1
|
{"args": {"mode": "bp", "dataset": "cifar10", "depth": 30, "width": 64, "act": "tanh", "residual": 1, "epochs": 5, "batch_size": 128, "eta": 0.05, "eta_A": 0.02, "eta_P": 0.002, "momentum": 0.9, "w_scale": 1.0, "a_scale": 1.0, "pert_sigma": 0.01, "pert_every": 4, "pert_ndirs": 16, "pert_mode": "simultaneous", "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, "predictor_mode": "diagonal", "normalize_delta": 0, "settle_steps": 0, "kappa": 0.0, "feedback": "error", "seed": 2, "device": "cuda", "log_every": 500, "max_steps": 0, "probe_bs": 256, "outdir": "results", "tag": "scale_v3_cifar10_bp_w64_d30_s2", "n_in": 3072}, "provenance": {"git_commit": "c8a372cae2612839bdbdafcf9c114f52cb4a6de3", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.7673251628875732}, {"epoch_end": 0, "step": 391, "test_acc": 0.361, "test_loss": 1.8110815307617187}, {"step": 500, "epoch": 1, "train_loss": 1.7386435270309448}, {"epoch_end": 1, "step": 782, "test_acc": 0.3907, "test_loss": 1.76063857421875}, {"step": 1000, "epoch": 2, "train_loss": 1.689368486404419}, {"epoch_end": 2, "step": 1173, "test_acc": 0.4017, "test_loss": 1.7096170776367188}, {"step": 1500, "epoch": 3, "train_loss": 1.5534716844558716}, {"epoch_end": 3, "step": 1564, "test_acc": 0.4079, "test_loss": 1.6882278442382812}, {"epoch_end": 4, "step": 1955, "test_acc": 0.4252, "test_loss": 1.6541592407226562}], "final": {"test_acc": 0.4252, "test_loss": 1.6541592407226562, "wall_s": 28.97341775894165}}
|
