Training in progress, step 3

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "up_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj",
     "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6bab913ea77ce8a7121a4b2637b490f99b7ff26bd18e546a8eb57d7a1e7004
+oid sha256:4e84e30c0301407719a3b1172dda3934172d624a33b10e40d6cde648c71dbb74
 size 48679352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53735c8d41900ce40f6c3121bd718f48f84ed9d653f3199c613a38cdb020c03e
+oid sha256:7480b656661917a67d93ad938c224b8cb1a941fbeef0225900c5bfb3a16922eb
 size 6776