Training in progress, epoch 1

adapter_config.json

@@ -15,12 +15,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "TOKEN_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ffd6cdb0fd6d073b1f46cd345a23ec6f4d33e3d9d2b454a3c53acc21911bd2
-size 33645690
+oid sha256:2945b4f98a5969e0d8efe6b92136abe85335db62837e7ace8be426056ab3d7fb
+size 16868386

runs/Mar17_22-20-38_beta-M12SWA-TF/events.out.tfevents.1710685241.beta-M12SWA-TF.663271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4711a205924401099058babbf6786e8db14fd428de7b5f2e95804f3ec2287d38
+size 6166

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a1dc18e2c4bed3e7a4ab8e53155eb90471ec0d0bdf088b667b1faf394c1cb5
+oid sha256:0a9294c6b54573e27d9f44e1df48dd876f645085d21b6e5a5af48e7e73a6dd62
 size 4603