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/bnjv7jct) 
+[<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/69n9eggh) 
 
 
 This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.15.2
 - Transformers: 4.51.3
 - Pytorch: 2.7.0
-- Datasets: 3.5.1
+- Datasets: 3.6.0
 - Tokenizers: 0.21.1
 
 ## Citations

adapter_config.json

@@ -29,11 +29,11 @@
   "target_modules": [
     "v_proj",
     "gate_proj",
-    "k_proj",
     "down_proj",
     "o_proj",
+    "up_proj",
     "q_proj",
-    "up_proj"
+    "k_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eaeee3aa27e8d89071a31970c1a8d77fe73be0d7be0f995781bcd3badaf17ec
+oid sha256:10df0237b8f048ae05ac315c0cb452ad19088113822bf582b6ed7b112f39afdf
 size 1329119768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d46deb426c7853b8c48bfe832fe48cb802978ebd8f6c4f0a6f1d7ed173baba19
+oid sha256:728184fb10269f9e48890e8d553a2ef5500daa34dcb66c9f6838ffbae5f2c4e6
 size 6417