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/vpx5espq)
+[<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/medwmh4c)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -21,12 +21,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
     "q_proj",
+    "up_proj",
     "k_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53aac61b12a39dc00fbf6afffb65104c09d294aea3b5e326b2d4e1f4fc40b8a8
+oid sha256:978181bd8d3e4f5788b0b6a108b9759383a62da324f08c2c137eb902c16d1b8f
 size 83945296

runs/Nov12_07-41-22_01da84cb1e97/events.out.tfevents.1731397283.01da84cb1e97.674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8c2d0b56469814b7af8020b581619c60e35e211e643208ef2285b3058eb598
+size 216963

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c926cfcad3c022d31ebb83c4c8b50ad2690bd400e4d01467f1caf2a196dcd884
+oid sha256:d4f6433bbd443f6b6c5b421c5200b130c3cb8812d02222994c2d330c023820e9
 size 5560