From 795d63a4764f6341c8a85471d8cdff310d69f394 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 10:56:46 -0500 Subject: results: select Oral-A apical vectorizers --- .../spatial_template_a0_etaA0.01.json | 378 +++++++++++++++++++++ 1 file changed, 378 insertions(+) create mode 100644 results/oral_a_apical_screen/spatial_template_a0_etaA0.01.json (limited to 'results/oral_a_apical_screen/spatial_template_a0_etaA0.01.json') diff --git a/results/oral_a_apical_screen/spatial_template_a0_etaA0.01.json b/results/oral_a_apical_screen/spatial_template_a0_etaA0.01.json new file mode 100644 index 0000000..d2403d8 --- /dev/null +++ b/results/oral_a_apical_screen/spatial_template_a0_etaA0.01.json @@ -0,0 +1,378 @@ +{ + "apical_warmup": { + "last": { + "calibration_mse": 518.2982058317765, + "prediction_target_cosine": 0.00015677468540085558, + "target_power": 518.2958984375 + }, + "steps": 100 + }, + "architecture": { + "adaptive_apical_parameters": 2260992, + "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": "spatial_template", + "vectorizer_parameters": 1884160 + }, + "args": { + "a_scale": 0.0, + "a_warmup_steps": 100, + "alignment_probe": 32, + "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_apical_screen/spatial_template_a0_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": "spatial_template", + "warmup_epochs": 0, + "weight_decay": 0.0001, + "weight_scale": 1.0, + "width": 16 + }, + "counters": { + "apical_warmup_examples": 12688, + "calibration_event_examples": 12688, + "causal_scalar_observations": 200, + "logical_batch_loss_queries": 200, + "ordinary_examples": 0, + "per_example_loss_terms": 25376, + "perturbation_events": 100, + "perturbation_forward_examples": 25376, + "predictor_warmup_examples": 0 + }, + "diagnostics": { + "early_third_mean": 5.210153176449239e-05, + "innovation_negative_gradient_cosine": [ + 0.001460368512198329, + -0.001773762283846736, + 0.0005576296243816614, + 0.002642326755449176, + -0.0018755876226350665, + -0.0006983657949604094, + -0.0005098751280456781, + 0.0053292931988835335, + -0.003289436688646674, + 0.0009565821383148432, + 0.007996374741196632, + 0.005934947170317173, + 0.0008049617754295468, + 0.0010773323010653257, + 0.0031135338358581066, + 0.00604074215516448, + -0.0038750299718230963, + 0.0030057388357818127, + 0.005638218019157648 + ], + "normalization_state": "training_batch_stats_without_running_update", + "raw_negative_gradient_cosine": [ + 0.001460368512198329, + -0.001773762283846736, + 0.0005576296243816614, + 0.002642326755449176, + -0.0018755876226350665, + -0.0006983657949604094, + -0.0005098751280456781, + 0.0053292931988835335, + -0.003289436688646674, + 0.0009565821383148432, + 0.007996374741196632, + 0.005934947170317173, + 0.0008049617754295468, + 0.0010773323010653257, + 0.0031135338358581066, + 0.00604074215516448, + -0.0038750299718230963, + 0.0030057388357818127, + 0.005638218019157648 + ], + "teaching_negative_gradient_cosine": [ + 0.001460368512198329, + -0.001773762283846736, + 0.0005576296243816614, + 0.002642326755449176, + -0.0018755876226350665, + -0.0006983657949604094, + -0.0005098751280456781, + 0.0053292931988835335, + -0.003289436688646674, + 0.0009565821383148432, + 0.007996374741196632, + 0.005934947170317173, + 0.0008049617754295468, + 0.0010773323010653257, + 0.0031135338358581066, + 0.00604074215516448, + -0.0038750299718230963, + 0.0030057388357818127, + 0.005638218019157648 + ], + "wall_s": 0.09761571884155273 + }, + "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": 1742341632, + "peak_memory_reserved_bytes": 2699034624, + "torch_version": "2.3.1+cu118" + }, + "protocol_family": "oral_a_cifar_local_resnet_development", + "provenance": { + "git_commit": "a1d060e6d96d4ab973d16cd75149dd61899c7c95", + "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": 5.951646089553833, + "evaluation_wall_s": 0.37953901290893555, + "predictor_warmup_wall_s": 0.0, + "timing_excludes_data_loading_hashing_and_model_construction": true, + "total_timed_wall_s": 6.331512212753296, + "train_wall_s": 0.0 + }, + "work": { + "apical_macs_per_example": 1884160, + "causal_scalar_observations": 200, + "components": { + "apical_projection_macs": 23906222080, + "apical_regression_macs": 23906222080, + "bp_reverse_macs_estimate": 0, + "local_weight_correlation_macs": 0, + "ordinary_forward_macs": 0, + "perturbation_forward_macs": 1029023191040, + "warmup_clean_forward_macs": 514511595520 + }, + "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": 200, + "per_example_cross_entropy_terms": 25376, + "total_clean_forward_examples": 12688, + "total_forward_equivalent_examples": 38064, + "total_macs_estimate": 1591347230720 + } +} -- cgit v1.2.3