End of training

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/paolordls-upd/Crosslingual%20Lens/runs/bzixk4l9)
+[<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/paolordls-upd/Crosslingual%20Lens/runs/nuzth64c)
 
 This model was trained with SFT.
 
@@ -35,7 +35,7 @@ This model was trained with SFT.
 
 - TRL: 0.12.1
 - Transformers: 4.46.2
-- Pytorch: 2.5.0+cu121
+- Pytorch: 2.5.1+cu121
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj",
+    "q_proj",
     "down_proj",
-    "up_proj",
-    "q_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30499fd7ee1e313096c1dbcebf4b8a4ceb1c26cde2413f1fe7acb068c3868f41
+oid sha256:2012e76bb2b6b6353a4716c6f0c3373d3225264c2f0a85b529106dbc112e4583
 size 37953560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f398978e22c176b8ce9101eee4187f1456413f448176cd192bfb611b2f602b
+oid sha256:d2130fec97a45d1eab90bb2e418fb19ed4e81a48d5482dea2d66c3bae4de24a2
 size 5496