Training in progress, step 25

adapter_config.json

@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
+    "down_proj",
     "o_proj",
     "up_proj",
-    "gate_proj",
-    "q_proj",
-    "down_proj"
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2777510109db20a04874eef5f934bf4e511240b694bc34279899246d0d70cb
+oid sha256:0b9b80c33aa6310efc7335f26293e447915106d45bd83f9e1aa11818b23a5b18
 size 45187904

runs/Jan11_00-33-54_dgx01/events.out.tfevents.1736530448.dgx01.1403304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a3bc248f06ba9d6ab83c9d7b202572d77142480efac7e0bbb3a6eb8651e710
+size 9238

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7604187532d65f2f2cc1f47975eb8bf4b5f84cb8a0884cdad56725367023930d
+oid sha256:8b733552339ed0ff86af32ff52ff019eda55145fcce69bdc2698c14703569fd6
 size 5624