PEFT
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer

Commit History

End of training
8ece1d4
verified

khongtrunght commited on

Model save
5405756
verified

khongtrunght commited on

Training in progress, step 980
748a602
verified

khongtrunght commited on

Training in progress, step 900
c1e68fc
verified

khongtrunght commited on

Training in progress, step 800
2923a37
verified

khongtrunght commited on

Training in progress, step 700
0bdb3ed
verified

khongtrunght commited on

Training in progress, step 600
e873f4a
verified

khongtrunght commited on

Training in progress, step 500
287e9ab
verified

khongtrunght commited on

Training in progress, step 400
76bcd49
verified

khongtrunght commited on

Training in progress, step 300
1f6dceb
verified

khongtrunght commited on

Training in progress, step 200
cdd631d
verified

khongtrunght commited on

Training in progress, step 100
b4c302f
verified

khongtrunght commited on

End of training
017105e
verified

khongtrunght commited on

Model save
6f7a339
verified

khongtrunght commited on

Training in progress, step 787
29081e0
verified

khongtrunght commited on

Training in progress, step 700
7f81922
verified

khongtrunght commited on

Training in progress, step 600
85a4f74
verified

khongtrunght commited on

Training in progress, step 500
00ea564
verified

khongtrunght commited on

Training in progress, step 400
eef6ccb
verified

khongtrunght commited on

Training in progress, step 300
9867405
verified

khongtrunght commited on

Training in progress, step 200
9968c13
verified

khongtrunght commited on

Training in progress, step 100
76e1c78
verified

khongtrunght commited on

initial commit
06805cd
verified

khongtrunght commited on