Training in progress, step 1400

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "k_proj",
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "down_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3e64cafe4eb7b869a78f1671dbad16d109dc02b8f909768a7c2ab19ed68c10
+oid sha256:00c5375bc3d21e278a8aa1907284b7fa9c4b69cedc38b533ad42b9f2f72fd11d
 size 671150064

runs/May11_22-24-47_gpu4-119-5/events.out.tfevents.1715430380.gpu4-119-5.1225720.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151a74ebad162e092fc39693811027c4a30bd9139928fe1de77a085cd39cebcb
-size 81124
+oid sha256:bfd9cad5c018d31695a506fbbba9415b26b9e7859d90d1d1ddde7eb6d68ea4cf
+size 93804

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475012aaba5e592a35fecc87b8cbd2410e93eed2254dffdcefde98525e0fbb07
+oid sha256:a05f96ec090263376cd228d635aca352f8b6b4cf2b5f952fe5cee47667e6313e
 size 5816