Training in progress, step 100

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
-    "q_proj",
+    "gate_proj",
     "k_proj",
+    "o_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
-    "o_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea213b0191b41b833d1327ddebf2515f82dc96c9b7c2acbc52fdd105d1fd57b
+oid sha256:747ba289590a814b5c61334e2cee30075e6ea7420291cd0abf771a375ec9b73d
 size 1342238560

runs/Dec14_01-37-07_c263-gz3-server-iv-002/events.out.tfevents.1734113266.c263-gz3-server-iv-002.2372944.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f439b72121650cc5e3c2305153e9eb0795fa6c3dace5e4b12fbc0745e6b99bd
+size 7131

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8ceea581249054ff6a858d0927c2ece1320c3c5013bd64739425b508292e3a
+oid sha256:53f3c62a13360c4c3fa4b2eaa65ce11e4394146a19d02ccdaf47ea559c21d5a8
 size 6136