End of training

README.md

@@ -33,8 +33,8 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.0
-- Transformers: 4.46.2
+- TRL: 0.12.1
+- Transformers: 4.46.3
 - Pytorch: 2.4.1+cu121
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
-    "gate_proj",
     "up_proj",
+    "o_proj",
+    "q_proj",
     "down_proj",
-    "k_proj",
-    "q_proj"
+    "gate_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:e300e9ce578ee5c5d293eb7a2081aba28c6d1693030e10d5649cc892d2c0c288
+oid sha256:e830baa159e4a1aaff250f0bc45abc80007ea82d02e342d5661ee940d81be0b6
 size 2332095256

runs/Nov21_04-31-02_8933ad4cbc21/events.out.tfevents.1732163476.8933ad4cbc21.3812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318c5ecbd04a08cc9890a145c68918fdd702224723835404826c13c3544923fc
+size 179568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ae18e8fac07e67fc5ea615a995e7dd1f92b8d9f9bb32e00065f4d5db168749
+oid sha256:24e4761bab1fa91296f4f5f66f1c766ba163a959610ab4ca5b16b39df3be6cb5
 size 5560