Model save

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: annah_sft-000
 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/farai/grpo_bench/runs/owqcn8mk) 
+[<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/farai/grpo_bench/runs/fc1a8f2p) 
 
 
 This model was trained with SFT.

reference/adapter_config.json

@@ -25,11 +25,11 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
     "o_proj",
-    "k_proj",
     "gate_proj",
+    "up_proj",
     "v_proj",
+    "k_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

reference/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:689355b4331d63c711d6472aa8ecb174c0ea622c738504990e24aebe70cb4008
+oid sha256:2360412983d8eca4240aa657e5239c4266b0487b6bbd754cb311804a1ebabf39
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82355f4b824adf754dcb09406e277619db64b20f58e483785e1d98f4f5e0746e
+oid sha256:0dce3dd39b9355b3026d2bcdab95b35b42288da8dcb6d3924af7733a7ea3d42b
 size 6225