phi2_question-answering

README.md

@@ -35,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- 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: cosine
-- num_epochs: 10
+- lr_scheduler_type: linear
+- num_epochs: 12
 
 ### Training results
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
+    "fc1",
     "fc2",
     "Wqkv",
-    "fc1"
+    "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:f24c0f4cf24d19141be7610c343d65e2b68016325fe08d91fb4bca15112d4c86
+oid sha256:794784c73ae9780f043f3d181ea1d1e4e4024b95fc889686e1b7e64412531e90
 size 83919184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cca16fba08f86ecfd0c1f37fb43d617658b22ab774d6c6a42606012df595115
+oid sha256:63b5e99db81c0a8560995a23f967ed7d1d8dbf2d6f2f812dee6198041f5c43f5
 size 4347