Hugging Face's logo

Flowersea37
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
Flowersea37 commited on
Commit
5d3b3cd
•
1 Parent(s): f9e043a

Training in progress, step 2547

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Sep26_15-25-38_interactive79915/events.out.tfevents.1727336010.interactive79915.142135.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:426583f346c8c8b166ebe06ed55901f8b88ec6ea3e044a809a4ebfd0bf3bebc8
3
  size 590925768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf024e6503b865fdbe79272d4eaa362b4ea117c81dc2a577d20685477bfa680e
3
  size 590925768
runs/Sep26_15-25-38_interactive79915/events.out.tfevents.1727336010.interactive79915.142135.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edd706b076f76bbb060001ba40d131be15ab782111c3b6db944f77bb92c3ea0b
3
- size 197322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac053c0c486dda7cc250883b56011eceb6fd766bf9618fec1a4e2f63b29a4fc
3
+ size 200428