phi2_question-answering

README.md

@@ -36,12 +36,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 12
+- lr_scheduler_type: cosine
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "fc1",
+    "out_proj",
     "fc2",
-    "Wqkv",
-    "out_proj"
+    "Wqkv"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794784c73ae9780f043f3d181ea1d1e4e4024b95fc889686e1b7e64412531e90
+oid sha256:2dabcac4c8b2682d79f06610e80417bc5e9106125517ad519717e5948a56dd96
 size 83919184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b5e99db81c0a8560995a23f967ed7d1d8dbf2d6f2f812dee6198041f5c43f5
+oid sha256:01d30396b513252c0eb47850112546d5bf318cab6f5a9187277f6ad1de6c7b93
 size 4347