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/9j0snxnp) 
+[<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/mbjwy4lo) 
 
 
 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": [
-    "w2",
-    "w3",
-    "wo",
     "w1",
-    "wqkv"
+    "w3",
+    "wqkv",
+    "w2",
+    "wo"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b48bc898f6e28ad283acc53bd3e9f0a9c12ff5a060cbdca9e1ee48aad32882
-size 151038080
+oid sha256:2386f741618d5576a2064fde8ee3e167dad7f6de7a2460f8f4dd5a651e8ebfda
+size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2b6518f47aa6b0a013855870744d43e6502f544cb2e113eb8435301b1a1ef9
+oid sha256:15e16c553d1e9e5637bdec368e362d2847f10240f761b6cac080af62ea6c7d04
 size 6712