Best model so far - eval_loss: 3.0929 -------------------------------------------------------- (Trained with Unsloth)

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj",
     "o_proj",
+    "down_proj",
     "v_proj",
-    "up_proj",
-    "k_proj"
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f00bbb9109d6ee732da0318f7b5a29266d7d5cb5e11173e1c3cc447ddeee65
+oid sha256:0da87520371b2837a5e2236fc4875fb36de722eb97939016fd6b33f0da7b77b8
 size 2372980568