Training in progress, step 200

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj",
     "q_proj",
-    "k_proj"
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_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:a3f656fb2f62b6ed374a04b4e0006f8f4d74fed8954cbc81da3730f829117e78
+oid sha256:6f175dc51d3060ccb5fc5162262cbf97f1bec26692437bca2fe5ed6cd4a10f31
 size 167832240

runs/Sep03_08-02-43_l4-instance-miltan/events.out.tfevents.1725350565.l4-instance-miltan.3233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9eeda3e4ce2c13c51756b350f352dfedf3bd8304bb6f6aa34e3d0e153923e2a
+size 9588

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03071aaffc71b8d2e216987688a1c6de83a86f76d083978813958c1cdf44295d
+oid sha256:a28f3658bef388edd796654d77b402b8f2440abb8f484aa29e8ba9464aec6aa7
 size 5240