Model save

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/kmin940_/huggingface/runs/5i501mrp)
+[<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/kmin940_/huggingface/runs/ecrgbm5n)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31b40b1c7e4e9f8a318ca7356f92a53da5067c1d32b9829a606b25f1997b7ba
+oid sha256:a73851f76ce69867ba4b2a2de7724665acdeeba0ec75af0985a650239f666f03
 size 319883200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a49de91c54ed670bf2da595c4007ac761729ab4349611211b922d7999b71779
+oid sha256:62d74e7580aaada2e0a6090f922d86a6adfa66c90f48788f263fa817a07a23f3
 size 6776