Training in progress, epoch 1

adapter_config.json

@@ -14,7 +14,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 8,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,17 +23,17 @@
   ],
   "only_lora": false,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "scheduler": "only_lora",
   "scheduler_verbose": true,
   "scheduler_verbose_interval": 100,
   "target_modules": [
+    "value",
     "key",
-    "dense",
     "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 sha256:8293a5682464adb849ddd459da7c77fa85dfe7f2ba7cbd33d565030efd58685c
-size 33056140
+oid sha256:87bf5e03c12a644c3a4c4fadaf19bf4a28671a20ec99c47600b6330d94477076
+size 9146060

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58db87f319c1ee87f432b120e638073823e064df56253f0af559dc9005226374
+oid sha256:e69dc92c939fbb05becee137bab63687518c7659bf33beabe8083923f017e44e
 size 5304