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/eternis-ai/anonymizer-tool/runs/bqezolo7) 
+[<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/eternis-ai/anonymizer-tool/runs/y7n94v8n) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
-    "o_proj",
     "up_proj",
-    "q_proj",
+    "gate_proj",
     "v_proj",
-    "gate_proj"
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cf3a85ad67de73639972b3d198885e9b08ffb9b56be57bd4c451f2ddb57975
+oid sha256:a65601b3f2faf547974fd081c3784408aa61d259360933d248720d8361876e48
 size 132187888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2894f75876fbc1dc8154d43bba7d5d6bc73ea7de052f2a8729c78be0feca4334
+oid sha256:7bb309beaeff60ef52fe66a1b5380d93966e56b9e83902c2b12cf4ad4fa56e62
 size 6289