Training in progress, epoch 1

adapter_config.json

@@ -9,8 +9,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -19,8 +19,8 @@
   "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:dc790fe014635b7c7be6c6191420ccb1b89e96f25b6506a668f248f598a917fc
+oid sha256:98a38d15bffdeb9421306650c86b631536e97f30c2ce6a0ef34924bc188c13cc
 size 27354210

runs/Mar18_16-43-11_beta-M12SWA-TF/events.out.tfevents.1710751393.beta-M12SWA-TF.713928.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52567d59e8446d8d49a5cb3def094cacc7d33588004f98fea201dbede9d57b0
-size 13363
+oid sha256:420c879941b49cb7bef7a46c4fbc87fdd7d08b0152cf86afef3f7f574d4b8e93
+size 13785

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0912a580b64fe0f150897cf69ad5b7914609299bb0012cfc8e8854b98a97a863
+size 6100

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae433a885f37c7298be6425c85608742eafa6ec19fade04d7533d8ada12c2702
+oid sha256:ad54f877b680a879dcd246ab6264b4d0153b85d216ba5bd9689686cddf329306
 size 4603