Hugging Face's logo

dball
/
zephyr-7b-dpo-qlora-no-sft

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
1
dball commited on
Commit
38e55fc
•
1 Parent(s): c4c59bc

Training in progress, step 7500

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Feb08_09-39-21_7dec04cc21c9/events.out.tfevents.1707385209.7dec04cc21c9.25454.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0cd2225dbf0f2143557c6e75b02af2935459e6995e83235320e88e0fa48dc90
3
  size 83946192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb4e980adfcadecb248f3032944b18f7459cf37bd196f5d3ea7e25a344958d6
3
  size 83946192
runs/Feb08_09-39-21_7dec04cc21c9/events.out.tfevents.1707385209.7dec04cc21c9.25454.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e318859551846ea887ff1216ef1001294631a1167a30749616354b25399f63b8
3
- size 529362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b33820f745065b0bfe37a3a8d1a6b576aab81a4483350bc59752c4ce7bd62b7
3
+ size 536442