Training in progress, step 300

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
-    "o_proj",
-    "gate_proj"
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7293d5c8c92db7ab7ea375b87f4ee580d94c8dd37b782cf0647e21f5c0928e15
+oid sha256:835de3b778af3afbc7f7d470e8bc51f958471d9be242b80eab2f688c920dbce5
 size 1342238560

runs/Sep25_22-43-42_m3h100/events.out.tfevents.1758804452.m3h100.2717525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504a9a3074e9ed46f1e40841110f17be2197f3cefd3a220f86be4e9f4ec174b7
+size 12261

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1e3e0028dee5d8a3bd413255a745f2891aa2e1bc47a1844ab479f6300488c4
+oid sha256:9a3c68503b09ba6cc0475a3d5877d6a63fd54cf4d76178a6241f70c3b2377877
 size 6456