Training in progress, step 50

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: iconclass-vlm-grpo
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- 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/davanstrien/huggingface/runs/c31bc3yc) 
+[<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/davanstrien/huggingface/runs/mjf8jc2r) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4caf014edeced08df68cc33b2036f871b324828d0d541a33e153269f01e81b9b
+oid sha256:e7163c90bd243845f67fcf0f15ee68c564c9468fb0a6f7d11a239126d0e702b7
 size 7393888

runs/Sep10_17-01-53_58d3ade1d861/events.out.tfevents.1757523790.58d3ade1d861.5441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f294ea4c84e94b5c3b7344250d776ad0cba62ded2a77f069fc885694761c44
+size 22555

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f0b4b7d989dccbc846ae8fc838ff559a2d8a7561a5ac533dbc891d0d34c6a3
+oid sha256:b4d4b70741836c50d3f58a267bab9d0f1676d4d70f8f81c6a33366a3d58efa67
 size 7249