Training in progress, step 2

adapter_config.json

@@ -28,14 +28,18 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": [
-    "down_proj",
-    "up_proj"
+    "7.mlp.experts.gate_up_proj",
+    "7.mlp.experts.down_proj",
+    "15.mlp.experts.gate_up_proj",
+    "15.mlp.experts.down_proj",
+    "23.mlp.experts.gate_up_proj",
+    "23.mlp.experts.down_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e7e71856637583becf65c60619a073422601a908b9ff28cc74e7548450df28
-size 157515072
+oid sha256:372963ddb62d8abec51013bbc77e92efaac3272249f908500155e56ebe13f88b
+size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095593e6b0aabba7b77c928fc41f28b6613b2ab4971641382afa29c821df33ae
-size 6161
+oid sha256:aeb8bb0f09d8160a8b40506c151389f641de748dac6f285829cba4e9636d9fcf
+size 6225