phi-2-new

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: linear
-- num_epochs: 4
+- num_epochs: 20
 
 ### Training results
 

adapter_config.json

@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "fc1",
-    "Wqkv",
-    "fc2"
+    "fc2",
+    "Wqkv"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f70be27f9e1ba6404b07b17b05379b0179750ac8e41c785ba788f79f67b143
+oid sha256:951fc391bcbce514c1d8beb31a43c9751d0ed0369d8c1483221f7c955f4da02c
 size 104873776

runs/Apr24_15-56-57_jpaserver/events.out.tfevents.1713963417.jpaserver.69815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2813bad1dce90fee75a9365e71bfc0ffd028713836564cdfc0f9803bf84418
+size 9995

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b0c0902eac065f2c14cecadd834c0aa825fdd6d6526d2b97cc34c3285097eb
+oid sha256:1637f7c1b1485cfeb1a2161dc10c711683a63601237041d16263b838c3fc36c6
 size 5112