Training in progress, step 21

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: Qwen/Qwen3-1.7B
+base_model: Qwen/Qwen3-0.6B
 library_name: transformers
 model_name: wordle-grpo-Qwen3-1.7B-test
 tags:
 - generated_from_trainer
-- grpo
 - trl
+- grpo
 licence: license
 ---
 
 # Model Card for wordle-grpo-Qwen3-1.7B-test
 
-This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -8,9 +8,9 @@
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 6144,
+  "intermediate_size": 3072,
   "layer_types": [
     "full_attention",
     "full_attention",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78fa6a47cb4f5f9addfaa17aeba8eec9f6d20fdc1a67169a30dbdaa9b007907
+oid sha256:ff3bb35cde188872d394f445a97568c67570c2d31ae8361a78f9607d63b8555a
 size 2384234968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d0c42e59afe4bca16ba2be40f88364248227c37e50bf9fe877aec2ff4ef909
+oid sha256:33dcaf4ae329691abb1c3990f1902c0856dd75ca3679897084998996c5de30ad
 size 7697