JingweiNi's picture
Publish original trained checkpoints and run metadata
085c688 verified
Raw History Blame Contribute Delete
2.66 kB
{
"backend": "nccl",
"chains_per_step_is_global_batch": true,
"dist_timeout_s": 10800,
"export": {
"files": {
"select_scored.jsonl": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-6-s2-fb/select_scored.jsonl",
"sha256": "3d249a6f9c26b6a51051f7281a7d34e50d340abed85399a9921e0a4d6a3ed76d"
},
"summary.json": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-6-s2-fb/summary.json",
"sha256": "1274494f45e74c219f226f03f18a3f13e614b5fc0cecd4cb1c4c7d21fca81cf6"
},
"val_scored.jsonl": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-6-s2-fb/val_scored.jsonl",
"sha256": "d0a1d76419eca30145afe23b4ab05245b9d2928c836ea28fec9ee2738c848450"
}
},
"n_dumped": {
"select": 3804,
"val": 1278
},
"n_select": 3804,
"n_val": 1278,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-6-s2-fb",
"world_size": 3,
"writer_rank": 0
},
"n_global_steps_per_epoch": 5224,
"parity_digests": {
"args_digest": "36a319e7471c3f2f",
"param_layout": "0f8d0e7904b5ca53",
"resume_epoch": "27f6c011776e8db7",
"resume_migration": "34234e98afe7498f",
"resume_plan": "07f9f27aaf7fea32",
"seed_lambda": "1bd399c9a10203d0",
"split_sizes": "320c275502e54dac",
"train_digest": "2eef28cfe61f5ba8"
},
"resume": {
"args_digest_loaded": "02f7e9dfa891d19e92e4e49dfb1e29c245312fdd4e639d5c73864137e5b03cbc",
"args_digest_now": "02f7e9dfa891d19e92e4e49dfb1e29c245312fdd4e639d5c73864137e5b03cbc",
"checkpoint_found": true,
"enabled": true,
"migration": null,
"plan": {
"complete": true,
"completed_epochs": 7,
"early_stopped": false,
"remaining": 0,
"start_epoch": 7
},
"resumed_from_epoch": 6,
"rng_replay_verified": true,
"train_digest": "2f23490618025ec10b7a8bd77eb7f04fec74326d3b0800e896fa58d63ce9dcc6"
},
"schema": "ospruner-execution/v1",
"score_shards": [
{
"attempt": "18dd700344903242",
"n_chains": 1278,
"n_scores": 73046,
"split": "val",
"world": 3
},
{
"attempt": "18dd700344903242",
"n_chains": 3801,
"n_scores": 158686,
"split": "select",
"world": 3
}
],
"validation": [],
"world_size": 3
}