Training in progress, step 375

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj",
-    "down_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "gate_proj",
+    "q_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 sha256:786ef9a34c470a703ba6d3130613c3fc453d63defeceaa624009c288401c35a3
+oid sha256:3fabf156ba1d5cfa79c5957793dd7dbc270fef1a6c061892cdfbf7aa288b7e9b
 size 47584968

runs/Dec28_02-23-39_scw-vibrant-shannon/events.out.tfevents.1735352620.scw-vibrant-shannon

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30daec47ac6e44935477597bba5f4daf565812214599160d6a5f1504250c2a68
+size 6746

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29731095b7f057176adb9284d0020503b193f5fd39511778640467dd026038c
+oid sha256:bfb4624e47e2608d3ae5fae52f89ec814a40d3680446887fd7122bd32fcfd6f8
 size 5304