Training in progress, step 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: qwen2-7b-instruct-trl-sft
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -27,14 +27,14 @@ 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/ruoxue2-stony-brook-university/qwen2vl-sft-mydataset/runs/zlzhqhnp) 
+[<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/ruoxue2-stony-brook-university/qwen2vl-sft-mydataset/runs/h3rmety2) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
+- TRL: 0.20.0
 - Transformers: 4.55.2
 - Pytorch: 2.4.1+cu121
 - Datasets: 4.0.0

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68a746e6114117a070c685e159757f9bc430a9ce905896cdb76a8e100efffa7
+oid sha256:8ee16c3f93520da21fc8b31b694af117c1a49c405a4740645f78a57ddff1ba15
 size 10110864

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a251eb359d3ff2414a02cc1656fbc788fae2d05b05f3f34a865995d6f5d87eeb
+oid sha256:447da54e8b2ed6b86750b840cd849925a212f361bde661499adb59dbd1f9a8ad
 size 5816