7 lines
893 B
Plaintext
7 lines
893 B
Plaintext
2026-07-24 01:24:59,550 INFO cleanslate.fsid.training.trainer: [RANK 0] FSID train: model=meta-llama/Llama-3.1-8B objective=rmu run_dir=results/rebuttal/train/llama-3_1-8b-rmu-bm25-10b/rmu_Llama-3.1-8B_20260724_012446
|
|
2026-07-24 01:24:59,550 INFO cleanslate.fsid.training.trainer: [RANK 0] Creating frozen reference model for rmu (dtype=torch.bfloat16)
|
|
2026-07-24 01:25:05,452 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=rmu epochs=2
|
|
2026-07-24 01:25:05,911 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 01:31:55,683 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to results/rebuttal/train/llama-3_1-8b-rmu-bm25-10b/rmu_Llama-3.1-8B_20260724_012446
|
|
2026-07-24 01:31:55,687 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (369.6s)
|