Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-test-longest-iter-0

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
BraylonDash commited on
Commit
de0b05c
•
1 Parent(s): ed8be06

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,9 +19,9 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "dense",
24
  "v_proj",
 
 
25
  "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "v_proj",
23
+ "dense",
24
+ "q_proj",
25
  "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:140c543600b18ee3b2d83f24deb70667a250c90e52e1ebb781b5322e627099de
3
  size 41977616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b950c475743272d17772f4131c649574db6ee1573ed2f4de766fd10c7a5000cf
3
  size 41977616
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb32fe01e4a8f701b7eda81ca7f1a16a6ee3d43a1f3ce2c9bc44a137a295ee7e
3
  size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc0beec4c029024d9b1a575fbc5d247bc8271ce25830167ada5f4f44aab50fc
3
  size 5880