1
|
{"args": {"mode": "sdil", "dataset": "tentmap", "depth": 4, "width": 8, "act": "relu", "residual": 1, "residual_lesion_fraction": 0.3333333333333333, "epochs": 80, "batch_size": 256, "train_examples": 0, "val_examples": 2000, "split_seed": 2027, "eval_split": "validation", "task_seed": 0, "task_train_examples": 10000, "task_test_examples": 5000, "task_levels": 2, "task_n_in": 1, "task_classes": 10, "teacher_depth": 8, "teacher_width": 64, "teacher_residual": 1, "eta": 0.03, "eta_A": 0.01, "eta_P": 0.002, "momentum": 0.9, "w_scale": 1.0, "a_scale": 1.0, "feedback_scale": 1.0, "pert_sigma": 0.01, "pert_every": 4, "pert_ndirs": 4, "pert_mode": "layerwise", "use_residual": 1, "raw_scale_control": "none", "learn_A": 1, "learn_P": 1, "p_neutral": 1, "p_warmup_steps": 200, "p_warmup_eta": 0.05, "nuis_rho": 0.0, "traffic_seed": 1234, "traffic_mode": "none", "predictor_mode": "diagonal", "vectorizer_mode": "context_gated", "normalize_delta": 0, "settle_steps": 0, "kappa": 0.0, "feedback": "error", "seed": 0, "device": "cuda", "log_every": 100000, "diagnostics": "alignment", "diagnostics_schedule": "final", "eval_every": 0, "max_steps": 0, "probe_bs": 512, "outdir": "results", "tag": "c2_calibdev_v1_tent_l2_w8_context_k4_d4_t0_s0", "n_in": 1, "n_out": 2}, "split": {"dataset": "tentmap", "task_seed": 0, "train_examples": 8000, "test_examples": 5000, "evaluation_split": "validation", "synthetic_generator": true, "split_seed": 2027, "validation_examples": 2000, "validation_index_sha256": "f292d9bfeef1b6e79c80d4cf1c572ac12dee1be799a71a126390709d0386c6e4", "validation_class_counts": {"0": 1000, "1": 1000}, "split_from_training_only": true}, "provenance": {"git_commit": "9c99df512ba18217a7ec5f7d95175e490a6ba7f5", "git_dirty": false}, "diagnostic_protocol": {"probe_source": "training_prefix", "probe_examples": 512, "schedule": "final"}, "steps": [{"step": 0, "epoch": 0, "train_loss": 0.6903698444366455}, {"epoch_end": 0, "step": 32}, {"epoch_end": 1, "step": 64}, {"epoch_end": 2, "step": 96}, {"epoch_end": 3, "step": 128}, {"epoch_end": 4, "step": 160}, {"epoch_end": 5, "step": 192}, {"epoch_end": 6, "step": 224}, {"epoch_end": 7, "step": 256}, {"epoch_end": 8, "step": 288}, {"epoch_end": 9, "step": 320}, {"epoch_end": 10, "step": 352}, {"epoch_end": 11, "step": 384}, {"epoch_end": 12, "step": 416}, {"epoch_end": 13, "step": 448}, {"epoch_end": 14, "step": 480}, {"epoch_end": 15, "step": 512}, {"epoch_end": 16, "step": 544}, {"epoch_end": 17, "step": 576}, {"epoch_end": 18, "step": 608}, {"epoch_end": 19, "step": 640}, {"epoch_end": 20, "step": 672}, {"epoch_end": 21, "step": 704}, {"epoch_end": 22, "step": 736}, {"epoch_end": 23, "step": 768}, {"epoch_end": 24, "step": 800}, {"epoch_end": 25, "step": 832}, {"epoch_end": 26, "step": 864}, {"epoch_end": 27, "step": 896}, {"epoch_end": 28, "step": 928}, {"epoch_end": 29, "step": 960}, {"epoch_end": 30, "step": 992}, {"epoch_end": 31, "step": 1024}, {"epoch_end": 32, "step": 1056}, {"epoch_end": 33, "step": 1088}, {"epoch_end": 34, "step": 1120}, {"epoch_end": 35, "step": 1152}, {"epoch_end": 36, "step": 1184}, {"epoch_end": 37, "step": 1216}, {"epoch_end": 38, "step": 1248}, {"epoch_end": 39, "step": 1280}, {"epoch_end": 40, "step": 1312}, {"epoch_end": 41, "step": 1344}, {"epoch_end": 42, "step": 1376}, {"epoch_end": 43, "step": 1408}, {"epoch_end": 44, "step": 1440}, {"epoch_end": 45, "step": 1472}, {"epoch_end": 46, "step": 1504}, {"epoch_end": 47, "step": 1536}, {"epoch_end": 48, "step": 1568}, {"epoch_end": 49, "step": 1600}, {"epoch_end": 50, "step": 1632}, {"epoch_end": 51, "step": 1664}, {"epoch_end": 52, "step": 1696}, {"epoch_end": 53, "step": 1728}, {"epoch_end": 54, "step": 1760}, {"epoch_end": 55, "step": 1792}, {"epoch_end": 56, "step": 1824}, {"epoch_end": 57, "step": 1856}, {"epoch_end": 58, "step": 1888}, {"epoch_end": 59, "step": 1920}, {"epoch_end": 60, "step": 1952}, {"epoch_end": 61, "step": 1984}, {"epoch_end": 62, "step": 2016}, {"epoch_end": 63, "step": 2048}, {"epoch_end": 64, "step": 2080}, {"epoch_end": 65, "step": 2112}, {"epoch_end": 66, "step": 2144}, {"epoch_end": 67, "step": 2176}, {"epoch_end": 68, "step": 2208}, {"epoch_end": 69, "step": 2240}, {"epoch_end": 70, "step": 2272}, {"epoch_end": 71, "step": 2304}, {"epoch_end": 72, "step": 2336}, {"epoch_end": 73, "step": 2368}, {"epoch_end": 74, "step": 2400}, {"epoch_end": 75, "step": 2432}, {"epoch_end": 76, "step": 2464}, {"epoch_end": 77, "step": 2496}, {"epoch_end": 78, "step": 2528}, {"epoch_end": 79, "step": 2560}], "final": {"eval_split": "validation", "eval_acc": 0.969, "eval_loss": 0.08845006942749023, "wall_s": 17.606709480285645, "val_acc": 0.969, "val_loss": 0.08845006942749023, "cos_r_negg": [0.48526817560195923, 0.8153876066207886, 0.5922392010688782, 0.9952086210250854], "cos_innovation_negg": [0.48526817560195923, 0.8153876066207886, 0.5922392010688782, 0.9952086210250854], "cos_apical_negg": [0.48526817560195923, 0.8153876066207886, 0.5922392010688782, 0.9952086210250854], "cos_Ac_negg": [0.48526817560195923, 0.8153876066207886, 0.5922392010688782, 0.9952086210250854], "r_norm": [1.2112762928009033, 1.2245585918426514, 0.9780949950218201, 0.7144197225570679], "g_norm": [0.005882170982658863, 0.004561249166727066, 0.003075423650443554, 0.00182157673407346], "traffic_norm": [0.0, 0.0, 0.0, 0.0], "traffic_residual_norm": [0.0, 0.0, 0.0, 0.0], "traffic_r2": [NaN, NaN, NaN, NaN], "residual_lesion": {"interior_layers": [1, 2, 3], "lesioned_layers": [3], "branch_to_skip_rms": [0.7262412905693054, 1.0530037879943848, 0.6449858546257019], "lesion_eval_acc": 0.557, "lesion_eval_loss": 5.51016943359375, "lesion_acc_drop": 0.4119999999999999}}, "lesion_protocol": {"fraction_of_interior_blocks": 0.3333333333333333, "selection": "final_contiguous_interior_blocks", "probe_source": "training_prefix", "probe_examples": 512, "evaluation_split": "validation"}, "timing": {"warmup_wall_s": 0.0, "training_loop_wall_s": 17.487297296524048, "diagnostics_wall_s": 0.07443833351135254, "inline_diagnostics_wall_s": 0.0, "optimizer_wall_s_excluding_inline_diagnostics": 17.487297296524048, "evaluation_wall_s": 0.040146827697753906}, "cost": {"train_steps": 2560, "ordinary_training_forward_examples": 640000, "predictor_warmup_forward_examples": 0, "perturbation_events": 640, "calibration_batch_loss_evaluations": 21120, "calibration_example_loss_evaluations": 5406720, "calibration_forward_equivalent_examples": 2882370.370370366, "training_forward_equivalent_examples": 3522370.370370366, "max_perturbation_batch_expansion": 1}, "hardware": {"device": "cuda", "torch_version": "2.3.1+cu118", "cuda_device_name": "NVIDIA GeForce GTX 1080", "cuda_visible_devices": "7", "device_total_memory_bytes": 8507949056, "peak_memory_allocated_bytes": 17590784, "peak_memory_reserved_bytes": 23068672}}
|
