{
  "architecture": {
    "adaptive_apical_parameters": 0,
    "adaptive_feedback_parameters": 267904,
    "base_width": 16,
    "blocks_per_stage": 3,
    "bn_eps": 1e-05,
    "bn_momentum": 0.1,
    "depth": 20,
    "family": "CIFAR 6n+2 ResNet, option-A shortcuts",
    "fixed_feedback_parameters": 0,
    "fixed_traffic_coefficients": 0,
    "forward_parameters": 269722,
    "hidden_shapes": [
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        16,
        32,
        32
      ],
      [
        32,
        16,
        16
      ],
      [
        32,
        16,
        16
      ],
      [
        32,
        16,
        16
      ],
      [
        32,
        16,
        16
      ],
      [
        32,
        16,
        16
      ],
      [
        32,
        16,
        16
      ],
      [
        64,
        8,
        8
      ],
      [
        64,
        8,
        8
      ],
      [
        64,
        8,
        8
      ],
      [
        64,
        8,
        8
      ],
      [
        64,
        8,
        8
      ],
      [
        64,
        8,
        8
      ]
    ],
    "normalization": "batchnorm",
    "predictor_parameters": 0,
    "residual_scale": 1.0,
    "vectorizer_mode": null,
    "vectorizer_parameters": 0
  },
  "args": {
    "a_scale": 1.0,
    "a_warmup_steps": 0,
    "alignment_probe": 32,
    "apical_calibration_mode": "unit_targets",
    "apical_seed": null,
    "augment_train": 1,
    "batch_size": 128,
    "bn_eps": 1e-05,
    "bn_momentum": 0.1,
    "data_dir": "/home/yurenh2/sdrn/data",
    "depth": 20,
    "device": "cuda",
    "epochs": 20,
    "eta_A": 0.01,
    "eta_P": 0.01,
    "eval_every": 0,
    "eval_split": "validation",
    "learn_P": 0,
    "loader_seed": 0,
    "lr": 0.1,
    "lr_gamma": 0.1,
    "lr_milestones": "100,150",
    "lr_schedule": "step",
    "max_steps": 0,
    "mirror_batch_size": 1,
    "mirror_eta": 0.1,
    "mirror_every": 16,
    "mirror_noise_std": 1.0,
    "mirror_seed": 3000,
    "mirror_warmup_steps": 0,
    "mode": "kp",
    "momentum": 0.9,
    "normalization": "batchnorm",
    "nuisance_scale": 0.0,
    "out": "results/kp_short/kp.json",
    "output_lr": 0.1,
    "pert_directions": 1,
    "pert_every": 4,
    "pert_sigma": 0.01,
    "perturb_seed": 1000,
    "predictor_warmup_steps": 0,
    "residual_scale": null,
    "seed": 0,
    "split_seed": 2027,
    "train_limit": 0,
    "use_residual": 1,
    "val_examples": 5000,
    "vectorizer_mode": "spatial_template",
    "warmup_epochs": 0,
    "weight_decay": 0.0001,
    "weight_scale": 1.0,
    "width": 16
  },
  "calibration_metric_space": "reciprocal_local_activity_products",
  "counters": {
    "apical_warmup_examples": 0,
    "calibration_event_examples": 0,
    "causal_scalar_observations": 0,
    "logical_batch_loss_queries": 0,
    "mirror_conv_examples": 0,
    "mirror_events": 0,
    "mirror_readout_examples": 0,
    "ordinary_examples": 900000,
    "per_example_loss_terms": 0,
    "perturbation_events": 0,
    "perturbation_forward_examples": 0,
    "predictor_warmup_examples": 0
  },
  "diagnostics": {
    "early_third_mean": 0.8855825364589691,
    "feedback_forward_cosine": [
      0.9264333248138428,
      0.9220218658447266,
      0.9038588404655457,
      0.8975453972816467,
      0.9213621616363525,
      0.8933338522911072,
      0.8915912508964539,
      0.9265133142471313,
      0.9061511754989624,
      0.8942975997924805,
      0.9047679901123047,
      0.8851061463356018,
      0.8851138353347778,
      0.9171422719955444,
      0.9053213000297546,
      0.8831733465194702,
      0.8767958879470825,
      0.7925058007240295,
      0.9866083860397339
    ],
    "feedback_forward_norm_ratio": [
      0.9885096549987793,
      1.0436758995056152,
      0.9917821884155273,
      1.058516263961792,
      1.0159763097763062,
      1.0456026792526245,
      1.008077621459961,
      1.0261797904968262,
      1.0106136798858643,
      1.0411553382873535,
      1.0132758617401123,
      1.0498096942901611,
      1.0225006341934204,
      1.0299837589263916,
      1.011872410774231,
      1.0414197444915771,
      1.0175153017044067,
      1.0444023609161377,
      1.090652585029602
    ],
    "feedback_forward_relative_error": [
      0.3815428614616394,
      0.4058021008968353,
      0.43677207827568054,
      0.46938687562942505,
      0.4000545144081116,
      0.47448983788490295,
      0.46758344769477844,
      0.3892383575439453,
      0.43566325306892395,
      0.4709555506706238,
      0.4395098090171814,
      0.49367427825927734,
      0.48523032665252686,
      0.4142261743545532,
      0.4378886818885803,
      0.49502187967300415,
      0.5010300874710083,
      0.6598381400108337,
      0.1934662163257599
    ],
    "innovation_negative_gradient_cosine": [
      0.8906962275505066,
      0.8764338493347168,
      0.8894688487052917,
      0.8657850027084351,
      0.8935482501983643,
      0.8975630402565002,
      0.9018489122390747,
      0.9003725051879883,
      0.9135095477104187,
      0.8963901996612549,
      0.9183286428451538,
      0.9015354514122009,
      0.9177113771438599,
      0.9407275915145874,
      0.9454699754714966,
      0.9456664323806763,
      0.9667372107505798,
      0.9770752787590027,
      0.9845573902130127
    ],
    "mean_feedback_forward_cosine": 0.9010338814635026,
    "mean_feedback_forward_relative_error": 0.44480918269408376,
    "normalization_state": "training_batch_stats_without_running_update",
    "raw_negative_gradient_cosine": [
      0.8906962275505066,
      0.8764338493347168,
      0.8894688487052917,
      0.8657850027084351,
      0.8935482501983643,
      0.8975630402565002,
      0.9018489122390747,
      0.9003725051879883,
      0.9135095477104187,
      0.8963901996612549,
      0.9183286428451538,
      0.9015354514122009,
      0.9177113771438599,
      0.9407275915145874,
      0.9454699754714966,
      0.9456664323806763,
      0.9667372107505798,
      0.9770752787590027,
      0.9845573902130127
    ],
    "teaching_negative_gradient_cosine": [
      0.8906962275505066,
      0.8764338493347168,
      0.8894688487052917,
      0.8657850027084351,
      0.8935482501983643,
      0.8975630402565002,
      0.9018489122390747,
      0.9003725051879883,
      0.9135095477104187,
      0.8963901996612549,
      0.9183286428451538,
      0.9015354514122009,
      0.9177113771438599,
      0.9407275915145874,
      0.9454699754714966,
      0.9456664323806763,
      0.9667372107505798,
      0.9770752787590027,
      0.9845573902130127
    ],
    "wall_s": 0.1368110179901123
  },
  "epochs": [
    {
      "epoch": 1,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.319318175315857,
        "mean_feedback_forward_cosine": 0.26153333798835154,
        "mean_feedback_forward_relative_error": 1.2144870224751925,
        "min_feedback_forward_cosine": 0.1322619915008545
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 352,
      "train_examples": 45000,
      "train_loss": 1.831467347378201
    },
    {
      "epoch": 2,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.2504557371139526,
        "mean_feedback_forward_cosine": 0.40932882773248774,
        "mean_feedback_forward_relative_error": 1.0874902041334855,
        "min_feedback_forward_cosine": 0.22793743014335632
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 704,
      "train_examples": 45000,
      "train_loss": 1.366863529311286
    },
    {
      "epoch": 3,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.19105064868927,
        "mean_feedback_forward_cosine": 0.5041392759272927,
        "mean_feedback_forward_relative_error": 0.9971762236795927,
        "min_feedback_forward_cosine": 0.30597037076950073
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 1056,
      "train_examples": 45000,
      "train_loss": 1.066310328886244
    },
    {
      "epoch": 4,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.1481163501739502,
        "mean_feedback_forward_cosine": 0.5715355308432328,
        "mean_feedback_forward_relative_error": 0.9270231566931072,
        "min_feedback_forward_cosine": 0.3590141832828522
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 1408,
      "train_examples": 45000,
      "train_loss": 0.8910715007040235
    },
    {
      "epoch": 5,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.1075339317321777,
        "mean_feedback_forward_cosine": 0.62295485170264,
        "mean_feedback_forward_relative_error": 0.8701311349868774,
        "min_feedback_forward_cosine": 0.40619510412216187
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 1760,
      "train_examples": 45000,
      "train_loss": 0.7831426847881741
    },
    {
      "epoch": 6,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.0683236122131348,
        "mean_feedback_forward_cosine": 0.6647130376414249,
        "mean_feedback_forward_relative_error": 0.8211206464391005,
        "min_feedback_forward_cosine": 0.44973599910736084
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 2112,
      "train_examples": 45000,
      "train_loss": 0.7067856804741753
    },
    {
      "epoch": 7,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 1.0321979522705078,
        "mean_feedback_forward_cosine": 0.6994027605182246,
        "mean_feedback_forward_relative_error": 0.7776816581424913,
        "min_feedback_forward_cosine": 0.487300843000412
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 2464,
      "train_examples": 45000,
      "train_loss": 0.6526998540454441
    },
    {
      "epoch": 8,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.9973180890083313,
        "mean_feedback_forward_cosine": 0.7283705755283958,
        "mean_feedback_forward_relative_error": 0.7394031474464818,
        "min_feedback_forward_cosine": 0.5232464075088501
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 2816,
      "train_examples": 45000,
      "train_loss": 0.6056941405296326
    },
    {
      "epoch": 9,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.9644169211387634,
        "mean_feedback_forward_cosine": 0.7529234384235582,
        "mean_feedback_forward_relative_error": 0.705177787103151,
        "min_feedback_forward_cosine": 0.5548381805419922
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 3168,
      "train_examples": 45000,
      "train_loss": 0.5672190690252517
    },
    {
      "epoch": 10,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.9325018525123596,
        "mean_feedback_forward_cosine": 0.7752530323831659,
        "mean_feedback_forward_relative_error": 0.6724935864147387,
        "min_feedback_forward_cosine": 0.5845517516136169
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 3520,
      "train_examples": 45000,
      "train_loss": 0.5412863729900784
    },
    {
      "epoch": 11,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.9008499383926392,
        "mean_feedback_forward_cosine": 0.7944865289487337,
        "mean_feedback_forward_relative_error": 0.6431144601420352,
        "min_feedback_forward_cosine": 0.6125654578208923
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 3872,
      "train_examples": 45000,
      "train_loss": 0.5144231326527066
    },
    {
      "epoch": 12,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.870076596736908,
        "mean_feedback_forward_cosine": 0.8117237467514841,
        "mean_feedback_forward_relative_error": 0.6155103241142473,
        "min_feedback_forward_cosine": 0.6389982104301453
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 4224,
      "train_examples": 45000,
      "train_loss": 0.4893017247200012
    },
    {
      "epoch": 13,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.8421436548233032,
        "mean_feedback_forward_cosine": 0.8270191926705209,
        "mean_feedback_forward_relative_error": 0.5898554764295879,
        "min_feedback_forward_cosine": 0.662228524684906
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 4576,
      "train_examples": 45000,
      "train_loss": 0.4666704408009847
    },
    {
      "epoch": 14,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.8131178021430969,
        "mean_feedback_forward_cosine": 0.8408146061395344,
        "mean_feedback_forward_relative_error": 0.5656935533410624,
        "min_feedback_forward_cosine": 0.6854491233825684
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 4928,
      "train_examples": 45000,
      "train_loss": 0.4554117670377096
    },
    {
      "epoch": 15,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.7860043048858643,
        "mean_feedback_forward_cosine": 0.8532820532196447,
        "mean_feedback_forward_relative_error": 0.5429034452689322,
        "min_feedback_forward_cosine": 0.7059769034385681
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 5280,
      "train_examples": 45000,
      "train_loss": 0.437559742252032
    },
    {
      "epoch": 16,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.7597430944442749,
        "mean_feedback_forward_cosine": 0.8647166176846153,
        "mean_feedback_forward_relative_error": 0.5210003123471612,
        "min_feedback_forward_cosine": 0.7249040603637695
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 5632,
      "train_examples": 45000,
      "train_loss": 0.4244806206067403
    },
    {
      "epoch": 17,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.7334027886390686,
        "mean_feedback_forward_cosine": 0.8751521863435444,
        "mean_feedback_forward_relative_error": 0.5003075152635574,
        "min_feedback_forward_cosine": 0.7437110543251038
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 5984,
      "train_examples": 45000,
      "train_loss": 0.4090740834448073
    },
    {
      "epoch": 18,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.7081427574157715,
        "mean_feedback_forward_cosine": 0.8844657948142604,
        "mean_feedback_forward_relative_error": 0.4810000712934293,
        "min_feedback_forward_cosine": 0.7609646320343018
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 6336,
      "train_examples": 45000,
      "train_loss": 0.39670369214481777
    },
    {
      "epoch": 19,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.6829538345336914,
        "mean_feedback_forward_cosine": 0.8932415654784754,
        "mean_feedback_forward_relative_error": 0.4622263304497066,
        "min_feedback_forward_cosine": 0.7776626348495483
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 6688,
      "train_examples": 45000,
      "train_loss": 0.3911194394800398
    },
    {
      "epoch": 20,
      "feedback_tracking": {
        "max_feedback_forward_relative_error": 0.6598381400108337,
        "mean_feedback_forward_cosine": 0.9010338814635026,
        "mean_feedback_forward_relative_error": 0.44480918269408376,
        "min_feedback_forward_cosine": 0.7925058007240295
      },
      "lr": 0.1,
      "output_lr": 0.1,
      "step": 7040,
      "train_examples": 45000,
      "train_loss": 0.3764604419231415
    }
  ],
  "evaluation_protocol": {
    "test_evaluations": 0,
    "test_used_for_selection": false,
    "validation_evaluations": 1
  },
  "final": {
    "accuracy": 0.8266,
    "epoch": 20,
    "evaluation_split": "validation",
    "finite": true,
    "loss": 0.5224007934570313,
    "step": 7040
  },
  "hardware": {
    "cuda_device_name": "NVIDIA GeForce GTX 1080",
    "cuda_visible_devices": "7",
    "device": "cuda",
    "device_total_memory_bytes": 8507949056,
    "peak_memory_allocated_bytes": 2162790400,
    "peak_memory_reserved_bytes": 2866806784,
    "torch_version": "2.3.1+cu118"
  },
  "protocol_family": "oral_a_cifar_local_resnet_development",
  "provenance": {
    "git_commit": "8f420f256aef160d79e3a9620a92ae156f06ef74",
    "git_tracked_dirty": false
  },
  "schema_version": 1,
  "split": {
    "cifar_source_files": [
      {
        "bytes": 31035704,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/data_batch_1",
        "sha256": "54636561a3ce25bd3e19253c6b0d8538147b0ae398331ac4a2d86c6d987368cd"
      },
      {
        "bytes": 31035320,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/data_batch_2",
        "sha256": "766b2cef9fbc745cf056b3152224f7cf77163b330ea9a15f9392beb8b89bc5a8"
      },
      {
        "bytes": 31035999,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/data_batch_3",
        "sha256": "0f00d98ebfb30b3ec0ad19f9756dc2630b89003e10525f5e148445e82aa6a1f9"
      },
      {
        "bytes": 31035696,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/data_batch_4",
        "sha256": "3f7bb240661948b8f4d53e36ec720d8306f5668bd0071dcb4e6c947f78e9682b"
      },
      {
        "bytes": 31035623,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/data_batch_5",
        "sha256": "d91802434d8376bbaeeadf58a737e3a1b12ac839077e931237e0dcd43adcb154"
      },
      {
        "bytes": 31035526,
        "path": "/home/yurenh2/sdrn/data/cifar-10-batches-py/test_batch",
        "sha256": "f53d8d457504f7cff4ea9e021afcf0e0ad8e24a91f3fc42091b8adef61157831"
      }
    ],
    "dataset": "cifar10",
    "evaluation_split": "validation",
    "input_layout": "NCHW",
    "input_shape": [
      3,
      32,
      32
    ],
    "loader_seed": 0,
    "normalization_mean": [
      0.49140000343322754,
      0.4821999967098236,
      0.4465000033378601
    ],
    "normalization_std": [
      0.24699999392032623,
      0.2434999942779541,
      0.26159998774528503
    ],
    "split_from_training_only": true,
    "split_seed": 2027,
    "test_examples": 10000,
    "train_examples": 45000,
    "training_augmentation": "random_crop_32_padding_4_zero_then_horizontal_flip_p0.5",
    "validation_class_counts": {
      "0": 500,
      "1": 500,
      "2": 500,
      "3": 500,
      "4": 500,
      "5": 500,
      "6": 500,
      "7": 500,
      "8": 500,
      "9": 500
    },
    "validation_examples": 5000,
    "validation_index_sha256": "8328b206a97c420e49e54e3eca4abe3274c4756b084355784ea3fb8059e4515b"
  },
  "timing": {
    "apical_warmup_wall_s": 0.0,
    "evaluation_wall_s": 0.36439943313598633,
    "mirror_warmup_wall_s": 0.0,
    "predictor_warmup_wall_s": 0.0,
    "timing_excludes_data_loading_hashing_and_model_construction": true,
    "total_timed_wall_s": 558.1345100402832,
    "train_wall_s": 557.5914545059204
  },
  "work": {
    "apical_macs_per_example": 40108672,
    "causal_scalar_observations": 0,
    "components": {
      "apical_projection_macs": 36097804800000,
      "apical_regression_macs": 0,
      "bp_reverse_macs_estimate": 0,
      "kp_reciprocal_correlation_macs": 36097804800000,
      "local_weight_correlation_macs": 36495936000000,
      "mirror_feedback_prediction_macs": 0,
      "mirror_local_correlation_macs": 0,
      "mirror_response_macs": 0,
      "ordinary_forward_macs": 36495936000000,
      "perturbation_forward_macs": 0,
      "warmup_clean_forward_macs": 0
    },
    "definition": "multiply-accumulates in conv/linear maps; one local weight correlation equals one forward-weight MAC count; BP reverse is estimated as one weight-gradient plus one activation-gradient convolution per forward convolution; elementwise nonlinearities and optimizer arithmetic excluded",
    "forward_macs_per_example": 40551040,
    "logical_batch_loss_queries": 0,
    "mirror_probe_examples": 0,
    "mirror_readout_probe_examples": 0,
    "per_example_cross_entropy_terms": 0,
    "total_clean_forward_examples": 900000,
    "total_forward_equivalent_examples": 900000,
    "total_macs_estimate": 145187481600000
  }
}