summaryrefslogtreecommitdiff
path: root/results
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 12:59:25 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 12:59:25 -0500
commit6fa80efc1c53905b6328c5b44df3db4e4da34dfe (patch)
treef8018d3d7fb41c6297d75cd00469b34dbe53f82d /results
parent612196a53285b6efc44c0dd84699c7b57a6dc8e1 (diff)
results: close Oral-A v3 causal-capture gate
Diffstat (limited to 'results')
-rw-r--r--results/oral_a_failure_diagnosis.json19
-rw-r--r--results/oral_a_v3_calibration/channel_subspace_etaA0.01.json393
-rw-r--r--results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json393
-rw-r--r--results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json393
-rw-r--r--results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.json393
-rw-r--r--results/oral_a_v3_calibration_gate.json115
6 files changed, 1701 insertions, 5 deletions
diff --git a/results/oral_a_failure_diagnosis.json b/results/oral_a_failure_diagnosis.json
index 1b142df..b26d81e 100644
--- a/results/oral_a_failure_diagnosis.json
+++ b/results/oral_a_failure_diagnosis.json
@@ -51,11 +51,12 @@
"target power grows by orders of magnitude before nonfiniteness",
"matched frozen-forward unit targets later yield only 0.0011 early-layer alignment",
"structured learning reaches 0.0072 versus a 0.0240 cross-validated family oracle",
- "unconstrained coefficients raise the same spatial basis oracle only to 0.0549"
+ "unconstrained coefficients raise the same spatial basis oracle only to 0.0549",
+ "direct A/G estimation leaves early alignment unchanged at 0.0071"
],
"interpretation_limit": "instantaneous target metrics alone do not prove zero conditional learning; structured v2 has low instantaneous cosine yet positive exact-gradient alignment",
- "next_design_constraint": "do not add the tested naive local-average/channel-mean bases; improve causal sample efficiency and use a more informative hierarchical or high-level contextual feedback signal",
- "next_test_outcome": "representable-subspace perturbation improved exact alignment but failed the frozen early-layer causal-capture gate"
+ "next_design_constraint": "do not add the tested naive local-average/channel-mean bases; do not repeat the closed A/G rate grid; use a more informative hierarchical or high-level contextual feedback signal and audit remaining cross-layer noise",
+ "next_test_outcome": "representable-subspace perturbation improved alignment but failed; direct vectorizer-space estimation then improved only middle/late layers and also failed the frozen early-layer gate"
},
"frozen_outcome": {
"confirmation_test_seeds_touched": false,
@@ -88,7 +89,14 @@
"unit_target_all_layer_alignment": 0.011664319529173602,
"unit_target_early_third_alignment": 0.0011051012067279469
},
- "protocol": "oral_a_A3_failure_diagnosis_v2",
+ "post_failure_v3_refinement": {
+ "matched_v2_all_layer_alignment": 0.052739956808325494,
+ "matched_v2_early_third_alignment": 0.007209058462952574,
+ "vectorizer_subspace_all_layer_alignment": 0.0625791079364717,
+ "vectorizer_subspace_early_third_alignment": 0.007139206010227402,
+ "vectorizer_subspace_gate_status": "failed"
+ },
+ "protocol": "oral_a_A3_failure_diagnosis_v3",
"short_screen_contrast": {
"accuracy": 0.4198,
"early_third_alignment": 0.08889565182228883,
@@ -104,6 +112,7 @@
"gate": "results/oral_a_full_gate.json",
"representation": "results/oral_a_representation_diagnosis.json",
"short": "results/oral_a_short/sdil_channel_gated_lr0.03.json",
- "v2_gate": "results/oral_a_v2_calibration_gate.json"
+ "v2_gate": "results/oral_a_v2_calibration_gate.json",
+ "v3_gate": "results/oral_a_v3_calibration_gate.json"
}
}
diff --git a/results/oral_a_v3_calibration/channel_subspace_etaA0.01.json b/results/oral_a_v3_calibration/channel_subspace_etaA0.01.json
new file mode 100644
index 0000000..04dc626
--- /dev/null
+++ b/results/oral_a_v3_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_v3_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": 0.007209058462952574,
+ "innovation_negative_gradient_cosine": [
+ 0.002150021493434906,
+ 0.005721020977944136,
+ 0.008716395124793053,
+ 0.011148940771818161,
+ 0.0053421612828969955,
+ 0.010175811126828194,
+ 0.006470846477895975,
+ 0.013490992598235607,
+ 0.025294749066233635,
+ 0.028453530743718147,
+ 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": [
+ 0.002150021493434906,
+ 0.005721020977944136,
+ 0.008716395124793053,
+ 0.011148940771818161,
+ 0.0053421612828969955,
+ 0.010175811126828194,
+ 0.006470846477895975,
+ 0.013490992598235607,
+ 0.025294749066233635,
+ 0.028453530743718147,
+ 0.041042692959308624,
+ 0.018679656088352203,
+ 0.04189874976873398,
+ 0.04070262610912323,
+ 0.09365405142307281,
+ 0.07153154909610748,
+ 0.11656917631626129,
+ 0.19568055868148804,
+ 0.26533564925193787
+ ],
+ "teaching_negative_gradient_cosine": [
+ 0.002150021493434906,
+ 0.005721020977944136,
+ 0.008716395124793053,
+ 0.011148940771818161,
+ 0.0053421612828969955,
+ 0.010175811126828194,
+ 0.006470846477895975,
+ 0.013490992598235607,
+ 0.025294749066233635,
+ 0.028453530743718147,
+ 0.041042692959308624,
+ 0.018679656088352203,
+ 0.04189874976873398,
+ 0.04070262610912323,
+ 0.09365405142307281,
+ 0.07153154909610748,
+ 0.11656917631626129,
+ 0.19568055868148804,
+ 0.26533564925193787
+ ],
+ "wall_s": 0.1165304183959961
+ },
+ "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": 24.140583515167236,
+ "evaluation_wall_s": 0.3799288272857666,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.520760536193848,
+ "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_v3_calibration/vectorizer_subspace_etaA0.01.json b/results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json
new file mode 100644
index 0000000..d959de9
--- /dev/null
+++ b/results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.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": 3.684547450998358e-05,
+ "parameter_update_rms": 0.006070047323537402,
+ "prediction_target_cosine": 0.01877143215663052,
+ "target_power": 3.6848756204287994e-05
+ },
+ "mean": {
+ "calibration_mse": 0.00019177845804523746,
+ "parameter_update_rms": 0.010982968905010668,
+ "prediction_target_cosine": 0.0018218688400943384,
+ "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": 0.01,
+ "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_v3_calibration/vectorizer_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": "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": 0.007139206010227402,
+ "innovation_negative_gradient_cosine": [
+ 0.0026028589345514774,
+ 0.006397380493581295,
+ 0.008704797364771366,
+ 0.010101381689310074,
+ 0.007746903225779533,
+ 0.0072819143533706665,
+ 0.020229119807481766,
+ 0.021337036043405533,
+ 0.021039098501205444,
+ 0.03162077069282532,
+ 0.03877360373735428,
+ 0.04704105108976364,
+ 0.06299921870231628,
+ 0.08475810289382935,
+ 0.07144122570753098,
+ 0.14218710362911224,
+ 0.16116924583911896,
+ 0.20310530066490173,
+ 0.24046693742275238
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ 0.0026028589345514774,
+ 0.006397380493581295,
+ 0.008704797364771366,
+ 0.010101381689310074,
+ 0.007746903225779533,
+ 0.0072819143533706665,
+ 0.020229119807481766,
+ 0.021337036043405533,
+ 0.021039098501205444,
+ 0.03162077069282532,
+ 0.03877360373735428,
+ 0.04704105108976364,
+ 0.06299921870231628,
+ 0.08475810289382935,
+ 0.07144122570753098,
+ 0.14218710362911224,
+ 0.16116924583911896,
+ 0.20310530066490173,
+ 0.24046693742275238
+ ],
+ "teaching_negative_gradient_cosine": [
+ 0.0026028589345514774,
+ 0.006397380493581295,
+ 0.008704797364771366,
+ 0.010101381689310074,
+ 0.007746903225779533,
+ 0.0072819143533706665,
+ 0.020229119807481766,
+ 0.021337036043405533,
+ 0.021039098501205444,
+ 0.03162077069282532,
+ 0.03877360373735428,
+ 0.04704105108976364,
+ 0.06299921870231628,
+ 0.08475810289382935,
+ 0.07144122570753098,
+ 0.14218710362911224,
+ 0.16116924583911896,
+ 0.20310530066490173,
+ 0.24046693742275238
+ ],
+ "wall_s": 0.1202707290649414
+ },
+ "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": "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": 24.03937554359436,
+ "evaluation_wall_s": 0.376523494720459,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 24.41608953475952,
+ "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_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
+ }
+}
diff --git a/results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.json b/results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.json
new file mode 100644
index 0000000..61c1891
--- /dev/null
+++ b/results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.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": 4.264974206656662e-05,
+ "parameter_update_rms": 0.006530676999099452,
+ "prediction_target_cosine": 0.0010701752475656546,
+ "target_power": 3.6848756204287994e-05
+ },
+ "mean": {
+ "calibration_mse": 0.00019906028706469792,
+ "parameter_update_rms": 0.01158272062540019,
+ "prediction_target_cosine": -0.0001920852658946125,
+ "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": 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_v3_calibration/vectorizer_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": "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": 0.002233794856389674,
+ "innovation_negative_gradient_cosine": [
+ -0.0005113005172461271,
+ 0.000137713534059003,
+ 0.00045850942842662334,
+ 0.0053695435635745525,
+ 0.0032934178598225117,
+ 0.004654885269701481,
+ -0.0017309020040556788,
+ 0.00377076817676425,
+ -0.007445689290761948,
+ -0.0006793281063437462,
+ 0.009065194055438042,
+ 0.0052467635832726955,
+ 0.03067660890519619,
+ 0.010736962780356407,
+ 0.010169688612222672,
+ 0.014299523085355759,
+ -0.00701782526448369,
+ 0.028061751276254654,
+ 0.020663894712924957
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.0005113005172461271,
+ 0.000137713534059003,
+ 0.00045850942842662334,
+ 0.0053695435635745525,
+ 0.0032934178598225117,
+ 0.004654885269701481,
+ -0.0017309020040556788,
+ 0.00377076817676425,
+ -0.007445689290761948,
+ -0.0006793281063437462,
+ 0.009065194055438042,
+ 0.0052467635832726955,
+ 0.03067660890519619,
+ 0.010736962780356407,
+ 0.010169688612222672,
+ 0.014299523085355759,
+ -0.00701782526448369,
+ 0.028061751276254654,
+ 0.020663894712924957
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.0005113005172461271,
+ 0.000137713534059003,
+ 0.00045850942842662334,
+ 0.0053695435635745525,
+ 0.0032934178598225117,
+ 0.004654885269701481,
+ -0.0017309020040556788,
+ 0.00377076817676425,
+ -0.007445689290761948,
+ -0.0006793281063437462,
+ 0.009065194055438042,
+ 0.0052467635832726955,
+ 0.03067660890519619,
+ 0.010736962780356407,
+ 0.010169688612222672,
+ 0.014299523085355759,
+ -0.00701782526448369,
+ 0.028061751276254654,
+ 0.020663894712924957
+ ],
+ "wall_s": 0.12106084823608398
+ },
+ "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": "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": 26.799011945724487,
+ "evaluation_wall_s": 0.38268423080444336,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 27.181934356689453,
+ "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_v3_calibration_gate.json b/results/oral_a_v3_calibration_gate.json
new file mode 100644
index 0000000..c0364bc
--- /dev/null
+++ b/results/oral_a_v3_calibration_gate.json
@@ -0,0 +1,115 @@
+{
+ "checks": {
+ "all_four_records_finite": true,
+ "v3_all_layer_at_least_0.05": true,
+ "v3_candidate_selected": true,
+ "v3_early_gain_over_v2_at_least_0.01": false,
+ "v3_early_third_at_least_0.01": false,
+ "v3_reaches_60pct_of_family_oracle": false
+ },
+ "confirmation_test_seeds_touched": false,
+ "family_oracle_early_third": 0.02396580002561188,
+ "matched_v2_reference": {
+ "calibration_mode": "channel_subspace",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "channel_basis_moments",
+ "metrics": {
+ "all_layer_alignment": 0.052739956808325494,
+ "early_third_alignment": 0.007209058462952574,
+ "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_v3_calibration/channel_subspace_etaA0.01.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ },
+ "protocol": "oral_a_v3_vectorizer_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": 0.052739956808325494,
+ "early_third_alignment": 0.007209058462952574,
+ "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_v3_calibration/channel_subspace_etaA0.01.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ },
+ {
+ "calibration_mode": "vectorizer_subspace",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "vectorizer_parameter_gradients",
+ "metrics": {
+ "all_layer_alignment": 0.0625791079364717,
+ "early_third_alignment": 0.007139206010227402,
+ "mean_calibration_mse": 0.00019177845804523746,
+ "mean_parameter_update_rms": 0.010982968905010668,
+ "mean_prediction_target_cosine": 0.0018218688400943384,
+ "mean_target_power": 0.00019176158875808158
+ },
+ "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ },
+ {
+ "calibration_mode": "vectorizer_subspace",
+ "eta_A": 0.1,
+ "finite": true,
+ "metric_space": "vectorizer_parameter_gradients",
+ "metrics": {
+ "all_layer_alignment": 0.0309489116587333,
+ "early_third_alignment": 0.004803654310914378,
+ "mean_calibration_mse": 0.0001923398035258008,
+ "mean_parameter_update_rms": 0.011050459120615532,
+ "mean_prediction_target_cosine": 0.0014602501420039524,
+ "mean_target_power": 0.00019176158875808158
+ },
+ "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.1.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ },
+ {
+ "calibration_mode": "vectorizer_subspace",
+ "eta_A": 1.0,
+ "finite": true,
+ "metric_space": "vectorizer_parameter_gradients",
+ "metrics": {
+ "all_layer_alignment": 0.006801062087393611,
+ "early_third_alignment": 0.002233794856389674,
+ "mean_calibration_mse": 0.00019906028706469792,
+ "mean_parameter_update_rms": 0.01158272062540019,
+ "mean_prediction_target_cosine": -0.0001920852658946125,
+ "mean_target_power": 0.00019176158875808158
+ },
+ "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA1.0.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ }
+ ],
+ "score_change_rule": "mechanics/calibration alone cannot raise score",
+ "selected_v3": {
+ "calibration_mode": "vectorizer_subspace",
+ "eta_A": 0.01,
+ "finite": true,
+ "metric_space": "vectorizer_parameter_gradients",
+ "metrics": {
+ "all_layer_alignment": 0.0625791079364717,
+ "early_third_alignment": 0.007139206010227402,
+ "mean_calibration_mse": 0.00019177845804523746,
+ "mean_parameter_update_rms": 0.010982968905010668,
+ "mean_prediction_target_cosine": 0.0018218688400943384,
+ "mean_target_power": 0.00019176158875808158
+ },
+ "path": "results/oral_a_v3_calibration/vectorizer_subspace_etaA0.01.json",
+ "source_commit": "612196a53285b6efc44c0dd84699c7b57a6dc8e1"
+ },
+ "status": "failed"
+}