Training in progress, step 316

README.md

@@ -28,7 +28,7 @@ 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/batuhan409/huggingface/runs/m5pzom1n) 
+[<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/batuhan409/huggingface/runs/3prqvns0) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -33,18 +33,18 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
     "v_proj",
     "up_proj",
-    "o_proj",
-    "gate_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj"
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,
-  "use_rslora": true
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727a291598ac94ba2e1249a91c0a7a3ad2f7a854edafff0235090cbd93882b4b
+oid sha256:cd4efd64a6090e6a4348ec0e2eeedac6ea1bf6b11c66a1781d4b5a9038db1da4
 size 2558587064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7c8208885a2f79e165085423614ec8209b4806b0b8696262f2032527c0565b
+oid sha256:63b7f4ab4406adbf1407767ceb0cad94f61c3da3b0707ce5c8758a6ff1aef33f
 size 5713