Training in progress, epoch 1

adapter_config.json

@@ -14,7 +14,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -30,10 +30,10 @@
   "scheduler_verbose": true,
   "scheduler_verbose_interval": 100,
   "target_modules": [
-    "dense",
-    "value",
+    "query",
     "key",
-    "query"
+    "value",
+    "dense"
   ],
   "task_type": null,
   "total_steps": 1290.0,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea2ad9ac4a0e01eb0b5204b0f0625e735dc39ed44e270bc1e028ee0cbfb69ce
+oid sha256:5c560d8ea20dcde4c357fe8799a94c18ed9d3dbd05fe86b11d968615b28e005f
 size 17116668

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67425e2ccf43aeaf721e4d02b22ebcad7f7da0ee4f395e16e7a4cff6fcafae08
+oid sha256:bc4af4cdbeec96a9016160a70d680873d15c50cb80af07408c91a7912828daac
 size 5304