Training in progress, step 35

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
-    "gate_proj",
-    "down_proj",
     "v_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "gate_proj",
+    "q_proj",
+    "up_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:b7a3d993aec0a5706079ec56fe94721831c99659ff31dbd78ce467208270abdc
+oid sha256:96b22a16257fa46bbfd5479458a007d609fad8d7aa42a3a1eed1a3ba3153445e
 size 167832240

runs/Nov29_13-10-26_RLHF000/events.out.tfevents.1732885850.RLHF000.687743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2581c00f4c1466bcf817413b6208387fb1ad5c48ea66e96a01ecf744c12266e5
+size 8570

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c28d768ef9e25219f7ed230d4f4a3e387af2b361399d2150e240e55b4549ee
-size 6264
+oid sha256:25360197da437c5652c8c63caa59c4f1fe929418de209fd66eb4507c7fbc9aa1
+size 6328