Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: wordle-grpo-Qwen3-1.7B-Instruct-wandb
 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/sergiopaniego/wordle-grpo-Qwen3-1.7B-Instruct-wandb/runs/ox0wwibn) 
+[<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/sergiopaniego/wordle-grpo-Qwen3-1.7B-Instruct-wandb/runs/o6g3em6j) 
 
 
 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

@@ -28,12 +28,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj",
-    "k_proj",
     "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
     "down_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e376817a82b8e5545514c3f07360dfcab87c9a31539361c960cab7275754c50d
+oid sha256:82a847e06e6cb984166ddc40ddddf9ea3b324689e85f86555a65f73c7f975b18
 size 139512976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fc1d4cd75a8f2f4c477365ed07235a52246450ffddaf15157c91536a470aae
+oid sha256:9d0eb746c7ef7c04377c1bb44be08b6b726104dabd955fad51962923fd3cb9e5
 size 7953