{ "model_id": "MatterWaveAI/grt-10m", "architecture": "GRTForCausalLM", "stored_parameters": 8684515, "non_embedding_parameters": 2234515, "dense_equiv_parameters": 17518848, "nn_linear_layers": 0, "pretraining": { "corpus": "nvidia/Nemotron-Pretraining-Dataset-sample", "steps": 336000, "optimizer": "PairAdam", "train_loss": 2.144, "val_loss": 4.033, "val_ppl": 56.4, "val_top1_acc": 0.4 }, "slm_bench": { "benchmark_suite": "SLM-Bench (10-Task Core Suite)", "evaluation_harness": "grt-slm-bench (training/slm_bench.py)", "hardware": "AMD Ryzen AI Max+ 395 (Radeon 8060S / ROCm gfx1151)", "macro_average_accuracy": { "random_baseline": 0.345, "zero_shot": 0.3647, "pair_adam": 0.3603, "symplectic_adam": 0.4463, "huygens_symplectic_adam": 0.46 }, "tasks": { "boolq": { "split": "validation", "n_eval": 3270, "random_baseline": 0.5, "zero_shot_acc": 0.6214, "pair_adam_acc": 0.6113, "symplectic_adam_acc": 0.6214, "huygens_symplectic_adam_acc": 0.6217 }, "arc_easy": { "split": "test", "n_eval": 2376, "random_baseline": 0.25, "zero_shot_acc": 0.2694, "pair_adam_acc": 0.266, "symplectic_adam_acc": 0.3173, "huygens_symplectic_adam_acc": 0.3228 }, "arc_challenge": { "split": "test", "n_eval": 1172, "random_baseline": 0.25, "zero_shot_acc": 0.2253, "pair_adam_acc": 0.2491, "symplectic_adam_acc": 0.2517, "huygens_symplectic_adam_acc": 0.2713 }, "openbookqa": { "split": "test", "n_eval": 500, "random_baseline": 0.25, "zero_shot_acc": 0.3, "pair_adam_acc": 0.226, "symplectic_adam_acc": 0.334, "huygens_symplectic_adam_acc": 0.352 }, "piqa": { "split": "validation", "n_eval": 1838, "random_baseline": 0.5, "zero_shot_acc": 0.5218, "pair_adam_acc": 0.5082, "symplectic_adam_acc": 0.5218, "huygens_symplectic_adam_acc": 0.5218 }, "winogrande": { "split": "validation", "n_eval": 1267, "random_baseline": 0.5, "zero_shot_acc": 0.5051, "pair_adam_acc": 0.5075, "symplectic_adam_acc": 0.5185, "huygens_symplectic_adam_acc": 0.5185 }, "hellaswag": { "split": "validation", "n_eval": 1000, "random_baseline": 0.25, "zero_shot_acc": 0.256, "pair_adam_acc": 0.291, "symplectic_adam_acc": 0.308, "huygens_symplectic_adam_acc": 0.308 }, "qnli": { "split": "validation", "n_eval": 1000, "random_baseline": 0.5, "zero_shot_acc": 0.527, "pair_adam_acc": 0.497, "symplectic_adam_acc": 0.568, "huygens_symplectic_adam_acc": 0.609 }, "commonsenseqa": { "split": "validation", "n_eval": 1221, "random_baseline": 0.2, "zero_shot_acc": 0.2015, "pair_adam_acc": 0.2285, "symplectic_adam_acc": 0.2285, "huygens_symplectic_adam_acc": 0.2285 }, "gsm8k": { "split": "test", "n_eval": 500, "random_baseline": 0.25, "zero_shot_acc": 0.22, "zero_shot_ppl": 145.85, "pair_adam_acc": 0.218, "pair_adam_ppl": 37.27, "symplectic_adam_acc": 0.794, "symplectic_adam_ppl": 43.47, "huygens_symplectic_adam_acc": 0.846, "huygens_symplectic_adam_ppl": 30.09 } } } }