Hugging Face's logo

DUAL-GPO
/
phi-2-kto-i0

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
5a5f1b6
•
1 Parent(s): 91d5187

Training in progress, step 1200

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Sep28_17-55-57_gpu4-119-5/events.out.tfevents.1727510204.gpu4-119-5.4042856.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe4c01ba60a4e498bb67ba3b02971d85bf8cfd0eedcba701d0dc856f6486458a
3
  size 335579632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9bc4a80d1cf0a3ad1797ccf1a84df3667af464b28a6567b983a8ee6f84d36c6
3
  size 335579632
runs/Sep28_17-55-57_gpu4-119-5/events.out.tfevents.1727510204.gpu4-119-5.4042856.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91fc5c7e802493abe5c6d731e0f35fe25641673c4c74fd091cebd66c180ad3c
3
- size 15022
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38950e7f91da8766f1a6dc7d7fea79353fe2356a40640c97282f8f93f7c8df10
3
+ size 16290