Training in progress, step 500

adapter_config.json

@@ -1,4 +1,5 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "kkboy1/Mistral-7B-v0.1-sharded",
   "bias": "none",
@@ -7,21 +8,22 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "up_proj",
     "v_proj",
     "o_proj",
     "gate_proj",
-    "up_proj",
+    "k_proj",
+    "lm_head",
     "down_proj",
-    "lm_head"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07b311e29c98938100eaff42202979571a85cf21e30ba2fa4f00cc99c84cdfb
+size 170244818

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc9601565cd49aa464d0ba01062fdf0b1adbe2f5cf4a62b83fac6f1d305c9cc
-size 170142632
+oid sha256:d706a335e1863ca5e7321bb7872bbcc4a386a4458902ca61b7af788c8575b9b7
+size 340225224

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b57aae45f5e1e2612cf1fa86adad1048b50e88c0c3ea4a027518901f5615e8c
-size 4728
+oid sha256:245cb3e0afb79d68934ac358a8aa7931a5a14c39e3670189d11328d5f05c9ed5
+size 4664