Training in progress, step 1000

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
+    "query_key_value",
     "dense_h_to_4h",
-    "dense",
-    "query_key_value"
+    "dense_4h_to_h",
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc893b41372f260eb02048401003e6873a3340a4358fa4e9eff49be4547bb6e
+oid sha256:84537801d6e89f13dca38d6cde98ea9752476ebf779f0e2197d740ce351f0245
 size 100690288

runs/Jun04_14-08-24_dd2d65c046ec/events.out.tfevents.1717510147.dd2d65c046ec.2884.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5b1bc6b1c0248ac159be847ae89f717db1bba3c22894149bb361eb44347d87
-size 8849
+oid sha256:2800f5b7aba42fa05ce20fa2f040f78ceecaf3cf7c206a3f810fae5383f95eea
+size 9693

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad55748ec06e413a027586c8e1fd4f2caab0220646b7640e6d7c67e870b6501c
+oid sha256:d80899da35a4e612286fbeb82c29f6266a94cabd7ded99775c50b488a6f42037
 size 5112