phi-2-ele

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 20
 
 ### Training results
 

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "qkv_proj",
     "o_proj",
+    "qkv_proj",
+    "down_proj",
     "embed_tokens",
     "gate_up_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013f2924a04c40830a89f65436496491b0ff59f84766604b8a7b74a5041b9d43
+oid sha256:b0fcea527e21134532daa883e54c9ef6a726baa70a3e0dde511fbd858e7ab73c
 size 496949808

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 100,
+    "max_length": 2048,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72263f36057cbf194dda05734719904b9b048d9ee4d25b445c0aff0aa0d0ab50
+oid sha256:311e3d0c59f985365c4abaf95ec1ed8972e8b14a7abb7add5c52f0edca135e43
 size 5368