Training in progress, step 1466

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "q_proj",
     "o_proj",
+    "down_proj",
     "k_proj",
+    "v_proj",
     "up_proj",
-    "v_proj"
+    "gate_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3112c941ccf1df707b70d7b0db80ffbd22a4d698c351cf1f4a4c9d87b9157b3a
+oid sha256:3959cf8ad5b5597398f2f82610a0386467c1ef305d2b8ef2987ca0e729f4da54
 size 4381342624

runs/Oct29_02-27-14_0732d6551ba0/events.out.tfevents.1761704842.0732d6551ba0.6225.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b5e71a49d6e11a0138b715f0ce3e1ca127a9ae23ef7a48e7c9da12aeb77472
+size 68808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e1ec2be85f09a3e23892925e3153254dfed70ee98465176b4693661bc84952
+oid sha256:dd82c90940c435ad6a4a76329161125d0c4b0d810b5341fae4d7633494d11d6e
 size 5624