phi2__multiple-choice

README.md

@@ -35,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.002
+- learning_rate: 0.0002
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 10
+- lr_scheduler_type: constant
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
     "fc1",
+    "Wqkv",
     "fc2",
-    "Wqkv"
+    "out_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed1215cf84301c3c4eb163f1980a8a6be1c6a3fababecb310399b7890d32c28
+oid sha256:8156ec0bdbaf087568038de1a5468188704ccad50c6c21e5baaae43b752fa353
 size 83919184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f034812650fd5e90df187340528193aad62ce88cf5f0cd2cd2b8c0c233c57a0d
+oid sha256:49ebc854d760477ed7ca2470c2d40e5eb44c87c57bed7e7809e02adafb5bcf1d
 size 4347