JingweiNi's picture
Publish original trained checkpoints and run metadata
085c688 verified
Raw History Blame Contribute Delete
2.88 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-5-s2-fb/select_scored.jsonl",
"sha256": "58c29913e3f6d193d44340f313932697044b7591c0251c38307cbcdd0d582dd5"
},
"summary.json": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-5-s2-fb/summary.json",
"sha256": "35304e4ee35c6bb08dcac3e77a62a7454f8ae77481c6169967f2cbe751d4035d"
},
"val_scored.jsonl": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam2e-5-s2-fb/val_scored.jsonl",
"sha256": "848bbebe1db38c80803de0b43c0a5a2bd6586246fd58583b709f51002066e1b0"
}
},
"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-5-s2-fb",
"world_size": 3,
"writer_rank": 0
},
"n_global_steps_per_epoch": 5224,
"parity_digests": {
"args_digest": "36290d7ad03d11a7",
"param_layout": "0f8d0e7904b5ca53",
"resume_epoch": "2f2d127de37b942b",
"resume_migration": "34234e98afe7498f",
"resume_plan": "105656dbbc573ac6",
"seed_lambda": "0f83f0e697db1b29",
"split_sizes": "320c275502e54dac",
"train_digest": "2eef28cfe61f5ba8"
},
"resume": {
"args_digest_loaded": "a50e742a3920ab064b33148e4f627b83d0c832088938c2bcc213eda4a316d5a4",
"args_digest_now": "a50e742a3920ab064b33148e4f627b83d0c832088938c2bcc213eda4a316d5a4",
"checkpoint_found": true,
"enabled": true,
"migration": null,
"plan": {
"complete": false,
"completed_epochs": 6,
"early_stopped": false,
"remaining": 1,
"start_epoch": 6
},
"resumed_from_epoch": 5,
"rng_replay_verified": true,
"train_digest": "2f23490618025ec10b7a8bd77eb7f04fec74326d3b0800e896fa58d63ce9dcc6"
},
"schema": "ospruner-execution/v1",
"score_shards": [
{
"attempt": "18dc976f66bf9ebc",
"n_chains": 1278,
"n_scores": 73046,
"split": "val",
"world": 3
},
{
"attempt": "18dc976f66bf9ebc",
"n_chains": 3801,
"n_scores": 158686,
"split": "select",
"world": 3
}
],
"validation": [
{
"epoch": 6,
"n_chains_contributing": 1278,
"n_chains_expected": 1278,
"n_chains_global": 1278,
"n_chains_local": 426,
"val_stat": -0.5452252895905052,
"world": 3
}
],
"world_size": 3
}