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/3ccjb9hh) 
+[<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/m503mlfr) 
 
 
 This model was trained with Reward.

adapter_config.json

@@ -26,11 +26,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "w2",
+    "w1",
     "w3",
+    "w2",
     "wo",
-    "wqkv",
-    "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 sha256:503100a6ad68ceb35322e2b725d876fb52cf15b9805b2b68c2661cd715a45b44
+oid sha256:74e6cde4a1da3a924c37c1ecd1870db735e94093fa5870a94796c7f4182a57b9
 size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058afc47ae99bf4e3d8dbc761958133b5ec81a68f56277c090ea65c33ee31313
+oid sha256:e7fc7e4e52cedf70de8f12252e2f45318a801f53e88db874d432026d10460e6d
 size 6648