Training in progress, epoch 0

adapter_config.json

@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,16 +20,16 @@
     "classifier"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "task_type": null,
   "use_base_model": true,
-  "use_bias": false,
+  "use_bias": true,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a70918ba8827636ec877142e78533787010b9eb62ec75ba591a473f4514d57
-size 2677140
+oid sha256:96275cd0dca76d30f72e057325cb25c7de8568d4fd814c844fe28384be504c16
+size 9841620

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee103db9c4bfa6b8449286f8f8c4ec9e9a3d8dbf00c6d9562042494bf3dfc2f
+oid sha256:eb3c050272040b71d23103452318228cc448d2a3f5ac8dda9e443e4b272d07b4
 size 4984