Training in progress, step 2500

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc96107dc71d45b4d0612a5e10c081c72b46cdbde69311d3e27f6677b521e1e
+oid sha256:12e25b9a7a393ac18c9e176f76fb621be2e6733cb85439a7b5eb219ff4286691
 size 7099360

runs/Apr13_17-07-19_27edc8b3c5f1/events.out.tfevents.1713028041.27edc8b3c5f1.273.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8337e03d6a361e0b4971856bf4d4fd674bda16e87fa2ce25ae5e8b0cc1620301
-size 10957
+oid sha256:ac637f71b83c18515c4450199ecbd14fe106ad4a942cb4dd345b34d92633a78a
+size 11439

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2582cba998b3ccda711291d02ad4edd9e89ab9799af734596a601b26b6586d1
+oid sha256:7a8e39932266814530278f72b966e6ff504e81438b48e31aecb4ece5603c1699
 size 5112