End of training

README.md

@@ -35,8 +35,8 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.13.0
-- Transformers: 4.48.0
+- TRL: 0.14.0
+- Transformers: 4.48.2
 - Pytorch: 2.5.1
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0

adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
-    "k_proj",
-    "up_proj",
     "q_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d74a0d34c09272d6683689bbe2692c5f6557e1c1be7c345a63b91982e23822d
+oid sha256:d924862baa71eb0a45fda2a67ec457ca468fef1e80fa4489c79bf86d69baef05
 size 194563400

runs/Jan30_21-44-43_bb21a8bc0f37/events.out.tfevents.1738273487.bb21a8bc0f37.3373.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66908e449e0a9644d30227e945bac7841a1cfd58bba8781503c81184a3022370
+size 58677

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963892d104427139b8c65da8d2d07358045bdd7658efb1ddd319514cd327bd70
+oid sha256:dcc0327c035c0d51113cd84a6d570c7d43a1e4beaee3140baee951fc16a07922
 size 5624