| { | |
| "model": "numbat", | |
| "run_id": "nt-1145862-3", | |
| "checkpoint": { | |
| "path": "nt-1145862-3/eval/step_1830000-nvfp4", | |
| "step": 1830000, | |
| "format": "safetensors", | |
| "dtype": "nvfp4" | |
| }, | |
| "eval": { | |
| "last_run": "2026-10-08T17:23:51Z", | |
| "harness": "lm-eval-harness@v0.4.13", | |
| "config": { | |
| "num_fewshot": 0, | |
| "batch_size": 16, | |
| "max_length": 4096, | |
| "compiler_flags": [ | |
| "--experimental-unsafe-fp8e4m3fn-as-fp8e4m3" | |
| ] | |
| }, | |
| "results": { | |
| "mmlu": { | |
| "acc": 0.8849, | |
| "acc_stderr": 0.0027, | |
| "n": 14042 | |
| }, | |
| "arc_challenge": { | |
| "acc": 0.7201, | |
| "acc_stderr": 0.0131, | |
| "acc_norm": 0.7568, | |
| "n": 1172 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.7185, | |
| "acc_stderr": 0.0045, | |
| "acc_norm": 0.8896, | |
| "acc_norm_stderr": 0.0031, | |
| "n": 10042 | |
| } | |
| } | |
| } | |
| } | |