Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
zfz1
/
deepseek-8b-orpo-lora
like
0
PEFT
TensorBoard
Safetensors
zfz1/my_preference_gsm8k_deepseek
llama
alignment-handbook
trl
orpo
Generated from Trainer
License:
other
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
dd36c6b
deepseek-8b-orpo-lora
/
runs
/
Jul18_00-59-35_phe108-jieyuzhao-01
1 contributor
History:
2 commits
zfz1
End of training
dd36c6b
verified
3 months ago
events.out.tfevents.1721289833.phe108-jieyuzhao-01.335789.0
32.2 kB
LFS
Training in progress, step 312
3 months ago
events.out.tfevents.1721295716.phe108-jieyuzhao-01.335789.1
997 Bytes
LFS
End of training
3 months ago