Training in progress, step 12

adapter_config.json

@@ -16,24 +16,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "up_proj",
+    "k_proj",
     "o_proj",
-    "v_proj",
     "gate_proj",
-    "q_proj",
-    "up_proj",
-    "k_proj"
+    "v_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851f4b0fe956eac509642f70fd14815493e76066844d87f487c1d0ec98575524
-size 8841928
+oid sha256:b49989a6af1fef377ce007ebbb3081e857efdd9ac5ed32f0572b399f54638528
+size 17640808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff5d866f3f58eded13df4e5d0f17d86b3f86cb9253959e5d718e586d0617838
+oid sha256:af3974b5d650bad10616ac85d5be43a43be3a632e9e6ca9838e55c33bd2fac4e
 size 7544