7 lines
891 B
Plaintext
7 lines
891 B
Plaintext
|
2026-07-24 01:32:17,795 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-igm-10b/rmu_Llama-3.1-8B_20260724_013205
|
||
|
|
2026-07-24 01:32:17,795 INFO cleanslate.fsid.training.trainer: [RANK 0] Creating frozen reference model for rmu (dtype=torch.bfloat16)
|
||
|
|
2026-07-24 01:32:23,520 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=rmu epochs=2
|
||
|
|
2026-07-24 01:32:23,976 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 01:38:37,173 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to results/rebuttal/train/llama-3_1-8b-rmu-igm-10b/rmu_Llama-3.1-8B_20260724_013205
|
||
|
|
2026-07-24 01:38:37,176 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (334.6s)
|