{ "method": "dfa", "seed": 42, "batch_size": 256, "y_first5": [ 3, 8, 8, 0, 6 ], "first_param_norm": 2842.21484375, "method_A": { "loss": 1.9194912910461426, "acc": 0.3203125, "per_layer": [ { "mean_norm": 1.831593551956598e-14, "median_norm": 1.831593551956598e-14, "max_norm": 1.831593551956598e-14, "s_1e6": 0.0 }, { "mean_norm": 3.0867769878465775e-17, "median_norm": 3.0867769878465775e-17, "max_norm": 3.0867769878465775e-17, "s_1e6": 0.0 }, { "mean_norm": 2.6333336159656264e-17, "median_norm": 2.6333336159656264e-17, "max_norm": 2.6333336159656264e-17, "s_1e6": 0.0 }, { "mean_norm": 1.706431748357901e-17, "median_norm": 1.706431748357901e-17, "max_norm": 1.706431748357901e-17, "s_1e6": 0.0 } ] }, "method_B": { "loss": 1.9194912910461426, "acc": 0.3203125, "per_layer": [ { "mean_norm": 1.831593551956598e-14, "median_norm": 1.831593551956598e-14, "max_norm": 1.831593551956598e-14, "s_1e6": 0.0 }, { "mean_norm": 3.0867769878465775e-17, "median_norm": 3.0867769878465775e-17, "max_norm": 3.0867769878465775e-17, "s_1e6": 0.0 }, { "mean_norm": 2.6333336159656264e-17, "median_norm": 2.6333336159656264e-17, "max_norm": 2.6333336159656264e-17, "s_1e6": 0.0 }, { "mean_norm": 1.706431748357901e-17, "median_norm": 1.706431748357901e-17, "max_norm": 1.706431748357901e-17, "s_1e6": 0.0 } ] }, "method_C_embed_grad_norm": 0.000234484818065539 }