Training in progress, step 232

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594bd5d62a7bfbedc9026a526616553de6d7484ede384218625ea65e40d08a2d
-size 54543184
+oid sha256:efff5f5e6f0f5a3099d350893706dcc50c1c750a2f00762eaf49fb772f0daf45
+size 13648432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b5bda79a59d20794234677f8cfe87124f54478171e411c85fcd55b15c772bb
+oid sha256:fa07c243c3027e556a408665d066b19b695f86f0a20f7da878906eb4ac14c17f
 size 5688