Training in progress, step 50

adapter_config.json

@@ -13,25 +13,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 256,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "w3",
+    "k_proj",
+    "q_proj",
     "v_proj",
+    "out_proj",
     "w2",
-    "w1",
     "in_proj",
-    "out_proj",
-    "w3",
-    "q_proj",
-    "k_proj"
+    "w1"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f051724003b4090851ee143e9f87c1492949fab7b59d9c74962c63db23444ba
-size 24010560
+oid sha256:6d434f381f12a5a1ceec4e1d23e2dbdd8e01d8a229491a8ea8a829456de9ca33
+size 95969208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3154b27a6e7e495fcfd2446ef416930cb8a294c2d8bee299642060a97c35c6
+oid sha256:4e71e34e8f138dae57cb48fe9606dd4481e0f28071914d8dfe3389e92e02f210
 size 5841