.2241804599761963, "decoder_belief_top1_on_support": 0.6171875, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.7037980556488037, "decoder_query_target_nll": 1.4018199443817139, "decoder_query_top1_on_support": 0.75390625, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 9, "n": 256, "query_target_mass": 0.29220426082611084, "query_target_nll": 2.417506217956543, "query_top1_on_support": 0.28515625, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.509953498840332, "probe_belief_target_nll": 2.2115001678466797, "probe_belief_top1_on_support": 0.66796875, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5188002586364746, "decoder_belief_target_nll": 2.2241804599761963, "decoder_belief_top1_on_support": 0.6171875, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.7037980556488037, "decoder_query_target_nll": 1.4018199443817139, "decoder_query_top1_on_support": 0.75390625, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A_MINUS_B", "k": 12, "n": 256, "query_target_mass": 0.29220426082611084, "query_target_nll": 2.417506217956543, "query_top1_on_support": 0.28515625, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.509953498840332, "probe_belief_target_nll": 2.2115001678466797, "probe_belief_top1_on_support": 0.66796875, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5188002586364746, "decoder_belief_target_nll": 2.2241804599761963, "decoder_belief_top1_on_support": 0.6171875, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.7037980556488037, "decoder_query_target_nll": 1.4018199443817139, "decoder_query_top1_on_support": 0.75390625, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.22010096907615662, "query_target_nll": 2.411013603210449, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.02220134250819683, "probe_belief_target_nll": 19.303890228271484, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.021950822323560715, "decoder_belief_target_nll": 24.38858413696289, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.21861568093299866, "decoder_query_target_nll": 2.4032137393951416, "decoder_query_top1_on_support": 0.21875, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.21935021877288818, "query_target_nll": 2.4202632904052734, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.035091061145067215, "probe_belief_target_nll": 15.083793640136719, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.035494253039360046, "decoder_belief_target_nll": 17.65489959716797, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.24402490258216858, "decoder_query_target_nll": 5.5741071701049805, "decoder_query_top1_on_support": 0.2734375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.22082877159118652, "query_target_nll": 2.404752254486084, "query_top1_on_support": 0.21875, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.0335833802819252, "probe_belief_target_nll": 13.965766906738281, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.03707928583025932, "decoder_belief_target_nll": 15.736716270446777, "decoder_belief_top1_on_support": 0.046875, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.2651031017303467, "decoder_query_target_nll": 6.036951541900635, "decoder_query_top1_on_support": 0.27734375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.22071950137615204, "query_target_nll": 2.407886028289795, "query_top1_on_support": 0.23046875, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.03909733146429062, "probe_belief_target_nll": 12.717486381530762, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.04204375296831131, "decoder_belief_target_nll": 14.239721298217773, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.2709215581417084, "decoder_query_target_nll": 6.206388473510742, "decoder_query_top1_on_support": 0.27734375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.21606789529323578, "query_target_nll": 2.4332780838012695, "query_top1_on_support": 0.20703125, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.06756911426782608, "probe_belief_target_nll": 9.535100936889648, "probe_belief_top1_on_support": 0.07421875, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.06948588788509369, "decoder_belief_target_nll": 10.548111915588379, "decoder_belief_top1_on_support": 0.0703125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.3185040056705475, "decoder_query_target_nll": 5.028907775878906, "decoder_query_top1_on_support": 0.3203125, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.21981926262378693, "query_target_nll": 2.4104974269866943, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.3304753303527832, "probe_belief_target_nll": 2.544452667236328, "probe_belief_top1_on_support": 0.453125, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.33838748931884766, "decoder_belief_target_nll": 2.5077576637268066, "decoder_belief_top1_on_support": 0.4453125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.5857373476028442, "decoder_query_target_nll": 1.4092745780944824, "decoder_query_top1_on_support": 0.66015625, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.21981926262378693, "query_target_nll": 2.4104974269866943, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.3304753303527832, "probe_belief_target_nll": 2.544452667236328, "probe_belief_top1_on_support": 0.453125, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.33838748931884766, "decoder_belief_target_nll": 2.5077576637268066, "decoder_belief_top1_on_support": 0.4453125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.5857373476028442, "decoder_query_target_nll": 1.4092745780944824, "decoder_query_top1_on_support": 0.66015625, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.193543940782547, "query_target_nll": 2.4087095260620117, "query_top1_on_support": 0.20703125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.024538155645132065, "probe_belief_target_nll": 19.04078483581543, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.025016166269779205, "decoder_belief_target_nll": 24.39712142944336, "decoder_belief_top1_on_support": 0.03515625, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.1941702961921692, "decoder_query_target_nll": 2.3934402465820312, "decoder_query_top1_on_support": 0.234375, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.19200292229652405, "query_target_nll": 2.418424129486084, "query_top1_on_support": 0.20703125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.026622891426086426, "probe_belief_target_nll": 15.573517799377441, "probe_belief_top1_on_support": 0.046875, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.025930874049663544, "decoder_belief_target_nll": 18.32387351989746, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.19285863637924194, "decoder_query_target_nll": 5.908019065856934, "decoder_query_top1_on_support": 0.16796875, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.19085699319839478, "query_target_nll": 2.429670572280884, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.033728886395692825, "probe_belief_target_nll": 13.617773056030273, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.030571289360523224, "decoder_belief_target_nll": 15.463726043701172, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.20884160697460175, "decoder_query_target_nll": 6.015504837036133, "decoder_query_top1_on_support": 0.2109375, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.19140000641345978, "query_target_nll": 2.424861431121826, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.033605530858039856, "probe_belief_target_nll": 12.625875473022461, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.030809566378593445, "decoder_belief_target_nll": 14.130053520202637, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.22726958990097046, "decoder_query_target_nll": 6.010664939880371, "decoder_query_top1_on_support": 0.2421875, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.19205333292484283, "query_target_nll": 2.4190969467163086, "query_top1_on_support": 0.171875, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.05301932618021965, "probe_belief_target_nll": 10.528427124023438, "probe_belief_top1_on_support": 0.0625, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.05129703879356384, "decoder_belief_target_nll": 11.590852737426758, "decoder_belief_top1_on_support": 0.05859375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.27825045585632324, "decoder_query_target_nll": 5.415653228759766, "decoder_query_top1_on_support": 0.296875, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.1909986436367035, "query_target_nll": 2.4327962398529053, "query_top1_on_support": 0.17578125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.3224598169326782, "probe_belief_target_nll": 2.407832622528076, "probe_belief_top1_on_support": 0.4375, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.32659775018692017, "decoder_belief_target_nll": 2.422135829925537, "decoder_belief_top1_on_support": 0.42578125, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.5590262413024902, "decoder_query_target_nll": 1.3879878520965576, "decoder_query_top1_on_support": 0.6640625, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.1909986436367035, "query_target_nll": 2.4327962398529053, "query_top1_on_support": 0.17578125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.3224598169326782, "probe_belief_target_nll": 2.407832622528076, "probe_belief_top1_on_support": 0.4375, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.32659775018692017, "decoder_belief_target_nll": 2.422135829925537, "decoder_belief_top1_on_support": 0.42578125, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.5590262413024902, "decoder_query_target_nll": 1.3879878520965576, "decoder_query_top1_on_support": 0.6640625, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 0, "n": 256, "query_target_mass": 0.22773805260658264, "query_target_nll": 2.4126052856445312, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.02346641942858696, "probe_belief_target_nll": 19.03647232055664, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.021973367780447006, "decoder_belief_target_nll": 24.161359786987305, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.22756363451480865, "decoder_query_target_nll": 2.400143623352051, "decoder_query_top1_on_support": 0.234375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 1, "n": 256, "query_target_mass": 0.2278088927268982, "query_target_nll": 2.421475887298584, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.030334491282701492, "probe_belief_target_nll": 15.271839141845703, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.030802400782704353, "decoder_belief_target_nll": 17.994842529296875, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.23574835062026978, "decoder_query_target_nll": 4.352008819580078, "decoder_query_top1_on_support": 0.23046875, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 2, "n": 256, "query_target_mass": 0.22794732451438904, "query_target_nll": 2.423764228820801, "query_top1_on_support": 0.23046875, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.02760476991534233, "probe_belief_target_nll": 13.27773666381836, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.026114990934729576, "decoder_belief_target_nll": 15.27619743347168, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.2149488925933838, "decoder_query_target_nll": 5.05734395980835, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 3, "n": 256, "query_target_mass": 0.22607660293579102, "query_target_nll": 2.4362120628356934, "query_top1_on_support": 0.24609375, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.04168013483285904, "probe_belief_target_nll": 11.726909637451172, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.042337872087955475, "decoder_belief_target_nll": 13.11721420288086, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.228382408618927, "decoder_query_target_nll": 4.659674644470215, "decoder_query_top1_on_support": 0.23828125, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 6, "n": 256, "query_target_mass": 0.22510674595832825, "query_target_nll": 2.435384750366211, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.05707002803683281, "probe_belief_target_nll": 9.627598762512207, "probe_belief_top1_on_support": 0.05859375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.055991753935813904, "decoder_belief_target_nll": 10.486563682556152, "decoder_belief_top1_on_support": 0.04296875, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.21872679889202118, "decoder_query_target_nll": 4.271492958068848, "decoder_query_top1_on_support": 0.19921875, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 9, "n": 256, "query_target_mass": 0.22854942083358765, "query_target_nll": 2.4182777404785156, "query_top1_on_support": 0.26171875, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.3327700197696686, "probe_belief_target_nll": 2.4915521144866943, "probe_belief_top1_on_support": 0.42578125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.34624120593070984, "decoder_belief_target_nll": 2.4404399394989014, "decoder_belief_top1_on_support": 0.44921875, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.5001667141914368, "decoder_query_target_nll": 1.6696357727050781, "decoder_query_top1_on_support": 0.58984375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_PLUS_B", "k": 12, "n": 256, "query_target_mass": 0.22854942083358765, "query_target_nll": 2.4182777404785156, "query_top1_on_support": 0.26171875, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.3327700197696686, "probe_belief_target_nll": 2.4915521144866943, "probe_belief_top1_on_support": 0.42578125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.34624120593070984, "decoder_belief_target_nll": 2.4404399394989014, "decoder_belief_top1_on_support": 0.44921875, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.5001667141914368, "decoder_query_target_nll": 1.6696357727050781, "decoder_query_top1_on_support": 0.58984375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 0, "n": 256, "query_target_mass": 0.21429771184921265, "query_target_nll": 2.424884796142578, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.01738450862467289, "probe_belief_target_nll": 19.566734313964844, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.017360873520374298, "decoder_belief_target_nll": 24.836469650268555, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.1835937798023224, "decoder_query_target_nll": 17.475845336914062, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 1, "n": 256, "query_target_mass": 0.21494249999523163, "query_target_nll": 2.4034481048583984, "query_top1_on_support": 0.24609375, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.0223536416888237, "probe_belief_target_nll": 15.257161140441895, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.020837698131799698, "decoder_belief_target_nll": 17.89769744873047, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.200091153383255, "decoder_query_target_nll": 9.310386657714844, "decoder_query_top1_on_support": 0.22265625, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 2, "n": 256, "query_target_mass": 0.21366716921329498, "query_target_nll": 2.4196877479553223, "query_top1_on_support": 0.22265625, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.025071004405617714, "probe_belief_target_nll": 13.398033142089844, "probe_belief_top1_on_support": 0.03515625, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.025590695440769196, "decoder_belief_target_nll": 15.327930450439453, "decoder_belief_top1_on_support": 0.03515625, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.24005095660686493, "decoder_query_target_nll": 7.609133720397949, "decoder_query_top1_on_support": 0.25, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 3, "n": 256, "query_target_mass": 0.2151491940021515, "query_target_nll": 2.408055305480957, "query_top1_on_support": 0.21875, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.029645465314388275, "probe_belief_target_nll": 12.772809982299805, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.030868016183376312, "decoder_belief_target_nll": 14.323205947875977, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.24201476573944092, "decoder_query_target_nll": 6.916339874267578, "decoder_query_top1_on_support": 0.23828125, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 6, "n": 256, "query_target_mass": 0.21501459181308746, "query_target_nll": 2.407771348953247, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.05705419182777405, "probe_belief_target_nll": 9.940338134765625, "probe_belief_top1_on_support": 0.078125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.055818721652030945, "decoder_belief_target_nll": 10.962053298950195, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.2454879879951477, "decoder_query_target_nll": 5.514425754547119, "decoder_query_top1_on_support": 0.25390625, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 9, "n": 256, "query_target_mass": 0.21725721657276154, "query_target_nll": 2.3929450511932373, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.33617937564849854, "probe_belief_target_nll": 2.4603705406188965, "probe_belief_top1_on_support": 0.4453125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.3426702916622162, "decoder_belief_target_nll": 2.458399772644043, "decoder_belief_top1_on_support": 0.4375, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.5441945791244507, "decoder_query_target_nll": 1.5438709259033203, "decoder_query_top1_on_support": 0.6171875, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A_MINUS_B", "k": 12, "n": 256, "query_target_mass": 0.21725721657276154, "query_target_nll": 2.3929450511932373, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.33617937564849854, "probe_belief_target_nll": 2.4603705406188965, "probe_belief_top1_on_support": 0.4453125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.3426702916622162, "decoder_belief_target_nll": 2.458399772644043, "decoder_belief_top1_on_support": 0.4375, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.5441945791244507, "decoder_query_target_nll": 1.5438709259033203, "decoder_query_top1_on_support": 0.6171875, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.17295099794864655, "query_target_nll": 2.424738645553589, "query_top1_on_support": 0.16796875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.018240483477711678, "probe_belief_target_nll": 19.199342727661133, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.01756516844034195, "decoder_belief_target_nll": 24.248973846435547, "decoder_belief_top1_on_support": 0.01171875, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.1731780469417572, "decoder_query_target_nll": 2.4063913822174072, "decoder_query_top1_on_support": 0.171875, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.1752001941204071, "query_target_nll": 2.405667781829834, "query_top1_on_support": 0.20703125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02913011610507965, "probe_belief_target_nll": 15.326465606689453, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02879510447382927, "decoder_belief_target_nll": 17.784177780151367, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.18818065524101257, "decoder_query_target_nll": 5.610430717468262, "decoder_query_top1_on_support": 0.203125, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.17185290157794952, "query_target_nll": 2.4341866970062256, "query_top1_on_support": 0.1328125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02220115065574646, "probe_belief_target_nll": 14.20823860168457, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.019308321177959442, "decoder_belief_target_nll": 15.97067642211914, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.18267476558685303, "decoder_query_target_nll": 6.359857559204102, "decoder_query_top1_on_support": 0.1875, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.17240294814109802, "query_target_nll": 2.429032325744629, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02520015835762024, "probe_belief_target_nll": 12.761363983154297, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02481451816856861, "decoder_belief_target_nll": 14.128837585449219, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.17262256145477295, "decoder_query_target_nll": 6.537018299102783, "decoder_query_top1_on_support": 0.17578125, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.17290018498897552, "query_target_nll": 2.421201467514038, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02306012064218521, "probe_belief_target_nll": 11.099533081054688, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02273371070623398, "decoder_belief_target_nll": 12.223663330078125, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.19422203302383423, "decoder_query_target_nll": 5.85289192199707, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.17204779386520386, "query_target_nll": 2.4242143630981445, "query_top1_on_support": 0.16015625, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.06283444166183472, "probe_belief_target_nll": 9.007758140563965, "probe_belief_top1_on_support": 0.10546875, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.060540273785591125, "decoder_belief_target_nll": 9.880760192871094, "decoder_belief_top1_on_support": 0.08203125, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.281036376953125, "decoder_query_target_nll": 4.411991119384766, "decoder_query_top1_on_support": 0.296875, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.17549361288547516, "query_target_nll": 2.396327495574951, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.23051172494888306, "probe_belief_target_nll": 2.7168731689453125, "probe_belief_top1_on_support": 0.3046875, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.23126111924648285, "decoder_belief_target_nll": 2.7379255294799805, "decoder_belief_top1_on_support": 0.32421875, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.47900572419166565, "decoder_query_target_nll": 1.4656957387924194, "decoder_query_top1_on_support": 0.54296875, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.15427175164222717, "query_target_nll": 2.3997817039489746, "query_top1_on_support": 0.1875, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.013586129061877728, "probe_belief_target_nll": 19.526546478271484, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.01350044459104538, "decoder_belief_target_nll": 24.426639556884766, "decoder_belief_top1_on_support": 0.0078125, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.15360091626644135, "decoder_query_target_nll": 2.397366523742676, "decoder_query_top1_on_support": 0.16796875, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.15465271472930908, "query_target_nll": 2.4018750190734863, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.013493221253156662, "probe_belief_target_nll": 15.594846725463867, "probe_belief_top1_on_support": 0.01171875, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.014538978226482868, "decoder_belief_target_nll": 18.28829574584961, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.15137231349945068, "decoder_query_target_nll": 5.185262203216553, "decoder_query_top1_on_support": 0.12890625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.15447914600372314, "query_target_nll": 2.4020724296569824, "query_top1_on_support": 0.1640625, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.015872692689299583, "probe_belief_target_nll": 13.663904190063477, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.01592313125729561, "decoder_belief_target_nll": 15.458024978637695, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.17213934659957886, "decoder_query_target_nll": 6.194061756134033, "decoder_query_top1_on_support": 0.1640625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.154474675655365, "query_target_nll": 2.4012012481689453, "query_top1_on_support": 0.15234375, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.013654566369950771, "probe_belief_target_nll": 12.79922103881836, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.013566017150878906, "decoder_belief_target_nll": 14.34869384765625, "decoder_belief_top1_on_support": 0.01171875, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.17197707295417786, "decoder_query_target_nll": 5.902646541595459, "decoder_query_top1_on_support": 0.17578125, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.15495574474334717, "query_target_nll": 2.402796745300293, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.017920952290296555, "probe_belief_target_nll": 11.165021896362305, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.016023971140384674, "decoder_belief_target_nll": 12.364017486572266, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.15781888365745544, "decoder_query_target_nll": 6.110826015472412, "decoder_query_top1_on_support": 0.15625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.15391826629638672, "query_target_nll": 2.402226448059082, "query_top1_on_support": 0.12109375, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.045646876096725464, "probe_belief_target_nll": 8.872591972351074, "probe_belief_top1_on_support": 0.0546875, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.04005810618400574, "decoder_belief_target_nll": 9.754579544067383, "decoder_belief_top1_on_support": 0.04296875, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.23819184303283691, "decoder_query_target_nll": 4.348093032836914, "decoder_query_top1_on_support": 0.265625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.15226225554943085, "query_target_nll": 2.4201409816741943, "query_top1_on_support": 0.15234375, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.21424508094787598, "probe_belief_target_nll": 2.7574820518493652, "probe_belief_top1_on_support": 0.3046875, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.22013597190380096, "decoder_belief_target_nll": 2.7485878467559814, "decoder_belief_top1_on_support": 0.30078125, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.450691282749176, "decoder_query_target_nll": 1.466652274131775, "decoder_query_top1_on_support": 0.5078125, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 0, "n": 256, "query_target_mass": 0.17389285564422607, "query_target_nll": 2.4324257373809814, "query_top1_on_support": 0.14453125, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.02453852817416191, "probe_belief_target_nll": 18.81281280517578, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.02478930354118347, "decoder_belief_target_nll": 23.761938095092773, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17500174045562744, "decoder_query_target_nll": 2.4132776260375977, "decoder_query_top1_on_support": 0.14453125, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 1, "n": 256, "query_target_mass": 0.17653369903564453, "query_target_nll": 2.415161371231079, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.015180273912847042, "probe_belief_target_nll": 15.82254695892334, "probe_belief_top1_on_support": 0.00390625, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.014875181019306183, "decoder_belief_target_nll": 18.718835830688477, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.18830761313438416, "decoder_query_target_nll": 4.584983825683594, "decoder_query_top1_on_support": 0.1953125, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 2, "n": 256, "query_target_mass": 0.17481961846351624, "query_target_nll": 2.4292585849761963, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.02037852257490158, "probe_belief_target_nll": 14.086230278015137, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.019534552469849586, "decoder_belief_target_nll": 16.065807342529297, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17213726043701172, "decoder_query_target_nll": 4.960493087768555, "decoder_query_top1_on_support": 0.1640625, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 3, "n": 256, "query_target_mass": 0.17332538962364197, "query_target_nll": 2.441030502319336, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.017365332692861557, "probe_belief_target_nll": 13.37894344329834, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.017901912331581116, "decoder_belief_target_nll": 14.857418060302734, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.18217086791992188, "decoder_query_target_nll": 4.966036319732666, "decoder_query_top1_on_support": 0.1953125, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 6, "n": 256, "query_target_mass": 0.1740090399980545, "query_target_nll": 2.4427595138549805, "query_top1_on_support": 0.1875, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.02451380528509617, "probe_belief_target_nll": 11.53221607208252, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.026328377425670624, "decoder_belief_target_nll": 12.704442977905273, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17916512489318848, "decoder_query_target_nll": 4.465616703033447, "decoder_query_top1_on_support": 0.1640625, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 9, "n": 256, "query_target_mass": 0.1746600866317749, "query_target_nll": 2.433422327041626, "query_top1_on_support": 0.1953125, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.04632238298654556, "probe_belief_target_nll": 9.430642127990723, "probe_belief_top1_on_support": 0.06640625, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.045934826135635376, "decoder_belief_target_nll": 10.428153991699219, "decoder_belief_top1_on_support": 0.046875, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.18645286560058594, "decoder_query_target_nll": 4.272585868835449, "decoder_query_top1_on_support": 0.20703125, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_PLUS_B", "k": 12, "n": 256, "query_target_mass": 0.17682558298110962, "query_target_nll": 2.411038398742676, "query_top1_on_support": 0.2109375, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.24126416444778442, "probe_belief_target_nll": 2.561464548110962, "probe_belief_top1_on_support": 0.31640625, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.23272249102592468, "decoder_belief_target_nll": 2.5903329849243164, "decoder_belief_top1_on_support": 0.27734375, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.3697502613067627, "decoder_query_target_nll": 1.7440781593322754, "decoder_query_top1_on_support": 0.43359375, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 0, "n": 256, "query_target_mass": 0.17854291200637817, "query_target_nll": 2.4217166900634766, "query_top1_on_support": 0.18359375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.019929006695747375, "probe_belief_target_nll": 18.869951248168945, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.020502451807260513, "decoder_belief_target_nll": 24.08452033996582, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.21484367549419403, "decoder_query_target_nll": 16.89476776123047, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 1, "n": 256, "query_target_mass": 0.17706432938575745, "query_target_nll": 2.4269943237304688, "query_top1_on_support": 0.2109375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.015377182513475418, "probe_belief_target_nll": 16.36806869506836, "probe_belief_top1_on_support": 0.0078125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.01758887618780136, "decoder_belief_target_nll": 18.973405838012695, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.18382634222507477, "decoder_query_target_nll": 9.54983901977539, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 2, "n": 256, "query_target_mass": 0.1765212118625641, "query_target_nll": 2.435542106628418, "query_top1_on_support": 0.1953125, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.016480617225170135, "probe_belief_target_nll": 14.380898475646973, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.016436360776424408, "decoder_belief_target_nll": 16.22071647644043, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.1628236621618271, "decoder_query_target_nll": 7.660752296447754, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 3, "n": 256, "query_target_mass": 0.17820405960083008, "query_target_nll": 2.4198875427246094, "query_top1_on_support": 0.24609375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.013534501194953918, "probe_belief_target_nll": 13.025348663330078, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.013668788596987724, "decoder_belief_target_nll": 14.451990127563477, "decoder_belief_top1_on_support": 0.0078125, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.16655397415161133, "decoder_query_target_nll": 6.766253471374512, "decoder_query_top1_on_support": 0.15625, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 6, "n": 256, "query_target_mass": 0.17692509293556213, "query_target_nll": 2.4230003356933594, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.01887703314423561, "probe_belief_target_nll": 11.330083847045898, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.018510043621063232, "decoder_belief_target_nll": 12.452545166015625, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.18306350708007812, "decoder_query_target_nll": 5.407058238983154, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 9, "n": 256, "query_target_mass": 0.17729230225086212, "query_target_nll": 2.4183177947998047, "query_top1_on_support": 0.1796875, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.047424085438251495, "probe_belief_target_nll": 8.870351791381836, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.05018243193626404, "decoder_belief_target_nll": 9.847485542297363, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.2018469274044037, "decoder_query_target_nll": 4.877822399139404, "decoder_query_top1_on_support": 0.2109375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_residual_mlp_d256", "supervision": "teacher_belief", "transition": "residual", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A_MINUS_B", "k": 12, "n": 256, "query_target_mass": 0.1792551428079605, "query_target_nll": 2.39700984954834, "query_top1_on_support": 0.19921875, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.21034984290599823, "probe_belief_target_nll": 2.8334078788757324, "probe_belief_top1_on_support": 0.28515625, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.2148093581199646, "decoder_belief_target_nll": 2.8196887969970703, "decoder_belief_top1_on_support": 0.265625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.4057474732398987, "decoder_query_target_nll": 1.7655470371246338, "decoder_query_top1_on_support": 0.46875, "mean_decoder_query_support_size": 1.95703125 } ] } ], "checkpoints": [ "large_artifacts/dense_teacher_distillation/checkpoints/pilot_residual_mlp_d256/checkpoint_final.pt" ] }