CoolFace
Modelpublic

Jongbin-kr/exaone-7b-verireason-reproduced-1513-fullft-best-grpo-reproduced-1.0

sourceHugging Faceupdated 9d agoView on Hugging Face
0likes977downloads
14 commits on main
2aaa7639d ago

End of training (part 2)

Jongbin-kr
f63ddc39d ago

End of training

Jongbin-kr
895a2679d ago

Model save (part 2)

Jongbin-kr
fd78b369d ago

Model save

Jongbin-kr
6f58f269d ago

Training in progress, epoch 5

Jongbin-kr
65a79b79d ago

Training in progress, epoch 4 (part 2)

Jongbin-kr
81c9d879d ago

Training in progress, epoch 4

Jongbin-kr
2301dc19d ago

Training in progress, epoch 3 (part 2)

Jongbin-kr
7169e2a9d ago

Training in progress, epoch 3

Jongbin-kr
38063649d ago

Training in progress, epoch 2 (part 2)

Jongbin-kr
3ca429a9d ago

Training in progress, epoch 2

Jongbin-kr
bb4c5069d ago

Training in progress, epoch 1

Jongbin-kr
93e0d4112d ago

GRPO checkpoint: epoch 9, global step 1701 (time-limit latest saved)

Jongbin-kr
65da96d13d ago

initial commit

Jongbin-kr