Hugging Face's logo

DUAL-GPO
/
phi-2-ipo-chatml-lora-40k-60k-i2

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
939440e
•
1 Parent(s): 830d47a

Training in progress, step 1200

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Sep17_23-03-02_gpu4-119-5/events.out.tfevents.1726578222.gpu4-119-5.2890131.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f692720294fd3d01aa85dda048af2f0295111d8cf795a4d18693ca638fc8c00f
3
  size 335579632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c314235a83640c2dc0f66481534146937295ccb386f25e4be28b6e8b3c44db8c
3
  size 335579632
runs/Sep17_23-03-02_gpu4-119-5/events.out.tfevents.1726578222.gpu4-119-5.2890131.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a47ae65e062abb9bcc608b58b464894f1a4b042d569fe3c9042241df15351c
3
- size 75193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d14d96e5efd41dee9bec833b87ecbb0aeb804b9d19f4bd77a55edd6e0a93342
3
+ size 81533