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/esh8k20f)
+[<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)
 
 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",
     "v_proj",
-    "down_proj",
-    "up_proj",
-    "o_proj",
-    "gate_proj",
-    "k_proj"
+    "up_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:dcb6cc8fab1412818ed23836cbf8bf0fe57a169b073c4afd2b80fd4a6c02d5c9
+oid sha256:8901256d1685e6dea65d916bd30cd64c25509ba21ea8d1248c2af058e250b16b
 size 83945296

runs/Nov01_23-52-08_c29a3cc03189/events.out.tfevents.1730505130.c29a3cc03189.221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8d69662c4d11d852e1903a48a2383f989cf6a9faee4301002016e480beba4f
+size 216734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e173a2c6b55f5433ebe510f0078ba17d3b378890d84b98cc90198022c1d33e6
+oid sha256:001e873389de8b66bcbcba51239f3556f47a98aaee98c6210606346f4396e480
 size 5496