{
  "model_id": "MatterWaveAI/grt-20m-base",
  "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_zero_shot": {
    "benchmark_suite": "SLM-Bench (9 Multiple-Choice Tasks + GSM8K Perplexity)",
    "evaluation_harness": "grt-slm-bench (training/slm_bench.py)",
    "mc_macro_average_accuracy": 0.3916,
    "pair_adam_mc_macro_average_accuracy": 0.3863,
    "random_macro_average": 0.3556,
    "tasks": {
      "boolq": {
        "split": "validation",
        "n_eval": 3270,
        "random": 0.5,
        "zero_shot_acc": 0.6217,
        "pair_adam_acc": 0.5343
      },
      "piqa": {
        "split": "validation",
        "n_eval": 1838,
        "random": 0.5,
        "zero_shot_acc": 0.5397,
        "pair_adam_acc": 0.5337
      },
      "winogrande": {
        "split": "validation",
        "n_eval": 1267,
        "random": 0.5,
        "zero_shot_acc": 0.5193,
        "pair_adam_acc": 0.5241
      },
      "qnli": {
        "split": "validation",
        "n_eval": 1000,
        "random": 0.5,
        "zero_shot_acc": 0.505,
        "pair_adam_acc": 0.557
      },
      "openbookqa": {
        "split": "test",
        "n_eval": 500,
        "random": 0.25,
        "zero_shot_acc": 0.342,
        "pair_adam_acc": 0.256
      },
      "hellaswag": {
        "split": "validation",
        "n_eval": 1000,
        "random": 0.25,
        "zero_shot_acc": 0.287,
        "pair_adam_acc": 0.318
      },
      "arc_easy": {
        "split": "test",
        "n_eval": 2376,
        "random": 0.25,
        "zero_shot_acc": 0.2643,
        "pair_adam_acc": 0.2685
      },
      "arc_challenge": {
        "split": "test",
        "n_eval": 1172,
        "random": 0.25,
        "zero_shot_acc": 0.2534,
        "pair_adam_acc": 0.2543
      },
      "commonsenseqa": {
        "split": "validation",
        "n_eval": 1221,
        "random": 0.2,
        "zero_shot_acc": 0.1916,
        "pair_adam_acc": 0.231
      },
      "gsm8k": {
        "split": "test",
        "n_eval": 500,
        "zero_shot_ppl": 60.12,
        "pair_adam_ppl": 12.52
      }
    }
  }
}