{ "benchmark": "Temporary variable binding", "training_examples": 16000, "results": { "fast_weight": { "parameters": 2508, "training_epochs": 20, "four_pairs_12_distractors": { "accuracy": 1.0, "cross_entropy": 0.07871694164350629 }, "eight_pairs_12_distractors": { "accuracy": 1.0, "cross_entropy": 0.09045482566580176 }, "four_pairs_64_distractors": { "accuracy": 1.0, "cross_entropy": 0.07799763092771173 }, "eight_pairs_64_distractors": { "accuracy": 0.99975, "cross_entropy": 0.09526938293129206 } }, "gru": { "parameters": 3050, "training_epochs": 50, "four_pairs_12_distractors": { "accuracy": 0.374, "cross_entropy": 1.337967962026596 }, "eight_pairs_12_distractors": { "accuracy": 0.27025, "cross_entropy": 2.0145242735743523 }, "four_pairs_64_distractors": { "accuracy": 0.3115, "cross_entropy": 2.1618038713932037 }, "eight_pairs_64_distractors": { "accuracy": 0.23825, "cross_entropy": 2.5799436271190643 } } }, "training_history": { "fast_weight": [ { "variant": "fast_weight", "epoch": 1, "training_loss": 1.0295030027627945, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 2, "training_loss": 0.030936013227180828, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 3, "training_loss": 0.010835887420745123, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 4, "training_loss": 0.006198568949623714, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 5, "training_loss": 0.004087505533197333, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 6, "training_loss": 0.002923791433521916, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 7, "training_loss": 0.002205265745047539, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 8, "training_loss": 0.0017280159813780633, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 9, "training_loss": 0.0013937751747786053, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 10, "training_loss": 0.001148996146632329, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 11, "training_loss": 0.0009644523434828789, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 12, "training_loss": 0.0008224385064317002, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 13, "training_loss": 0.0007094257014123575, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 14, "training_loss": 0.0006176355989679457, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 15, "training_loss": 0.0005433608903475698, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 16, "training_loss": 0.00048117371394284185, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 17, "training_loss": 0.000429233452046497, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 18, "training_loss": 0.0003849036833603999, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 19, "training_loss": 0.00034724543285038736, "validation_accuracy": 1.0 }, { "variant": "fast_weight", "epoch": 20, "training_loss": 0.00031471504258834536, "validation_accuracy": 1.0 } ], "gru": [ { "variant": "gru", "epoch": 1, "training_loss": 2.30176459796845, "validation_accuracy": 0.148 }, { "variant": "gru", "epoch": 2, "training_loss": 2.2673269188593306, "validation_accuracy": 0.181 }, { "variant": "gru", "epoch": 3, "training_loss": 2.20308005999005, "validation_accuracy": 0.214 }, { "variant": "gru", "epoch": 4, "training_loss": 2.073779126954457, "validation_accuracy": 0.275 }, { "variant": "gru", "epoch": 5, "training_loss": 1.9181506936512296, "validation_accuracy": 0.324 }, { "variant": "gru", "epoch": 6, "training_loss": 1.7754394440423875, "validation_accuracy": 0.3175 }, { "variant": "gru", "epoch": 7, "training_loss": 1.6792653269237943, "validation_accuracy": 0.3405 }, { "variant": "gru", "epoch": 8, "training_loss": 1.6136303837337191, "validation_accuracy": 0.3415 }, { "variant": "gru", "epoch": 9, "training_loss": 1.5580230913464985, "validation_accuracy": 0.355 }, { "variant": "gru", "epoch": 10, "training_loss": 1.5131285304114932, "validation_accuracy": 0.349 }, { "variant": "gru", "epoch": 11, "training_loss": 1.4721362969231984, "validation_accuracy": 0.351 }, { "variant": "gru", "epoch": 12, "training_loss": 1.4381263615593078, "validation_accuracy": 0.371 }, { "variant": "gru", "epoch": 13, "training_loss": 1.4131997729104662, "validation_accuracy": 0.369 }, { "variant": "gru", "epoch": 14, "training_loss": 1.3921367497671218, "validation_accuracy": 0.366 }, { "variant": "gru", "epoch": 15, "training_loss": 1.3752350996411036, "validation_accuracy": 0.36 }, { "variant": "gru", "epoch": 16, "training_loss": 1.3600610343236772, "validation_accuracy": 0.375 }, { "variant": "gru", "epoch": 17, "training_loss": 1.350090401513236, "validation_accuracy": 0.3675 }, { "variant": "gru", "epoch": 18, "training_loss": 1.3397450371394082, "validation_accuracy": 0.375 }, { "variant": "gru", "epoch": 19, "training_loss": 1.3330339874540056, "validation_accuracy": 0.3735 }, { "variant": "gru", "epoch": 20, "training_loss": 1.3186499731881278, "validation_accuracy": 0.3745 }, { "variant": "gru", "epoch": 21, "training_loss": 1.3137422989285181, "validation_accuracy": 0.376 }, { "variant": "gru", "epoch": 22, "training_loss": 1.3108702462816995, "validation_accuracy": 0.3715 }, { "variant": "gru", "epoch": 23, "training_loss": 1.3006561313356673, "validation_accuracy": 0.3715 }, { "variant": "gru", "epoch": 24, "training_loss": 1.291312327460637, "validation_accuracy": 0.369 }, { "variant": "gru", "epoch": 25, "training_loss": 1.2901321441408187, "validation_accuracy": 0.374 }, { "variant": "gru", "epoch": 26, "training_loss": 1.283520429853409, "validation_accuracy": 0.374 }, { "variant": "gru", "epoch": 27, "training_loss": 1.2761712244578771, "validation_accuracy": 0.3745 }, { "variant": "gru", "epoch": 28, "training_loss": 1.2719707943144298, "validation_accuracy": 0.3785 }, { "variant": "gru", "epoch": 29, "training_loss": 1.26511964343843, "validation_accuracy": 0.375 }, { "variant": "gru", "epoch": 30, "training_loss": 1.2616949081420898, "validation_accuracy": 0.378 }, { "variant": "gru", "epoch": 31, "training_loss": 1.2597541241418748, "validation_accuracy": 0.3705 }, { "variant": "gru", "epoch": 32, "training_loss": 1.2553172735940843, "validation_accuracy": 0.3755 }, { "variant": "gru", "epoch": 33, "training_loss": 1.250368530788119, "validation_accuracy": 0.368 }, { "variant": "gru", "epoch": 34, "training_loss": 1.2492833989007133, "validation_accuracy": 0.3785 }, { "variant": "gru", "epoch": 35, "training_loss": 1.2454108302555387, "validation_accuracy": 0.379 }, { "variant": "gru", "epoch": 36, "training_loss": 1.2419150027017745, "validation_accuracy": 0.3835 }, { "variant": "gru", "epoch": 37, "training_loss": 1.2380726621264504, "validation_accuracy": 0.383 }, { "variant": "gru", "epoch": 38, "training_loss": 1.2354776140243289, "validation_accuracy": 0.3705 }, { "variant": "gru", "epoch": 39, "training_loss": 1.2319395958431183, "validation_accuracy": 0.3765 }, { "variant": "gru", "epoch": 40, "training_loss": 1.2327304643297952, "validation_accuracy": 0.3855 }, { "variant": "gru", "epoch": 41, "training_loss": 1.2301562305480715, "validation_accuracy": 0.378 }, { "variant": "gru", "epoch": 42, "training_loss": 1.2272724480856032, "validation_accuracy": 0.376 }, { "variant": "gru", "epoch": 43, "training_loss": 1.223879613573589, "validation_accuracy": 0.3785 }, { "variant": "gru", "epoch": 44, "training_loss": 1.220575767850119, "validation_accuracy": 0.379 }, { "variant": "gru", "epoch": 45, "training_loss": 1.2178495970983354, "validation_accuracy": 0.3805 }, { "variant": "gru", "epoch": 46, "training_loss": 1.21574023980943, "validation_accuracy": 0.371 }, { "variant": "gru", "epoch": 47, "training_loss": 1.2135314487275624, "validation_accuracy": 0.376 }, { "variant": "gru", "epoch": 48, "training_loss": 1.2135897912676372, "validation_accuracy": 0.3765 }, { "variant": "gru", "epoch": 49, "training_loss": 1.210650818688529, "validation_accuracy": 0.377 }, { "variant": "gru", "epoch": 50, "training_loss": 1.209133299570235, "validation_accuracy": 0.3735 } ] } }