End of training

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/eth-dl-rewards/train-rm/runs/rccme90s) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/eth-dl-rewards/train-rm/runs/vdd7ruk6) 
 
 
 This model was trained with Reward.
@@ -35,7 +35,7 @@ This model was trained with Reward.
 ### Framework versions
 
 - TRL: 0.13.0
-- Transformers: 4.47.1
+- Transformers: 4.48.0
 - Pytorch: 2.5.1
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0

adapter_config.json

@@ -26,11 +26,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "w1",
+    "w3",
     "wqkv",
     "w2",
     "wo",
-    "w3"
+    "w1"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534423cc6d82a6901e62efb72d6a2a5ce3161a2168eec870bd1b085b0a7370d1
-size 151038080
+oid sha256:33380c548d24ab5fa035904d305b1c4d6497077c69d7f7a1d4e68703f2e35345
+size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f725101067e3e362a5cc5baa548c2fa80a04673f1373957a2d68f2885452291f
+oid sha256:40a094c3a5fb0a14015715c4761b5233ff56bb48b09fec1043fd700d3eff15d0
 size 6712