MoNo-light / results /metrics.json
yushuang88's picture
Upload folder using huggingface_hub
db32cff verified
Raw History Blame Contribute Delete
3.33 kB
{
"mean_relative_l2_raw": 0.006937251414878938,
"test_samples": 200,
"actual_training_epochs": 500,
"optimizer_updates": 125000,
"paper_table3": 0.007,
"signed_gap": -6.274858512106234e-05,
"absolute_gap": 6.274858512106234e-05,
"relative_gap_percent": -0.8964083588723137,
"selection": "final_epoch_500_no_test_selection",
"checkpoint": "/public/home/liuyushuang/zhaomingsi/onescience-cfd-repro-packages/MoNo-light/weight/best_model.pth",
"checkpoint_sha256": "d20393f9ae89d38f53b8da9e09799db57bef37154ec8c7fddb9a9dd4a6666122",
"min": 0.0023765875482458245,
"max": 0.02536537307374934,
"median": 0.006544329873232485,
"training_environment": {
"python": "3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0]",
"torch": "2.4.1",
"hip": "6.1.25065",
"cuda": null,
"device": "BW",
"device_count": 1,
"platform": "Linux-5.10.134-17.1.3.sga8.x86_64-x86_64-with-glibc2.28",
"hostname": "f11r3n13",
"slurm_job_id": "1100920",
"trainable_parameters": 1696705,
"all_parameters": 1734241,
"precision": "float32",
"code_hashes": {
"model/MoNo.py": "7af09c5106dbadc7bac35100c2c852c9739b1fa86a4ab52cc5fe12955b095e72",
"config/config.yaml": "c333c872f00ea12eb9bb8c61b85df5614b18e17e49cfb76d8f19e7c038657517",
"scripts/train.py": "a1bee1c36f6361c546b4a9ff166681e99baab2f19842ff480f033449673db958",
"scripts/common.py": "f4283c26f3bbb3747a6d4a632ac0f499e066c8c411bd5eb73775f0cc01c6e1a9"
}
},
"inference_environment": {
"python": "3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0]",
"torch": "2.4.1",
"hip": "6.1.25065",
"cuda": null,
"device": "BW",
"device_count": 1,
"platform": "Linux-5.10.134-17.1.3.sga8.x86_64-x86_64-with-glibc2.28",
"hostname": "f11r3n13",
"slurm_job_id": "1100920"
},
"software_versions": {
"torch": "2.4.1+das.opt2.dtk2504",
"triton": "3.0.0+das.opt4.dtk2504",
"onescience": "0.1.2rc1",
"numpy": "1.26.4",
"scipy": "1.15.2",
"PyYAML": "6.0.2",
"matplotlib": "3.10.1"
},
"configured_cluster": {
"partition": "hx1hdnormal01",
"nodes": 1,
"gpus_per_node": 1,
"cpus_per_task": 8,
"memory": "30G",
"time_limit": "24:00:00",
"gpu_type": "dcu",
"ntasks_per_node": 1
},
"gpu_total_memory_bytes": 68702699520,
"limitations": [
"Single DCU/PyTorch 2.4.1 HIP backend versus paper RTX4090/PyTorch2.8 CUDA12.8.",
"Configured system RAM allocation is 30G, versus up to 600GB reported by the paper; all 1000/200 samples and model dimensions retained.",
"Installed Triton is 3.0.0 with DTK customizations, versus paper Triton3.4.0; author fused kernels are not used.",
"Independent implementation, packed QKV/SDPA attention, and RNG consumption differ from explicit author attention; not bitwise reproduction.",
"Portable PyTorch log-domain Sinkhorn instead of author fused Triton kernels; same finite-step equations and differentiation.",
"Identical Darcy geometry is computed once and broadcast over batch; arithmetic ordering differs.",
"Paper does not specify seed uncertainty or a tolerance for the Table3 result.",
"Final epoch checkpoint named best_model.pth; no test-set model selection.",
"Units unspecified by supplied data; metric uses stored pressure scale."
]
}