Wing Lian 22810c97b7 use warmup_ratio as a better default than warmup steps since it's data dependent (#2897) [skip ci] ...

* use warmup_ratio as a better default than warmup steps since it's data dependent

* replace remainder of warmup_steps

2025-07-30 06:44:06 -04:00

..

dpo.yaml

use warmup_ratio as a better default than warmup steps since it's data dependent (#2897) [skip ci]

2025-07-30 06:44:06 -04:00

prm.yaml

make pad_to_sequence_len default to the same value as sample_packing (#2941) [skip ci]

2025-07-21 11:40:56 -04:00

qlora-fsdp.yaml

use warmup_ratio as a better default than warmup steps since it's data dependent (#2897) [skip ci]

2025-07-30 06:44:06 -04:00

reward-model.yaml

make pad_to_sequence_len default to the same value as sample_packing (#2941) [skip ci]

2025-07-21 11:40:56 -04:00