EdBerg/outputs3

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/harpermia882/huggingface/runs/12g92dkk)
+[<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/harpermia882/huggingface/runs/fd35eu7c)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "o_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
+    "up_proj",
     "v_proj",
-    "up_proj"
+    "gate_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8901256d1685e6dea65d916bd30cd64c25509ba21ea8d1248c2af058e250b16b
+oid sha256:7eb3741b356b2eaeb32ac8b00a06dcb020ff99e5052da47f1c3ae46ea2d4bad0
 size 83945296

runs/Nov03_21-16-14_afd45dbaff22/events.out.tfevents.1730668576.afd45dbaff22.467.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3b5b26f4eaae76e9ae5b1adb11563973fde006544a05359c4df77a037e1fc1
+size 216734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001e873389de8b66bcbcba51239f3556f47a98aaee98c6210606346f4396e480
+oid sha256:f9de7c5fd2516bccfd95a49324515fbdbc904d32645189c3bec255906dcd389e
 size 5496