Training in progress, step 100

adapter_config.json

@@ -11,17 +11,17 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "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",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aaefbf9302337dbabec74ad0dd4f2d90755e7edcd2b9168f891a51885904691
-size 13648432
+oid sha256:3dc4ef791a926cd80edfcaf90629e7de621cf5a87010c7bd71ef02edc02e5965
+size 27280152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cedface56d34fa67cfae022ea1a16601a963a718ffbbd814811d04e7b65237b9
+oid sha256:8da70643df584803d10bb95f072a1368de84aa3c23b5bf5fda0a6ef509562aef
 size 5432