rl_model / world.json
lupele's picture
Publish verified formal StatePlay model and reproducibility metadata
20f6cfd verified
Raw History Blame Contribute Delete
1.04 kB
{
"sha256": "56328f45f3ee19237b63add2eb666dfcaa8aaebf505d29aa400a78519aea28ac",
"schema": "rl-world-checkpoint-v1",
"state": {
"optimizer_step": 652,
"batch_id": 81,
"update_cursor": 0,
"batch_done": true,
"stage": "api",
"smoke": false,
"backend": {
"deterministic_algorithms": true,
"cudnn_deterministic": true,
"cudnn_benchmark": false,
"cublas_workspace_config": ":4096:8",
"gradient_reduction": "name-ordered-fp32-global-mean-v2",
"torch_version": "2.4.1+cu124"
},
"schedule_world_size": 7,
"ema_eta": 0.5,
"all_filtered_batch": false,
"rng_topology_mapping": {
"saved_visible_devices": 7,
"current_visible_devices": 7,
"kept_logical_devices": [
0,
1,
2,
3,
4,
5,
6
]
}
},
"mode": "B-only",
"config_hash": "74ca72fa2f0970e3d7364ac36593e02514d9585512294cbf92c876e7337bad4a",
"sft_sha256": "53eff9e5e59e92bb3cc7810e3ff36f9ee490be4a122a3a8ff96a4de0a03b4c5d"
}