Training in progress, epoch 1

adapter_config.json

@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "TOKEN_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b2046b39d06d0c53213f55170fba9e407ce36cf47f902f9f0ea79f7a47fc85
+oid sha256:15928fba7a55977fb7ca77133a93354fd9ae0abadb09c11da66ab95d872ded1e
 size 27354210

runs/Mar18_18-05-25_beta-M12SWA-TF/events.out.tfevents.1710756328.beta-M12SWA-TF.722899.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed671773e3138bdbb2b3bd9bb6030b9b43f9e969e15605a32c78aa685692f82b
-size 13363
+oid sha256:552ba9cf2f41d8f5393626c2628713c20d282946bc59254d148ddefc6f6deb16
+size 14207

runs/Mar18_19-24-21_beta-M12SWA-TF/events.out.tfevents.1710761064.beta-M12SWA-TF.727421.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a342481c07805788acb97c53b18cc7f1ec07810dc2be4999e40060c1721345
+size 6101

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad54f877b680a879dcd246ab6264b4d0153b85d216ba5bd9689686cddf329306
+oid sha256:92cc204833919bc379f9eb949aa014956b5f76e7fdf356707bbb7abb83067b7d
 size 4603