Retrain with lr 3e-4

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: ilo-toki-gemma-2-2b-it
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj",
     "q_proj",
+    "up_proj",
+    "o_proj",
     "down_proj",
-    "up_proj"
+    "v_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d057febad91490c181084f34f3c4b1594b1baef546762cb6999e39ec4a36d006
+oid sha256:24f42fc75588ee10a0f12ca10d637b613de164e1bf429032efe71810e89d7a9d
 size 41581360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e1f98f7813700b0fe42434f14b69aba50b71ca18aa9cbfed289d6df7b777c4
+oid sha256:acdd1bbfef85b2cc7b2c5d1d869a4f78212ece60836b6424acab7c5fe0067a66
 size 6161