devils-agent / reports /bench-v000-mean-fp32.json
devildasdf's picture
Upload experimental BAIM code, research checkpoints and measured evaluations
795f737 verified
Raw History Blame Contribute Delete
1.82 kB
{
"checkpoint": "models/v000-mean",
"quantization": "FP32",
"platform": "Windows-11-10.0.26200-SP0",
"torch_version": "2.14.0+cpu",
"threads": 2,
"load_ms": 7.2376999305561185,
"disk_bytes": 516312,
"artifact_sha256": "8d12e9cd89fb7c96a56a8b667c511580ecbe00be49edd5d6fcff5e84ad5c649f",
"observed_process_rss_bytes": 275996672,
"memory_scope": "Observed Python RSS including training-library imports and evaluation tensors, not browser or exact peak",
"end_to_end_policy_ms": {
"median": 1.7656999407336116,
"p95": 2.8466000221669674
},
"neural_forward_ms": {
"median": 0.4911000141873956,
"p95": 0.6762000266462564
},
"feature_encoding_ms": {
"median": 1.292550005018711,
"p95": 2.2985999239608645
},
"python_cpu_ms": {
"median": 0.0,
"p95": 31.25
},
"evaluation": {
"validation": {
"samples": 480,
"action_accuracy": 1.0,
"target_accuracy": 1.0,
"joint_step_accuracy": 1.0,
"action_ece": 0.0,
"target_ece": 2.86102294921875e-06,
"candidate_recall": 1.0
},
"test": {
"samples": 480,
"action_accuracy": 1.0,
"target_accuracy": 1.0,
"joint_step_accuracy": 1.0,
"action_ece": 0.0,
"target_ece": 6.4373016357421875e-06,
"candidate_recall": 1.0
},
"novel_wording": {
"samples": 480,
"action_accuracy": 0.574999988079071,
"target_accuracy": 0.9208333492279053,
"joint_step_accuracy": 0.5583333373069763,
"action_ece": 0.418779332539998,
"target_ece": 0.06966802896931767,
"candidate_recall": 1.0
}
},
"target_vps_validated": false,
"scope": "Synthetic single-step benchmark. Two torch threads, not two-vCPU CPU affinity or target EPYC."
}