7 lines
865 B
Plaintext
7 lines
865 B
Plaintext
|
2026-07-24 02:09:03,557 INFO cleanslate.fsid.training.trainer: [RANK 0] FSID train: model=Qwen/Qwen3-8B objective=rmu run_dir=results/rebuttal/train/qwen3-8b-rmu-bm25-6t/rmu_Qwen3-8B_20260724_020851
|
||
|
|
2026-07-24 02:09:03,557 INFO cleanslate.fsid.training.trainer: [RANK 0] Creating frozen reference model for rmu (dtype=torch.bfloat16)
|
||
|
|
2026-07-24 02:09:09,539 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=rmu epochs=2
|
||
|
|
2026-07-24 02:09:09,958 INFO cleanslate.fsid.training.trainer: [RANK 0] RMU control_vec init: dim=4096 seed=0 rank=0 world_size=1 per_rank_norm=2.000000
|
||
|
|
2026-07-24 02:12:52,076 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to results/rebuttal/train/qwen3-8b-rmu-bm25-6t/rmu_Qwen3-8B_20260724_020851
|
||
|
|
2026-07-24 02:12:52,080 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (187.6s)
|