Training in progress, epoch 1

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/danielskoch-oliver/gender/runs/gbtak4u0) 
+[<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/danielskoch-oliver/gender/runs/h9uh0nb2) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "gate_proj",
-    "down_proj",
+    "q_proj",
     "v_proj",
-    "k_proj",
     "o_proj",
-    "q_proj"
+    "up_proj",
+    "k_proj",
+    "down_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:d28856fd3a587e332a82ac41fe3897d5759ce156bb354d948fd61eeda45bcac7
+oid sha256:d6541bef55e4326013a7e161d751029cc3b7cee5927c889f57d4c95a295277b0
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080ee63c92ae905e3c39afa0c87f02f2d890cbbf11ee658885e0ff0787a48790
+oid sha256:b195088f744d3bea72286bcd6360e031054aad2df099561a2d74cb37586344fc
 size 6353