Training in progress, step 500

adapter_config.json

@@ -8,19 +8,22 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 32,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": [
     "classifier"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "value",
-    "key",
-    "query"
+    "query",
+    "key"
   ],
   "task_type": "SEQ_CLS"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d56ac2fd13c3ec21068c693384a63f55e8fa9246a10fd4d1aa95cafd0090343
-size 1782816
+oid sha256:35398b36a707b768492dad1c5b0e3bf58fd13319c146f39e6b00e6a1fd111f2d
+size 3552336

runs/Dec06_13-41-01_502a3f046fc0/events.out.tfevents.1701870217.502a3f046fc0.207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fe1659d79728a107729ccc7a4d955ef441200421bacc3b1bec0ccc5eef0e86
+size 8757

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a2330ada25c299642886b670b46d1f2841a2fdcdc7c20f5085d463015b36be
-size 17098206
+oid sha256:169c843363eff31fa143c9c81d270e0ae265e2d1c3ab5256e6276e6022f553be
+size 17098270

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c01e80852799fdae66502e99756fa8360d8aeaf5d68845c886147e471912ab
-size 4664
+oid sha256:225321eeda2f99579ed2fb5043d439cea2d444bc7a99ac27fada81ef47521cc2
+size 4792