{
  "model_id": "MatterWaveAI/grt-20m",
  "architecture": "GRTForCausalLM",
  "stored_parameters": 16730869,
  "non_embedding_parameters": 10280869,
  "dense_equiv_parameters": 22237440,
  "nn_linear_layers": 0,
  "pretraining": {
    "corpus": [
      "OptimalScale/ClimbMix",
      "wikimedia/wikipedia",
      "tiiuae/falcon-refinedweb",
      "HuggingFaceFW/fineweb-edu",
      "HuggingFaceTB/cosmopedia",
      "nvidia/Nemotron-Pretraining-Dataset-sample",
      "HuggingFaceTB/finemath"
    ],
    "steps": 158000,
    "optimizer": "PairAdam",
    "train_loss": 2.114
  },
  "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)",
    "mc_9task_macro_average_accuracy": {
      "random_baseline": 0.3556,
      "zero_shot": 0.3916,
      "pair_adam": 0.3863,
      "symplectic_adam": 0.4403,
      "huygens_symplectic_adam": 0.4503
    },
    "macro_average_accuracy": {
      "random_baseline": 0.345,
      "zero_shot": 0.3734,
      "pair_adam": 0.3765,
      "symplectic_adam": 0.4877,
      "huygens_symplectic_adam": 0.4984
    },
    "tasks": {
      "boolq": {
        "split": "validation",
        "n_eval": 3270,
        "random_baseline": 0.5,
        "zero_shot_acc": 0.6217,
        "pair_adam_acc": 0.5343,
        "symplectic_adam_acc": 0.6217,
        "huygens_symplectic_adam_acc": 0.6235
      },
      "arc_easy": {
        "split": "test",
        "n_eval": 2376,
        "random_baseline": 0.25,
        "zero_shot_acc": 0.2643,
        "pair_adam_acc": 0.2685,
        "symplectic_adam_acc": 0.343,
        "huygens_symplectic_adam_acc": 0.367
      },
      "arc_challenge": {
        "split": "test",
        "n_eval": 1172,
        "random_baseline": 0.25,
        "zero_shot_acc": 0.2534,
        "pair_adam_acc": 0.2543,
        "symplectic_adam_acc": 0.2679,
        "huygens_symplectic_adam_acc": 0.2713
      },
      "openbookqa": {
        "split": "test",
        "n_eval": 500,
        "random_baseline": 0.25,
        "zero_shot_acc": 0.342,
        "pair_adam_acc": 0.256,
        "symplectic_adam_acc": 0.36,
        "huygens_symplectic_adam_acc": 0.372
      },
      "piqa": {
        "split": "validation",
        "n_eval": 1838,
        "random_baseline": 0.5,
        "zero_shot_acc": 0.5397,
        "pair_adam_acc": 0.5337,
        "symplectic_adam_acc": 0.5397,
        "huygens_symplectic_adam_acc": 0.5397
      },
      "winogrande": {
        "split": "validation",
        "n_eval": 1267,
        "random_baseline": 0.5,
        "zero_shot_acc": 0.5193,
        "pair_adam_acc": 0.5241,
        "symplectic_adam_acc": 0.5241,
        "huygens_symplectic_adam_acc": 0.5241
      },
      "hellaswag": {
        "split": "validation",
        "n_eval": 1000,
        "random_baseline": 0.25,
        "zero_shot_acc": 0.287,
        "pair_adam_acc": 0.318,
        "symplectic_adam_acc": 0.327,
        "huygens_symplectic_adam_acc": 0.327
      },
      "qnli": {
        "split": "validation",
        "n_eval": 1000,
        "random_baseline": 0.5,
        "zero_shot_acc": 0.505,
        "pair_adam_acc": 0.557,
        "symplectic_adam_acc": 0.74,
        "huygens_symplectic_adam_acc": 0.782
      },
      "commonsenseqa": {
        "split": "validation",
        "n_eval": 1221,
        "random_baseline": 0.2,
        "zero_shot_acc": 0.1916,
        "pair_adam_acc": 0.231,
        "symplectic_adam_acc": 0.2391,
        "huygens_symplectic_adam_acc": 0.2457
      },
      "gsm8k": {
        "split": "test",
        "n_eval": 500,
        "random_baseline": 0.25,
        "zero_shot_acc": 0.21,
        "zero_shot_ppl": 60.12,
        "pair_adam_acc": 0.288,
        "pair_adam_ppl": 12.52,
        "symplectic_adam_acc": 0.914,
        "symplectic_adam_ppl": 10.7,
        "huygens_symplectic_adam_acc": 0.932,
        "huygens_symplectic_adam_ppl": 9.11
      }
    }
  }
}