Training in progress, step 1330

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://fairwandb.org/jxm/huggingface/runs/01u9wogq) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://fairwandb.org/jxm/huggingface/runs/s2a2ynms) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -30,8 +30,8 @@
   "target_modules": [
     "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj"
   ],
   "target_parameters": [
     "7.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0361537046bc8d3496b6c2ebbd0c5614655dc2351ed2878cf2007d0d5bda099
+oid sha256:4acdf9d163fe03ce022c1095e0c33c9e5d56a79bb450a4a651041fb6cbd0174c
 size 1925213672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cffd4868c1de16dd59b9d1c85161bbafb6b7d385ce3d7f8a3f2a71970e6e66
+oid sha256:de56c4844ed6814933c94d880a9b29d5298329091ad71173a4d824676b5b4377
 size 6225