summaryrefslogtreecommitdiff
path: root/results
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 12:41:18 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 12:41:18 -0500
commit5dcd29000579d9dea626b47f84aa3fdc16700605 (patch)
tree967424289535ab0c0fe4044562de613c5b4b3cc1 /results
parentfc8fe99504fe86a3636721031a7dc3d41a7909a6 (diff)
results: close Oral-A v2 causal-capture gate
Diffstat (limited to 'results')
-rw-r--r--results/oral_a_failure_diagnosis.json23
-rw-r--r--results/oral_a_v2_calibration/channel_subspace_etaA0.01.json393
-rw-r--r--results/oral_a_v2_calibration/channel_subspace_etaA0.1.json393
-rw-r--r--results/oral_a_v2_calibration/channel_subspace_etaA1.0.json393
-rw-r--r--results/oral_a_v2_calibration/unit_targets_etaA0.01.json390
-rw-r--r--results/oral_a_v2_calibration/unit_targets_etaA0.1.json390
-rw-r--r--results/oral_a_v2_calibration/unit_targets_etaA1.0.json390
-rw-r--r--results/oral_a_v2_calibration_gate.json147
8 files changed, 2512 insertions, 7 deletions
diff --git a/results/oral_a_failure_diagnosis.json b/results/oral_a_failure_diagnosis.json
index 7c6b31b..5239e8b 100644
--- a/results/oral_a_failure_diagnosis.json
+++ b/results/oral_a_failure_diagnosis.json
@@ -44,14 +44,15 @@
"target_power_growth_epoch1_to_87": 2126827049.3932126
},
"diagnosis": {
- "classification": "causal_target_not_captured_before_runaway",
+ "classification": "unit_target_regression_snr_inadequate_before_runaway",
"evidence": [
- "prediction-target cosine remains effectively zero",
- "calibration MSE remains indistinguishable from target power",
+ "instantaneous prediction-target cosine remains effectively zero",
+ "calibration MSE remains indistinguishable from stochastic target power",
"target power grows by orders of magnitude before nonfiniteness",
- "short-run teaching alignment therefore cannot be attributed to learned A"
+ "matched frozen-forward unit targets later yield only 0.0011 early-layer alignment"
],
- "next_test": "reduce estimator variance by perturbing the representable channel-gated feedback subspace, not every spatial unit"
+ "interpretation_limit": "instantaneous target metrics alone do not prove zero conditional learning; structured v2 has low instantaneous cosine yet positive exact-gradient alignment",
+ "next_test_outcome": "representable-subspace perturbation improved exact alignment but failed the frozen early-layer causal-capture gate"
},
"frozen_outcome": {
"confirmation_test_seeds_touched": false,
@@ -71,7 +72,14 @@
"loss": null
}
},
- "protocol": "oral_a_A3_failure_diagnosis_v1",
+ "post_failure_v2_refinement": {
+ "structured_all_layer_alignment": 0.05273995646520665,
+ "structured_early_third_alignment": 0.007209055746595065,
+ "structured_gate_status": "failed",
+ "unit_target_all_layer_alignment": 0.011664319529173602,
+ "unit_target_early_third_alignment": 0.0011051012067279469
+ },
+ "protocol": "oral_a_A3_failure_diagnosis_v2",
"short_screen_contrast": {
"accuracy": 0.4198,
"early_third_alignment": 0.08889565182228883,
@@ -85,6 +93,7 @@
"source_paths": {
"full": "results/oral_a_dev/sdil_full_r20_s0.json",
"gate": "results/oral_a_full_gate.json",
- "short": "results/oral_a_short/sdil_channel_gated_lr0.03.json"
+ "short": "results/oral_a_short/sdil_channel_gated_lr0.03.json",
+ "v2_gate": "results/oral_a_v2_calibration_gate.json"
}
}
diff --git a/results/oral_a_v2_calibration/channel_subspace_etaA0.01.json b/results/oral_a_v2_calibration/channel_subspace_etaA0.01.json
new file mode 100644
index 0000000..4282d51
--- /dev/null
+++ b/results/oral_a_v2_calibration/channel_subspace_etaA0.01.json
@@ -0,0 +1,393 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 0.667037273962917,
+ "parameter_update_rms": 0.023085309606734133,
+ "prediction_target_cosine": 0.0,
+ "target_power": 0.667037273962917
+ },
+ "last": {
+ "calibration_mse": 0.014343140418299469,
+ "parameter_update_rms": 0.00343628282575056,
+ "prediction_target_cosine": -0.005531953824674762,
+ "target_power": 0.014335632392748118
+ },
+ "mean": {
+ "calibration_mse": 0.2708950854477958,
+ "parameter_update_rms": 0.011981565658686305,
+ "prediction_target_cosine": 0.00018159585958168355,
+ "target_power": 0.2708926473589623
+ },
+ "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": "channel_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": 0.01,
+ "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_v2_calibration/channel_subspace_etaA0.01.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": "channel_basis_moments",
+ "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": 0.007209055746595065,
+ "innovation_negative_gradient_cosine": [
+ 0.0021500173024833202,
+ 0.005721019580960274,
+ 0.008716392330825329,
+ 0.01114893238991499,
+ 0.005342159885913134,
+ 0.010175812989473343,
+ 0.006470849737524986,
+ 0.013490993529558182,
+ 0.025294749066233635,
+ 0.028453536331653595,
+ 0.041042692959308624,
+ 0.018679656088352203,
+ 0.04189874976873398,
+ 0.04070262610912323,
+ 0.09365405142307281,
+ 0.07153154909610748,
+ 0.11656917631626129,
+ 0.19568055868148804,
+ 0.26533564925193787
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ 0.0021500173024833202,
+ 0.005721019580960274,
+ 0.008716392330825329,
+ 0.01114893238991499,
+ 0.005342159885913134,
+ 0.010175812989473343,
+ 0.006470849737524986,
+ 0.013490993529558182,
+ 0.025294749066233635,
+ 0.028453536331653595,
+ 0.041042692959308624,
+ 0.018679656088352203,
+ 0.04189874976873398,
+ 0.04070262610912323,
+ 0.09365405142307281,
+ 0.07153154909610748,
+ 0.11656917631626129,
+ 0.19568055868148804,
+ 0.26533564925193787
+ ],
+ "teaching_negative_gradient_cosine": [
+ 0.0021500173024833202,
+ 0.005721019580960274,
+ 0.008716392330825329,
+ 0.01114893238991499,
+ 0.005342159885913134,
+ 0.010175812989473343,
+ 0.006470849737524986,
+ 0.013490993529558182,
+ 0.025294749066233635,
+ 0.028453536331653595,
+ 0.041042692959308624,
+ 0.018679656088352203,
+ 0.04189874976873398,
+ 0.04070262610912323,
+ 0.09365405142307281,
+ 0.07153154909610748,
+ 0.11656917631626129,
+ 0.19568055868148804,
+ 0.26533564925193787
+ ],
+ "wall_s": 0.11891794204711914
+ },
+ "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": "7",
+ "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": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 23.970787286758423,
+ "evaluation_wall_s": 0.3708672523498535,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.341848134994507,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration/channel_subspace_etaA0.1.json b/results/oral_a_v2_calibration/channel_subspace_etaA0.1.json
new file mode 100644
index 0000000..95a7fbb
--- /dev/null
+++ b/results/oral_a_v2_calibration/channel_subspace_etaA0.1.json
@@ -0,0 +1,393 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 0.667037273962917,
+ "parameter_update_rms": 0.023085309606734133,
+ "prediction_target_cosine": 0.0,
+ "target_power": 0.667037273962917
+ },
+ "last": {
+ "calibration_mse": 0.014407349533643737,
+ "parameter_update_rms": 0.0035494557764320068,
+ "prediction_target_cosine": -0.0026674387418668616,
+ "target_power": 0.014335632392748118
+ },
+ "mean": {
+ "calibration_mse": 0.27095736647643465,
+ "parameter_update_rms": 0.012069313096218597,
+ "prediction_target_cosine": 0.00010544442092045836,
+ "target_power": 0.2708926473589623
+ },
+ "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": "channel_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_v2_calibration/channel_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": "channel_basis_moments",
+ "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": 0.0038381816702894866,
+ "innovation_negative_gradient_cosine": [
+ -0.0012592253042384982,
+ 0.00399992149323225,
+ 0.006424956023693085,
+ 0.005883498582988977,
+ 0.006901413202285767,
+ 0.0010785260237753391,
+ 0.002761237556114793,
+ 0.010423609055578709,
+ 0.009150509722530842,
+ 0.017207007855176926,
+ 0.015042684972286224,
+ 0.00847631599754095,
+ 0.012668993324041367,
+ 0.03519224375486374,
+ 0.042540062218904495,
+ 0.011548444628715515,
+ 0.04734557867050171,
+ 0.10991379618644714,
+ 0.15230399370193481
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.0012592253042384982,
+ 0.00399992149323225,
+ 0.006424956023693085,
+ 0.005883498582988977,
+ 0.006901413202285767,
+ 0.0010785260237753391,
+ 0.002761237556114793,
+ 0.010423609055578709,
+ 0.009150509722530842,
+ 0.017207007855176926,
+ 0.015042684972286224,
+ 0.00847631599754095,
+ 0.012668993324041367,
+ 0.03519224375486374,
+ 0.042540062218904495,
+ 0.011548444628715515,
+ 0.04734557867050171,
+ 0.10991379618644714,
+ 0.15230399370193481
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.0012592253042384982,
+ 0.00399992149323225,
+ 0.006424956023693085,
+ 0.005883498582988977,
+ 0.006901413202285767,
+ 0.0010785260237753391,
+ 0.002761237556114793,
+ 0.010423609055578709,
+ 0.009150509722530842,
+ 0.017207007855176926,
+ 0.015042684972286224,
+ 0.00847631599754095,
+ 0.012668993324041367,
+ 0.03519224375486374,
+ 0.042540062218904495,
+ 0.011548444628715515,
+ 0.04734557867050171,
+ 0.10991379618644714,
+ 0.15230399370193481
+ ],
+ "wall_s": 0.11558938026428223
+ },
+ "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": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 23.933976888656616,
+ "evaluation_wall_s": 0.36545491218566895,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.29965043067932,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration/channel_subspace_etaA1.0.json b/results/oral_a_v2_calibration/channel_subspace_etaA1.0.json
new file mode 100644
index 0000000..f000fa4
--- /dev/null
+++ b/results/oral_a_v2_calibration/channel_subspace_etaA1.0.json
@@ -0,0 +1,393 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 0.667037273962917,
+ "parameter_update_rms": 0.023085309606734133,
+ "prediction_target_cosine": 0.0,
+ "target_power": 0.667037273962917
+ },
+ "last": {
+ "calibration_mse": 0.015573981316265417,
+ "parameter_update_rms": 0.005349574497052361,
+ "prediction_target_cosine": 0.004038878111100969,
+ "target_power": 0.014335632392748118
+ },
+ "mean": {
+ "calibration_mse": 0.2717085534018111,
+ "parameter_update_rms": 0.012732941480864037,
+ "prediction_target_cosine": -8.862524765940711e-05,
+ "target_power": 0.2708926473589623
+ },
+ "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": "channel_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": 1.0,
+ "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_v2_calibration/channel_subspace_etaA1.0.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": "channel_basis_moments",
+ "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": 0.001714374249180158,
+ "innovation_negative_gradient_cosine": [
+ -0.000828517833724618,
+ 0.0012920019216835499,
+ 0.005332308355718851,
+ 0.004775108303874731,
+ 0.0038991339970380068,
+ -0.004183789249509573,
+ 0.006285618990659714,
+ 0.003322963137179613,
+ 0.0036540841683745384,
+ 0.0062436810694634914,
+ -0.003957148641347885,
+ 0.006059933453798294,
+ 0.006437992211431265,
+ 0.021154729649424553,
+ 0.012715594843029976,
+ -0.02445901930332184,
+ -0.019053492695093155,
+ 0.021413326263427734,
+ 0.025747042149305344
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.000828517833724618,
+ 0.0012920019216835499,
+ 0.005332308355718851,
+ 0.004775108303874731,
+ 0.0038991339970380068,
+ -0.004183789249509573,
+ 0.006285618990659714,
+ 0.003322963137179613,
+ 0.0036540841683745384,
+ 0.0062436810694634914,
+ -0.003957148641347885,
+ 0.006059933453798294,
+ 0.006437992211431265,
+ 0.021154729649424553,
+ 0.012715594843029976,
+ -0.02445901930332184,
+ -0.019053492695093155,
+ 0.021413326263427734,
+ 0.025747042149305344
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.000828517833724618,
+ 0.0012920019216835499,
+ 0.005332308355718851,
+ 0.004775108303874731,
+ 0.0038991339970380068,
+ -0.004183789249509573,
+ 0.006285618990659714,
+ 0.003322963137179613,
+ 0.0036540841683745384,
+ 0.0062436810694634914,
+ -0.003957148641347885,
+ 0.006059933453798294,
+ 0.006437992211431265,
+ 0.021154729649424553,
+ 0.012715594843029976,
+ -0.02445901930332184,
+ -0.019053492695093155,
+ 0.021413326263427734,
+ 0.025747042149305344
+ ],
+ "wall_s": 0.11605238914489746
+ },
+ "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": "7",
+ "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": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 23.875094175338745,
+ "evaluation_wall_s": 0.37113046646118164,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.24647092819214,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration/unit_targets_etaA0.01.json b/results/oral_a_v2_calibration/unit_targets_etaA0.01.json
new file mode 100644
index 0000000..b421acf
--- /dev/null
+++ b/results/oral_a_v2_calibration/unit_targets_etaA0.01.json
@@ -0,0 +1,390 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 4.1123504638671875,
+ "prediction_target_cosine": 0.0,
+ "target_power": 4.1123504638671875
+ },
+ "last": {
+ "calibration_mse": 60.77315496361774,
+ "prediction_target_cosine": 0.0006244406591329739,
+ "target_power": 60.77318373970363
+ },
+ "mean": {
+ "calibration_mse": 306.8068681861785,
+ "prediction_target_cosine": -1.0456776873674686e-06,
+ "target_power": 306.80684325786916
+ },
+ "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": "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:0",
+ "epochs": 0,
+ "eta_A": 0.01,
+ "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_v2_calibration/unit_targets_etaA0.01.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": "full_hidden_field",
+ "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": 0.0011051012067279469,
+ "innovation_negative_gradient_cosine": [
+ -0.00034784310264512897,
+ -0.0025916527956724167,
+ 2.2646039724349976e-05,
+ 0.007553194649517536,
+ 0.005484188441187143,
+ -0.003489925991743803,
+ -0.006299270782619715,
+ 0.006761397235095501,
+ -0.005489094648510218,
+ -0.012966052629053593,
+ 0.01738702319562435,
+ 0.004095735028386116,
+ 0.015238979831337929,
+ 0.026438727974891663,
+ -0.006385758984833956,
+ 0.02158680558204651,
+ 0.019882317632436752,
+ 0.046531397849321365,
+ 0.08820925652980804
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.00034784310264512897,
+ -0.0025916527956724167,
+ 2.2646039724349976e-05,
+ 0.007553194649517536,
+ 0.005484188441187143,
+ -0.003489925991743803,
+ -0.006299270782619715,
+ 0.006761397235095501,
+ -0.005489094648510218,
+ -0.012966052629053593,
+ 0.01738702319562435,
+ 0.004095735028386116,
+ 0.015238979831337929,
+ 0.026438727974891663,
+ -0.006385758984833956,
+ 0.02158680558204651,
+ 0.019882317632436752,
+ 0.046531397849321365,
+ 0.08820925652980804
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.00034784310264512897,
+ -0.0025916527956724167,
+ 2.2646039724349976e-05,
+ 0.007553194649517536,
+ 0.005484188441187143,
+ -0.003489925991743803,
+ -0.006299270782619715,
+ 0.006761397235095501,
+ -0.005489094648510218,
+ -0.012966052629053593,
+ 0.01738702319562435,
+ 0.004095735028386116,
+ 0.015238979831337929,
+ 0.026438727974891663,
+ -0.006385758984833956,
+ 0.02158680558204651,
+ 0.019882317632436752,
+ 0.046531397849321365,
+ 0.08820925652980804
+ ],
+ "wall_s": 0.11040592193603516
+ },
+ "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": 2690646016,
+ "torch_version": "2.3.1+cu118"
+ },
+ "protocol_family": "oral_a_cifar_local_resnet_development",
+ "provenance": {
+ "git_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 24.429534912109375,
+ "evaluation_wall_s": 0.3710341453552246,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.80078649520874,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration/unit_targets_etaA0.1.json b/results/oral_a_v2_calibration/unit_targets_etaA0.1.json
new file mode 100644
index 0000000..7da80b1
--- /dev/null
+++ b/results/oral_a_v2_calibration/unit_targets_etaA0.1.json
@@ -0,0 +1,390 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 4.1123504638671875,
+ "prediction_target_cosine": 0.0,
+ "target_power": 4.1123504638671875
+ },
+ "last": {
+ "calibration_mse": 60.77357632180919,
+ "prediction_target_cosine": 0.0003734676299838721,
+ "target_power": 60.77318373970363
+ },
+ "mean": {
+ "calibration_mse": 306.80736262691147,
+ "prediction_target_cosine": -8.709214493754583e-06,
+ "target_power": 306.80684325786916
+ },
+ "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": "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: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_v2_calibration/unit_targets_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": "full_hidden_field",
+ "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": -0.0007603219904315969,
+ "innovation_negative_gradient_cosine": [
+ -0.0026482653338462114,
+ -0.0014026857679709792,
+ -0.0032926220446825027,
+ 0.003918738104403019,
+ 0.006381125655025244,
+ -0.00751822255551815,
+ -3.789784386754036e-06,
+ 0.007395345717668533,
+ 0.0014983054716140032,
+ -0.00718093104660511,
+ 0.018063008785247803,
+ -0.006030107382684946,
+ 0.01317618228495121,
+ 0.04094434902071953,
+ 0.011970864608883858,
+ 0.0008559874258935452,
+ 0.03555452078580856,
+ 0.03732839599251747,
+ 0.038500867784023285
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.0026482653338462114,
+ -0.0014026857679709792,
+ -0.0032926220446825027,
+ 0.003918738104403019,
+ 0.006381125655025244,
+ -0.00751822255551815,
+ -3.789784386754036e-06,
+ 0.007395345717668533,
+ 0.0014983054716140032,
+ -0.00718093104660511,
+ 0.018063008785247803,
+ -0.006030107382684946,
+ 0.01317618228495121,
+ 0.04094434902071953,
+ 0.011970864608883858,
+ 0.0008559874258935452,
+ 0.03555452078580856,
+ 0.03732839599251747,
+ 0.038500867784023285
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.0026482653338462114,
+ -0.0014026857679709792,
+ -0.0032926220446825027,
+ 0.003918738104403019,
+ 0.006381125655025244,
+ -0.00751822255551815,
+ -3.789784386754036e-06,
+ 0.007395345717668533,
+ 0.0014983054716140032,
+ -0.00718093104660511,
+ 0.018063008785247803,
+ -0.006030107382684946,
+ 0.01317618228495121,
+ 0.04094434902071953,
+ 0.011970864608883858,
+ 0.0008559874258935452,
+ 0.03555452078580856,
+ 0.03732839599251747,
+ 0.038500867784023285
+ ],
+ "wall_s": 0.11375069618225098
+ },
+ "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": "7",
+ "device": "cuda:0",
+ "device_total_memory_bytes": 8507949056,
+ "peak_memory_allocated_bytes": 1734868480,
+ "peak_memory_reserved_bytes": 2690646016,
+ "torch_version": "2.3.1+cu118"
+ },
+ "protocol_family": "oral_a_cifar_local_resnet_development",
+ "provenance": {
+ "git_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 24.465684175491333,
+ "evaluation_wall_s": 0.37288689613342285,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.83878993988037,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration/unit_targets_etaA1.0.json b/results/oral_a_v2_calibration/unit_targets_etaA1.0.json
new file mode 100644
index 0000000..a648c1b
--- /dev/null
+++ b/results/oral_a_v2_calibration/unit_targets_etaA1.0.json
@@ -0,0 +1,390 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 4.1123504638671875,
+ "prediction_target_cosine": 0.0,
+ "target_power": 4.1123504638671875
+ },
+ "last": {
+ "calibration_mse": 60.785771079685375,
+ "prediction_target_cosine": 0.00018066191971056846,
+ "target_power": 60.77318373970363
+ },
+ "mean": {
+ "calibration_mse": 306.8130476901478,
+ "prediction_target_cosine": 1.1424882244632998e-06,
+ "target_power": 306.80684325786916
+ },
+ "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": "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:0",
+ "epochs": 0,
+ "eta_A": 1.0,
+ "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_v2_calibration/unit_targets_etaA1.0.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": "full_hidden_field",
+ "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": -0.0031450521055376157,
+ "innovation_negative_gradient_cosine": [
+ -0.0038595087826251984,
+ -0.0002608323993626982,
+ -0.0040445514023303986,
+ -0.001344867399893701,
+ -0.001432035001926124,
+ -0.007928517647087574,
+ -0.004752017557621002,
+ 0.009463246911764145,
+ -0.0019811633974313736,
+ -0.005859529599547386,
+ 0.01658852957189083,
+ -0.009742104448378086,
+ 0.005521662067621946,
+ 0.04838317632675171,
+ 0.024612773209810257,
+ -0.0016448963433504105,
+ -0.001705970149487257,
+ -0.004393921699374914,
+ 0.0048246243968605995
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.0038595087826251984,
+ -0.0002608323993626982,
+ -0.0040445514023303986,
+ -0.001344867399893701,
+ -0.001432035001926124,
+ -0.007928517647087574,
+ -0.004752017557621002,
+ 0.009463246911764145,
+ -0.0019811633974313736,
+ -0.005859529599547386,
+ 0.01658852957189083,
+ -0.009742104448378086,
+ 0.005521662067621946,
+ 0.04838317632675171,
+ 0.024612773209810257,
+ -0.0016448963433504105,
+ -0.001705970149487257,
+ -0.004393921699374914,
+ 0.0048246243968605995
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.0038595087826251984,
+ -0.0002608323993626982,
+ -0.0040445514023303986,
+ -0.001344867399893701,
+ -0.001432035001926124,
+ -0.007928517647087574,
+ -0.004752017557621002,
+ 0.009463246911764145,
+ -0.0019811633974313736,
+ -0.005859529599547386,
+ 0.01658852957189083,
+ -0.009742104448378086,
+ 0.005521662067621946,
+ 0.04838317632675171,
+ 0.024612773209810257,
+ -0.0016448963433504105,
+ -0.001705970149487257,
+ -0.004393921699374914,
+ 0.0048246243968605995
+ ],
+ "wall_s": 0.11835074424743652
+ },
+ "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": 2690646016,
+ "torch_version": "2.3.1+cu118"
+ },
+ "protocol_family": "oral_a_cifar_local_resnet_development",
+ "provenance": {
+ "git_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6",
+ "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": 24.51742196083069,
+ "evaluation_wall_s": 0.3782050609588623,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.89581036567688,
+ "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
+ }
+}
diff --git a/results/oral_a_v2_calibration_gate.json b/results/oral_a_v2_calibration_gate.json
new file mode 100644
index 0000000..1ffc605
--- /dev/null
+++ b/results/oral_a_v2_calibration_gate.json
@@ -0,0 +1,147 @@
+{
+ "checks": {
+ "all_six_records_finite": true,
+ "both_modes_selected": true,
+ "structured_all_layer_at_least_0.01": true,
+ "structured_early_gain_over_unit_at_least_0.01": false,
+ "structured_early_third_at_least_0.01": false
+ },
+ "confirmation_test_seeds_touched": false,
+ "protocol": "oral_a_v2_causal_capture_v1",
+ "review_score_after": 5,
+ "review_score_before": 5,
+ "rows": [
+ {
+ "calibration_mode": "channel_subspace",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "channel_basis_moments",
+ "metrics": {
+ "all_layer_alignment": 0.05273995646520665,
+ "early_third_alignment": 0.007209055746595065,
+ "mean_calibration_mse": 0.2708950854477958,
+ "mean_parameter_update_rms": 0.011981565658686305,
+ "mean_prediction_target_cosine": 0.00018159585958168355,
+ "mean_target_power": 0.2708926473589623
+ },
+ "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.01.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ {
+ "calibration_mode": "channel_subspace",
+ "eta_A": 0.1,
+ "finite": true,
+ "metric_space": "channel_basis_moments",
+ "metrics": {
+ "all_layer_alignment": 0.026189661456124957,
+ "early_third_alignment": 0.0038381816702894866,
+ "mean_calibration_mse": 0.27095736647643465,
+ "mean_parameter_update_rms": 0.012069313096218597,
+ "mean_prediction_target_cosine": 0.00010544442092045836,
+ "mean_target_power": 0.2708926473589623
+ },
+ "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.1.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ {
+ "calibration_mode": "channel_subspace",
+ "eta_A": 1.0,
+ "finite": true,
+ "metric_space": "channel_basis_moments",
+ "metrics": {
+ "all_layer_alignment": 0.003992186883758558,
+ "early_third_alignment": 0.001714374249180158,
+ "mean_calibration_mse": 0.2717085534018111,
+ "mean_parameter_update_rms": 0.012732941480864037,
+ "mean_prediction_target_cosine": -8.862524765940711e-05,
+ "mean_target_power": 0.2708926473589623
+ },
+ "path": "results/oral_a_v2_calibration/channel_subspace_etaA1.0.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ {
+ "calibration_mode": "unit_targets",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "full_hidden_field",
+ "metrics": {
+ "all_layer_alignment": 0.011664319529173602,
+ "early_third_alignment": 0.0011051012067279469,
+ "mean_calibration_mse": 306.8068681861785,
+ "mean_parameter_update_rms": 0.0,
+ "mean_prediction_target_cosine": -1.0456776873674686e-06,
+ "mean_target_power": 306.80684325786916
+ },
+ "path": "results/oral_a_v2_calibration/unit_targets_etaA0.01.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ {
+ "calibration_mode": "unit_targets",
+ "eta_A": 0.1,
+ "finite": true,
+ "metric_space": "full_hidden_field",
+ "metrics": {
+ "all_layer_alignment": 0.00986900356426639,
+ "early_third_alignment": -0.0007603219904315969,
+ "mean_calibration_mse": 306.80736262691147,
+ "mean_parameter_update_rms": 0.0,
+ "mean_prediction_target_cosine": -8.709214493754583e-06,
+ "mean_target_power": 306.80684325786916
+ },
+ "path": "results/oral_a_v2_calibration/unit_targets_etaA0.1.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ {
+ "calibration_mode": "unit_targets",
+ "eta_A": 1.0,
+ "finite": true,
+ "metric_space": "full_hidden_field",
+ "metrics": {
+ "all_layer_alignment": 0.0031812682450675454,
+ "early_third_alignment": -0.0031450521055376157,
+ "mean_calibration_mse": 306.8130476901478,
+ "mean_parameter_update_rms": 0.0,
+ "mean_prediction_target_cosine": 1.1424882244632998e-06,
+ "mean_target_power": 306.80684325786916
+ },
+ "path": "results/oral_a_v2_calibration/unit_targets_etaA1.0.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ }
+ ],
+ "score_change_rule": "mechanics/calibration alone cannot raise score",
+ "selected": {
+ "channel_subspace": {
+ "calibration_mode": "channel_subspace",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "channel_basis_moments",
+ "metrics": {
+ "all_layer_alignment": 0.05273995646520665,
+ "early_third_alignment": 0.007209055746595065,
+ "mean_calibration_mse": 0.2708950854477958,
+ "mean_parameter_update_rms": 0.011981565658686305,
+ "mean_prediction_target_cosine": 0.00018159585958168355,
+ "mean_target_power": 0.2708926473589623
+ },
+ "path": "results/oral_a_v2_calibration/channel_subspace_etaA0.01.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ },
+ "unit_targets": {
+ "calibration_mode": "unit_targets",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "full_hidden_field",
+ "metrics": {
+ "all_layer_alignment": 0.011664319529173602,
+ "early_third_alignment": 0.0011051012067279469,
+ "mean_calibration_mse": 306.8068681861785,
+ "mean_parameter_update_rms": 0.0,
+ "mean_prediction_target_cosine": -1.0456776873674686e-06,
+ "mean_target_power": 306.80684325786916
+ },
+ "path": "results/oral_a_v2_calibration/unit_targets_etaA0.01.json",
+ "source_commit": "fc8fe99504fe86a3636721031a7dc3d41a7909a6"
+ }
+ },
+ "status": "failed"
+}