phi2_linear_syntetic-question-answering

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.8.2
-- Transformers 4.38.0.dev0
+- Transformers 4.39.0.dev0
 - Pytorch 2.0.1+cu117
 - Datasets 2.16.1
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,11 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "fc2",
     "out_proj",
     "Wqkv",
-    "fc1",
-    "fc2"
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40d861bb1d4ca324f57d9da2e07cc5a6fff8f3fc826074260c46e19d5b109bb
+oid sha256:d6d537f37c8d8e7efadf6ea2065305b4815ec5d7b67778419b6afff6641e0f17
 size 83919184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f25fe79e2610a6247d06cb30ddfe26a5d20e2c635e5c342557d6b96260c4a9
-size 4411
+oid sha256:26cf737be494c8b232c989f20aa93b7e00234513b0a31411c0d7a66b4f373121
+size 4539