diff options
Diffstat (limited to 'results/mirror_causal_capture/wm_etaM0.1.json')
| -rw-r--r-- | results/mirror_causal_capture/wm_etaM0.1.json | 451 |
1 files changed, 451 insertions, 0 deletions
diff --git a/results/mirror_causal_capture/wm_etaM0.1.json b/results/mirror_causal_capture/wm_etaM0.1.json new file mode 100644 index 0000000..fe2506a --- /dev/null +++ b/results/mirror_causal_capture/wm_etaM0.1.json @@ -0,0 +1,451 @@ +{ + "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": 0, + "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": 0.01, + "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, + "mirror_batch_size": 1, + "mirror_eta": 0.1, + "mirror_every": 16, + "mirror_noise_std": 1.0, + "mirror_seed": 3000, + "mirror_warmup_steps": 20, + "mode": "wm", + "momentum": 0.9, + "normalization": "batchnorm", + "nuisance_scale": 0.0, + "out": "results/mirror_causal_capture/wm_etaM0.1.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": "local_parent_child_response", + "counters": { + "apical_warmup_examples": 0, + "calibration_event_examples": 0, + "causal_scalar_observations": 0, + "logical_batch_loss_queries": 0, + "mirror_conv_examples": 20, + "mirror_events": 20, + "mirror_readout_examples": 20480, + "ordinary_examples": 0, + "per_example_loss_terms": 0, + "perturbation_events": 0, + "perturbation_forward_examples": 0, + "predictor_warmup_examples": 0 + }, + "diagnostics": { + "early_third_mean": 0.44614077111085254, + "feedback_forward_cosine": [ + 0.9858509302139282, + 0.9850707054138184, + 0.9865717887878418, + 0.9863734841346741, + 0.9856951236724854, + 0.9871067404747009, + 0.9731586575508118, + 0.9550088047981262, + 0.9547361135482788, + 0.9553405046463013, + 0.954055905342102, + 0.9542233943939209, + 0.8649038672447205, + 0.7760670185089111, + 0.7740859985351562, + 0.7775933742523193, + 0.7737482190132141, + 0.7765145301818848, + 0.9880185127258301 + ], + "feedback_forward_norm_ratio": [ + 0.8923099637031555, + 0.8901821374893188, + 0.8893439173698425, + 0.8961004018783569, + 0.8912216424942017, + 0.8968877196311951, + 0.9173983335494995, + 0.9227779507637024, + 0.914923369884491, + 0.9082641005516052, + 0.9238913059234619, + 0.9232812523841858, + 1.0126720666885376, + 1.1361547708511353, + 1.1570484638214111, + 1.1266412734985352, + 1.137105941772461, + 1.1543664932250977, + 0.8931937217712402 + ], + "innovation_negative_gradient_cosine": [ + 0.43270143866539, + 0.43993276357650757, + 0.44664573669433594, + 0.44853127002716064, + 0.4532058835029602, + 0.455827534198761, + 0.4590722918510437, + 0.4557003974914551, + 0.47527873516082764, + 0.4777085483074188, + 0.5002998113632202, + 0.49793124198913574, + 0.5148465633392334, + 0.4711496829986572, + 0.6135821342468262, + 0.6229155659675598, + 0.7880423665046692, + 0.758634626865387, + 0.9890177249908447 + ], + "normalization_state": "training_batch_stats_without_running_update", + "raw_negative_gradient_cosine": [ + 0.43270143866539, + 0.43993276357650757, + 0.44664573669433594, + 0.44853127002716064, + 0.4532058835029602, + 0.455827534198761, + 0.4590722918510437, + 0.4557003974914551, + 0.47527873516082764, + 0.4777085483074188, + 0.5002998113632202, + 0.49793124198913574, + 0.5148465633392334, + 0.4711496829986572, + 0.6135821342468262, + 0.6229155659675598, + 0.7880423665046692, + 0.758634626865387, + 0.9890177249908447 + ], + "teaching_negative_gradient_cosine": [ + 0.43270143866539, + 0.43993276357650757, + 0.44664573669433594, + 0.44853127002716064, + 0.4532058835029602, + 0.455827534198761, + 0.4590722918510437, + 0.4557003974914551, + 0.47527873516082764, + 0.4777085483074188, + 0.5002998113632202, + 0.49793124198913574, + 0.5148465633392334, + 0.4711496829986572, + 0.6135821342468262, + 0.6229155659675598, + 0.7880423665046692, + 0.758634626865387, + 0.9890177249908447 + ], + "wall_s": 0.15237092971801758 + }, + "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", + "device_total_memory_bytes": 8507949056, + "peak_memory_allocated_bytes": 1730634752, + "peak_memory_reserved_bytes": 2181038080, + "torch_version": "2.3.1+cu118" + }, + "mirror_warmup": { + "first": { + "conv_batch_size": 1, + "mirror_estimate_rms": 0.1821084153449638, + "mirror_update_rms": 0.19537643727527548, + "readout_batch_size": 1024 + }, + "last": { + "conv_batch_size": 1, + "mirror_estimate_rms": 0.18073508053859827, + "mirror_update_rms": 0.17050672066264347, + "readout_batch_size": 1024 + }, + "mean": { + "conv_batch_size": 1.0, + "mirror_estimate_rms": 0.1793198434405597, + "mirror_update_rms": 0.17517745811581048, + "readout_batch_size": 1024.0 + }, + "steps": 20 + }, + "protocol_family": "oral_a_cifar_local_resnet_development", + "provenance": { + "git_commit": "37cf78b7f696c9eedc0745ebdaa656bff0ab2f81", + "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": 0.0, + "evaluation_wall_s": 0.4133622646331787, + "mirror_warmup_wall_s": 0.5381975173950195, + "predictor_warmup_wall_s": 0.0, + "timing_excludes_data_loading_hashing_and_model_construction": true, + "total_timed_wall_s": 0.9518508911132812, + "train_wall_s": 0.0 + }, + "work": { + "apical_macs_per_example": 40108672, + "causal_scalar_observations": 0, + "components": { + "apical_projection_macs": 0, + "apical_regression_macs": 0, + "bp_reverse_macs_estimate": 0, + "local_weight_correlation_macs": 0, + "mirror_local_correlation_macs": 815267840, + "mirror_response_macs": 815267840, + "ordinary_forward_macs": 0, + "perturbation_forward_macs": 0, + "warmup_clean_forward_macs": 0 + }, + "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": 0, + "mirror_probe_examples": 20, + "mirror_readout_probe_examples": 20480, + "per_example_cross_entropy_terms": 0, + "total_clean_forward_examples": 0, + "total_forward_equivalent_examples": 0, + "total_macs_estimate": 1630535680 + } +} |
