{ "model_id": "MatterWaveAI/grt-30m-code", "architecture": "GRTForCausalLM", "pipeline_tag": "text-generation", "base_model": "MatterWaveAI/grt-30m", "parameters": 29305498, "trainable_parameters": 811907, "trainable_scope": "blocks[11:12] + final_norm + <|im_end|> phase calibration", "nn_linear_layers": 0, "nn_conv1d_layers": 0, "steps": 200, "batch_size": 16, "learning_rate": 0.0035, "seed": 42, "best_optimizer": "huygens_adam", "before_training": { "val_loss": 4.0061, "val_ppl": 54.9316, "corrupted_prompt_val_loss": 4.9059, "code_conditioning_margin": 0.8998, "code_token_acc": 46.8, "tool_call_token_acc": 36.44, "json_schema_match_rate": 0.0, "python_ast_syntax_validity": 0.0 }, "optimizers": { "pair_adam": { "optimizer_type": "pair_adam", "variant": "PairAdam (Factored Toroidal Baseline)", "final_train_loss": 1.0994, "val_loss": 0.6018, "val_ppl": 1.8253, "code_token_acc": 97.6, "tool_call_token_acc": 90.69, "json_schema_match_rate": 83.33, "python_ast_syntax_validity": 50.0, "code_conditioning_margin": 1.6597, "corrupted_prompt_val_loss": 2.2614, "wall_time_s": 278.8 }, "hessian_pair_adam": { "optimizer_type": "hessian_pair_adam", "variant": "HessianPairAdam (Sophia-Torus Cauchy-Riemann Curvature)", "final_train_loss": 1.2171, "val_loss": 0.7292, "val_ppl": 2.0734, "code_token_acc": 97.87, "tool_call_token_acc": 87.33, "json_schema_match_rate": 66.67, "python_ast_syntax_validity": 58.33, "code_conditioning_margin": 1.4236, "corrupted_prompt_val_loss": 2.1528, "wall_time_s": 117.82 }, "polar_natural_adam": { "optimizer_type": "polar_natural_adam", "variant": "PolarNaturalAdam (Riemannian Polar Metric + Cauchy-Riemann Hessian)", "final_train_loss": 1.2463, "val_loss": 0.7891, "val_ppl": 2.2015, "code_token_acc": 96.93, "tool_call_token_acc": 86.34, "json_schema_match_rate": 66.67, "python_ast_syntax_validity": 50.0, "code_conditioning_margin": 1.4294, "corrupted_prompt_val_loss": 2.2185, "wall_time_s": 108.18 }, "cyclide_adam": { "optimizer_type": "cyclide_adam", "variant": "CyclideAdam (Dupin Cyclide Conic Metric + Deviatoric Twist)", "final_train_loss": 1.1564, "val_loss": 0.64, "val_ppl": 1.8965, "code_token_acc": 98.93, "tool_call_token_acc": 89.5, "json_schema_match_rate": 75.0, "python_ast_syntax_validity": 83.33, "code_conditioning_margin": 1.5727, "corrupted_prompt_val_loss": 2.2127, "wall_time_s": 141.92 }, "symplectic_adam": { "optimizer_type": "symplectic_adam", "variant": "SymplecticAdam (Gromov-Liouville Non-Squeezing Floor + Casimir Cavity)", "final_train_loss": 1.2764, "val_loss": 0.8445, "val_ppl": 2.3268, "code_token_acc": 97.6, "tool_call_token_acc": 81.39, "json_schema_match_rate": 50.0, "python_ast_syntax_validity": 50.0, "code_conditioning_margin": 1.5766, "corrupted_prompt_val_loss": 2.421, "wall_time_s": 138.1 }, "gyric_adam": { "optimizer_type": "gyric_adam", "variant": "GyricAdam (Poinsot-Lande Gyroscopic Projection + Thomas Precession)", "final_train_loss": 1.1168, "val_loss": 0.6216, "val_ppl": 1.8619, "code_token_acc": 98.53, "tool_call_token_acc": 87.92, "json_schema_match_rate": 75.0, "python_ast_syntax_validity": 50.0, "code_conditioning_margin": 1.5745, "corrupted_prompt_val_loss": 2.1961, "wall_time_s": 138.83 }, "huygens_adam": { "optimizer_type": "huygens_adam", "variant": "HuygensAdam (Circular Order Parameter R_p Splay Torque)", "final_train_loss": 1.0882, "val_loss": 0.5672, "val_ppl": 1.7632, "code_token_acc": 99.07, "tool_call_token_acc": 90.69, "json_schema_match_rate": 83.33, "python_ast_syntax_validity": 91.67, "code_conditioning_margin": 1.5152, "corrupted_prompt_val_loss": 2.0824, "wall_time_s": 138.63 }, "huygens_symplectic_adam": { "optimizer_type": "huygens_symplectic_adam", "variant": "HuygensSymplecticAdam (Two-Stage Huygens -> Symplectic Curriculum)", "final_train_loss": 1.1819, "val_loss": 0.6537, "val_ppl": 1.9227, "code_token_acc": 98.27, "tool_call_token_acc": 89.31, "json_schema_match_rate": 75.0, "python_ast_syntax_validity": 66.67, "code_conditioning_margin": 1.4057, "corrupted_prompt_val_loss": 2.0594, "wall_time_s": 122.82 } } }