Training in progress, step 500

adapter_config.json

@@ -14,21 +14,24 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "up_proj",
     "gate_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "down_proj"
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "task_type": "SEQ_CLS",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e580e84394c835f6a247ae9c0df2f4f34fc462cae8da46d5643db94a89720aa9
+oid sha256:91fb67578fb07d8c3a0f2c08fc47c07cfb4a35446a7219e490b343c74d75d0cd
 size 332316480

runs/Sep22_07-37-49_ef7dc31b7d1f/events.out.tfevents.1726990674.ef7dc31b7d1f.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69cb26f38a5ef582fd352199889ddfd5f5c99032b8457cd48862161584071fc
+size 6008

runs/Sep22_07-39-13_ef7dc31b7d1f/events.out.tfevents.1726990760.ef7dc31b7d1f.36.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dae325266c60df5b0bf4c0d5cc909de845cf07c3aba27b3a155dc6b7788f6ae
+size 6008

runs/Sep22_07-39-28_ef7dc31b7d1f/events.out.tfevents.1726990773.ef7dc31b7d1f.36.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c46c9f190ba91d0298aaa73e7f84ef548972ea2a338fb584d4eecb1b262344
+size 12410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e312dd63348f188d71793658619b2428040cfe28f014627cab8cfdff3869c0fa
+oid sha256:1d364eece572a93e3e9cdfd6a8c9e59dcc87d01c4be52a4f0065a31598a4dc5c
 size 5560