Model save

README.md

@@ -22,10 +22,10 @@ It achieves the following results on the evaluation set:
 - Rewards/rejected: 0.0
 - Rewards/accuracies: 0.0
 - Rewards/margins: 0.0
-- Logps/rejected: -200.2201
-- Logps/chosen: -64.1429
-- Logits/rejected: -2.0307
-- Logits/chosen: -1.6500
+- Logps/rejected: -200.4062
+- Logps/chosen: -64.1242
+- Logits/rejected: -2.0309
+- Logits/chosen: -1.6493
 
 ## Model description
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "o_proj",
+    "q_proj",
     "k_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d22c6726ae22df7493d6df3d7d3a0ca214e99f6323a39459e4c8f645092e8f
+oid sha256:850c3f2e0e0a28d7713b0947b67d85baa660c4b7a0ae230df4b6a7b3d131d061
 size 27297032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55be1d529084039296674e9b1899bdbf3b16972734743277e5ec5272b1c7c6b
+oid sha256:3cfbec3cec9a3723bf52c1da5fa438d2709e3e69a485f08f9c2b7e3ee7472df3
 size 5304