Training in progress, epoch 1

adapter_config.json

@@ -14,7 +14,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,17 +23,17 @@
   ],
   "only_lora": false,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "scheduler": "only_lora",
   "scheduler_verbose": true,
   "scheduler_verbose_interval": 100,
   "target_modules": [
-    "query",
     "key",
-    "value",
-    "dense"
+    "dense",
+    "query",
+    "value"
   ],
   "task_type": null,
   "total_steps": 1290.0,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300a460fad96be41516588679cb3fb4773c580654847d16b825a6e467f646ee1
-size 17116668
+oid sha256:f8a3dad886cf09e48943804401ab192433dde008c1a81ef849de9a22bd3c48c1
+size 33056140

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4af4cdbeec96a9016160a70d680873d15c50cb80af07408c91a7912828daac
+oid sha256:58db87f319c1ee87f432b120e638073823e064df56253f0af559dc9005226374
 size 5304