Training in progress, step 3

adapter_config.json

@@ -10,22 +10,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj",
     "down_proj",
+    "o_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d07f9b8ca6c7b3704a2d57980e29caea0eada57a613903fe4cc536389c4d47a
-size 9048
+oid sha256:c5f6af426f724ff5c6018dc76990308987f86662c338298e3d511514e4618636
+size 14696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b47330427cd22a8907a56e3bdd78e3a175b459857acf73be72782d88cc50291
+oid sha256:4a8c939205a0e542a6460379054a4d7f52032e951713166b356d84205eb9c5c0
 size 6776