Training in progress, epoch 0

adapter_config.json

@@ -11,18 +11,18 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.06,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 5,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q",
-    "o",
     "v",
+    "o",
     "k"
   ],
   "task_type": "SEQ_2_SEQ_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1051fd2b8accd4c2afa1ed118c7f7d2e202db5bc0a98f92be74de0e64f6fa8
-size 4463560
+oid sha256:0ac1f76b04f1bf5a27bdc28a387af714650ae0b6094ee180c2cb72d337957e74
+size 7117824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654224882136aa5ac090d2260dff0404c58ed90e53fe779eb9cdec69e43d1171
+oid sha256:95aa391aaccf78dceb41e875c5c2cb4ca56aee06d496b86054d7f1fdbd48167d
 size 5304