Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-30k-i1

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
025aa93
•
1 Parent(s): ccfe35b

Training in progress, step 1800

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/May12_03-20-42_gpu4-119-5/events.out.tfevents.1715448183.gpu4-119-5.1641529.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a810bdf638ce4edc6f7463ff0dd192233ca2991ddddcadae0e4e63d9778d820
3
  size 167807296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662761b7e368b545e1b485be4dcecc424f060c732675395610c6b1af472f3259
3
  size 167807296
runs/May12_03-20-42_gpu4-119-5/events.out.tfevents.1715448183.gpu4-119-5.1641529.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc4c7978ce90d63888ab9b66e4595c443586c37cd8b612e1c7748cc5198d749b
3
- size 113154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aad8719994e3bdec1841db0bec7b319a73bda82933d53c410886e60346cf803
3
+ size 119494