Training in progress, epoch 0

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
+    "gate_proj",
+    "k_proj",
     "v_proj",
-    "gate_proj"
+    "down_proj",
+    "o_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:cc36a8e37dd54f1611000c6fb5b8a2b1fac16a87eccb3c03b80d950e8d920cf0
-size 14696
+oid sha256:b6cf0b38fd50b5592fcdd90cde67f3953803b845427a6da838198ae49e8910ea
+size 9048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42859b767e48a28bd6aa4d7de82f9e080fc3f6e573f77325e209b5bb86fef1a3
+oid sha256:9728de9c04ba459f8a150ca989a490b015c26610cf896681f245b555b37edd32
 size 6776