PEFT
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer

Commit History

End of training
6e97270
verified

nthakur commited on

Model save
f9e6f19
verified

nthakur commited on

Training in progress, step 500
4a899bd
verified

nthakur commited on

Training in progress, step 400
eae9948
verified

nthakur commited on

Training in progress, step 300
76c8e37
verified

nthakur commited on

Training in progress, step 100
d68c3da
verified

nthakur commited on

initial commit
f28d67d
verified

nthakur commited on