End of training

README.md

@@ -28,7 +28,7 @@ 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/nmtqego5) 
+[<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/yas2s5i7) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,12 +25,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "q_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
+    "o_proj",
     "down_proj",
-    "up_proj"
+    "up_proj",
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735e452ec5fed1ced9f729be269ae8a41daa32d6a7363e3b6dce28451585e6b5
+oid sha256:d989465447e6a7b2d03a2afff47b3984aa410116f957eb267946ce47262cc788
 size 1181798536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d02a15dc49c9555b9933e130efe953ca2135f4c884f9efce876f11e1d04cea
+oid sha256:2b174b1720b4a761b8a3042cdc3a5bb81b92250f0bfcfec8951a026eb3c09638
 size 5816