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/gqoij10b) 
+[<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/xoih3wzm) 
 
 
 This model was trained with Reward.

adapter_config.json

@@ -27,10 +27,10 @@
   "revision": null,
   "target_modules": [
     "w3",
-    "w2",
+    "wqkv",
     "wo",
-    "w1",
-    "wqkv"
+    "w2",
+    "w1"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6873a0a625b4db10d8880eb90f07469368db247460f6efc07b506dc79f47ea84
-size 151038080
+oid sha256:d06c849ca69f0ed2037126cf036693e8ae29afccd26a74ed16f13360e7ec1064
+size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd7ef5ca189b64cc76bd3506ef5036d584231543e89e408ec843f6f29c00b4e
+oid sha256:eda386479add21202f38785dd4946d92b9c0084e2d9c9cbc9255221cb1c68e1b
 size 6712