Hugging Face's logo

dhmeltzer
/
llama-7b-SFT-qlora-eli5_DPO_ds_RM_contrast_1024_r_64_alpha_16

Generated from Trainer
Model card Files Community
llama-7b-SFT-qlora-eli5_DPO_ds_RM_contrast_1024_r_64_alpha_16

Commit History

Model save
8735d58

dhmeltzer commited on

End of training
d812484

dhmeltzer commited on

Training in progress, step 171
bfca6b2

dhmeltzer commited on

Training in progress, step 152
eebec80

dhmeltzer commited on

Training in progress, step 133
1e966c2

dhmeltzer commited on

Training in progress, step 114
89b9b25

dhmeltzer commited on

Training in progress, step 95
14163ae

dhmeltzer commited on

Training in progress, step 76
4ee1e10

dhmeltzer commited on

Training in progress, step 57
60eb25a

dhmeltzer commited on

Training in progress, step 38
2df18ff

dhmeltzer commited on

Training in progress, step 19
c9b5615

dhmeltzer commited on

initial commit
a86cd1f

dhmeltzer commited on