Training in progress, step 4000

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
-    "down_proj",
+    "k_proj",
     "q_proj",
+    "up_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "down_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:bab256b364119c1dda78ed159b14503cca190d3307c29b77d00c1e5a867bc88f
+oid sha256:41a435d00a5242973090f721e0e134becef302cfb046e0b94bdc62f0d0a484fa
 size 180845208

logs/events.out.tfevents.1740939412.b23.cluster.helixon.com.2799727.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007b1b70c10ec282e0ecb1b16ef4eeff8206c781796487025fa73b1771d31084
-size 638530
+oid sha256:23c7772740fafae72caffacd65b2ed49cb68987b2a64f6a9f83fdc370c8992d2
+size 849530

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce2c7685c462c3102ef4dab6a4ee0455a17028a1395377b2c73c9bca071ee7b
+oid sha256:d5998388b60ac76920e64a061f497378506511bfb654617fd97dc3c8b881957d
 size 5368