End of training

DPO/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "v_proj",
     "k_proj",
+    "up_proj",
     "down_proj",
-    "q_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

DPO/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b94ab9a341d39d9ced0d90914ca965619e12abf5c15310870802002b8c474a
+oid sha256:dcf7576d4f871e77a990b4e06fd930defd975db0eb70160a695e96468d6b530a
 size 167832240

reference/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "v_proj",
     "k_proj",
+    "up_proj",
     "down_proj",
-    "q_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7311bd35bf930a7d8c4dfe988e8970c434c579b4ef29e673ab60d555b39cbb1
+oid sha256:e8ec2f319eef1ae8ce52d6b600c23decb92c0e9f031eabe7177c4392d4947e93
 size 6200