Training in progress, step 13

adapter_config.json

@@ -51,7 +51,7 @@
     40
   ],
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -61,13 +61,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "q_proj",
-    "k_proj",
     "o_proj",
     "v_proj",
-    "up_proj"
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ff287073468fb2c296434e7be50a5e5f1208dfd0bb41e30204477cb2122763
+oid sha256:6c5fcefc886be992d30a3ab573a086937d299cb8a3d0909f9d7367cda6cb5c7a
 size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89fd87d8af6d2616f774850f2f449c533b5101818db86fea737ee9882810d915
+oid sha256:382d0bb02fa7ebb5ad45632e2ba9cc22d77ff97e80e913e774b925d6b8a2421d
 size 5112