language, library_name, tags
language library_name tags
en
transformers
qwen
sft
ifeval
retaining-by-doing

Qwen2.5-0.5B Instruct IFEval Half-Epoch SFT

This checkpoint was trained from Qwen2.5-0.5B-Instruct on IFEvalSFTDataset.

Training setup:

  • num_train_datapoints=4064
  • num_epochs=1
  • effective half-epoch setting
  • learning rate 1e-4
  • total batch size 64

Observed local IFEval accuracy:

  • 0.4209445585
Description
Model synced from source: SeongryongJung/qwen2.5-0.5b-ifeval-halfepoch-sft
Readme 2 MiB
Languages
Jinja 100%