End of training

README.md

@@ -37,7 +37,7 @@ This model was trained with SFT.
 
 - TRL: 0.14.0
 - Transformers: 4.48.2
-- Pytorch: 2.5.1
+- Pytorch: 2.6.0
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0
 

adapter_config.json

@@ -25,11 +25,11 @@
   "target_modules": [
     "o_proj",
     "v_proj",
+    "k_proj",
     "up_proj",
-    "gate_proj",
+    "down_proj",
     "q_proj",
-    "k_proj",
-    "down_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:324956000e15215290274db1c7baa1c7761ac9fa271f290c1b78147ab5bbaf36
+oid sha256:d992627fd061af7073ef32a8e3b2904dd51e170226fa936e056561471a4f68fe
 size 194563400

runs/Feb01_22-51-47_f4bb93778a7e/events.out.tfevents.1738450311.f4bb93778a7e.1564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c386ec07f3fc0460343f6b375d9dedef6f68f9bea3957f9ff0548e00afbc51ec
+size 58677

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc64d73a4e8bb33bb855da10b39e431313dc5705037411590edce1a9e981c7af
+oid sha256:41d7e854ad572f999504c591e20ec68a9758104befe4eed5cb452fc46fded405
 size 5624