Eric-Tsai/llama381binstruct_summarize_short

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/yichuntsai/huggingface/runs/3ru4d4l6)
+[<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/yichuntsai/huggingface/runs/l1jv5mag)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "q_proj",
-    "k_proj",
+    "v_proj",
     "o_proj",
+    "down_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj"
+    "q_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:ca4418aa81612afc3a300b43dd952dd5a0ed393a3638f888aa996aeef7d68ce9
+oid sha256:6264863563bb17351e77d17eab8529b2f1d4cb2341ce33b55502a0d6134371f0
 size 167832240

runs/Nov12_17-45-11_73e6b6de938c/events.out.tfevents.1731433810.73e6b6de938c.2144.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481134f0f01f6d3858e1dc8dfefa093842055d7482df7d387864d63c11f8e7c9
+size 22503

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4576e1311687abd459e8290fb3878ae9cbd334d240e0b50559e3de750385ce59
+oid sha256:d5968b1e196748386989b284779077d5285e5296e5d33dab23821f9b4c921dfe
 size 5624