Training in progress, step 253

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
+    "down_proj",
     "k_proj",
     "o_proj",
+    "q_proj",
     "gate_proj",
-    "down_proj",
-    "v_proj"
+    "v_proj",
+    "up_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:f6d37cc0d2e92f80510976a84af59edf8db95f921e5642ca647c03be6c006aad
+oid sha256:8568fc0c6ac26e8302be06adf97f09eb53267efe64896e1418beaa9df6d3180d
 size 4381342624

runs/Jan05_18-56-34_61dfa4e62882/events.out.tfevents.1767639404.61dfa4e62882.9454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfac3e8ca2d3a6ad548529d1b17cec494a4a1e7ab145c22cdd1864970308f55
+size 17531

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36a82c528121cea28ed68fd8ccbf17ee0af177e5915eefa5151973cfe38ea32
+oid sha256:0461fe35e14c160736540bc59db09fc98422859edf3e0d21e83e24f60284e788
 size 5624