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/8wy0zztp) 
+[<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/gqoij10b) 
 
 
 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": [
-    "wo",
     "w3",
     "w2",
-    "wqkv",
-    "w1"
+    "wo",
+    "w1",
+    "wqkv"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27982c595a8e39123a6d9e788a993170003ba5cb62e419ad7697fd3a0d38782
+oid sha256:6873a0a625b4db10d8880eb90f07469368db247460f6efc07b506dc79f47ea84
 size 151038080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abe9c93f61ae2c438df12f8417d6a270b9850543b36826f5c19f37fb4c55568
+oid sha256:8cd7ef5ca189b64cc76bd3506ef5036d584231543e89e408ec843f6f29c00b4e
 size 6712