Training in progress, step 500

adapter_config.json

@@ -12,9 +12,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -23,7 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c4fb83c3e9bdd971b68316f4f8b04d805e35549211ba472e222d1ccf6f2043
-size 16794200
+oid sha256:e49ad88242e639f9f0d42292553ff47b06449769cd8e1db9807f4e6cf78290d1
+size 33588528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96a512352c65f3c006b3ac6720e4e29729b46cee166a3e1d07e53fd9b43dc4b
+oid sha256:de32895b0faf06cb46c1544176f95807a79e4e55f88572bcdfc83deb50ab3110
 size 5304