Training in progress, step 200

adapter_config.json

@@ -15,17 +15,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "q_proj",
-    "up_proj",
+    "v_proj",
     "k_proj",
+    "q_proj",
     "down_proj",
-    "v_proj"
+    "gate_proj",
+    "o_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925bbeeaa3899b1578cf2674a667c27a23dd16b4d227788b1c91e15e1463764e
-size 671150064
+oid sha256:855bb6804ddc37049a25b2a2777a37222f8a2d4b524adae068c06d36fcafd590
+size 335605144

runs/May06_15-12-45_gpu4-119-4/events.out.tfevents.1714976509.gpu4-119-4.2643643.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbfb0a1f04e37d35384163ce2f6b0d41a5be767ce539be2654bbd5ca898df04
+size 17726

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf7ff86f242e9432f15e1ac282b4ff9206c7416815b5d6512a2a029e3173b6d
+oid sha256:08317e6aeae09bf4934ce5b843f0a5aa79691b70112619e0e37ac6432dd46138
 size 5816