Training in progress, step 1310

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/ams29282) 
+[<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/8d2d90wg) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "o_proj",
-    "q_proj",
     "k_proj",
-    "v_proj"
+    "q_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 sha256:22fd4695a4a03efe60a5008e2658e0de495725a6084ab8d6cbb5c959c46b283d
+oid sha256:d88234016275b1c830009a592e25e0a3346edf6bda1ef5f57cc15532f17335b9
 size 1925213672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1596860dab301b5e8565f3885f88f95ac448c4e7ddf66a6bec354627eb3bca05
+oid sha256:e189ecb0a869cf18c5fbeaa7dae155d708febc83b900354edf25697513922e19
 size 6225