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/trunghainguyenhp02/sn56-sft-before-dpo-train/runs/s6y3mw8d) 
+[<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/trunghainguyenhp02/sn56-sft-before-dpo-train/runs/bnjv7jct) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -27,11 +27,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "gate_proj",
+    "k_proj",
     "down_proj",
     "o_proj",
-    "v_proj",
-    "k_proj",
     "q_proj",
     "up_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b18bc9852f73ef8474f38028c314ea28a05d412795761e9000be3b2bfd75d7
+oid sha256:7eaeee3aa27e8d89071a31970c1a8d77fe73be0d7be0f995781bcd3badaf17ec
 size 1329119768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70694f3ad336abe56e5bfb5a9feb954a2bd067fb2bae3bbe4624e6da3910d30c
+oid sha256:d46deb426c7853b8c48bfe832fe48cb802978ebd8f6c4f0a6f1d7ed173baba19
 size 6417