diff options
Diffstat (limited to 'results/oral_a_v5_calibration/result.json')
| -rw-r--r-- | results/oral_a_v5_calibration/result.json | 404 |
1 files changed, 404 insertions, 0 deletions
diff --git a/results/oral_a_v5_calibration/result.json b/results/oral_a_v5_calibration/result.json new file mode 100644 index 0000000..ac9f477 --- /dev/null +++ b/results/oral_a_v5_calibration/result.json @@ -0,0 +1,404 @@ +{ + "architecture": { + "adaptive_feedback_parameters": 267904, + "family": "CIFAR 6n+2 ResNet, option-A shortcuts", + "feedback_macs_per_example": 40108672, + "forward_macs_per_example": 40551040, + "forward_parameters": 269722 + }, + "finite": true, + "fixed_hfa": { + "all_layer_alignment": 0.01127886861764924, + "early_third_alignment": -0.00026316156436223537, + "feedback_forward_cosine": [ + 0.0008809715509414673, + -0.002320552244782448, + 0.03730485588312149, + 0.02497659996151924, + -0.03438456356525421, + -0.001257734838873148, + 0.023045765236020088, + 0.010684739798307419, + -0.013966654427349567, + -0.03158111870288849, + 0.009583890438079834, + -9.433389641344547e-05, + 0.004490766208618879, + -0.004784357734024525, + 0.004104882013052702, + 0.004543168004602194, + -0.005818712059408426, + 0.0014950999757274985, + 0.003767170011997223 + ], + "feedback_forward_norm_ratio": [ + 0.9996462464332581, + 1.0550107955932617, + 0.9593725800514221, + 1.0017613172531128, + 0.999921441078186, + 0.9631232619285583, + 0.9992203712463379, + 0.9976226687431335, + 1.0018895864486694, + 1.0030434131622314, + 1.0180330276489258, + 1.0107296705245972, + 0.9962885975837708, + 0.9891077876091003, + 1.0009011030197144, + 1.0021207332611084, + 1.0043002367019653, + 1.0021206140518188, + 0.9992877244949341 + ], + "max_feedback_forward_norm_ratio": 1.0550107955932617, + "mean_feedback_forward_cosine": 0.0016142042954207252, + "min_feedback_forward_norm_ratio": 0.9593725800514221, + "per_layer": [ + -0.0005718563916161656, + -0.0006265100091695786, + 0.0012021171860396862, + 3.7638936191797256e-05, + 0.0004848289827350527, + -0.002105188090354204, + 0.0032924648839980364, + 0.0002729729749262333, + 0.0075433761812746525, + -0.005317362025380135, + 0.009830434806644917, + -0.001097709871828556, + 0.02368866838514805, + 0.007433340419083834, + 0.04359162598848343, + 0.0057456037029623985, + 0.039965368807315826, + 0.0030560996383428574, + 0.07787258923053741 + ] + }, + "hardware": { + "cuda_device_name": "NVIDIA GeForce GTX 1080", + "cuda_visible_devices": "5", + "device": "cuda", + "peak_memory_allocated_bytes": 986384384, + "torch_version": "2.3.1+cu118" + }, + "learned_lcb": { + "all_layer_alignment": 0.0866869534748778, + "early_third_alignment": 0.0011474320829923574, + "feedback_forward_cosine": [ + -0.004378448240458965, + -0.007337348069995642, + 0.04171781986951828, + 0.02352023683488369, + -0.039886925369501114, + 0.0006825287127867341, + 0.02527846209704876, + 0.0136695746332407, + -0.011026157066226006, + -0.027840018272399902, + 0.00775768980383873, + 0.00863435585051775, + 0.009166959673166275, + 0.0012933104299008846, + 0.010724963620305061, + 0.011407784186303616, + 0.004035680089145899, + 0.005515150260180235, + 0.17713752388954163 + ], + "feedback_forward_norm_ratio": [ + 0.9522605538368225, + 0.9822989702224731, + 0.9040371775627136, + 0.9258716702461243, + 0.9323726892471313, + 0.8777714967727661, + 0.9508335590362549, + 0.9598008394241333, + 0.9715808629989624, + 0.9627054333686829, + 0.9862542152404785, + 0.972489595413208, + 0.9752699136734009, + 0.9769584536552429, + 0.9962733387947083, + 0.9905397295951843, + 1.0036309957504272, + 0.9967941641807556, + 0.8897679448127747 + ], + "max_feedback_forward_norm_ratio": 1.0036309957504272, + "mean_feedback_forward_cosine": 0.0131617443648314, + "min_feedback_forward_norm_ratio": 0.8777714967727661, + "per_layer": [ + -0.0008834822801873088, + -0.0023195152170956135, + 0.0026626307517290115, + -0.00018003323930315673, + 0.00810601282864809, + -0.0005010203458368778, + 0.017151430249214172, + -0.0013304761378094554, + 0.03392089158296585, + -0.0038246146868914366, + 0.06399191915988922, + 0.011081752367317677, + 0.11008386313915253, + 0.052304450422525406, + 0.1991788148880005, + 0.13974127173423767, + 0.2924402058124542, + 0.38367098569869995, + 0.34175702929496765 + ] + }, + "method_audit": { + "causal_query_normalization_state": "evaluation_running_statistics", + "forward_state_max_absolute_difference": 0.0, + "forward_weight_reads_in_feedback_update": 0, + "ordinary_task_normalization_state": "not_run_forward_frozen", + "reverse_mode_learning_operations": 0 + }, + "protocol": "oral_a_v5_layerwise_causal_bootstrap_capture_v1", + "provenance": { + "git_commit": "640522076c770d0746dc58dde868586ace568752", + "git_tracked_dirty": false + }, + "schema_version": 1, + "settings": { + "alignment_probe": 64, + "batch_size": 128, + "calibration_augmentation": false, + "depth": 20, + "eta_A": 0.1, + "feedback_scale": 1.0, + "loader_seed": 0, + "normalization": "batchnorm", + "perturb_seed": 5000, + "residual_scale": 1.0, + "seed": 0, + "sigma": 0.01, + "split_seed": 2027, + "sweeps": 20, + "train_limit": 10000, + "val_examples": 5000, + "width": 16 + }, + "split": { + "dataset": "cifar10", + "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": "none", + "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" + }, + "sweeps": [ + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.06403723350284288, + "mean_field_prediction_target_cosine": 0.0004417389199711075, + "mean_parameter_update_rms": 0.03444637028278504, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.06253894281438753, + "mean_field_prediction_target_cosine": 0.0018398856551996173, + "mean_parameter_update_rms": 0.03581342072986328, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.06352942784015662, + "mean_field_prediction_target_cosine": 0.0007146904780988803, + "mean_parameter_update_rms": 0.037026025369156314, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.06931613884208412, + "mean_field_prediction_target_cosine": 0.0020960899414459977, + "mean_parameter_update_rms": 0.03692294811063335, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.07834713139232216, + "mean_field_prediction_target_cosine": 0.0013170423593140336, + "mean_parameter_update_rms": 0.039807939050467284, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.07501814697739963, + "mean_field_prediction_target_cosine": 0.002235385887437107, + "mean_parameter_update_rms": 0.04167423709322971, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.08537822862592329, + "mean_field_prediction_target_cosine": 0.0018632679655232866, + "mean_parameter_update_rms": 0.04244392278182938, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.08774229177580244, + "mean_field_prediction_target_cosine": 0.003061714145077791, + "mean_parameter_update_rms": 0.04222976858811638, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.09508034534172614, + "mean_field_prediction_target_cosine": 0.00234870503581423, + "mean_parameter_update_rms": 0.043422751889732325, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.09905501294247436, + "mean_field_prediction_target_cosine": 0.003315453860516912, + "mean_parameter_update_rms": 0.04370078720903135, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.1189526810892697, + "mean_field_prediction_target_cosine": 0.0028806602201959576, + "mean_parameter_update_rms": 0.046994848933308166, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.08835658663303694, + "mean_field_prediction_target_cosine": 0.0036876431588643115, + "mean_parameter_update_rms": 0.0414807426622568, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.09948273630711328, + "mean_field_prediction_target_cosine": 0.0031894343839509965, + "mean_parameter_update_rms": 0.04500005709476786, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.11277010760757089, + "mean_field_prediction_target_cosine": 0.0036998344357462333, + "mean_parameter_update_rms": 0.04482713238777737, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.10252816278564553, + "mean_field_prediction_target_cosine": 0.004821155006692386, + "mean_parameter_update_rms": 0.041077959193793326, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.10446445100929329, + "mean_field_prediction_target_cosine": 0.0029003324771935436, + "mean_parameter_update_rms": 0.04271476741395773, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.10518028307101368, + "mean_field_prediction_target_cosine": 0.004133514758470006, + "mean_parameter_update_rms": 0.048030305729152116, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.11175108755039062, + "mean_field_prediction_target_cosine": 0.0042756213137445384, + "mean_parameter_update_rms": 0.04818789939741672, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.13193168146187756, + "mean_field_prediction_target_cosine": 0.004254287067517157, + "mean_parameter_update_rms": 0.049472996929179495, + "per_example_causal_observations": 2432 + }, + { + "events": 19, + "logical_batch_loss_queries": 38, + "max_parameter_update_rms": 0.11125775394135021, + "mean_field_prediction_target_cosine": 0.00429639637704831, + "mean_parameter_update_rms": 0.048118302209782284, + "per_example_causal_observations": 2432 + } + ], + "test_examples_touched": 0, + "validation_endpoints_observed": 0, + "wall_seconds": 13.465652227401733, + "work": { + "clean_forward_examples": 2560, + "edge_events": 380, + "forward_macs": 4048615833600, + "hierarchical_teaching_and_local_correlation_macs_estimate": 1950885806080, + "logical_batch_loss_queries": 760, + "per_example_causal_observations": 48640, + "per_example_cross_entropy_terms": 97280, + "perturbation_forward_examples": 97280, + "total_macs_estimate": 5999501639680 + } +} |