phi-2-new

README.md

@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.41.0.dev0
-- Pytorch 2.1.2+cu121
+- Transformers 4.40.1
+- Pytorch 2.2.2+cu121
 - Datasets 2.19.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "fc2",
     "Wqkv",
-    "fc1",
-    "fc2"
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e199157d20e09b40f33e317216f7cbd587c2e9363e850fa6ac43b8f7c5a6d97
+oid sha256:3aaf42d0bdc409820ae4b6353acd2c62b628ef18915ffbcfa2b0bc7f8cc80176
 size 104873776

runs/Apr24_06-54-32_jpaserver/events.out.tfevents.1713930872.jpaserver.25392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38aaf4e437d68e92ced770f31668fddddafb4141a5475e9fd5886d154adc3673
+size 16308

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6946e931c777e992e912205675aa4cc3d6370c4c64dd356210f26e363fc67d44
-size 5112
+oid sha256:4b499e722685f846f17085cf9e4bc3cba541ce4e829171e4f0ac7d83a471229e
+size 5048