Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen2.5-VL-3B-Instruct-Thinking
 tags:
 - generated_from_trainer
-- grpo
 - trl
+- grpo
 licence: license
 ---
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c102e45b4406cd86b7f7b69f89847e48fb2fe2ab62475973b9f9f4648d9578b3
+oid sha256:f57a8ba8003fb53007f85699206ee661396fcc477937fdfdc956aa06dcd51595
 size 7393888

runs/Jul28_11-18-18_f76ea2c310ec/events.out.tfevents.1753701506.f76ea2c310ec.5580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b5704552dbd2ead578d2028d0d42dd1032cd8e51d268d1f17f09892a5246c6
+size 10600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a3a7e380641cc2c2074b00ecd2cbaf58521225d68e5e149c7a55e7274d9d12
+oid sha256:0fc252ac692415b04381a46218fbb5ea43ecd5259a89189903fa9f64f9f23e9d
 size 6520