Training in progress, epoch 1

adapter_config.json

@@ -10,19 +10,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
     "value",
-    "key"
+    "key",
+    "query",
+    "output.dense",
+    "dense"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa7a378a8402c79e69e63d77a25f3edd474dda62504da88d565f17853d416b3
-size 3786108
+oid sha256:041c66e12eb8cb9cc64f318a0e2a4c36937e66d5b068a1ae90a09451b37994d7
+size 5614796

runs/Feb26_20-34-54_modal/events.out.tfevents.1740602096.modal.2.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d0a79e1ea11a1c59da8fc8bda13cc4483764729267b7689506b410335e2690
+size 13298

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1830fddf31503d5dd3f00344bd297cc1f7f03bfcce80340c7d38d747f762efb
+oid sha256:4c9d1e676bc96ab0201ec5a875930e7100718cbd28118f2ce6d3bd80f263c524
 size 5368