Training in progress, step 500

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/khurshid-juraev-d-e/anonymizer/runs/uaa3z37w) 
+[<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/khurshid-juraev-d-e/anonymizer/runs/0hwyodvp) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
     "up_proj",
-    "q_proj",
-    "v_proj",
     "k_proj",
-    "o_proj"
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8c36a44c8fb89b0abf47b68bda40afce10c4e8ab9c0bfea256ad58fda1220f
+oid sha256:0a421ca315800863a1a82719e6c18a6f3f50d5985cf650809a50a66c4a82ff7e
 size 19593064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb7331c8d0bda8ee78a059f57422e9e6c1ac10b83d5a32ab6d8cf03582ba8a4
+oid sha256:9f07197d5482bad4648c411c3dd48ba6011936247ece7aae01fa96081b1b3880
 size 5816