Training in progress, step 10

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "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": [
-    "v_proj",
-    "gate_proj",
+    "k_proj",
     "up_proj",
+    "v_proj",
     "q_proj",
-    "o_proj",
-    "k_proj",
-    "down_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 sha256:6796a6ccffe6eaef88db481d26667f620e506143f681ddfffec5c7758c31d70a
-size 80013120
+oid sha256:db035bf35128e9c64508764ab4868db32ff5f35d059b8a33ce51ce4b9d8de248
+size 159967880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d084b8c72bde113bc93dcdd2db429269f664d9595d7b2aa78f117eba13424ad
+oid sha256:941d5085ebca954b274b9a9a2731ee3b9b47f0fd93cdf2c16f6d939a54a2448f
 size 5560