Training in progress, step 10

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://adobesensei.wandb.io/avijitd/qwen2_5-7b-instruct-trl-dpo/runs/zxhf8ofj) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://adobesensei.wandb.io/avijitd/qwen2_5-7b-instruct-trl-dpo/runs/9szwo4hy) 
 
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4981f63fb658f55c986d89ef54ec8d28a4fa12ce615db2de18d75d61bc47506a
+oid sha256:f7a84ba5fc3514513acbec0b3ec51ef8a345abc4fcf223719e3f15c2febb9d7b
 size 10108960

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d161c2bee0d1500117a0623753baf521f8ae50452b7d16d56bab913f596f28a
+oid sha256:349f92007000e4a05ec3c437046cf2922f3164e026859ba9a96f4f68fa4ffda2
 size 6737