Training in progress, step 125

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "k_proj",
-    "o_proj",
-    "down_proj",
     "up_proj",
-    "q_proj",
+    "o_proj",
     "v_proj",
-    "gate_proj"
+    "down_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:a631280948cd9c2fcd2daf90a96b0ad0edc1563a2fcf563ff6a550411b40cd8e
+oid sha256:e9316194e4b9ebc32bfef1e7cea273333c72269b0bc28a59bf82a9d38a0d04f7
 size 100966336

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7b1b0fb1dd1866c2bba4445a370643a7a5ef1eaa7977889b7b49fab3ac64fe
+oid sha256:e39a4f0eb4f3d2b080abb45f3c3380673d49436b382e60fdf095ebad818ee511
 size 6712