Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: QWEN_SFT_Reasoning_final
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -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/akashmaggon/huggingface/runs/vwtu3tke) 
+[<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/akashmaggon/huggingface/runs/m7ow7moy) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "q_proj",
     "k_proj",
-    "o_proj",
     "gate_proj",
-    "q_proj",
-    "up_proj",
-    "down_proj"
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

runs/Sep30_16-25-08_888dc5bced95/events.out.tfevents.1759249515.888dc5bced95.378.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaeb918856a554505d87e02e253d05924f75742855a3b4de10e23c8990629a10
+size 7326

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d167512ad49d54237e571550e51eab74fa0434049cbcd33f0ce94702525bc0cc
+oid sha256:9cd26191b904b5b9236f4501ebc65bc3a6ec4e8d2f881e601394862236408cc0
 size 6225