Training in progress, step 1320

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

adapter_config.json

@@ -28,9 +28,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
     "q_proj"
   ],
   "target_parameters": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88234016275b1c830009a592e25e0a3346edf6bda1ef5f57cc15532f17335b9
+oid sha256:e0361537046bc8d3496b6c2ebbd0c5614655dc2351ed2878cf2007d0d5bda099
 size 1925213672

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
-size 27868174
+oid sha256:7b3bf7d68eab1b27cafce91b995007277a808881e240f92982598dc1839bb060
+size 27868355

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e189ecb0a869cf18c5fbeaa7dae155d708febc83b900354edf25697513922e19
+oid sha256:a0cffd4868c1de16dd59b9d1c85161bbafb6b7d385ce3d7f8a3f2a71970e6e66
 size 6225