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-lam4e-5-s0-fb/select_scored.jsonl",
"sha256": "9dea3017c6de6479a39db4df7e584a897718a43bea6207b7f5e15128770a8f83"
},
"summary.json": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam4e-5-s0-fb/summary.json",
"sha256": "6c45f0b0095cc5adbcbcabb19fef4e2b070bbb50f62df67ba89ed425cddf62a0"
},
"val_scored.jsonl": {
"commit": "996adf51777e618d115e27e9d7f8723cac857ab1",
"dirty": false,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam4e-5-s0-fb/val_scored.jsonl",
"sha256": "8a7f365a0d2729a7ddd7501dfe9bfe1df02621e4767ab379970e98c8a372e527"
}
},
"n_dumped": {
"select": 3804,
"val": 1278
},
"n_select": 3804,
"n_val": 1278,
"path": "/cluster/scratch/jingni/iclr/olmo3_rep/runs/s3_full_fb/osp-lam4e-5-s0-fb",
"world_size": 3,
"writer_rank": 0
},
"n_global_steps_per_epoch": 5224,
"parity_digests": {
"args_digest": "3c72397e7f7774cf",
"param_layout": "0f8d0e7904b5ca53",
"resume_epoch": "2f2d127de37b942b",
"resume_migration": "34234e98afe7498f",
"resume_plan": "105656dbbc573ac6",
"seed_lambda": "1567a2a899b43eda",
"split_sizes": "320c275502e54dac",
"train_digest": "2eef28cfe61f5ba8"
},
"resume": {
"args_digest_loaded": "df3170326b7b83eb420ce4f5ff9469ef1be2e8eb9abe4d7f0ba08d1e7a58af88",
"args_digest_now": "df3170326b7b83eb420ce4f5ff9469ef1be2e8eb9abe4d7f0ba08d1e7a58af88",
"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": "18ddf29d915b0e7a",
"n_chains": 1278,
"n_scores": 73046,
"split": "val",
"world": 3
},
{
"attempt": "18ddf29d915b0e7a",
"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": -0.44885472555139067,
"world": 3
}
],
"world_size": 3
}