1
|
{"args": {"mode": "bp", "dataset": "cifar10", "depth": 60, "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": 3, "device": "cuda", "log_every": 500, "max_steps": 0, "probe_bs": 256, "outdir": "results", "tag": "scale_v3_cifar10_bp_w64_d60_s3", "n_in": 3072}, "provenance": {"git_commit": "c8a372cae2612839bdbdafcf9c114f52cb4a6de3", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.4164717197418213}, {"epoch_end": 0, "step": 391, "test_acc": 0.3643, "test_loss": 1.7990243774414063}, {"step": 500, "epoch": 1, "train_loss": 1.651111364364624}, {"epoch_end": 1, "step": 782, "test_acc": 0.3959, "test_loss": 1.7507692626953124}, {"step": 1000, "epoch": 2, "train_loss": 1.7603168487548828}, {"epoch_end": 2, "step": 1173, "test_acc": 0.403, "test_loss": 1.7118653442382812}, {"step": 1500, "epoch": 3, "train_loss": 1.7584331035614014}, {"epoch_end": 3, "step": 1564, "test_acc": 0.4114, "test_loss": 1.6929181884765625}, {"epoch_end": 4, "step": 1955, "test_acc": 0.4138, "test_loss": 1.6663089965820312}], "final": {"test_acc": 0.4138, "test_loss": 1.6663089965820312, "wall_s": 56.848419189453125}}
|