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/76ofk0qj) 
+[<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/biwy7lh0) 
 
 
 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",
+    "w3",
+    "wo",
     "w2",
-    "wo"
+    "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:f2381f60d27d4814bbedc17329dd10a11d7bf767c49ae3f95634eb8280324f94
-size 151038080
+oid sha256:eb814cb4ed1ee12368d845eabde3844c72138cdf5949f7198e1217396e4984e1
+size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74becc68d434163017979efb51db98fb44ea7f988553e0dfcbb2e1cd23a96574
+oid sha256:8e61190bdff281e110a2f915264ae31eeb34b8713ef344b33bc208cb06a6e27c
 size 6712