summaryrefslogtreecommitdiff
path: root/results/oral_a_v4_calibration/learned_hfa_etaA0.1.json
diff options
context:
space:
mode:
Diffstat (limited to 'results/oral_a_v4_calibration/learned_hfa_etaA0.1.json')
-rw-r--r--results/oral_a_v4_calibration/learned_hfa_etaA0.1.json437
1 files changed, 437 insertions, 0 deletions
diff --git a/results/oral_a_v4_calibration/learned_hfa_etaA0.1.json b/results/oral_a_v4_calibration/learned_hfa_etaA0.1.json
new file mode 100644
index 0000000..e92cc38
--- /dev/null
+++ b/results/oral_a_v4_calibration/learned_hfa_etaA0.1.json
@@ -0,0 +1,437 @@
+{
+ "apical_warmup": {
+ "first": {
+ "calibration_mse": 4.429747588410153e-08,
+ "parameter_update_rms": 0.00021046965549480413,
+ "prediction_target_cosine": -0.02308727157707865,
+ "target_power": 4.4068150205784043e-08
+ },
+ "last": {
+ "calibration_mse": 7.57351844983796e-08,
+ "parameter_update_rms": 0.00027520026253326793,
+ "prediction_target_cosine": 0.008176687138101971,
+ "target_power": 7.566517331129459e-08
+ },
+ "mean": {
+ "calibration_mse": 1.2829968753120993e-06,
+ "parameter_update_rms": 0.0009033753133269748,
+ "prediction_target_cosine": 0.0006682040486695352,
+ "target_power": 1.2829480604683788e-06
+ },
+ "steps": 400
+ },
+ "architecture": {
+ "adaptive_apical_parameters": 0,
+ "adaptive_feedback_parameters": 267904,
+ "base_width": 16,
+ "blocks_per_stage": 3,
+ "bn_eps": 1e-05,
+ "bn_momentum": 0.1,
+ "depth": 20,
+ "family": "CIFAR 6n+2 ResNet, option-A shortcuts",
+ "fixed_feedback_parameters": 0,
+ "fixed_traffic_coefficients": 0,
+ "forward_parameters": 269722,
+ "hidden_shapes": [
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 16,
+ 32,
+ 32
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 32,
+ 16,
+ 16
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ],
+ [
+ 64,
+ 8,
+ 8
+ ]
+ ],
+ "normalization": "batchnorm",
+ "predictor_parameters": 0,
+ "residual_scale": 1.0,
+ "vectorizer_mode": null,
+ "vectorizer_parameters": 0
+ },
+ "args": {
+ "a_scale": 1.0,
+ "a_warmup_steps": 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",
+ "epochs": 0,
+ "eta_A": 0.1,
+ "eta_P": 0.01,
+ "eval_every": 0,
+ "eval_split": "validation",
+ "learn_P": 0,
+ "loader_seed": 0,
+ "lr": 0.1,
+ "lr_gamma": 0.1,
+ "lr_milestones": "100,150",
+ "lr_schedule": "constant",
+ "max_steps": 0,
+ "mode": "lhfa",
+ "momentum": 0.9,
+ "normalization": "batchnorm",
+ "nuisance_scale": 0.0,
+ "out": "results/oral_a_v4_calibration/learned_hfa_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": "spatial_template",
+ "warmup_epochs": 0,
+ "weight_decay": 0.0001,
+ "weight_scale": 1.0,
+ "width": 16
+ },
+ "calibration_metric_space": "hierarchical_feedback_parameters",
+ "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": -0.0001799722813302651,
+ "feedback_forward_cosine": [
+ 0.00087751355022192,
+ -0.002306785434484482,
+ 0.03730355575680733,
+ 0.024973055347800255,
+ -0.03437461704015732,
+ -0.0012589972466230392,
+ 0.02304646745324135,
+ 0.010723255574703217,
+ -0.013957379385828972,
+ -0.03159216791391373,
+ 0.009621845558285713,
+ -8.752243593335152e-05,
+ 0.0044714659452438354,
+ -0.004768045619130135,
+ 0.004082047380506992,
+ 0.004587260074913502,
+ -0.005784230772405863,
+ 0.0014915686333552003,
+ 0.057022809982299805
+ ],
+ "feedback_forward_norm_ratio": [
+ 0.9984350204467773,
+ 1.0541573762893677,
+ 0.9591503143310547,
+ 1.0013585090637207,
+ 0.9998340606689453,
+ 0.9629143476486206,
+ 0.9992043972015381,
+ 0.9973520040512085,
+ 1.0017883777618408,
+ 1.0028769969940186,
+ 1.0179988145828247,
+ 1.0106147527694702,
+ 0.9962611794471741,
+ 0.9889401793479919,
+ 1.0009331703186035,
+ 1.00214684009552,
+ 1.0044093132019043,
+ 1.0020496845245361,
+ 1.0028640031814575
+ ],
+ "innovation_negative_gradient_cosine": [
+ -0.000455486006103456,
+ -0.00046591833233833313,
+ 0.0007518491474911571,
+ -0.00010768519132398069,
+ 0.0012330973986536264,
+ -0.0020356907043606043,
+ 0.004193619824945927,
+ 0.00030038447584956884,
+ 0.009274046868085861,
+ -0.004511808976531029,
+ 0.0123829934746027,
+ 0.0020061261020600796,
+ 0.024534553289413452,
+ -0.0031216288916766644,
+ 0.05966883897781372,
+ 0.010687511414289474,
+ 0.0716584175825119,
+ -0.002210831269621849,
+ 0.1456024944782257
+ ],
+ "normalization_state": "training_batch_stats_without_running_update",
+ "raw_negative_gradient_cosine": [
+ -0.000455486006103456,
+ -0.00046591833233833313,
+ 0.0007518491474911571,
+ -0.00010768519132398069,
+ 0.0012330973986536264,
+ -0.0020356907043606043,
+ 0.004193619824945927,
+ 0.00030038447584956884,
+ 0.009274046868085861,
+ -0.004511808976531029,
+ 0.0123829934746027,
+ 0.0020061261020600796,
+ 0.024534553289413452,
+ -0.0031216288916766644,
+ 0.05966883897781372,
+ 0.010687511414289474,
+ 0.0716584175825119,
+ -0.002210831269621849,
+ 0.1456024944782257
+ ],
+ "teaching_negative_gradient_cosine": [
+ -0.000455486006103456,
+ -0.00046591833233833313,
+ 0.0007518491474911571,
+ -0.00010768519132398069,
+ 0.0012330973986536264,
+ -0.0020356907043606043,
+ 0.004193619824945927,
+ 0.00030038447584956884,
+ 0.009274046868085861,
+ -0.004511808976531029,
+ 0.0123829934746027,
+ 0.0020061261020600796,
+ 0.024534553289413452,
+ -0.0031216288916766644,
+ 0.05966883897781372,
+ 0.010687511414289474,
+ 0.0716584175825119,
+ -0.002210831269621849,
+ 0.1456024944782257
+ ],
+ "wall_s": 0.11083364486694336
+ },
+ "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",
+ "device_total_memory_bytes": 8507949056,
+ "peak_memory_allocated_bytes": 1951938048,
+ "peak_memory_reserved_bytes": 2814377984,
+ "torch_version": "2.3.1+cu118"
+ },
+ "protocol_family": "oral_a_cifar_local_resnet_development",
+ "provenance": {
+ "git_commit": "d4a521072a25d8afdd62021f43538d7dad7586fd",
+ "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": 30.135460138320923,
+ "evaluation_wall_s": 0.36730265617370605,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 30.503045558929443,
+ "train_wall_s": 0.0
+ },
+ "work": {
+ "apical_macs_per_example": 40108672,
+ "causal_scalar_observations": 800,
+ "components": {
+ "apical_projection_macs": 2031103150080,
+ "apical_regression_macs": 4062206300160,
+ "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": 12253823447040
+ }
+}
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-01 00:54:58 +0000