Training in progress, step 100

adapter_config.json

@@ -13,18 +13,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b10c58ef68ede2e73caac6fa9129ab6fa5f036db56894646a88013bbc0442b2
-size 2366304
+oid sha256:ac367b7abc8c4db373942ff30640a9979dfd734d8001b1a4aaf0adf3f794bf0d
+size 4725624

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2601864b59a857be42eb379782a488682b5e66331c125489597e0fef1331bd
-size 5112
+oid sha256:b5fa8c309569095f3e17e9aefe47d50e979bf484635ad8e104a9677cab438285
+size 5176