Training in progress, step 13

adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "shared_expert_gate",
+    "gate_proj",
     "v_proj",
-    "gate",
     "k_proj",
     "up_proj",
+    "gate",
     "down_proj",
-    "gate_proj",
-    "shared_expert_gate"
+    "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:f39f6bf26cb50090be465cc764f74e9bc5ac17f17be6b92d0c218354321345b2
+oid sha256:e32de30c41f448cde19fce48f0221352cb72f430a1c9a5c27392ee60eaf354b7
 size 327040

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8bfc4e432da6998ca18fcd6664e9c1d35f23d456a214fb1019bb0325ffea51
+oid sha256:11cee8b5f4028a12bb206185bfb42fe071f5620c1fbe0fb67df89315c43febbd
 size 6776