summaryrefslogtreecommitdiff
path: root/results/oral_a_short/dfa_lr0.1.json
diff options
context:
space:
mode:
Diffstat (limited to 'results/oral_a_short/dfa_lr0.1.json')
-rw-r--r--results/oral_a_short/dfa_lr0.1.json464
1 files changed, 464 insertions, 0 deletions
diff --git a/results/oral_a_short/dfa_lr0.1.json b/results/oral_a_short/dfa_lr0.1.json
new file mode 100644
index 0000000..33aad3d
--- /dev/null
+++ b/results/oral_a_short/dfa_lr0.1.json
@@ -0,0 +1,464 @@
+{
+ "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": 1.0,
+ "a_warmup_steps": 0,
+ "alignment_probe": 0,
+ "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": 20,
+ "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": "cosine",
+ "max_steps": 0,
+ "mode": "dfa",
+ "momentum": 0.9,
+ "normalization": "batchnorm",
+ "nuisance_scale": 0.0,
+ "out": "results/oral_a_short/dfa_lr0.1.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
+ },
+ "counters": {
+ "apical_warmup_examples": 0,
+ "calibration_event_examples": 0,
+ "causal_scalar_observations": 0,
+ "logical_batch_loss_queries": 0,
+ "ordinary_examples": 200000,
+ "per_example_loss_terms": 0,
+ "perturbation_events": 0,
+ "perturbation_forward_examples": 0,
+ "predictor_warmup_examples": 0
+ },
+ "diagnostics": null,
+ "epochs": [
+ {
+ "epoch": 1,
+ "lr": 0.1,
+ "output_lr": 0.1,
+ "step": 79,
+ "train_examples": 10000,
+ "train_loss": 2.835949954223633
+ },
+ {
+ "epoch": 2,
+ "lr": 0.0993844170297569,
+ "output_lr": 0.0993844170297569,
+ "step": 158,
+ "train_examples": 10000,
+ "train_loss": 2.8182399749755858
+ },
+ {
+ "epoch": 3,
+ "lr": 0.09755282581475769,
+ "output_lr": 0.09755282581475769,
+ "step": 237,
+ "train_examples": 10000,
+ "train_loss": 4.338047203826904
+ },
+ {
+ "epoch": 4,
+ "lr": 0.09455032620941839,
+ "output_lr": 0.09455032620941839,
+ "step": 316,
+ "train_examples": 10000,
+ "train_loss": 4.830230680847168
+ },
+ {
+ "epoch": 5,
+ "lr": 0.09045084971874738,
+ "output_lr": 0.09045084971874738,
+ "step": 395,
+ "train_examples": 10000,
+ "train_loss": 4.160814493560791
+ },
+ {
+ "epoch": 6,
+ "lr": 0.08535533905932738,
+ "output_lr": 0.08535533905932738,
+ "step": 474,
+ "train_examples": 10000,
+ "train_loss": 7.872198279571533
+ },
+ {
+ "epoch": 7,
+ "lr": 0.07938926261462366,
+ "output_lr": 0.07938926261462366,
+ "step": 553,
+ "train_examples": 10000,
+ "train_loss": 5.239408417892456
+ },
+ {
+ "epoch": 8,
+ "lr": 0.07269952498697733,
+ "output_lr": 0.07269952498697733,
+ "step": 632,
+ "train_examples": 10000,
+ "train_loss": 7.5435514030456545
+ },
+ {
+ "epoch": 9,
+ "lr": 0.06545084971874737,
+ "output_lr": 0.06545084971874737,
+ "step": 711,
+ "train_examples": 10000,
+ "train_loss": 6.3907674743652345
+ },
+ {
+ "epoch": 10,
+ "lr": 0.05782172325201155,
+ "output_lr": 0.05782172325201155,
+ "step": 790,
+ "train_examples": 10000,
+ "train_loss": 8.492947927856445
+ },
+ {
+ "epoch": 11,
+ "lr": 0.05,
+ "output_lr": 0.05,
+ "step": 869,
+ "train_examples": 10000,
+ "train_loss": 5.571098100280762
+ },
+ {
+ "epoch": 12,
+ "lr": 0.04217827674798845,
+ "output_lr": 0.04217827674798845,
+ "step": 948,
+ "train_examples": 10000,
+ "train_loss": 5.536634136199951
+ },
+ {
+ "epoch": 13,
+ "lr": 0.03454915028125263,
+ "output_lr": 0.03454915028125263,
+ "step": 1027,
+ "train_examples": 10000,
+ "train_loss": 4.147188665771484
+ },
+ {
+ "epoch": 14,
+ "lr": 0.027300475013022664,
+ "output_lr": 0.027300475013022664,
+ "step": 1106,
+ "train_examples": 10000,
+ "train_loss": 2.4310934539794924
+ },
+ {
+ "epoch": 15,
+ "lr": 0.02061073738537635,
+ "output_lr": 0.02061073738537635,
+ "step": 1185,
+ "train_examples": 10000,
+ "train_loss": 2.091388729095459
+ },
+ {
+ "epoch": 16,
+ "lr": 0.014644660940672627,
+ "output_lr": 0.014644660940672627,
+ "step": 1264,
+ "train_examples": 10000,
+ "train_loss": 2.1787188812255858
+ },
+ {
+ "epoch": 17,
+ "lr": 0.009549150281252633,
+ "output_lr": 0.009549150281252633,
+ "step": 1343,
+ "train_examples": 10000,
+ "train_loss": 1.9502821924209595
+ },
+ {
+ "epoch": 18,
+ "lr": 0.005449673790581611,
+ "output_lr": 0.005449673790581611,
+ "step": 1422,
+ "train_examples": 10000,
+ "train_loss": 1.8884031147003173
+ },
+ {
+ "epoch": 19,
+ "lr": 0.0024471741852423235,
+ "output_lr": 0.0024471741852423235,
+ "step": 1501,
+ "train_examples": 10000,
+ "train_loss": 1.8296160148620606
+ },
+ {
+ "epoch": 20,
+ "lr": 0.0006155829702431171,
+ "output_lr": 0.0006155829702431171,
+ "step": 1580,
+ "train_examples": 10000,
+ "train_loss": 1.809558029937744
+ }
+ ],
+ "evaluation_protocol": {
+ "test_evaluations": 0,
+ "test_used_for_selection": false,
+ "validation_evaluations": 1
+ },
+ "final": {
+ "accuracy": 0.3642,
+ "epoch": 20,
+ "evaluation_split": "validation",
+ "finite": true,
+ "loss": 1.7964451171875,
+ "step": 1580
+ },
+ "hardware": {
+ "cuda_device_name": "NVIDIA GeForce GTX 1080",
+ "cuda_visible_devices": "5",
+ "device": "cuda:0",
+ "device_total_memory_bytes": 8507949056,
+ "peak_memory_allocated_bytes": 1739555840,
+ "peak_memory_reserved_bytes": 2424307712,
+ "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": 0.0,
+ "evaluation_wall_s": 0.36763930320739746,
+ "predictor_warmup_wall_s": 0.0,
+ "timing_excludes_data_loading_hashing_and_model_construction": true,
+ "total_timed_wall_s": 74.36485743522644,
+ "train_wall_s": 73.99453210830688
+ },
+ "work": {
+ "apical_macs_per_example": 1884160,
+ "causal_scalar_observations": 0,
+ "components": {
+ "apical_projection_macs": 376832000000,
+ "apical_regression_macs": 0,
+ "bp_reverse_macs_estimate": 0,
+ "local_weight_correlation_macs": 8110208000000,
+ "ordinary_forward_macs": 8110208000000,
+ "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,
+ "per_example_cross_entropy_terms": 0,
+ "total_clean_forward_examples": 200000,
+ "total_forward_equivalent_examples": 200000,
+ "total_macs_estimate": 16597248000000
+ }
+}
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-01 15:14:26 +0000