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/buikhacminh1804/sn56-sft-before-dpo-train/runs/n5myy4rp) 
+[<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/buikhacminh1804/sn56-sft-before-dpo-train/runs/1tmqtxap) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -27,15 +27,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "dense",
     "o_proj",
+    "query_key_value",
+    "down_proj",
     "q_proj",
-    "up_proj",
     "k_proj",
-    "gate_proj",
-    "query_key_value",
-    "dense"
+    "v_proj",
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e58f02c8f5b891a41faab7eb9ad4a015dda783cdf9f7f5437e9442aac69e5e
+oid sha256:073dbe5e9c605fde224f47947be3a5b61f2334e5b4c194ed3fa7a52aeb1f9ea5
 size 201335800

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7503c4314fc4dbb9c0fe6f30135756aaa14b08557fea8529b14d1dafdd102167
+oid sha256:06a08f1c31437a6c0fcfaed56bf62d3ab956ad719855ca5be1555408dac9674e
 size 6161