Training in progress, step 4

adapter_config.json

@@ -13,8 +13,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.0,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "v_proj",
     "up_proj",
-    "down_proj",
-    "o_proj",
+    "q_proj",
     "gate_proj",
     "k_proj",
-    "q_proj"
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadd4bc411b8785fb18f5763a84f20a80e4e9f1ae3028427cdfda7c450bb153f
+oid sha256:215d8d6b963029d95f242e1969392a92466ee52dd19e27e8c901007be260adc7
 size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463abf89ab8e791b1ee4488f7dfeb8e3fd5bf4140d9f3f33359c2cf2cda2e5f2
+oid sha256:33e0e55fbd8d36c917eabe21bb4f61a2fcad4819af40b08dae6e8f05f6cfb6f6
 size 5368