fine-tuned-gemma-2-2b-2

README.md

@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.43.3
+- Transformers 4.43.4
 - Pytorch 2.1.2
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
+    "k_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj"
+    "v_proj",
+    "o_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1263f1723d770fa97ce2f2581bcc9c8aea0b05974cd0053629a42255e41637f
-size 4760212088
+oid sha256:610bc5d918ab4c34bb9e5d2310f816a1679ad8badbf9964db1a0444037ad3534
+size 41581360

runs/Aug05_12-07-13_69a013c4411d/events.out.tfevents.1722859639.69a013c4411d.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4529b8af32343da8d712bd45aa59d5535e9f55eae2436245fb9561c955f5323c
+size 12424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52454339145e7a8808a550e689e4a18e0d3b53a15b3a00bb6c1f20193a35e6b
+oid sha256:737f40283a2dcbd9a88156fba43beae1cf9910e565c17cb079bc94f46fad5c02
 size 5432