{ "architecture": "tr_hash_moe", "benchmarks": { "arc_challenge": { "acc": 0.2713310580204778, "acc_norm": 0.2901023890784983, "backend": "mlx-fp16", "examples": 1172, "split": "test" }, "arc_combined": { "acc": 0.4729425028184893, "acc_norm": 0.44983089064261555, "aggregation": "micro-average over ARC-Easy and ARC-Challenge", "backend": "derived", "examples": 3548, "split": "test" }, "arc_easy": { "acc": 0.5723905723905723, "acc_norm": 0.5286195286195287, "backend": "mlx-fp16", "examples": 2376, "split": "test" }, "hellaswag": { "acc": 0.33210515833499304, "acc_norm": 0.3873730332603067, "backend": "mlx-fp16", "examples": 10042, "split": "validation" }, "piqa": { "acc": 0.6800870511425462, "acc_norm": 0.690968443960827, "backend": "pytorch-fp16-custom-triton", "examples": 1838, "split": "validation" } }, "benchmark_protocol": "zero-shot causal choice log-likelihood; no chat template; max_length=2048", "behavior_gate_passed": false, "dataset": "AETHORIA-AI/TR-HASH-MoE-200M-SFT-v2-300K", "dataset_revision": "084a658ec47e4ee872f6d67fdbad3602f599424b", "floating_parameters": 201194880, "matched_eval_loss": 0.959617, "matched_eval_ppl": 2.61, "method": "full-parameter-sft", "num_experts": 4, "num_experts_per_tok": 2, "parameters": 202731072, "piqa_acc": 0.6800870511425462, "piqa_acc_norm": 0.690968443960827, "release": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", "schema_version": 2, "selected_epoch": 3, "selected_step": 5982, "selection_policy": "manual promotion of epoch 3: highest full-PIQA acc_norm and acc, lowest held-out SFT loss; strict behavior failures retained", "source_checkpoint_step": 8156, "source_model": "AETHORIA-AI/TR-HASH-MoE-200M-160B-Refinement", "weights_bytes": 813515232, "weights_dtype": "float32", "weights_sha256": "5aeb736c897373ace818a46df92edf81c9bf688723c20d1a31ed31f02028a758" }