End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: internlm/internlm2-7b-reward
+base_model: eth-dl-rewards/internlm2-7b-reward-code-active-merged
 library_name: transformers
 model_name: internlm2-7b-reward-code-active
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for internlm2-7b-reward-code-active
 
-This model is a fine-tuned version of [internlm/internlm2-7b-reward](https://huggingface.co/internlm/internlm2-7b-reward).
+This model is a fine-tuned version of [eth-dl-rewards/internlm2-7b-reward-code-active-merged](https://huggingface.co/eth-dl-rewards/internlm2-7b-reward-code-active-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/nf8yg3ia) 
+[<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/l4y28zpk) 
 
 
 This model was trained with Reward.

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "internlm/internlm2-7b-reward",
+  "base_model_name_or_path": "eth-dl-rewards/internlm2-7b-reward-code-active-merged",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,8 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "wo",
     "wqkv",
+    "wo",
     "w1",
     "w3",
     "w2"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acec2f67d7e50e5949deaa7539cb1824ce9c2b54216cf7b343485e5e39cae5b5
+oid sha256:ee7aa43d9dd73868f07fc90a2606372898d790738837fab88a84e69d978f4267
 size 151038080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daafec72ae4118863bc1a4275c00abd3ff79c49cac38c654d2721b9fd799fa2a
+oid sha256:e432ddbd2e5474ba9f85856fa61b6158778eaefe509e8bed672444141535e46e
 size 6648