Training complete, uploading model.

README.md

@@ -36,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 5e-05
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 3407

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "q_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj"
+    "v_proj",
+    "q_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24bc15ac067833831a0cf28ec96a7df5b55efa782ced4d8ef90ec53b2e30d4df
+oid sha256:a3063e88840b41fd2c7a71f1114c0e322c097a7e6e6f8221418ab8138e241610
 size 5496