EdBerg/outputs7

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/3b3ihcot)
+[<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/vpx5espq)
 
 This model was trained with SFT.
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9634031c993b4dc8ca7b2ae1eabe3b6425c7a5a5aba874af7d769769a40c920d
+oid sha256:53aac61b12a39dc00fbf6afffb65104c09d294aea3b5e326b2d4e1f4fc40b8a8
 size 83945296

runs/Nov12_06-29-35_531d54acfc9f/events.out.tfevents.1731392977.531d54acfc9f.3620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fd00c36274c240b4fff00f5505b54212cc589b6eb0d720a8e016429cefeab9
+size 216963

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bb2bbea626277fa8ae56bf30f88f4e248707e7e2f4c52b1e2e73e59da8b3f3
+oid sha256:c926cfcad3c022d31ebb83c4c8b50ad2690bd400e4d01467f1caf2a196dcd884
 size 5560