results: close Oral-A v3 causal-capture gate

1 files changed, 393 insertions, 0 deletions

diff --git a/results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json b/results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json
new file mode 100644
index 0000000..7c5b244
--- /dev/null
+++ b/results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json
@@ -0,0 +1,393 @@
+{
+  "apical_warmup": {
+    "first": {
+      "calibration_mse": 1.9545826862768833e-07,
+      "parameter_update_rms": 0.0004421066258581614,
+      "prediction_target_cosine": 0.0,
+      "target_power": 1.9545826862768833e-07
+    },
+    "last": {
+      "calibration_mse": 3.7359160583142764e-05,
+      "parameter_update_rms": 0.006112214049192221,
+      "prediction_target_cosine": 0.011668008991139992,
+      "target_power": 3.6848756204287994e-05
+    },
+    "mean": {
+      "calibration_mse": 0.0001923398035258008,
+      "parameter_update_rms": 0.011050459120615532,
+      "prediction_target_cosine": 0.0014602501420039524,
+      "target_power": 0.00019176158875808158
+    },
+    "steps": 400
+  },
+  "architecture": {
+    "adaptive_apical_parameters": 390592,
+    "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_traffic_coefficients": 188416,
+    "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": 376832,
+    "residual_scale": 1.0,
+    "vectorizer_mode": "channel_gated",
+    "vectorizer_parameters": 13760
+  },
+  "args": {
+    "a_scale": 0.0,
+    "a_warmup_steps": 400,
+    "alignment_probe": 64,
+    "apical_calibration_mode": "vectorizer_subspace",
+    "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:0",
+    "epochs": 0,
+    "eta_A": 0.1,
+    "eta_P": 0.01,
+    "eval_every": 0,
+    "eval_split": "validation",
+    "learn_P": 0,
+    "loader_seed": 0,
+    "lr": 0.03,
+    "lr_gamma": 0.1,
+    "lr_milestones": "100,150",
+    "lr_schedule": "constant",
+    "max_steps": 0,
+    "mode": "sdil",
+    "momentum": 0.9,
+    "normalization": "batchnorm",
+    "nuisance_scale": 0.0,
+    "out": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.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": 10000,
+    "use_residual": 1,
+    "val_examples": 5000,
+    "vectorizer_mode": "channel_gated",
+    "warmup_epochs": 0,
+    "weight_decay": 0.0001,
+    "weight_scale": 1.0,
+    "width": 16
+  },
+  "calibration_metric_space": "vectorizer_parameter_gradients",
+  "counters": {
+    "apical_warmup_examples": 50640,
+    "calibration_event_examples": 50640,
+    "causal_scalar_observations": 800,
+    "logical_batch_loss_queries": 800,
+    "ordinary_examples": 0,
+    "per_example_loss_terms": 101280,
+    "perturbation_events": 400,
+    "perturbation_forward_examples": 101280,
+    "predictor_warmup_examples": 0
+  },
+  "diagnostics": {
+    "early_third_mean": 0.004803654310914378,
+    "innovation_negative_gradient_cosine": [
+      0.0022225109860301018,
+      0.0028289039619266987,
+      0.0034330247435718775,
+      0.009060748852789402,
+      0.005170748569071293,
+      0.006105988752096891,
+      0.006368447095155716,
+      0.01181209459900856,
+      0.006666069850325584,
+      0.010817515663802624,
+      0.02869417518377304,
+      0.02690061554312706,
+      0.04461611434817314,
+      0.0371469110250473,
+      0.024002932012081146,
+      0.0602751150727272,
+      0.06595541536808014,
+      0.109754279255867,
+      0.1261977106332779
+    ],
+    "normalization_state": "training_batch_stats_without_running_update",
+    "raw_negative_gradient_cosine": [
+      0.0022225109860301018,
+      0.0028289039619266987,
+      0.0034330247435718775,
+      0.009060748852789402,
+      0.005170748569071293,
+      0.006105988752096891,
+      0.006368447095155716,
+      0.01181209459900856,
+      0.006666069850325584,
+      0.010817515663802624,
+      0.02869417518377304,
+      0.02690061554312706,
+      0.04461611434817314,
+      0.0371469110250473,
+      0.024002932012081146,
+      0.0602751150727272,
+      0.06595541536808014,
+      0.109754279255867,
+      0.1261977106332779
+    ],
+    "teaching_negative_gradient_cosine": [
+      0.0022225109860301018,
+      0.0028289039619266987,
+      0.0034330247435718775,
+      0.009060748852789402,
+      0.005170748569071293,
+      0.006105988752096891,
+      0.006368447095155716,
+      0.01181209459900856,
+      0.006666069850325584,
+      0.010817515663802624,
+      0.02869417518377304,
+      0.02690061554312706,
+      0.04461611434817314,
+      0.0371469110250473,
+      0.024002932012081146,
+      0.0602751150727272,
+      0.06595541536808014,
+      0.109754279255867,
+      0.1261977106332779
+    ],
+    "wall_s": 0.1158304214477539
+  },
+  "epochs": [],
+  "evaluation_protocol": {
+    "test_evaluations": 0,
+    "test_used_for_selection": false,
+    "validation_evaluations": 1
+  },
+  "final": {
+    "accuracy": 0.1004,
+    "epoch": 0,
+    "evaluation_split": "validation",
+    "finite": true,
+    "loss": 16.593759375,
+    "step": 0
+  },
+  "hardware": {
+    "cuda_device_name": "NVIDIA GeForce GTX 1080",
+    "cuda_visible_devices": "5",
+    "device": "cuda:0",
+    "device_total_memory_bytes": 8507949056,
+    "peak_memory_allocated_bytes": 1734868480,
+    "peak_memory_reserved_bytes": 2575302656,
+    "torch_version": "2.3.1+cu118"
+  },
+  "protocol_family": "oral_a_cifar_local_resnet_development",
+  "provenance": {
+    "git_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1",
+    "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": 10000,
+    "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": 24.720736503601074,
+    "evaluation_wall_s": 0.3711373805999756,
+    "predictor_warmup_wall_s": 0.0,
+    "timing_excludes_data_loading_hashing_and_model_construction": true,
+    "total_timed_wall_s": 25.092053651809692,
+    "train_wall_s": 0.0
+  },
+  "work": {
+    "apical_macs_per_example": 202176,
+    "causal_scalar_observations": 800,
+    "components": {
+      "apical_projection_macs": 10238192640,
+      "apical_regression_macs": 10238192640,
+      "bp_reverse_macs_estimate": 0,
+      "local_weight_correlation_macs": 0,
+      "ordinary_forward_macs": 0,
+      "perturbation_forward_macs": 4107009331200,
+      "warmup_clean_forward_macs": 2053504665600
+    },
+    "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": 800,
+    "per_example_cross_entropy_terms": 101280,
+    "total_clean_forward_examples": 50640,
+    "total_forward_equivalent_examples": 151920,
+    "total_macs_estimate": 6180990382080
+  }
+}