{ "mode": "dense", "variant": "pilot_gru_mlp_d256", "transition": "gru", "decoder_type": "mlp", "args": { "variant_name": "pilot_gru_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": "gru", "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_gru_mlp_d256", "checkpoint_dir": "large_artifacts/dense_teacher_distillation/checkpoints/pilot_gru_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": 4.813065052032471, "grad_norm": 0.378798246383667, "query_loss": 0.0, "belief_loss": 4.813065052032471, "decoder_query_loss": 0.0, "query_target_mass": 0.4229942560195923, "query_target_nll": 2.418551445007324, "query_top1_on_support": 0.4296875, "mean_query_support_size": 4.65625, "decoder_belief_target_mass": 0.051594868302345276, "decoder_belief_target_nll": 4.647534370422363, "decoder_belief_top1_on_support": 0.15234375, "mean_decoder_belief_support_size": 5.6953125, "decoder_query_target_mass": 0.4268272817134857, "decoder_query_target_nll": 2.3726484775543213, "decoder_query_top1_on_support": 0.5078125, "mean_decoder_query_support_size": 4.65625 }, { "step": 100, "loss": 3.1800241470336914, "grad_norm": 0.4200664460659027, "query_loss": 0.0, "belief_loss": 3.1800241470336914, "decoder_query_loss": 0.0, "query_target_mass": 0.4306916296482086, "query_target_nll": 2.4116244316101074, "query_top1_on_support": 0.44140625, "mean_query_support_size": 4.73046875, "decoder_belief_target_mass": 0.2637162208557129, "decoder_belief_target_nll": 3.5952200889587402, "decoder_belief_top1_on_support": 0.3203125, "mean_decoder_belief_support_size": 5.9453125, "decoder_query_target_mass": 0.5896897912025452, "decoder_query_target_nll": 2.0126261711120605, "decoder_query_top1_on_support": 0.65234375, "mean_decoder_query_support_size": 4.73046875 }, { "step": 200, "loss": 2.8324759006500244, "grad_norm": 0.654343843460083, "query_loss": 0.0, "belief_loss": 2.8324759006500244, "decoder_query_loss": 0.0, "query_target_mass": 0.4748761057853699, "query_target_nll": 2.4071314334869385, "query_top1_on_support": 0.5, "mean_query_support_size": 5.20703125, "decoder_belief_target_mass": 0.38848134875297546, "decoder_belief_target_nll": 3.055988073348999, "decoder_belief_top1_on_support": 0.50390625, "mean_decoder_belief_support_size": 5.75390625, "decoder_query_target_mass": 0.7036318778991699, "decoder_query_target_nll": 1.852623701095581, "decoder_query_top1_on_support": 0.76953125, "mean_decoder_query_support_size": 5.20703125 }, { "step": 300, "loss": 2.332012891769409, "grad_norm": 0.6626783609390259, "query_loss": 0.0, "belief_loss": 2.332012891769409, "decoder_query_loss": 0.0, "query_target_mass": 0.44950950145721436, "query_target_nll": 2.417227029800415, "query_top1_on_support": 0.4375, "mean_query_support_size": 4.94921875, "decoder_belief_target_mass": 0.6251513361930847, "decoder_belief_target_nll": 2.4034433364868164, "decoder_belief_top1_on_support": 0.734375, "mean_decoder_belief_support_size": 5.81640625, "decoder_query_target_mass": 0.8076519966125488, "decoder_query_target_nll": 1.5757806301116943, "decoder_query_top1_on_support": 0.87890625, "mean_decoder_query_support_size": 4.94921875 }, { "step": 400, "loss": 2.2534749507904053, "grad_norm": 0.48740920424461365, "query_loss": 0.0, "belief_loss": 2.2534749507904053, "decoder_query_loss": 0.0, "query_target_mass": 0.43221864104270935, "query_target_nll": 2.3995590209960938, "query_top1_on_support": 0.45703125, "mean_query_support_size": 4.734375, "decoder_belief_target_mass": 0.6420519351959229, "decoder_belief_target_nll": 2.315478801727295, "decoder_belief_top1_on_support": 0.71875, "mean_decoder_belief_support_size": 5.515625, "decoder_query_target_mass": 0.8111111521720886, "decoder_query_target_nll": 1.5198962688446045, "decoder_query_top1_on_support": 0.87109375, "mean_decoder_query_support_size": 4.734375 }, { "step": 500, "loss": 2.156681776046753, "grad_norm": 0.4323832392692566, "query_loss": 0.0, "belief_loss": 2.156681776046753, "decoder_query_loss": 0.0, "query_target_mass": 0.4322691559791565, "query_target_nll": 2.4069132804870605, "query_top1_on_support": 0.43359375, "mean_query_support_size": 4.73828125, "decoder_belief_target_mass": 0.7085942029953003, "decoder_belief_target_nll": 2.1235873699188232, "decoder_belief_top1_on_support": 0.8046875, "mean_decoder_belief_support_size": 5.671875, "decoder_query_target_mass": 0.8568092584609985, "decoder_query_target_nll": 1.4254800081253052, "decoder_query_top1_on_support": 0.9296875, "mean_decoder_query_support_size": 4.73828125 }, { "step": 600, "loss": 2.153493881225586, "grad_norm": 0.5331100821495056, "query_loss": 0.0, "belief_loss": 2.153493881225586, "decoder_query_loss": 0.0, "query_target_mass": 0.44185370206832886, "query_target_nll": 2.4126877784729004, "query_top1_on_support": 0.4296875, "mean_query_support_size": 4.85546875, "decoder_belief_target_mass": 0.756794810295105, "decoder_belief_target_nll": 2.0546927452087402, "decoder_belief_top1_on_support": 0.8515625, "mean_decoder_belief_support_size": 6.046875, "decoder_query_target_mass": 0.889145016670227, "decoder_query_target_nll": 1.3761974573135376, "decoder_query_top1_on_support": 0.953125, "mean_decoder_query_support_size": 4.85546875 }, { "step": 700, "loss": 2.1240785121917725, "grad_norm": 0.45322927832603455, "query_loss": 0.0, "belief_loss": 2.1240785121917725, "decoder_query_loss": 0.0, "query_target_mass": 0.4618549942970276, "query_target_nll": 2.408527374267578, "query_top1_on_support": 0.48046875, "mean_query_support_size": 5.0625, "decoder_belief_target_mass": 0.7628631591796875, "decoder_belief_target_nll": 2.0064704418182373, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.8671875, "decoder_query_target_mass": 0.8888527154922485, "decoder_query_target_nll": 1.4259068965911865, "decoder_query_top1_on_support": 0.9453125, "mean_decoder_query_support_size": 5.0625 }, { "step": 800, "loss": 2.0258712768554688, "grad_norm": 0.3708508312702179, "query_loss": 0.0, "belief_loss": 2.0258712768554688, "decoder_query_loss": 0.0, "query_target_mass": 0.46777504682540894, "query_target_nll": 2.399602174758911, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.1171875, "decoder_belief_target_mass": 0.8010770678520203, "decoder_belief_target_nll": 1.956331491470337, "decoder_belief_top1_on_support": 0.86328125, "mean_decoder_belief_support_size": 5.98046875, "decoder_query_target_mass": 0.9055441617965698, "decoder_query_target_nll": 1.4172003269195557, "decoder_query_top1_on_support": 0.9375, "mean_decoder_query_support_size": 5.1171875 } ], "probe_train": [ { "step": 1, "loss": 4.813758373260498, "grad_norm": 0.5232709646224976, "probe_belief_target_mass": 0.06012779846787453, "probe_belief_target_nll": 4.813758373260498, "probe_belief_top1_on_support": 0.063058041036129, "mean_belief_support_size": 7.3058037757873535 }, { "step": 100, "loss": 2.25643253326416, "grad_norm": 0.3564361035823822, "probe_belief_target_mass": 0.794096052646637, "probe_belief_target_nll": 2.25643253326416, "probe_belief_top1_on_support": 0.8688616752624512, "mean_belief_support_size": 7.245535850524902 }, { "step": 200, "loss": 2.1250805854797363, "grad_norm": 0.3031345009803772, "probe_belief_target_mass": 0.8532631397247314, "probe_belief_target_nll": 2.1250805854797363, "probe_belief_top1_on_support": 0.910714328289032, "mean_belief_support_size": 7.470424652099609 }, { "step": 300, "loss": 2.0019097328186035, "grad_norm": 0.3431372046470642, "probe_belief_target_mass": 0.8941127061843872, "probe_belief_target_nll": 2.0019097328186035, "probe_belief_top1_on_support": 0.9464285969734192, "mean_belief_support_size": 7.313058376312256 }, { "step": 400, "loss": 2.0456416606903076, "grad_norm": 0.3814433515071869, "probe_belief_target_mass": 0.8621965646743774, "probe_belief_target_nll": 2.0456416606903076, "probe_belief_top1_on_support": 0.9174107313156128, "mean_belief_support_size": 7.136160850524902 } ], "eval": [ { "step": 800, "rows": [ { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.4725129008293152, "query_target_nll": 2.4080357551574707, "query_top1_on_support": 0.46484375, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.06330319494009018, "probe_belief_target_nll": 15.244365692138672, "probe_belief_top1_on_support": 0.05859375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.06317909061908722, "decoder_belief_target_nll": 18.52483367919922, "decoder_belief_top1_on_support": 0.0703125, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.47120654582977295, "decoder_query_target_nll": 2.402869701385498, "decoder_query_top1_on_support": 0.46875, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.4726637601852417, "query_target_nll": 2.408449411392212, "query_top1_on_support": 0.48046875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.12147754430770874, "probe_belief_target_nll": 11.992364883422852, "probe_belief_top1_on_support": 0.12109375, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.1219494640827179, "decoder_belief_target_nll": 13.215036392211914, "decoder_belief_top1_on_support": 0.1328125, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.5590718984603882, "decoder_query_target_nll": 3.8220744132995605, "decoder_query_top1_on_support": 0.5859375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.4735095500946045, "query_target_nll": 2.3989224433898926, "query_top1_on_support": 0.484375, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.2532787322998047, "probe_belief_target_nll": 8.052383422851562, "probe_belief_top1_on_support": 0.25, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.25423216819763184, "decoder_belief_target_nll": 8.697732925415039, "decoder_belief_top1_on_support": 0.2265625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.696056604385376, "decoder_query_target_nll": 3.1793527603149414, "decoder_query_top1_on_support": 0.6796875, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.4774681031703949, "query_target_nll": 2.38023042678833, "query_top1_on_support": 0.51171875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7734000086784363, "probe_belief_target_nll": 2.0203590393066406, "probe_belief_top1_on_support": 0.8828125, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7908084392547607, "decoder_belief_target_nll": 1.9745678901672363, "decoder_belief_top1_on_support": 0.87890625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591154456138611, "decoder_query_target_nll": 1.3887773752212524, "decoder_query_top1_on_support": 0.99609375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.4774681031703949, "query_target_nll": 2.38023042678833, "query_top1_on_support": 0.51171875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7734000086784363, "probe_belief_target_nll": 2.0203590393066406, "probe_belief_top1_on_support": 0.8828125, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7908084392547607, "decoder_belief_target_nll": 1.9745678901672363, "decoder_belief_top1_on_support": 0.87890625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591154456138611, "decoder_query_target_nll": 1.3887773752212524, "decoder_query_top1_on_support": 0.99609375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.4774681031703949, "query_target_nll": 2.38023042678833, "query_top1_on_support": 0.51171875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7734000086784363, "probe_belief_target_nll": 2.0203590393066406, "probe_belief_top1_on_support": 0.8828125, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7908084392547607, "decoder_belief_target_nll": 1.9745678901672363, "decoder_belief_top1_on_support": 0.87890625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591154456138611, "decoder_query_target_nll": 1.3887773752212524, "decoder_query_top1_on_support": 0.99609375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.4774681031703949, "query_target_nll": 2.38023042678833, "query_top1_on_support": 0.51171875, "mean_query_support_size": 5.18359375, "probe_belief_target_mass": 0.7734000086784363, "probe_belief_target_nll": 2.0203590393066406, "probe_belief_top1_on_support": 0.8828125, "mean_belief_support_size": 5.84375, "decoder_belief_target_mass": 0.7908084392547607, "decoder_belief_target_nll": 1.9745678901672363, "decoder_belief_top1_on_support": 0.87890625, "mean_decoder_belief_support_size": 5.84375, "decoder_query_target_mass": 0.9591154456138611, "decoder_query_target_nll": 1.3887773752212524, "decoder_query_top1_on_support": 0.99609375, "mean_decoder_query_support_size": 5.18359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.46774908900260925, "query_target_nll": 2.422912120819092, "query_top1_on_support": 0.484375, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.053480200469493866, "probe_belief_target_nll": 15.413002967834473, "probe_belief_top1_on_support": 0.04296875, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.053481973707675934, "decoder_belief_target_nll": 18.685203552246094, "decoder_belief_top1_on_support": 0.04296875, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.4674762487411499, "decoder_query_target_nll": 2.4115490913391113, "decoder_query_top1_on_support": 0.4453125, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.4685201644897461, "query_target_nll": 2.4147844314575195, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.13410639762878418, "probe_belief_target_nll": 11.47542667388916, "probe_belief_top1_on_support": 0.14453125, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.13357874751091003, "decoder_belief_target_nll": 12.579654693603516, "decoder_belief_top1_on_support": 0.1171875, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.5350732207298279, "decoder_query_target_nll": 3.949978828430176, "decoder_query_top1_on_support": 0.5, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.468138188123703, "query_target_nll": 2.4145569801330566, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.270742803812027, "probe_belief_target_nll": 8.052581787109375, "probe_belief_top1_on_support": 0.26953125, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.26820462942123413, "decoder_belief_target_nll": 8.755812644958496, "decoder_belief_top1_on_support": 0.265625, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.6835877895355225, "decoder_query_target_nll": 3.392648696899414, "decoder_query_top1_on_support": 0.6796875, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.46709954738616943, "query_target_nll": 2.418890953063965, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.8016785383224487, "probe_belief_target_nll": 1.974765419960022, "probe_belief_top1_on_support": 0.8671875, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8110651969909668, "decoder_belief_target_nll": 1.9374971389770508, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9524992108345032, "decoder_query_target_nll": 1.3672468662261963, "decoder_query_top1_on_support": 0.97265625, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.46709954738616943, "query_target_nll": 2.418890953063965, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.8016785383224487, "probe_belief_target_nll": 1.974765419960022, "probe_belief_top1_on_support": 0.8671875, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8110651969909668, "decoder_belief_target_nll": 1.9374971389770508, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9524992108345032, "decoder_query_target_nll": 1.3672468662261963, "decoder_query_top1_on_support": 0.97265625, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.46709954738616943, "query_target_nll": 2.418890953063965, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.8016785383224487, "probe_belief_target_nll": 1.974765419960022, "probe_belief_top1_on_support": 0.8671875, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8110651969909668, "decoder_belief_target_nll": 1.9374971389770508, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9524992108345032, "decoder_query_target_nll": 1.3672468662261963, "decoder_query_top1_on_support": 0.97265625, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 3, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.46709954738616943, "query_target_nll": 2.418890953063965, "query_top1_on_support": 0.46875, "mean_query_support_size": 5.15234375, "probe_belief_target_mass": 0.8016785383224487, "probe_belief_target_nll": 1.974765419960022, "probe_belief_top1_on_support": 0.8671875, "mean_belief_support_size": 5.77734375, "decoder_belief_target_mass": 0.8110651969909668, "decoder_belief_target_nll": 1.9374971389770508, "decoder_belief_top1_on_support": 0.87109375, "mean_decoder_belief_support_size": 5.77734375, "decoder_query_target_mass": 0.9524992108345032, "decoder_query_target_nll": 1.3672468662261963, "decoder_query_top1_on_support": 0.97265625, "mean_decoder_query_support_size": 5.15234375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.48818734288215637, "query_target_nll": 2.4154582023620605, "query_top1_on_support": 0.4765625, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.06494613736867905, "probe_belief_target_nll": 15.040424346923828, "probe_belief_top1_on_support": 0.06640625, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.06509169936180115, "decoder_belief_target_nll": 18.328105926513672, "decoder_belief_top1_on_support": 0.0546875, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.4871097803115845, "decoder_query_target_nll": 2.407170534133911, "decoder_query_top1_on_support": 0.4296875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.4885973334312439, "query_target_nll": 2.413475751876831, "query_top1_on_support": 0.51171875, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.1557888686656952, "probe_belief_target_nll": 11.98361587524414, "probe_belief_top1_on_support": 0.19140625, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.1556256115436554, "decoder_belief_target_nll": 13.276405334472656, "decoder_belief_top1_on_support": 0.16015625, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.4930241107940674, "decoder_query_target_nll": 4.282423973083496, "decoder_query_top1_on_support": 0.49609375, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.49003463983535767, "query_target_nll": 2.405386447906494, "query_top1_on_support": 0.5078125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.2461491823196411, "probe_belief_target_nll": 8.976069450378418, "probe_belief_top1_on_support": 0.24609375, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.24738526344299316, "decoder_belief_target_nll": 9.67303466796875, "decoder_belief_top1_on_support": 0.25390625, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.5458094477653503, "decoder_query_target_nll": 4.3741655349731445, "decoder_query_top1_on_support": 0.5625, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.4893856942653656, "query_target_nll": 2.4095699787139893, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8338966369628906, "probe_belief_target_nll": 1.7960994243621826, "probe_belief_top1_on_support": 0.9453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8495199084281921, "decoder_belief_target_nll": 1.7544828653335571, "decoder_belief_top1_on_support": 0.93359375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9260527491569519, "decoder_query_target_nll": 1.5379242897033691, "decoder_query_top1_on_support": 0.96875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.4893856942653656, "query_target_nll": 2.4095699787139893, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8338966369628906, "probe_belief_target_nll": 1.7960994243621826, "probe_belief_top1_on_support": 0.9453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8495199084281921, "decoder_belief_target_nll": 1.7544828653335571, "decoder_belief_top1_on_support": 0.93359375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9260527491569519, "decoder_query_target_nll": 1.5379242897033691, "decoder_query_top1_on_support": 0.96875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.4893856942653656, "query_target_nll": 2.4095699787139893, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8338966369628906, "probe_belief_target_nll": 1.7960994243621826, "probe_belief_top1_on_support": 0.9453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8495199084281921, "decoder_belief_target_nll": 1.7544828653335571, "decoder_belief_top1_on_support": 0.93359375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9260527491569519, "decoder_query_target_nll": 1.5379242897033691, "decoder_query_top1_on_support": 0.96875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.4893856942653656, "query_target_nll": 2.4095699787139893, "query_top1_on_support": 0.48828125, "mean_query_support_size": 5.3671875, "probe_belief_target_mass": 0.8338966369628906, "probe_belief_target_nll": 1.7960994243621826, "probe_belief_top1_on_support": 0.9453125, "mean_belief_support_size": 5.484375, "decoder_belief_target_mass": 0.8495199084281921, "decoder_belief_target_nll": 1.7544828653335571, "decoder_belief_top1_on_support": 0.93359375, "mean_decoder_belief_support_size": 5.484375, "decoder_query_target_mass": 0.9260527491569519, "decoder_query_target_nll": 1.5379242897033691, "decoder_query_top1_on_support": 0.96875, "mean_decoder_query_support_size": 5.3671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42383742332458496, "query_target_nll": 2.4223387241363525, "query_top1_on_support": 0.40625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.05924174189567566, "probe_belief_target_nll": 14.911308288574219, "probe_belief_top1_on_support": 0.0625, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.05811202526092529, "decoder_belief_target_nll": 18.11775016784668, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.4726559817790985, "decoder_query_target_nll": 14.258946418762207, "decoder_query_top1_on_support": 0.47265625, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42424362897872925, "query_target_nll": 2.4167590141296387, "query_top1_on_support": 0.42578125, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.1584545373916626, "probe_belief_target_nll": 11.188312530517578, "probe_belief_top1_on_support": 0.14453125, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.15650923550128937, "decoder_belief_target_nll": 12.276501655578613, "decoder_belief_top1_on_support": 0.14453125, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.5281824469566345, "decoder_query_target_nll": 7.539258003234863, "decoder_query_top1_on_support": 0.52734375, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.425129771232605, "query_target_nll": 2.4202747344970703, "query_top1_on_support": 0.43359375, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.2907291650772095, "probe_belief_target_nll": 7.748624801635742, "probe_belief_top1_on_support": 0.296875, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.2913394570350647, "decoder_belief_target_nll": 8.316614151000977, "decoder_belief_top1_on_support": 0.29296875, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.588882327079773, "decoder_query_target_nll": 5.207962989807129, "decoder_query_top1_on_support": 0.578125, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42477452754974365, "query_target_nll": 2.4133853912353516, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.806111216545105, "probe_belief_target_nll": 1.8876014947891235, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8246329426765442, "decoder_belief_target_nll": 1.8585118055343628, "decoder_belief_top1_on_support": 0.90234375, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.9485651254653931, "decoder_query_target_nll": 1.1911569833755493, "decoder_query_top1_on_support": 0.98046875, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42477452754974365, "query_target_nll": 2.4133853912353516, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.806111216545105, "probe_belief_target_nll": 1.8876014947891235, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8246329426765442, "decoder_belief_target_nll": 1.8585118055343628, "decoder_belief_top1_on_support": 0.90234375, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.9485651254653931, "decoder_query_target_nll": 1.1911569833755493, "decoder_query_top1_on_support": 0.98046875, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42477452754974365, "query_target_nll": 2.4133853912353516, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.806111216545105, "probe_belief_target_nll": 1.8876014947891235, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8246329426765442, "decoder_belief_target_nll": 1.8585118055343628, "decoder_belief_top1_on_support": 0.90234375, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.9485651254653931, "decoder_query_target_nll": 1.1911569833755493, "decoder_query_top1_on_support": 0.98046875, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.42477452754974365, "query_target_nll": 2.4133853912353516, "query_top1_on_support": 0.41015625, "mean_query_support_size": 4.671875, "probe_belief_target_mass": 0.806111216545105, "probe_belief_target_nll": 1.8876014947891235, "probe_belief_top1_on_support": 0.89453125, "mean_belief_support_size": 5.6015625, "decoder_belief_target_mass": 0.8246329426765442, "decoder_belief_target_nll": 1.8585118055343628, "decoder_belief_top1_on_support": 0.90234375, "mean_decoder_belief_support_size": 5.6015625, "decoder_query_target_mass": 0.9485651254653931, "decoder_query_target_nll": 1.1911569833755493, "decoder_query_top1_on_support": 0.98046875, "mean_decoder_query_support_size": 4.671875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.2527521848678589, "query_target_nll": 2.430842399597168, "query_top1_on_support": 0.26171875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.029376259073615074, "probe_belief_target_nll": 15.472391128540039, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.03020666539669037, "decoder_belief_target_nll": 18.844532012939453, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.2538325786590576, "decoder_query_target_nll": 2.394862651824951, "decoder_query_top1_on_support": 0.28515625, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.2507173418998718, "query_target_nll": 2.4355719089508057, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.0720084086060524, "probe_belief_target_nll": 12.988448143005371, "probe_belief_top1_on_support": 0.06640625, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.07013039290904999, "decoder_belief_target_nll": 14.278857231140137, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.28142625093460083, "decoder_query_target_nll": 4.734046459197998, "decoder_query_top1_on_support": 0.27734375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.25031381845474243, "query_target_nll": 2.435594081878662, "query_top1_on_support": 0.2421875, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.08478601276874542, "probe_belief_target_nll": 11.828655242919922, "probe_belief_top1_on_support": 0.08203125, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.08720474690198898, "decoder_belief_target_nll": 12.993318557739258, "decoder_belief_top1_on_support": 0.09765625, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.3525177240371704, "decoder_query_target_nll": 4.780427932739258, "decoder_query_top1_on_support": 0.37109375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.25084900856018066, "query_target_nll": 2.4277100563049316, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.11025019735097885, "probe_belief_target_nll": 10.880439758300781, "probe_belief_top1_on_support": 0.1171875, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.1103605180978775, "decoder_belief_target_nll": 11.928997039794922, "decoder_belief_top1_on_support": 0.10546875, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.4091343283653259, "decoder_query_target_nll": 4.796308517456055, "decoder_query_top1_on_support": 0.4140625, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.2562483549118042, "query_target_nll": 2.390423536300659, "query_top1_on_support": 0.2578125, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5308836698532104, "probe_belief_target_nll": 2.1198320388793945, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5478077530860901, "decoder_belief_target_nll": 2.0724825859069824, "decoder_belief_top1_on_support": 0.70703125, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.734225869178772, "decoder_query_target_nll": 1.2348437309265137, "decoder_query_top1_on_support": 0.84375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.2562483549118042, "query_target_nll": 2.390423536300659, "query_top1_on_support": 0.2578125, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5308836698532104, "probe_belief_target_nll": 2.1198320388793945, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5478077530860901, "decoder_belief_target_nll": 2.0724825859069824, "decoder_belief_top1_on_support": 0.70703125, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.734225869178772, "decoder_query_target_nll": 1.2348437309265137, "decoder_query_top1_on_support": 0.84375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.2562483549118042, "query_target_nll": 2.390423536300659, "query_top1_on_support": 0.2578125, "mean_query_support_size": 2.78125, "probe_belief_target_mass": 0.5308836698532104, "probe_belief_target_nll": 2.1198320388793945, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 3.45703125, "decoder_belief_target_mass": 0.5478077530860901, "decoder_belief_target_nll": 2.0724825859069824, "decoder_belief_top1_on_support": 0.70703125, "mean_decoder_belief_support_size": 3.45703125, "decoder_query_target_mass": 0.734225869178772, "decoder_query_target_nll": 1.2348437309265137, "decoder_query_top1_on_support": 0.84375, "mean_decoder_query_support_size": 2.78125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.31087014079093933, "query_target_nll": 2.419114351272583, "query_top1_on_support": 0.33203125, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.034830302000045776, "probe_belief_target_nll": 15.882955551147461, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.034113239496946335, "decoder_belief_target_nll": 19.579822540283203, "decoder_belief_top1_on_support": 0.03515625, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.3096124529838562, "decoder_query_target_nll": 2.4132204055786133, "decoder_query_top1_on_support": 0.28125, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.3125934600830078, "query_target_nll": 2.4043102264404297, "query_top1_on_support": 0.34765625, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.04487051069736481, "probe_belief_target_nll": 14.134980201721191, "probe_belief_top1_on_support": 0.0625, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.04497210308909416, "decoder_belief_target_nll": 15.530216217041016, "decoder_belief_top1_on_support": 0.05859375, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.33940738439559937, "decoder_query_target_nll": 5.072040557861328, "decoder_query_top1_on_support": 0.3515625, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.31253814697265625, "query_target_nll": 2.4050917625427246, "query_top1_on_support": 0.3359375, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.07344675809144974, "probe_belief_target_nll": 12.379852294921875, "probe_belief_top1_on_support": 0.0859375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.07447506487369537, "decoder_belief_target_nll": 13.576050758361816, "decoder_belief_top1_on_support": 0.0859375, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.38898181915283203, "decoder_query_target_nll": 4.993934631347656, "decoder_query_top1_on_support": 0.38671875, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.31181800365448, "query_target_nll": 2.406595230102539, "query_top1_on_support": 0.36328125, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.10265067219734192, "probe_belief_target_nll": 11.237008094787598, "probe_belief_top1_on_support": 0.109375, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.10503938794136047, "decoder_belief_target_nll": 12.244726181030273, "decoder_belief_top1_on_support": 0.109375, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.4437401592731476, "decoder_query_target_nll": 5.102283477783203, "decoder_query_top1_on_support": 0.4609375, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.310892254114151, "query_target_nll": 2.4029555320739746, "query_top1_on_support": 0.32421875, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5524153709411621, "probe_belief_target_nll": 2.2298598289489746, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.5475417375564575, "decoder_belief_target_nll": 2.2229840755462646, "decoder_belief_top1_on_support": 0.65625, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7681776285171509, "decoder_query_target_nll": 1.3425644636154175, "decoder_query_top1_on_support": 0.84765625, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.310892254114151, "query_target_nll": 2.4029555320739746, "query_top1_on_support": 0.32421875, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5524153709411621, "probe_belief_target_nll": 2.2298598289489746, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.5475417375564575, "decoder_belief_target_nll": 2.2229840755462646, "decoder_belief_top1_on_support": 0.65625, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7681776285171509, "decoder_query_target_nll": 1.3425644636154175, "decoder_query_top1_on_support": 0.84765625, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 6, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.310892254114151, "query_target_nll": 2.4029555320739746, "query_top1_on_support": 0.32421875, "mean_query_support_size": 3.4140625, "probe_belief_target_mass": 0.5524153709411621, "probe_belief_target_nll": 2.2298598289489746, "probe_belief_top1_on_support": 0.69140625, "mean_belief_support_size": 4.03125, "decoder_belief_target_mass": 0.5475417375564575, "decoder_belief_target_nll": 2.2229840755462646, "decoder_belief_top1_on_support": 0.65625, "mean_decoder_belief_support_size": 4.03125, "decoder_query_target_mass": 0.7681776285171509, "decoder_query_target_nll": 1.3425644636154175, "decoder_query_top1_on_support": 0.84765625, "mean_decoder_query_support_size": 3.4140625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.32961317896842957, "query_target_nll": 2.4136228561401367, "query_top1_on_support": 0.31640625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.03287859633564949, "probe_belief_target_nll": 15.680054664611816, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.033366523683071136, "decoder_belief_target_nll": 19.11514663696289, "decoder_belief_top1_on_support": 0.046875, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.3283906579017639, "decoder_query_target_nll": 2.4081249237060547, "decoder_query_top1_on_support": 0.30078125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3310490846633911, "query_target_nll": 2.416564702987671, "query_top1_on_support": 0.36328125, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.051085639744997025, "probe_belief_target_nll": 13.459341049194336, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.05060480162501335, "decoder_belief_target_nll": 14.878570556640625, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.33536165952682495, "decoder_query_target_nll": 3.7741146087646484, "decoder_query_top1_on_support": 0.33203125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3290514647960663, "query_target_nll": 2.4173152446746826, "query_top1_on_support": 0.33984375, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.0721902996301651, "probe_belief_target_nll": 11.88775634765625, "probe_belief_top1_on_support": 0.08203125, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.07437349855899811, "decoder_belief_target_nll": 13.039655685424805, "decoder_belief_top1_on_support": 0.078125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.33138519525527954, "decoder_query_target_nll": 4.5209879875183105, "decoder_query_top1_on_support": 0.3359375, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3295985758304596, "query_target_nll": 2.4114725589752197, "query_top1_on_support": 0.3515625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.10283654183149338, "probe_belief_target_nll": 10.452611923217773, "probe_belief_top1_on_support": 0.109375, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.10102640092372894, "decoder_belief_target_nll": 11.402389526367188, "decoder_belief_top1_on_support": 0.109375, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.324940025806427, "decoder_query_target_nll": 4.564630508422852, "decoder_query_top1_on_support": 0.33203125, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3306472599506378, "query_target_nll": 2.399394989013672, "query_top1_on_support": 0.34765625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5100086331367493, "probe_belief_target_nll": 2.2678825855255127, "probe_belief_top1_on_support": 0.6484375, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5021605491638184, "decoder_belief_target_nll": 2.2884678840637207, "decoder_belief_top1_on_support": 0.61328125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6484229564666748, "decoder_query_target_nll": 1.6318684816360474, "decoder_query_top1_on_support": 0.74609375, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3306472599506378, "query_target_nll": 2.399394989013672, "query_top1_on_support": 0.34765625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5100086331367493, "probe_belief_target_nll": 2.2678825855255127, "probe_belief_top1_on_support": 0.6484375, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5021605491638184, "decoder_belief_target_nll": 2.2884678840637207, "decoder_belief_top1_on_support": 0.61328125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6484229564666748, "decoder_query_target_nll": 1.6318684816360474, "decoder_query_top1_on_support": 0.74609375, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.3306472599506378, "query_target_nll": 2.399394989013672, "query_top1_on_support": 0.34765625, "mean_query_support_size": 3.6171875, "probe_belief_target_mass": 0.5100086331367493, "probe_belief_target_nll": 2.2678825855255127, "probe_belief_top1_on_support": 0.6484375, "mean_belief_support_size": 3.97265625, "decoder_belief_target_mass": 0.5021605491638184, "decoder_belief_target_nll": 2.2884678840637207, "decoder_belief_top1_on_support": 0.61328125, "mean_decoder_belief_support_size": 3.97265625, "decoder_query_target_mass": 0.6484229564666748, "decoder_query_target_nll": 1.6318684816360474, "decoder_query_top1_on_support": 0.74609375, "mean_decoder_query_support_size": 3.6171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2936413884162903, "query_target_nll": 2.4077587127685547, "query_top1_on_support": 0.32421875, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.031013712286949158, "probe_belief_target_nll": 15.48013687133789, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.03175600618124008, "decoder_belief_target_nll": 18.906930923461914, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.3125000298023224, "decoder_query_target_nll": 15.002533912658691, "decoder_query_top1_on_support": 0.3125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2925530970096588, "query_target_nll": 2.4131641387939453, "query_top1_on_support": 0.30859375, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.04429906606674194, "probe_belief_target_nll": 13.419204711914062, "probe_belief_top1_on_support": 0.0625, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.044472940266132355, "decoder_belief_target_nll": 14.777156829833984, "decoder_belief_top1_on_support": 0.04296875, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.30155909061431885, "decoder_query_target_nll": 8.468896865844727, "decoder_query_top1_on_support": 0.29296875, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2918384075164795, "query_target_nll": 2.4257092475891113, "query_top1_on_support": 0.28125, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.07068156450986862, "probe_belief_target_nll": 12.08123779296875, "probe_belief_top1_on_support": 0.078125, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.07005371898412704, "decoder_belief_target_nll": 13.18807601928711, "decoder_belief_top1_on_support": 0.06640625, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.3299984931945801, "decoder_query_target_nll": 7.030763626098633, "decoder_query_top1_on_support": 0.32421875, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2926408350467682, "query_target_nll": 2.415118455886841, "query_top1_on_support": 0.265625, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.07922109961509705, "probe_belief_target_nll": 10.978706359863281, "probe_belief_top1_on_support": 0.07421875, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.08342334628105164, "decoder_belief_target_nll": 11.95687484741211, "decoder_belief_top1_on_support": 0.0703125, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.3178284764289856, "decoder_query_target_nll": 6.3934855461120605, "decoder_query_top1_on_support": 0.31640625, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2906482219696045, "query_target_nll": 2.4328203201293945, "query_top1_on_support": 0.2578125, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.5127094984054565, "probe_belief_target_nll": 2.2502920627593994, "probe_belief_top1_on_support": 0.640625, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5166929960250854, "decoder_belief_target_nll": 2.237926483154297, "decoder_belief_top1_on_support": 0.62890625, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.6997896432876587, "decoder_query_target_nll": 1.4024161100387573, "decoder_query_top1_on_support": 0.78125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2906482219696045, "query_target_nll": 2.4328203201293945, "query_top1_on_support": 0.2578125, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.5127094984054565, "probe_belief_target_nll": 2.2502920627593994, "probe_belief_top1_on_support": 0.640625, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5166929960250854, "decoder_belief_target_nll": 2.237926483154297, "decoder_belief_top1_on_support": 0.62890625, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.6997896432876587, "decoder_query_target_nll": 1.4024161100387573, "decoder_query_top1_on_support": 0.78125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2906482219696045, "query_target_nll": 2.4328203201293945, "query_top1_on_support": 0.2578125, "mean_query_support_size": 3.2265625, "probe_belief_target_mass": 0.5127094984054565, "probe_belief_target_nll": 2.2502920627593994, "probe_belief_top1_on_support": 0.640625, "mean_belief_support_size": 3.76171875, "decoder_belief_target_mass": 0.5166929960250854, "decoder_belief_target_nll": 2.237926483154297, "decoder_belief_top1_on_support": 0.62890625, "mean_decoder_belief_support_size": 3.76171875, "decoder_query_target_mass": 0.6997896432876587, "decoder_query_target_nll": 1.4024161100387573, "decoder_query_top1_on_support": 0.78125, "mean_decoder_query_support_size": 3.2265625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.21904213726520538, "query_target_nll": 2.4177322387695312, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.02185863070189953, "probe_belief_target_nll": 15.829938888549805, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.021801289170980453, "decoder_belief_target_nll": 19.404380798339844, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.2182275950908661, "decoder_query_target_nll": 2.404773712158203, "decoder_query_top1_on_support": 0.19140625, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.22209003567695618, "query_target_nll": 2.3995065689086914, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.035085104405879974, "probe_belief_target_nll": 13.456113815307617, "probe_belief_top1_on_support": 0.03515625, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.034028310328722, "decoder_belief_target_nll": 14.903675079345703, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.24182386696338654, "decoder_query_target_nll": 4.848419666290283, "decoder_query_top1_on_support": 0.234375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.2218569815158844, "query_target_nll": 2.3958969116210938, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.03457830846309662, "probe_belief_target_nll": 13.002406120300293, "probe_belief_top1_on_support": 0.04296875, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.035994142293930054, "decoder_belief_target_nll": 14.200169563293457, "decoder_belief_top1_on_support": 0.03515625, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.2612351179122925, "decoder_query_target_nll": 5.598180294036865, "decoder_query_top1_on_support": 0.26171875, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.22239068150520325, "query_target_nll": 2.392183303833008, "query_top1_on_support": 0.26171875, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.04123641550540924, "probe_belief_target_nll": 12.26916790008545, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.04567928612232208, "decoder_belief_target_nll": 13.38184642791748, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.27017900347709656, "decoder_query_target_nll": 6.1035943031311035, "decoder_query_top1_on_support": 0.265625, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.21995091438293457, "query_target_nll": 2.4069409370422363, "query_top1_on_support": 0.25, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.06998832523822784, "probe_belief_target_nll": 9.720464706420898, "probe_belief_top1_on_support": 0.0625, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.0678403377532959, "decoder_belief_target_nll": 10.435083389282227, "decoder_belief_top1_on_support": 0.08203125, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.32485198974609375, "decoder_query_target_nll": 5.114333629608154, "decoder_query_top1_on_support": 0.3203125, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.22407379746437073, "query_target_nll": 2.369497299194336, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.3485429286956787, "probe_belief_target_nll": 2.54239559173584, "probe_belief_top1_on_support": 0.48046875, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.33954817056655884, "decoder_belief_target_nll": 2.5364017486572266, "decoder_belief_top1_on_support": 0.40625, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.5901453495025635, "decoder_query_target_nll": 1.4146919250488281, "decoder_query_top1_on_support": 0.68359375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.22407379746437073, "query_target_nll": 2.369497299194336, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.40625, "probe_belief_target_mass": 0.3485429286956787, "probe_belief_target_nll": 2.54239559173584, "probe_belief_top1_on_support": 0.48046875, "mean_belief_support_size": 2.73828125, "decoder_belief_target_mass": 0.33954817056655884, "decoder_belief_target_nll": 2.5364017486572266, "decoder_belief_top1_on_support": 0.40625, "mean_decoder_belief_support_size": 2.73828125, "decoder_query_target_mass": 0.5901453495025635, "decoder_query_target_nll": 1.4146919250488281, "decoder_query_top1_on_support": 0.68359375, "mean_decoder_query_support_size": 2.40625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.19031204283237457, "query_target_nll": 2.428558349609375, "query_top1_on_support": 0.171875, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.025631651282310486, "probe_belief_target_nll": 15.683303833007812, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.02529103308916092, "decoder_belief_target_nll": 19.265213012695312, "decoder_belief_top1_on_support": 0.02734375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.19353154301643372, "decoder_query_target_nll": 2.3961730003356934, "decoder_query_top1_on_support": 0.19921875, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.19548793137073517, "query_target_nll": 2.3941707611083984, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.025664322078227997, "probe_belief_target_nll": 13.8343505859375, "probe_belief_top1_on_support": 0.03515625, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.025997895747423172, "decoder_belief_target_nll": 15.321475982666016, "decoder_belief_top1_on_support": 0.03515625, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.19545599818229675, "decoder_query_target_nll": 4.974857807159424, "decoder_query_top1_on_support": 0.2109375, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.19355882704257965, "query_target_nll": 2.4094724655151367, "query_top1_on_support": 0.20703125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.030690381303429604, "probe_belief_target_nll": 12.731435775756836, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.02965332195162773, "decoder_belief_target_nll": 14.062420845031738, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.20868927240371704, "decoder_query_target_nll": 5.476099014282227, "decoder_query_top1_on_support": 0.1953125, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.191858172416687, "query_target_nll": 2.422646999359131, "query_top1_on_support": 0.17578125, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.03145966678857803, "probe_belief_target_nll": 12.109609603881836, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.030567312613129616, "decoder_belief_target_nll": 13.214247703552246, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.22909708321094513, "decoder_query_target_nll": 5.669642448425293, "decoder_query_top1_on_support": 0.23046875, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.19403687119483948, "query_target_nll": 2.4052278995513916, "query_top1_on_support": 0.21875, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.0519600510597229, "probe_belief_target_nll": 10.783454895019531, "probe_belief_top1_on_support": 0.046875, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.04970889538526535, "decoder_belief_target_nll": 11.533651351928711, "decoder_belief_top1_on_support": 0.0625, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.27455151081085205, "decoder_query_target_nll": 5.349540710449219, "decoder_query_top1_on_support": 0.28125, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.1931993067264557, "query_target_nll": 2.4044370651245117, "query_top1_on_support": 0.19140625, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.3181188106536865, "probe_belief_target_nll": 2.534818410873413, "probe_belief_top1_on_support": 0.39453125, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.3222886025905609, "decoder_belief_target_nll": 2.5025830268859863, "decoder_belief_top1_on_support": 0.37109375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.5406306982040405, "decoder_query_target_nll": 1.4596413373947144, "decoder_query_top1_on_support": 0.578125, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 9, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.1931993067264557, "query_target_nll": 2.4044370651245117, "query_top1_on_support": 0.19140625, "mean_query_support_size": 2.1171875, "probe_belief_target_mass": 0.3181188106536865, "probe_belief_target_nll": 2.534818410873413, "probe_belief_top1_on_support": 0.39453125, "mean_belief_support_size": 2.37109375, "decoder_belief_target_mass": 0.3222886025905609, "decoder_belief_target_nll": 2.5025830268859863, "decoder_belief_top1_on_support": 0.37109375, "mean_decoder_belief_support_size": 2.37109375, "decoder_query_target_mass": 0.5406306982040405, "decoder_query_target_nll": 1.4596413373947144, "decoder_query_top1_on_support": 0.578125, "mean_decoder_query_support_size": 2.1171875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.22772061824798584, "query_target_nll": 2.4115233421325684, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.02324359305202961, "probe_belief_target_nll": 15.806795120239258, "probe_belief_top1_on_support": 0.0390625, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.02214018628001213, "decoder_belief_target_nll": 19.445068359375, "decoder_belief_top1_on_support": 0.0078125, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.22649967670440674, "decoder_query_target_nll": 2.408040761947632, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2298968881368637, "query_target_nll": 2.402158260345459, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.031648699194192886, "probe_belief_target_nll": 13.617276191711426, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.03085542842745781, "decoder_belief_target_nll": 15.162343978881836, "decoder_belief_top1_on_support": 0.0390625, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.23793300986289978, "decoder_query_target_nll": 3.798825740814209, "decoder_query_top1_on_support": 0.23828125, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2297879010438919, "query_target_nll": 2.3979687690734863, "query_top1_on_support": 0.234375, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.027920018881559372, "probe_belief_target_nll": 12.636880874633789, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.026493269950151443, "decoder_belief_target_nll": 13.80246353149414, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.21445763111114502, "decoder_query_target_nll": 4.704691410064697, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2285710871219635, "query_target_nll": 2.404756546020508, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.04323021322488785, "probe_belief_target_nll": 11.360239028930664, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.042316291481256485, "decoder_belief_target_nll": 12.454768180847168, "decoder_belief_top1_on_support": 0.04296875, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.2273169308900833, "decoder_query_target_nll": 4.558669090270996, "decoder_query_top1_on_support": 0.2265625, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2297588437795639, "query_target_nll": 2.400279998779297, "query_top1_on_support": 0.23828125, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.06192636489868164, "probe_belief_target_nll": 9.539604187011719, "probe_belief_top1_on_support": 0.0859375, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.054608870297670364, "decoder_belief_target_nll": 10.154462814331055, "decoder_belief_top1_on_support": 0.0546875, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.21642985939979553, "decoder_query_target_nll": 4.346843719482422, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.22933483123779297, "query_target_nll": 2.4009933471679688, "query_top1_on_support": 0.265625, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.3291372060775757, "probe_belief_target_nll": 2.587831974029541, "probe_belief_top1_on_support": 0.42578125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.3224460482597351, "decoder_belief_target_nll": 2.6188340187072754, "decoder_belief_top1_on_support": 0.40234375, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.4839943051338196, "decoder_query_target_nll": 1.7487281560897827, "decoder_query_top1_on_support": 0.56640625, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.22933483123779297, "query_target_nll": 2.4009933471679688, "query_top1_on_support": 0.265625, "mean_query_support_size": 2.50390625, "probe_belief_target_mass": 0.3291372060775757, "probe_belief_target_nll": 2.587831974029541, "probe_belief_top1_on_support": 0.42578125, "mean_belief_support_size": 2.71875, "decoder_belief_target_mass": 0.3224460482597351, "decoder_belief_target_nll": 2.6188340187072754, "decoder_belief_top1_on_support": 0.40234375, "mean_decoder_belief_support_size": 2.71875, "decoder_query_target_mass": 0.4839943051338196, "decoder_query_target_nll": 1.7487280368804932, "decoder_query_top1_on_support": 0.56640625, "mean_decoder_query_support_size": 2.50390625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2141994833946228, "query_target_nll": 2.4148573875427246, "query_top1_on_support": 0.20703125, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.01694008894264698, "probe_belief_target_nll": 16.115135192871094, "probe_belief_top1_on_support": 0.0078125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.01665453240275383, "decoder_belief_target_nll": 19.824665069580078, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.18359389901161194, "decoder_query_target_nll": 15.415618896484375, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.21323423087596893, "query_target_nll": 2.4216041564941406, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.02123255282640457, "probe_belief_target_nll": 13.581571578979492, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.02140103466808796, "decoder_belief_target_nll": 15.005537986755371, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.20061710476875305, "decoder_query_target_nll": 7.983117580413818, "decoder_query_top1_on_support": 0.1796875, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.214576855301857, "query_target_nll": 2.4147653579711914, "query_top1_on_support": 0.203125, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.024152709171175957, "probe_belief_target_nll": 12.664714813232422, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.023294027894735336, "decoder_belief_target_nll": 13.855112075805664, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.2346598505973816, "decoder_query_target_nll": 6.99997091293335, "decoder_query_top1_on_support": 0.234375, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.21430203318595886, "query_target_nll": 2.415771484375, "query_top1_on_support": 0.1953125, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.026605382561683655, "probe_belief_target_nll": 12.353952407836914, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.031296227127313614, "decoder_belief_target_nll": 13.510624885559082, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.24060049653053284, "decoder_query_target_nll": 6.494307041168213, "decoder_query_top1_on_support": 0.22265625, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.2126978635787964, "query_target_nll": 2.4220402240753174, "query_top1_on_support": 0.19921875, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.05515944957733154, "probe_belief_target_nll": 10.089404106140137, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.050271667540073395, "decoder_belief_target_nll": 10.844111442565918, "decoder_belief_top1_on_support": 0.046875, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.23617571592330933, "decoder_query_target_nll": 5.391231536865234, "decoder_query_top1_on_support": 0.25390625, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.21331632137298584, "query_target_nll": 2.4205260276794434, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.33382347226142883, "probe_belief_target_nll": 2.578495502471924, "probe_belief_top1_on_support": 0.421875, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.32219767570495605, "decoder_belief_target_nll": 2.62894868850708, "decoder_belief_top1_on_support": 0.39453125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.5104910135269165, "decoder_query_target_nll": 1.6539771556854248, "decoder_query_top1_on_support": 0.55859375, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.21331632137298584, "query_target_nll": 2.4205260276794434, "query_top1_on_support": 0.2265625, "mean_query_support_size": 2.35546875, "probe_belief_target_mass": 0.33382347226142883, "probe_belief_target_nll": 2.578495502471924, "probe_belief_top1_on_support": 0.421875, "mean_belief_support_size": 2.48046875, "decoder_belief_target_mass": 0.32219767570495605, "decoder_belief_target_nll": 2.62894868850708, "decoder_belief_top1_on_support": 0.39453125, "mean_decoder_belief_support_size": 2.48046875, "decoder_query_target_mass": 0.5104910135269165, "decoder_query_target_nll": 1.6539771556854248, "decoder_query_top1_on_support": 0.55859375, "mean_decoder_query_support_size": 2.35546875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 0, "n": 256, "query_target_mass": 0.17423376441001892, "query_target_nll": 2.416886329650879, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.017182879149913788, "probe_belief_target_nll": 15.775033950805664, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.017423033714294434, "decoder_belief_target_nll": 19.27115821838379, "decoder_belief_top1_on_support": 0.00390625, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.17322269082069397, "decoder_query_target_nll": 2.4061875343322754, "decoder_query_top1_on_support": 0.1796875, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 1, "n": 256, "query_target_mass": 0.17287515103816986, "query_target_nll": 2.4140663146972656, "query_top1_on_support": 0.1796875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02858828939497471, "probe_belief_target_nll": 13.677520751953125, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02802731841802597, "decoder_belief_target_nll": 14.957172393798828, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.1874464750289917, "decoder_query_target_nll": 4.80465030670166, "decoder_query_top1_on_support": 0.203125, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 2, "n": 256, "query_target_mass": 0.17284885048866272, "query_target_nll": 2.417107582092285, "query_top1_on_support": 0.171875, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.02042873203754425, "probe_belief_target_nll": 13.314788818359375, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.01806330308318138, "decoder_belief_target_nll": 14.41362476348877, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.18118683993816376, "decoder_query_target_nll": 5.794458389282227, "decoder_query_top1_on_support": 0.15625, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 3, "n": 256, "query_target_mass": 0.17307458817958832, "query_target_nll": 2.420621871948242, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.024547846987843513, "probe_belief_target_nll": 12.37460994720459, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02136918157339096, "decoder_belief_target_nll": 13.303157806396484, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.17415502667427063, "decoder_query_target_nll": 6.215707778930664, "decoder_query_top1_on_support": 0.1484375, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 6, "n": 256, "query_target_mass": 0.17324396967887878, "query_target_nll": 2.411909580230713, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.021058298647403717, "probe_belief_target_nll": 11.180856704711914, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.02072800323367119, "decoder_belief_target_nll": 11.908620834350586, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.19177904725074768, "decoder_query_target_nll": 5.741723537445068, "decoder_query_top1_on_support": 0.2109375, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 9, "n": 256, "query_target_mass": 0.17329920828342438, "query_target_nll": 2.4109764099121094, "query_top1_on_support": 0.15625, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.05304304510354996, "probe_belief_target_nll": 9.287503242492676, "probe_belief_top1_on_support": 0.05859375, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.0536532998085022, "decoder_belief_target_nll": 9.755149841308594, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.263613224029541, "decoder_query_target_nll": 4.517159461975098, "decoder_query_top1_on_support": 0.30078125, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "A", "k": 12, "n": 256, "query_target_mass": 0.17809702455997467, "query_target_nll": 2.368511915206909, "query_top1_on_support": 0.203125, "mean_query_support_size": 1.90625, "probe_belief_target_mass": 0.22953221201896667, "probe_belief_target_nll": 2.8278183937072754, "probe_belief_top1_on_support": 0.27734375, "mean_belief_support_size": 2.21484375, "decoder_belief_target_mass": 0.22300027310848236, "decoder_belief_target_nll": 2.865262269973755, "decoder_belief_top1_on_support": 0.26953125, "mean_decoder_belief_support_size": 2.21484375, "decoder_query_target_mass": 0.4637809991836548, "decoder_query_target_nll": 1.5394186973571777, "decoder_query_top1_on_support": 0.52734375, "mean_decoder_query_support_size": 1.90625 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 0, "n": 256, "query_target_mass": 0.1511363536119461, "query_target_nll": 2.425067186355591, "query_top1_on_support": 0.14453125, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.013064919970929623, "probe_belief_target_nll": 15.885766983032227, "probe_belief_top1_on_support": 0.00390625, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.013427208177745342, "decoder_belief_target_nll": 19.543502807617188, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.1541413962841034, "decoder_query_target_nll": 2.3933448791503906, "decoder_query_top1_on_support": 0.19140625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 1, "n": 256, "query_target_mass": 0.15343040227890015, "query_target_nll": 2.4060540199279785, "query_top1_on_support": 0.140625, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.01476304791867733, "probe_belief_target_nll": 13.820089340209961, "probe_belief_top1_on_support": 0.0078125, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.014233927242457867, "decoder_belief_target_nll": 15.381696701049805, "decoder_belief_top1_on_support": 0.01171875, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.14923708140850067, "decoder_query_target_nll": 4.485424995422363, "decoder_query_top1_on_support": 0.10546875, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 2, "n": 256, "query_target_mass": 0.1519204080104828, "query_target_nll": 2.419619083404541, "query_top1_on_support": 0.125, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.015604414977133274, "probe_belief_target_nll": 12.685043334960938, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.015978287905454636, "decoder_belief_target_nll": 13.905414581298828, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.17123499512672424, "decoder_query_target_nll": 5.575024604797363, "decoder_query_top1_on_support": 0.16015625, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 3, "n": 256, "query_target_mass": 0.1548706293106079, "query_target_nll": 2.398648738861084, "query_top1_on_support": 0.15625, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.012064693495631218, "probe_belief_target_nll": 12.29527473449707, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.012357041239738464, "decoder_belief_target_nll": 13.439238548278809, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.17377212643623352, "decoder_query_target_nll": 5.655503749847412, "decoder_query_top1_on_support": 0.1953125, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 6, "n": 256, "query_target_mass": 0.1532955765724182, "query_target_nll": 2.4166088104248047, "query_top1_on_support": 0.18359375, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.019590187817811966, "probe_belief_target_nll": 11.231204986572266, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.021735448390245438, "decoder_belief_target_nll": 12.057817459106445, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.1595156490802765, "decoder_query_target_nll": 5.857226371765137, "decoder_query_top1_on_support": 0.171875, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 9, "n": 256, "query_target_mass": 0.15341895818710327, "query_target_nll": 2.4130406379699707, "query_top1_on_support": 0.1796875, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.04941472411155701, "probe_belief_target_nll": 9.07325553894043, "probe_belief_top1_on_support": 0.046875, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.05029865726828575, "decoder_belief_target_nll": 9.558283805847168, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.24008527398109436, "decoder_query_target_nll": 4.321152210235596, "decoder_query_top1_on_support": 0.25, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "decoder_type": "mlp", "state_dim": 256, "instr_dim": 128, "decoder_rank": 16, "length": 12, "query_type": "B", "k": 12, "n": 256, "query_target_mass": 0.15515020489692688, "query_target_nll": 2.399482250213623, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.6796875, "probe_belief_target_mass": 0.21104197204113007, "probe_belief_target_nll": 2.8728132247924805, "probe_belief_top1_on_support": 0.27734375, "mean_belief_support_size": 1.84765625, "decoder_belief_target_mass": 0.21852131187915802, "decoder_belief_target_nll": 2.832650661468506, "decoder_belief_top1_on_support": 0.31640625, "mean_decoder_belief_support_size": 1.84765625, "decoder_query_target_mass": 0.4445546865463257, "decoder_query_target_nll": 1.5352756977081299, "decoder_query_top1_on_support": 0.51171875, "mean_decoder_query_support_size": 1.6796875 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1781894415616989, "query_target_nll": 2.3907065391540527, "query_top1_on_support": 0.18359375, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.02441384270787239, "probe_belief_target_nll": 15.264070510864258, "probe_belief_top1_on_support": 0.0234375, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.02487998642027378, "decoder_belief_target_nll": 18.83340072631836, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17563709616661072, "decoder_query_target_nll": 2.405383586883545, "decoder_query_top1_on_support": 0.14453125, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1777312159538269, "query_target_nll": 2.395596504211426, "query_top1_on_support": 0.19140625, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.015822896733880043, "probe_belief_target_nll": 13.818219184875488, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.015739966183900833, "decoder_belief_target_nll": 15.384530067443848, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.18732163310050964, "decoder_query_target_nll": 3.9631307125091553, "decoder_query_top1_on_support": 0.1875, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17685647308826447, "query_target_nll": 2.407264232635498, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.020381920039653778, "probe_belief_target_nll": 13.148037910461426, "probe_belief_top1_on_support": 0.01953125, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.019673693925142288, "decoder_belief_target_nll": 14.631010055541992, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17114350199699402, "decoder_query_target_nll": 4.648799419403076, "decoder_query_top1_on_support": 0.15625, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17789098620414734, "query_target_nll": 2.3988900184631348, "query_top1_on_support": 0.19140625, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.015232425183057785, "probe_belief_target_nll": 13.147272109985352, "probe_belief_top1_on_support": 0.015625, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.015157854184508324, "decoder_belief_target_nll": 14.288064956665039, "decoder_belief_top1_on_support": 0.01953125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.1766427755355835, "decoder_query_target_nll": 4.875778675079346, "decoder_query_top1_on_support": 0.171875, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17533519864082336, "query_target_nll": 2.4162180423736572, "query_top1_on_support": 0.1640625, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.026617012917995453, "probe_belief_target_nll": 11.510566711425781, "probe_belief_top1_on_support": 0.02734375, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.02698969468474388, "decoder_belief_target_nll": 12.360770225524902, "decoder_belief_top1_on_support": 0.03125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.1735033392906189, "decoder_query_target_nll": 4.453761100769043, "decoder_query_top1_on_support": 0.18359375, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1759822964668274, "query_target_nll": 2.412839412689209, "query_top1_on_support": 0.1640625, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.047662779688835144, "probe_belief_target_nll": 9.514201164245605, "probe_belief_top1_on_support": 0.0703125, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.04184507578611374, "decoder_belief_target_nll": 10.263879776000977, "decoder_belief_top1_on_support": 0.05078125, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.17361947894096375, "decoder_query_target_nll": 4.112119674682617, "decoder_query_top1_on_support": 0.1875, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1784052848815918, "query_target_nll": 2.4019787311553955, "query_top1_on_support": 0.234375, "mean_query_support_size": 1.93359375, "probe_belief_target_mass": 0.2339688539505005, "probe_belief_target_nll": 2.7716493606567383, "probe_belief_top1_on_support": 0.28125, "mean_belief_support_size": 2.0, "decoder_belief_target_mass": 0.22610749304294586, "decoder_belief_target_nll": 2.755117893218994, "decoder_belief_top1_on_support": 0.29296875, "mean_decoder_belief_support_size": 2.0, "decoder_query_target_mass": 0.3515675663948059, "decoder_query_target_nll": 1.858444333076477, "decoder_query_top1_on_support": 0.43359375, "mean_decoder_query_support_size": 1.93359375 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1769540011882782, "query_target_nll": 2.418069362640381, "query_top1_on_support": 0.17578125, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.02151389606297016, "probe_belief_target_nll": 15.654606819152832, "probe_belief_top1_on_support": 0.03125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.02078099548816681, "decoder_belief_target_nll": 19.117626190185547, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.2148434966802597, "decoder_query_target_nll": 14.828850746154785, "decoder_query_top1_on_support": 0.21484375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17684608697891235, "query_target_nll": 2.429981231689453, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.015436114743351936, "probe_belief_target_nll": 14.412967681884766, "probe_belief_top1_on_support": 0.01171875, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.016259633004665375, "decoder_belief_target_nll": 15.778497695922852, "decoder_belief_top1_on_support": 0.01171875, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.18107256293296814, "decoder_query_target_nll": 8.103097915649414, "decoder_query_top1_on_support": 0.16796875, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.176822692155838, "query_target_nll": 2.4244003295898438, "query_top1_on_support": 0.15234375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.01657245121896267, "probe_belief_target_nll": 13.47033977508545, "probe_belief_top1_on_support": 0.0078125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.01692991331219673, "decoder_belief_target_nll": 14.718857765197754, "decoder_belief_top1_on_support": 0.0234375, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.15774005651474, "decoder_query_target_nll": 6.989782333374023, "decoder_query_top1_on_support": 0.15234375, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1766432374715805, "query_target_nll": 2.4209189414978027, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.013794470578432083, "probe_belief_target_nll": 12.53950023651123, "probe_belief_top1_on_support": 0.0078125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.01464779395610094, "decoder_belief_target_nll": 13.642139434814453, "decoder_belief_top1_on_support": 0.01171875, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.1650940626859665, "decoder_query_target_nll": 6.407591342926025, "decoder_query_top1_on_support": 0.171875, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17773611843585968, "query_target_nll": 2.4125969409942627, "query_top1_on_support": 0.1484375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.020603442564606667, "probe_belief_target_nll": 11.361099243164062, "probe_belief_top1_on_support": 0.01171875, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.020408697426319122, "decoder_belief_target_nll": 12.085891723632812, "decoder_belief_top1_on_support": 0.015625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.1804923713207245, "decoder_query_target_nll": 5.079685688018799, "decoder_query_top1_on_support": 0.1875, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.17804992198944092, "query_target_nll": 2.413273334503174, "query_top1_on_support": 0.18359375, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.04830275848507881, "probe_belief_target_nll": 9.145145416259766, "probe_belief_top1_on_support": 0.05078125, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.05051541328430176, "decoder_belief_target_nll": 9.565871238708496, "decoder_belief_top1_on_support": 0.05859375, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.20314311981201172, "decoder_query_target_nll": 4.706549644470215, "decoder_query_top1_on_support": 0.2421875, "mean_decoder_query_support_size": 1.95703125 }, { "model": "dense", "variant": "pilot_gru_mlp_d256", "supervision": "teacher_belief", "transition": "gru", "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": 0.1759767234325409, "query_target_nll": 2.435214042663574, "query_top1_on_support": 0.1640625, "mean_query_support_size": 1.95703125, "probe_belief_target_mass": 0.20323260128498077, "probe_belief_target_nll": 2.898895740509033, "probe_belief_top1_on_support": 0.25, "mean_belief_support_size": 2.17578125, "decoder_belief_target_mass": 0.21387723088264465, "decoder_belief_target_nll": 2.86985445022583, "decoder_belief_top1_on_support": 0.2890625, "mean_decoder_belief_support_size": 2.17578125, "decoder_query_target_mass": 0.3963977098464966, "decoder_query_target_nll": 1.7716608047485352, "decoder_query_top1_on_support": 0.4609375, "mean_decoder_query_support_size": 1.95703125 } ] } ], "checkpoints": [ "large_artifacts/dense_teacher_distillation/checkpoints/pilot_gru_mlp_d256/checkpoint_final.pt" ] }