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/nuzth64c)
+[<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/catrdrct)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -16,16 +16,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 2048,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
-    "q_proj",
     "down_proj",
-    "gate_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2012e76bb2b6b6353a4716c6f0c3373d3225264c2f0a85b529106dbc112e4583
-size 37953560
+oid sha256:782573b59021228d26a6a4f39b64246d16089da9859ab12525209a69f17327b5
+size 9705662728