End of training

README.md

@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5a422c9dc3d247ec2b10d2aeb5a2148047a52520e1815671fcd084b2697958
+oid sha256:5f5ceb47041ed813346d77dc3a8a1852c0f55dbbe330d4d8f31ee2f9e9b8f36e
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e292a85c2a8cd3f365eb0612ee3b6b5310b26f47b783f3a89e7c38d53b1be645
+oid sha256:cc25aaf41ea9e18ddbcf5b81fff23e35788f4fbd439297c39bbf898d91b12650
 size 5368