Training in progress, step 3

adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "shared_expert_gate",
-    "k_proj",
+    "gate",
     "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
     "up_proj",
-    "o_proj",
-    "down_proj",
-    "gate"
+    "shared_expert_gate",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5273ed67ed07557c357f7d9c2a134c73c14bbab7da8d5e75cb9d3417a5556d63
+oid sha256:cf0e485870825f64d302019f5843d7db11744a138aec55c16990179f622a09f8
 size 619632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d17a2d7c753668038fc708e931afd4960bfaccc6778ffcb05c17982c263115
+oid sha256:6836878b4d58f42aba8b8da9c26e88662a423037cdadf955f0d7e08457efa733
 size 6776