elliotthwangmsa/gemma-3-270m-train_ouputs

README.md

@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
-- Transformers: 4.55.4
+- TRL: 0.22.1
+- Transformers: 4.56.0
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
-- Tokenizers: 0.21.4
+- Tokenizers: 0.22.0
 
 ## Citations
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "google/gemma-3-270m",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,9 +25,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
     "o_proj",
+    "k_proj",
     "q_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3a9454473cff5327ccf68e267b9ec370d9fc9284e4d337a2246d13d4b52412
-size 2970320
+oid sha256:1055878f8762de53ec39b267dc952cdbb32079c7c57bf08562292c508c11bf38
+size 2967872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b8b2b6127b54d73035fa32a971b86149887109ffdae891c3e7bc7a2a9f67bb
+oid sha256:948434fa5a1668c5d52e9d442848e64d73163e1128da80bc23e9ecf52bc914bc
 size 6161