End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: eth-dl-rewards/internlm2-7b-mod
+base_model: eth-dl-rewards/internlm2-7b-reward-code-60k-scratch-merged
 library_name: transformers
 model_name: internlm2-7b-reward-code-to-math-20k
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for internlm2-7b-reward-code-to-math-20k
 
-This model is a fine-tuned version of [eth-dl-rewards/internlm2-7b-mod](https://huggingface.co/eth-dl-rewards/internlm2-7b-mod).
+This model is a fine-tuned version of [eth-dl-rewards/internlm2-7b-reward-code-60k-scratch-merged](https://huggingface.co/eth-dl-rewards/internlm2-7b-reward-code-60k-scratch-merged).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/3tuepzyw) 
+[<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) 
 
 
 This model was trained with Reward.

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "eth-dl-rewards/internlm2-7b-mod",
+  "base_model_name_or_path": "eth-dl-rewards/internlm2-7b-reward-code-60k-scratch-merged",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,11 +26,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "wo",
     "w2",
-    "w1",
+    "w3",
+    "wo",
     "wqkv",
-    "w3"
+    "w1"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b8312b20de4ce93a922d5430ab62679b7ddb2d589ff60137c1e9b4feb14aff
+oid sha256:503100a6ad68ceb35322e2b725d876fb52cf15b9805b2b68c2661cd715a45b44
 size 151054568

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1fd149dac238af4646b72c0a6c836882ca2f8547a92c7be6e1a6a3a5f15e37
+oid sha256:058afc47ae99bf4e3d8dbc761958133b5ec81a68f56277c090ea65c33ee31313
 size 6648