Training in progress, epoch 1

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 1,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "key",
     "value",
-    "dense"
+    "key",
+    "dense",
+    "query"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb9e62139bc20496fac612182f09a5b04024528bdd18a7083c39a39a17b9c91
+oid sha256:12935fe97573f8b5e1fa6977fa14298e21525cc059de31abc3ec6eec2d8c42dd
 size 21688828

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36dcacff85e3c97dc1aa68909a9ab8d57bcad9117196164724dfe3036b4aa8b
+oid sha256:22b6caa1eb8b2275eba146a4d1540c6e4189aac4425226c79e87ab702aa941ba
 size 5304