{ "apical_warmup": { "first": { "calibration_mse": 4.429747588407501e-08, "parameter_update_rms": 0.0002104696554947411, "prediction_target_cosine": -0.02308727157965524, "target_power": 4.4068150205784043e-08 }, "last": { "calibration_mse": NaN, "parameter_update_rms": NaN, "prediction_target_cosine": NaN, "target_power": NaN }, "mean": { "calibration_mse": NaN, "parameter_update_rms": NaN, "prediction_target_cosine": NaN, "target_power": NaN }, "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": 10.0, "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_etaA10.0.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": "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": NaN, "feedback_forward_cosine": [ NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN ], "feedback_forward_norm_ratio": [ NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN ], "innovation_negative_gradient_cosine": [ NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, NaN, NaN, NaN, NaN, NaN, NaN ], "normalization_state": "training_batch_stats_without_running_update", "raw_negative_gradient_cosine": [ NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, NaN, NaN, NaN, NaN, NaN, NaN ], "teaching_negative_gradient_cosine": [ NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, 0.0, NaN, NaN, NaN, NaN, NaN, NaN, NaN ], "wall_s": 0.11645221710205078 }, "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": 30.35198736190796, "evaluation_wall_s": 0.3776404857635498, "predictor_warmup_wall_s": 0.0, "timing_excludes_data_loading_hashing_and_model_construction": true, "total_timed_wall_s": 30.72986936569214, "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 } }